{ "accounting": { "cells": [ [ { "administrativelyAccepted503": 0, "administrativelyAcceptedNullStatus": 0, "eligible": 80, "knownFailed": 0, "scheduled": 80, "unattempted": 0, "unknown": 0 }, { "administrativelyAccepted503": 0, "administrativelyAcceptedNullStatus": 0, "eligible": 80, "knownFailed": 0, "scheduled": 80, "unattempted": 0, "unknown": 0 } ], [ { "administrativelyAccepted503": 1, "administrativelyAcceptedNullStatus": 1, "eligible": 78, "knownFailed": 0, "scheduled": 80, "unattempted": 0, "unknown": 2 }, { "administrativelyAccepted503": 0, "administrativelyAcceptedNullStatus": 0, "eligible": 79, "knownFailed": 1, "scheduled": 80, "unattempted": 0, "unknown": 0 } ] ], "eligible": 317, "knownFailed": 1, "pilotAttempts": [ { "eligible": 36, "knownFailed": 4, "label": "First epoch measurement pilot (closed no-go)", "nativeTargetStudyId": "PRICE03-SOL-TERRA-20261007", "scheduled": 40, "stage": "measurement", "unattempted": 0, "unknown": 0 }, { "eligible": 40, "knownFailed": 0, "label": "E2 measurement pilot", "nativeTargetStudyId": "PRICE03-SOL-TERRA-20261007-E2", "scheduled": 40, "stage": "measurement", "unattempted": 0, "unknown": 0 }, { "eligible": 4, "knownFailed": 0, "label": "E2 execution pilot", "nativeTargetStudyId": "PRICE03-SOL-TERRA-20261007-E2", "scheduled": 4, "stage": "execution", "unattempted": 0, "unknown": 0 } ], "pilotsExcluded": 84, "scheduled": 320, "unattempted": 0, "unknown": 2 }, "checks": [ { "cells": [ [ { "failed": 0, "missing": 0, "missingByReason": {}, "passed": 80, "scheduled": 80 }, { "failed": 0, "missing": 0, "missingByReason": {}, "passed": 80, "scheduled": 80 } ], [ { "failed": 0, "missing": 2, "missingByReason": { "known-failure": 2 }, "passed": 78, "scheduled": 80 }, { "failed": 0, "missing": 1, "missingByReason": { "known-failure": 1 }, "passed": 79, "scheduled": 80 } ] ], "expected": 300, "name": "Protected count" }, { "cells": [ [ { "failed": 0, "missing": 0, "missingByReason": {}, "passed": 80, "scheduled": 80 }, { "failed": 0, "missing": 0, "missingByReason": {}, "passed": 80, "scheduled": 80 } ], [ { "failed": 0, "missing": 2, "missingByReason": { "known-failure": 2 }, "passed": 78, "scheduled": 80 }, { "failed": 0, "missing": 1, "missingByReason": { "known-failure": 1 }, "passed": 79, "scheduled": 80 } ] ], "expected": 600, "name": "Unprotected count" } ], "codingNote": "All 320 captured rationales were coded once by the single frozen Claude Sonnet 5 coding instrument: 317 eligible scientific rationales and 3 audit-only captures. All 320 replies passed the registered coding parser; no invalid or unavailable coder replies remained. Audit-only codes are retained for coverage but excluded from scientific estimates. The 80 previously coded pilot rationales plus these 320 exhaust the explicitly authorized 400 PRICE03 transfers; PRICE02 was excluded. This is one coder, not a consensus panel.", "comparison": [ { "id": "H1a", "model": "GPT-5.6 Terra", "outcome": "price", "price02": { "effect": 9.577524893314369, "effectInterval": null, "effectIntervalMethod": null, "gain": { "interval": { "lower": 16.24531042223116, "upper": 21.646581469660735 }, "mean": 18.945945945945947, "n": 37, "sd": 8.099883215707996 }, "loss": { "interval": { "lower": 8.030709944268061, "upper": 10.706132160995097 }, "mean": 9.368421052631579, "n": 38, "sd": 4.069803452532752 }, "sourceSha": "sha256:a926f9489071713b43eafe086008a1e5c580c481d3f116afd3546fa7ae377a13" }, "price03": { "effect": 8.369620253164557, "effectInterval": null, "effectIntervalMethod": null, "gain": { "interval": { "lower": 14.983642996651662, "upper": 18.61635700334834 }, "mean": 16.8, "n": 80, "sd": 8.161967993014144 }, "loss": { "interval": { "lower": 7.960424625650669, "upper": 8.900334868020218 }, "mean": 8.430379746835444, "n": 79, "sd": 2.0981282519512083 }, "sourceSha": "sha256:a8bb0432c101ec03b5453c29ff40bc0074f5e8f4ad0ea4ba7f68d90fbdec9d9b" } }, { "id": "H1b", "model": "GPT-6 Sol", "outcome": "price", "price02": { "effect": 10.282051282051281, "effectInterval": null, "effectIntervalMethod": null, "gain": { "interval": { "lower": 23.51272304009386, "upper": 25.205225677854855 }, "mean": 24.358974358974358, "n": 39, "sd": 2.6105774667401755 }, "loss": { "interval": { "lower": 11.528384865006512, "upper": 16.62546128883964 }, "mean": 14.076923076923077, "n": 39, "sd": 7.861915580772302 }, "sourceSha": "sha256:a926f9489071713b43eafe086008a1e5c580c481d3f116afd3546fa7ae377a13" }, "price03": { "effect": 10.027884615384616, "effectInterval": null, "effectIntervalMethod": null, "gain": { "interval": { "lower": 23.1229664163184, "upper": 24.702033583681605 }, "mean": 23.9125, "n": 80, "sd": 3.5478420968673055 }, "loss": { "interval": { "lower": 12.234987263099066, "upper": 15.534243506131704 }, "mean": 13.884615384615385, "n": 78, "sd": 7.316554382492351 }, "sourceSha": "sha256:a8bb0432c101ec03b5453c29ff40bc0074f5e8f4ad0ea4ba7f68d90fbdec9d9b" } }, { "id": "H2a", "model": "GPT-5.6 Terra", "outcome": "likelihood", "price02": { "effect": 3.2290184921763867, "effectInterval": null, "effectIntervalMethod": null, "gain": { "interval": { "lower": 3.7866835658063143, "upper": 5.618721839599091 }, "mean": 4.702702702702703, "n": 37, "sd": 2.747371115821095 }, "loss": { "interval": { "lower": 1.023284398399007, "upper": 1.9240840226536244 }, "mean": 1.4736842105263157, "n": 38, "sd": 1.370279949800418 }, "sourceSha": "sha256:a926f9489071713b43eafe086008a1e5c580c481d3f116afd3546fa7ae377a13" }, "price03": { "effect": 2.4984177215189876, "effectInterval": null, "effectIntervalMethod": null, "gain": { "interval": { "lower": 3.037415903541361, "upper": 4.212584096458639 }, "mean": 3.625, "n": 80, "sd": 2.6403634195583328 }, "loss": { "interval": { "lower": 1.0292313724043076, "upper": 1.2239331845577177 }, "mean": 1.1265822784810127, "n": 79, "sd": 0.43462594019115985 }, "sourceSha": "sha256:a8bb0432c101ec03b5453c29ff40bc0074f5e8f4ad0ea4ba7f68d90fbdec9d9b" } }, { "id": "H2b", "model": "GPT-6 Sol", "outcome": "likelihood", "price02": { "effect": 2.3333333333333335, "effectInterval": null, "effectIntervalMethod": null, "gain": { "interval": { "lower": 4.5837222553780546, "upper": 5.211149539493741 }, "mean": 4.897435897435898, "n": 39, "sd": 0.967766603954742 }, "loss": { "interval": { "lower": 2.0288862359858, "upper": 3.0993188922193284 }, "mean": 2.5641025641025643, "n": 39, "sd": 1.6510741606422834 }, "sourceSha": "sha256:a926f9489071713b43eafe086008a1e5c580c481d3f116afd3546fa7ae377a13" }, "price03": { "effect": 2.4919871794871793, "effectInterval": null, "effectIntervalMethod": null, "gain": { "interval": { "lower": 4.5747251294113775, "upper": 5.0502748705886225 }, "mean": 4.8125, "n": 80, "sd": 1.0684633470787066 }, "loss": { "interval": { "lower": 1.9562471350595234, "upper": 2.684778505966118 }, "mean": 2.3205128205128207, "n": 78, "sd": 1.6156184915452998 }, "sourceSha": "sha256:a8bb0432c101ec03b5453c29ff40bc0074f5e8f4ad0ea4ba7f68d90fbdec9d9b" } } ], "continuation": { "accepted503": 1, "acceptedNullStatus": 1, "acceptedTechnicalMissing": 2, "administrativelyAccounted": true, "amendmentSha": "sha256:6f12e66a2e33f8c143d2ccb9ce80bbff6dfb3a41bd970f776777e8bd2f3f4ceb", "computationalAccounting": { "eligible": 317, "knownFailed": 3, "scheduled": 320, "unattempted": 0, "unknown": 0 }, "computationalDisposition": "known-failure-with-all-values-null", "originalSamples": [ { "cells": [ [ { "administrativelyAccepted503": 0, "administrativelyAcceptedNullStatus": 0, "eligible": 40, "knownFailed": 0, "scheduled": 40, "unattempted": 0, "unknown": 0 }, { "administrativelyAccepted503": 0, "administrativelyAcceptedNullStatus": 0, "eligible": 40, "knownFailed": 0, "scheduled": 40, "unattempted": 0, "unknown": 0 } ], [ { "administrativelyAccepted503": 1, "administrativelyAcceptedNullStatus": 0, "eligible": 39, "knownFailed": 0, "scheduled": 40, "unattempted": 0, "unknown": 1 }, { "administrativelyAccepted503": 0, "administrativelyAcceptedNullStatus": 0, "eligible": 40, "knownFailed": 0, "scheduled": 40, "unattempted": 0, "unknown": 0 } ] ], "id": "sample-1" }, { "cells": [ [ { "administrativelyAccepted503": 0, "administrativelyAcceptedNullStatus": 0, "eligible": 40, "knownFailed": 0, "scheduled": 40, "unattempted": 0, "unknown": 0 }, { "administrativelyAccepted503": 0, "administrativelyAcceptedNullStatus": 0, "eligible": 40, "knownFailed": 0, "scheduled": 40, "unattempted": 0, "unknown": 0 } ], [ { "administrativelyAccepted503": 0, "administrativelyAcceptedNullStatus": 1, "eligible": 39, "knownFailed": 0, "scheduled": 40, "unattempted": 0, "unknown": 1 }, { "administrativelyAccepted503": 0, "administrativelyAcceptedNullStatus": 0, "eligible": 39, "knownFailed": 1, "scheduled": 40, "unattempted": 0, "unknown": 0 } ] ], "id": "sample-2" } ], "originalUnknownPreserved": true, "predecessorAmendmentSha": "sha256:4fd3f510ca94934857aaef25f391ad6d3b146d81120fc4c1c55ae8ae7af389b9", "projectionPolicySha": "sha256:b7e3d5adbe8eb5437fdec2e692d0ef6e93dd858d341a76429cef98e1cf28e329", "schemaVersion": 2, "scope": "Post-stop, pre-residual stream-disconnection amendment retains its prior503 amendment and disjoint accepted503 and explicit-null-status subsets. Null status is never described as HTTP503. Original unresolved custody is preserved; accepted technical missingness permits the unchanged numerical engine to use null outcomes. No remote completion, cancellation, provider truncation, retry or replacement is inferred.", "sourceOutcome": "unknown", "transportSubsets": [ "http-503", "null-http-status" ], "unacceptedUnknown": 0 }, "deviations": [ { "area": "Native model and compute evidence", "detail": "Requested/configured GPT-6 Sol and GPT-5.6 Terra with low-effort native controls are pinned. Served backend identity and actual compute remain unobserved; no claim of provider-level identity equivalence.", "evidenceSha": "sha256:622001976aad81a710bad3244cc25c3cfd768699bd7ab06be32b85bf41642f55" }, { "area": "Output limit and unavailable outcomes", "detail": "The original1024 reference is locally recorded but not requested/enforced by native transport. Provider truncation is not-evaluable; six-turn completion and per-outcome grammar define the prospective endpoint. Retain every missing/failure and both registered/native sensitivity scopes without replacement.", "evidenceSha": "sha256:46884e8c0f57b5d8acda96b9eb0b16b054c0bfd02e63df0d06d6fdfe9e21e589" }, { "area": "Separate pilot epochs and compatibility policy", "detail": "Epoch1 closed no-go after40 scheduled:36eligible and4local compatibility failures. Epoch2 uses the separately reviewed opt-in observed streamed-terminal policy. No prior rows were retried,salvaged,pooled or recoded as E2; scientific prompts,hypotheses,N and strict thresholds remain unchanged.", "evidenceSha": "sha256:11bc0da507ce3be71161731ee183d3d0631139f5c82a33dc8ef603a26cb77041" }, { "area": "Single coder and audit-only coverage", "detail": "One external Claude Sonnet 5 coder used the unchanged frozen codebook and fresh 40-case calibration. Final coding covered all 320 captured rationales, including 3 audit-only captures; 317 complete-session rationales contribute to scientific estimates. Every coder reply was parser-valid, with no invalid or unavailable reply. Audit-only coverage does not make an incomplete session eligible.", "evidenceSha": "sha256:91296e92f09907f7644fa008eaf9b832d13793f24f4dd7b2bde5461041e6785c" }, { "area": "Fixed sample size and prior exposure", "detail": "Main320 was fixed after prior PRICE02 numerical results were viewed. The historical-slot planning proxy is unvalidated and weak for Terra; no all-hypothesis80% power claim. Five unlabeled E1 code vectors were viewed after E2 design freeze,without subsequent design/analysis change. Later E2 scientific viewing must be separately retained.", "evidenceSha": "sha256:8f2678e91a1ea67d71edcb0e69e7b0be7957dd829a614888b5a8fdac76348fa2" }, { "area": "Exposure timing", "detail": "Preregistration-era E2 exposure was recorded separately and remains unchanged. After completed collection and coding, the author, root reviewer and independent numerical reviewer viewed actual aggregate results during initial analysis review; their real view times and scopes are retained. No raw participant response text, rationale text or individual E2 code vectors were reported viewed in this scoped record. Later report-viewing provenance must be retained separately; no permanent or global blindness claim is made.", "evidenceSha": "sha256:e35eb3d54080d85b5038f764c90d7b8bb2ded391339616e376db6a3ae0ffc89b" }, { "area": "Native source and app lineage", "detail": "The study uses an explicit source-registration adapter retaining original compiler ancestry; it is not a current canonical Library import. A genuine native recorded analysis may be completed only through its signed original reader. App integration remains pending absent separate supported import evidence.", "evidenceSha": "sha256:622001976aad81a710bad3244cc25c3cfd768699bd7ab06be32b85bf41642f55" }, { "area": "Pilot versus main gates", "detail": "The .0999 refusal/completion-failure cap is pilot-only. Main inference retains at least .90 valid observations in each pooled condition for the relevant outcome/code and the original five-consecutive dispatch-failure stop. Do not invent a new .0999 main cap.", "evidenceSha": "sha256:4fd3f510ca94934857aaef25f391ad6d3b146d81120fc4c1c55ae8ae7af389b9" }, { "area": "Software and admission chronology", "detail": "The grant-empty historical software baseline belongs to R2. R4 later completed full browser/build checks with its installed participant-continuation row. The original R5 normal build attempt remains recorded as exit 1: its completed broad test suites passed, but the unchanged stale-browser-evidence gate refused a pre-coder-admission fingerprint and the bundler did not run in that attempt. A separately recorded continuation at the current source fingerprint then passed fresh browser journeys 30/30, the original browser-evidence gate, and the exact application bundler, each with exit 0. The previously passed broad suites were carried from the preserved attempt, not rerun; this is not a claim that the earlier full command returned zero. Nonfatal large-chunk and static unknown-route notices remain disclosed. These bounded software receipts do not certify a generic completed app/Library scientific workflow.", "evidenceSha": "sha256:fd5140dd1e7e625be7f02a6f580e8f097b270ea336a28d4f2d15dcdcec72ea37" }, { "area": "Post-stop HTTP503 technical-missing amendment", "detail": "Ordinal 63 remains a raw provider-unknown, incomplete six-turn session. The signed D2 amendment accepts its narrowly verified HTTP503 stream disconnection as technical missingness for continued collection and computational analysis only; no terminal completion, score, retry, replacement or new sample is manufactured. The raw unknown is retained in source accounting.", "evidenceSha": "sha256:4fd3f510ca94934857aaef25f391ad6d3b146d81120fc4c1c55ae8ae7af389b9" }, { "area": "Post-stop null-status residual amendment", "detail": "The signed D3 amendment preserved the prior 277 attempts and admitted only untouched slots 278–320. Ordinal 277 has a literal null HTTP-status stream disconnection, distinct from numeric503 at63 and the separate known protocol failure at217. Final source accounting retains317 complete,1 known failure and2 raw unknowns, with one503 and one null-status technical-missing acceptance. Both accepted incomplete sessions remain ineligible. They enter native-all-unavailable sensitivity, not grammar-only missingness. No retries, reserves, enlarged N, new seed or generic unknown exemption were introduced.", "evidenceSha": "sha256:6f12e66a2e33f8c143d2ccb9ce80bbff6dfb3a41bd970f776777e8bd2f3f4ceb" }, { "area": "Final collection and computational accounting", "detail": "All 320 scheduled main slots were claimed and accounted for. Source dispositions remain317 complete,1 known failure and2 raw unknowns, with no unattempted slots. The separately labeled computational projection maps only the two authenticated technical-missing unknowns to missing known-failure observations, yielding317 eligible and3 unavailable sessions. Source history is not relabeled as resolved.", "evidenceSha": "sha256:8fd0a34f292aa488dd4bcb87a96b2112e98a3c2766b1bde33582a4bf88e12f6d" }, { "area": "Local pre-coding preparation handoff correction", "detail": "The first cached preparation stopped before any coding model call because its generic metadata traversal misclassified registered relative checklist and preserved root-relative inventory entries, followed by a pinned historical executable path inside a worktree directory. A separately reviewed additive local preparer handled only those exact metadata contexts and the empty pre-custody pack. The frozen runtime, scientific instrument, coding rules and original records were unchanged; actual coding then used the reviewed successor once.", "evidenceSha": "sha256:523d944c100e40751fd6161e97ed6084a74157c0d893374c6586163dde08ea8c" } ], "displayLabel": "PRICE-03", "frames": [ "Gain frame", "Loss frame" ], "hypotheses": [ { "adjustedP": 6.4655529674975555e-15, "comparisonId": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "id": "H1a", "model": "GPT-5.6 Terra", "outcome": "price", "prediction": "gain > loss", "verdict": "confirmed" }, { "adjustedP": 5.7465115942312956e-18, "comparisonId": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "id": "H1b", "model": "GPT-6 Sol", "outcome": "price", "prediction": "gain > loss", "verdict": "confirmed" }, { "adjustedP": 1.3037420881976849e-14, "comparisonId": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "id": "H2a", "model": "GPT-5.6 Terra", "outcome": "likelihood", "prediction": "gain > loss", "verdict": "confirmed" }, { "adjustedP": 9.114794351497384e-19, "comparisonId": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "id": "H2b", "model": "GPT-6 Sol", "outcome": "likelihood", "prediction": "gain > loss", "verdict": "confirmed" } ], "lineageNote": "PRICE-03 uses an explicit native source-registration adapter with original PRICE-01 ancestry and a fixed 320-slot E2 plan. The retained 84 prior pilot slots are excluded from main estimates. Original R2 records, the R4 HTTP503 continuation and the separate R5 null-status residual amendment remain linked without rewriting provider unknowns. Native final recording and OpenPsy app/Library integration are distinct: no canonical Library import or generic app scientific-workflow completion is claimed.", "models": [ "GPT-6 Sol", "GPT-5.6 Terra" ], "outcomes": [ { "cells": [ [ { "counts": [ 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 2, 0, 0, 0, 0, 3, 0, 0, 0, 0, 2, 0, 0, 0, 0, 72, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "interval": { "lower": 23.1229664163184, "upper": 24.702033583681605 }, "mean": 23.9125, "missing": {}, "n": 80, "scheduled": 80, "sd": 3.5478420968673055 }, { "counts": [ 0, 0, 0, 0, 0, 0, 0, 0, 28, 0, 10, 0, 0, 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 39, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "interval": { "lower": 14.983642996651662, "upper": 18.61635700334834 }, "mean": 16.8, "missing": {}, "n": 80, "scheduled": 80, "sd": 8.161967993014144 } ], [ { "counts": [ 0, 0, 0, 0, 0, 0, 0, 0, 31, 0, 19, 0, 0, 0, 0, 5, 0, 0, 0, 0, 1, 0, 0, 0, 0, 22, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "interval": { "lower": 12.234987263099066, "upper": 15.534243506131704 }, "mean": 13.884615384615385, "missing": { "known-failure": 2 }, "n": 78, "scheduled": 80, "sd": 7.316554382492351 }, { "counts": [ 0, 0, 0, 0, 0, 0, 0, 0, 72, 0, 5, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "interval": { "lower": 7.960424625650669, "upper": 8.900334868020218 }, "mean": 8.430379746835444, "missing": { "known-failure": 1 }, "n": 79, "scheduled": 80, "sd": 2.0981282519512083 } ] ], "id": "price", "inference": { "comparisons": [ { "adjustedP": 5.7465115942312956e-18, "df": null, "effect": 10.027884615384616, "exactDenominator": "2889449982408278562837529605317066835833256100", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 1.4366278985578239e-18, "second": [ 1, 0 ], "secondN": 78, "significant": true, "sourceContrastEstimate": 10.027884615384616, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 20.05576923076923, "stars": "***", "statistic": 20.05576923076923, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 6.4655529674975555e-15, "df": null, "effect": 8.369620253164557, "exactDenominator": "5778899964816557125675059210634133671666512200", "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 2.155184322499185e-15, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 8.369620253164557, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 16.746153846153845, "stars": "***", "statistic": 16.746153846153845, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.3723769942101888e-10, "df": null, "effect": 7.112500000000001, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 6.861884971050944e-11, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 7.112500000000001, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 14.225, "stars": "***", "statistic": 14.225, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.6183842358407942e-10, "df": null, "effect": 5.4542356377799415, "exactDenominator": "1463012649320647373588622584970666752320636000", "exactNumerator": null, "first": [ 1, 0 ], "firstN": 78, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 1.6183842358407942e-10, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 5.4542356377799415, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 10.915384615384616, "stars": "***", "statistic": 10.915384615384616, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." } ], "mode": "computed", "sourceBasis": "declared", "terms": [ { "b": 9.19690692713165, "df": 312, "interval": { "lower": 7.9027497324521, "upper": 10.4910641218112 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 7.897112381364753e-35, "se": 0.6577350566078346, "statistic": 13.982692323810829, "statisticLabel": "t", "term": "rows", "title": "main effect of Frame", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 6.281522311747034, "df": 312, "interval": { "lower": 4.987365117067484, "upper": 7.575679506426584 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 3.9664851525651024e-19, "se": 0.6577350566078346, "statistic": 9.55023188841872, "statisticLabel": "t", "term": "columns", "title": "main effect of Model", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 1.6619553765059316, "df": 312, "interval": { "lower": -0.9263590128531689, "upper": 4.250269765865032 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 0.20739131234847785, "se": 1.3154701132156692, "statistic": 1.2633927291919074, "statisticLabel": "t", "term": "interaction", "title": "interaction", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." } ] }, "kind": "scalar", "maximum": 60, "minimum": 0, "samples": [ { "cells": [ [ { "counts": [ 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 36, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "interval": { "lower": 22.3979792666738, "upper": 25.002020733326198 }, "mean": 23.7, "missing": {}, "n": 40, "scheduled": 40, "sd": 4.071161870321416 }, { "counts": [ 0, 0, 0, 0, 0, 0, 0, 0, 15, 0, 6, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 18, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "interval": { "lower": 13.496511845078409, "upper": 18.75348815492159 }, "mean": 16.125, "missing": {}, "n": 40, "scheduled": 40, "sd": 8.21876371013773 } ], [ { "counts": [ 0, 0, 0, 0, 0, 0, 0, 0, 20, 0, 7, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 11, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "interval": { "lower": 10.896907018540968, "upper": 15.7697596481257 }, "mean": 13.333333333333334, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "sd": 7.516064666444497 }, { "counts": [ 0, 0, 0, 0, 0, 0, 0, 0, 36, 0, 2, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "interval": { "lower": 7.774785775459093, "upper": 9.625214224540905 }, "mean": 8.7, "missing": {}, "n": 40, "scheduled": 40, "sd": 2.8929622827183157 } ] ], "id": "sample-1" }, { "cells": [ [ { "counts": [ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 2, 0, 0, 0, 0, 36, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "interval": { "lower": 23.174651192300097, "upper": 25.075348807699903 }, "mean": 24.125, "missing": {}, "n": 40, "scheduled": 40, "sd": 2.9715531637728114 }, { "counts": [ 0, 0, 0, 0, 0, 0, 0, 0, 13, 0, 4, 0, 0, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 21, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "interval": { "lower": 14.867750275240612, "upper": 20.082249724759393 }, "mean": 17.475, "missing": {}, "n": 40, "scheduled": 40, "sd": 8.152355330571494 } ], [ { "counts": [ 0, 0, 0, 0, 0, 0, 0, 0, 11, 0, 12, 0, 0, 0, 0, 4, 0, 0, 0, 0, 1, 0, 0, 0, 0, 11, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "interval": { "lower": 12.112811697319133, "upper": 16.758983174475738 }, "mean": 14.435897435897436, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "sd": 7.166423433715667 }, { "counts": [ 0, 0, 0, 0, 0, 0, 0, 0, 36, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 ], "interval": { "lower": 7.978829028994249, "upper": 8.328863278698059 }, "mean": 8.153846153846153, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "sd": 0.539905524799017 } ] ], "id": "sample-2" } ], "sensitivity": [ { "bounds": [ { "condition": [ 0, 0 ], "includedMissing": 0, "lower": 23.9125, "observed": 23.9125, "upper": 23.9125 }, { "condition": [ 0, 1 ], "includedMissing": 0, "lower": 16.8, "observed": 16.8, "upper": 16.8 }, { "condition": [ 1, 0 ], "includedMissing": 0, "lower": 13.884615384615385, "observed": 13.884615384615385, "upper": 13.884615384615385 }, { "condition": [ 1, 1 ], "includedMissing": 0, "lower": 8.430379746835444, "observed": 8.430379746835444, "upper": 8.430379746835444 } ], "id": "registered-grammar", "label": "Registered grammar-only endpoint sensitivity", "scenarios": [ { "id": "all-minimum", "inference": { "comparisons": [ { "adjustedP": 5.7465115942312956e-18, "df": null, "effect": 10.027884615384616, "exactDenominator": "2889449982408278562837529605317066835833256100", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 1.4366278985578239e-18, "second": [ 1, 0 ], "secondN": 78, "significant": true, "sourceContrastEstimate": 10.027884615384616, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 20.05576923076923, "stars": "***", "statistic": 20.05576923076923, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 6.4655529674975555e-15, "df": null, "effect": 8.369620253164557, "exactDenominator": "5778899964816557125675059210634133671666512200", "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 2.155184322499185e-15, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 8.369620253164557, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 16.746153846153845, "stars": "***", "statistic": 16.746153846153845, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.3723769942101888e-10, "df": null, "effect": 7.112500000000001, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 6.861884971050944e-11, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 7.112500000000001, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 14.225, "stars": "***", "statistic": 14.225, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.6183842358407942e-10, "df": null, "effect": 5.4542356377799415, "exactDenominator": "1463012649320647373588622584970666752320636000", "exactNumerator": null, "first": [ 1, 0 ], "firstN": 78, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 1.6183842358407942e-10, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 5.4542356377799415, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 10.915384615384616, "stars": "***", "statistic": 10.915384615384616, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." } ], "mode": "computed" }, "label": "all-minimum", "modelTerms": { "status": "available", "terms": [ { "b": 9.19690692713165, "df": 312, "interval": { "lower": 7.9027497324521, "upper": 10.4910641218112 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 7.897112381364753e-35, "se": 0.6577350566078346, "statistic": 13.982692323810829, "statisticLabel": "t", "term": "rows", "title": "main effect of Frame", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 6.281522311747034, "df": 312, "interval": { "lower": 4.987365117067484, "upper": 7.575679506426584 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 3.9664851525651024e-19, "se": 0.6577350566078346, "statistic": 9.55023188841872, "statisticLabel": "t", "term": "columns", "title": "main effect of Model", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 1.6619553765059316, "df": 312, "interval": { "lower": -0.9263590128531689, "upper": 4.250269765865032 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 0.20739131234847785, "se": 1.3154701132156692, "statistic": 1.2633927291919074, "statisticLabel": "t", "term": "interaction", "title": "interaction", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." } ] } }, { "id": "all-maximum", "inference": { "comparisons": [ { "adjustedP": 5.7465115942312956e-18, "df": null, "effect": 10.027884615384616, "exactDenominator": "2889449982408278562837529605317066835833256100", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 1.4366278985578239e-18, "second": [ 1, 0 ], "secondN": 78, "significant": true, "sourceContrastEstimate": 10.027884615384616, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 20.05576923076923, "stars": "***", "statistic": 20.05576923076923, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 6.4655529674975555e-15, "df": null, "effect": 8.369620253164557, "exactDenominator": "5778899964816557125675059210634133671666512200", "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 2.155184322499185e-15, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 8.369620253164557, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 16.746153846153845, "stars": "***", "statistic": 16.746153846153845, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.3723769942101888e-10, "df": null, "effect": 7.112500000000001, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 6.861884971050944e-11, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 7.112500000000001, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 14.225, "stars": "***", "statistic": 14.225, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.6183842358407942e-10, "df": null, "effect": 5.4542356377799415, "exactDenominator": "1463012649320647373588622584970666752320636000", "exactNumerator": null, "first": [ 1, 0 ], "firstN": 78, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 1.6183842358407942e-10, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 5.4542356377799415, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 10.915384615384616, "stars": "***", "statistic": 10.915384615384616, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." } ], "mode": "computed" }, "label": "all-maximum", "modelTerms": { "status": "available", "terms": [ { "b": 9.19690692713165, "df": 312, "interval": { "lower": 7.9027497324521, "upper": 10.4910641218112 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 7.897112381364753e-35, "se": 0.6577350566078346, "statistic": 13.982692323810829, "statisticLabel": "t", "term": "rows", "title": "main effect of Frame", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 6.281522311747034, "df": 312, "interval": { "lower": 4.987365117067484, "upper": 7.575679506426584 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 3.9664851525651024e-19, "se": 0.6577350566078346, "statistic": 9.55023188841872, "statisticLabel": "t", "term": "columns", "title": "main effect of Model", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 1.6619553765059316, "df": 312, "interval": { "lower": -0.9263590128531689, "upper": 4.250269765865032 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 0.20739131234847785, "se": 1.3154701132156692, "statistic": 1.2633927291919074, "statisticLabel": "t", "term": "interaction", "title": "interaction", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." } ] } }, { "id": "least-favourable", "inference": { "comparisons": [ { "adjustedP": 5.7465115942312956e-18, "df": null, "effect": 10.027884615384616, "exactDenominator": "2889449982408278562837529605317066835833256100", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 1.4366278985578239e-18, "second": [ 1, 0 ], "secondN": 78, "significant": true, "sourceContrastEstimate": 10.027884615384616, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 20.05576923076923, "stars": "***", "statistic": 20.05576923076923, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 6.4655529674975555e-15, "df": null, "effect": 8.369620253164557, "exactDenominator": "5778899964816557125675059210634133671666512200", "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 2.155184322499185e-15, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 8.369620253164557, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 16.746153846153845, "stars": "***", "statistic": 16.746153846153845, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.3723769942101888e-10, "df": null, "effect": 7.112500000000001, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 6.861884971050944e-11, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 7.112500000000001, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 14.225, "stars": "***", "statistic": 14.225, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.6183842358407942e-10, "df": null, "effect": 5.4542356377799415, "exactDenominator": "1463012649320647373588622584970666752320636000", "exactNumerator": null, "first": [ 1, 0 ], "firstN": 78, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 1.6183842358407942e-10, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 5.4542356377799415, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 10.915384615384616, "stars": "***", "statistic": 10.915384615384616, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." } ], "mode": "computed" }, "label": "least-favourable", "modelTerms": { "status": "available", "terms": [ { "b": 9.19690692713165, "df": 312, "interval": { "lower": 7.9027497324521, "upper": 10.4910641218112 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 7.897112381364753e-35, "se": 0.6577350566078346, "statistic": 13.982692323810829, "statisticLabel": "t", "term": "rows", "title": "main effect of Frame", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 6.281522311747034, "df": 312, "interval": { "lower": 4.987365117067484, "upper": 7.575679506426584 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 3.9664851525651024e-19, "se": 0.6577350566078346, "statistic": 9.55023188841872, "statisticLabel": "t", "term": "columns", "title": "main effect of Model", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 1.6619553765059316, "df": 312, "interval": { "lower": -0.9263590128531689, "upper": 4.250269765865032 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 0.20739131234847785, "se": 1.3154701132156692, "statistic": 1.2633927291919074, "statisticLabel": "t", "term": "interaction", "title": "interaction", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." } ] } } ], "scope": "registered-grammar-only", "status": "available" }, { "bounds": [ { "condition": [ 0, 0 ], "includedMissing": 0, "lower": 23.9125, "observed": 23.9125, "upper": 23.9125 }, { "condition": [ 0, 1 ], "includedMissing": 0, "lower": 16.8, "observed": 16.8, "upper": 16.8 }, { "condition": [ 1, 0 ], "includedMissing": 2, "lower": 13.5375, "observed": 13.884615384615385, "upper": 15.0375 }, { "condition": [ 1, 1 ], "includedMissing": 1, "lower": 8.325, "observed": 8.430379746835444, "upper": 9.075 } ], "id": "native-unavailable", "label": "All unavailable scheduled outcomes: native endpoint sensitivity", "scenarios": [ { "id": "all-minimum", "inference": { "comparisons": [ { "adjustedP": 1.922921270734387e-18, "df": null, "effect": 10.375000000000002, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 4.807303176835967e-19, "second": [ 1, 0 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 10.375000000000002, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 20.75, "stars": "***", "statistic": 20.75, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 3.1115933271182335e-15, "df": null, "effect": 8.475000000000001, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 1.0371977757060778e-15, "second": [ 1, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 8.475000000000001, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 16.95, "stars": "***", "statistic": 16.95, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.3723769942101888e-10, "df": null, "effect": 7.112500000000001, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 6.861884971050944e-11, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 7.112500000000001, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 14.225, "stars": "***", "statistic": 14.225, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 6.076399003944069e-09, "df": null, "effect": 5.2125, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 1, 0 ], "firstN": 80, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 6.076399003944069e-09, "second": [ 1, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 5.2125, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 10.425, "stars": "***", "statistic": 10.425, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." } ], "mode": "computed" }, "label": "all-minimum", "modelTerms": { "status": "available", "terms": [ { "b": 9.425, "df": 315, "interval": { "lower": 8.116449805048457, "upper": 10.733550194951544 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 1.3173361223427632e-35, "se": 0.6650747362228585, "statistic": 14.171339680600644, "statisticLabel": "t", "term": "rows", "title": "main effect of Frame", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 6.1625000000000005, "df": 315, "interval": { "lower": 4.853949805048456, "upper": 7.471050194951545 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 3.1283941701146723e-18, "se": 0.6650747362228585, "statistic": 9.265875945008112, "statisticLabel": "t", "term": "columns", "title": "main effect of Model", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 1.9000000000000001, "df": 315, "interval": { "lower": -0.7171003899030877, "upper": 4.517100389903088 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 0.1541643852956336, "se": 1.330149472445717, "statistic": 1.4284108961878632, "statisticLabel": "t", "term": "interaction", "title": "interaction", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." } ] } }, { "id": "all-maximum", "inference": { "comparisons": [ { "adjustedP": 1.1623394939661636e-11, "df": null, "effect": 8.875000000000002, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 2.905848734915409e-12, "second": [ 1, 0 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 8.875000000000002, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 17.75, "stars": "***", "statistic": 17.75, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.0357341317793132e-10, "df": null, "effect": 7.725000000000001, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 3.4524471059310436e-11, "second": [ 1, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 7.725000000000001, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 15.45, "stars": "***", "statistic": 15.45, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.3723769942101888e-10, "df": null, "effect": 7.112500000000001, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 6.861884971050944e-11, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 7.112500000000001, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 14.225, "stars": "***", "statistic": 14.225, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 6.606109650343677e-07, "df": null, "effect": 5.9625, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 1, 0 ], "firstN": 80, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 6.606109650343677e-07, "second": [ 1, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 5.9625, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 11.925, "stars": "***", "statistic": 11.925, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." } ], "mode": "computed" }, "label": "all-maximum", "modelTerms": { "status": "available", "terms": [ { "b": 8.3, "df": 315, "interval": { "lower": 6.6636408223619785, "upper": 9.936359177638023 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 1.465472842013943e-20, "se": 0.8316846786865228, "statistic": 9.979743781150527, "statisticLabel": "t", "term": "rows", "title": "main effect of Frame", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 6.5375000000000005, "df": 315, "interval": { "lower": 4.9011408223619775, "upper": 8.173859177638024 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 6.121912390385711e-14, "se": 0.8316846786865228, "statistic": 7.860551201117056, "statisticLabel": "t", "term": "columns", "title": "main effect of Model", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 1.1500000000000001, "df": 315, "interval": { "lower": -2.122718355276045, "upper": 4.422718355276046 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 0.4898436466433439, "se": 1.6633693573730457, "statistic": 0.691367792067657, "statisticLabel": "t", "term": "interaction", "title": "interaction", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." } ] } }, { "id": "least-favourable", "inference": { "comparisons": [ { "adjustedP": 1.1623394939661636e-11, "df": null, "effect": 8.875000000000002, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 2.905848734915409e-12, "second": [ 1, 0 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 8.875000000000002, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 17.75, "stars": "***", "statistic": 17.75, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.0357341317793132e-10, "df": null, "effect": 7.725000000000001, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 3.4524471059310436e-11, "second": [ 1, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 7.725000000000001, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 15.45, "stars": "***", "statistic": 15.45, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.3723769942101888e-10, "df": null, "effect": 7.112500000000001, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 6.861884971050944e-11, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 7.112500000000001, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 14.225, "stars": "***", "statistic": 14.225, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 6.606109650343677e-07, "df": null, "effect": 5.9625, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 1, 0 ], "firstN": 80, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 6.606109650343677e-07, "second": [ 1, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 5.9625, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 11.925, "stars": "***", "statistic": 11.925, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." } ], "mode": "computed" }, "label": "least-favourable", "modelTerms": { "status": "available", "terms": [ { "b": 8.3, "df": 315, "interval": { "lower": 6.6636408223619785, "upper": 9.936359177638023 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 1.465472842013943e-20, "se": 0.8316846786865228, "statistic": 9.979743781150527, "statisticLabel": "t", "term": "rows", "title": "main effect of Frame", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 6.5375000000000005, "df": 315, "interval": { "lower": 4.9011408223619775, "upper": 8.173859177638024 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 6.121912390385711e-14, "se": 0.8316846786865228, "statistic": 7.860551201117056, "statisticLabel": "t", "term": "columns", "title": "main effect of Model", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 1.1500000000000001, "df": 315, "interval": { "lower": -2.122718355276045, "upper": 4.422718355276046 }, "intervalMethod": "Reporting-derived individual unadjusted 95% Wald-t coefficient interval from native b, SE and residual df.", "intervalUnavailableReason": null, "method": "ols-wald-t", "p": 0.4898436466433439, "se": 1.6633693573730457, "statistic": 0.691367792067657, "statisticLabel": "t", "term": "interaction", "title": "interaction", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." } ] } } ], "scope": "native-all-unavailable", "status": "available" } ], "title": "Maximum price for one course (US dollars)" }, { "cells": [ [ { "counts": [ 1, 5, 2, 8, 48, 16, 0 ], "interval": { "lower": 4.5747251294113775, "upper": 5.0502748705886225 }, "mean": 4.8125, "missing": {}, "n": 80, "scheduled": 80, "sd": 1.0684633470787066 }, { "counts": [ 32, 9, 0, 8, 2, 5, 24 ], "interval": { "lower": 3.037415903541361, "upper": 4.212584096458639 }, "mean": 3.625, "missing": {}, "n": 80, "scheduled": 80, "sd": 2.6403634195583328 } ], [ { "counts": [ 35, 21, 0, 9, 10, 3, 0 ], "interval": { "lower": 1.9562471350595234, "upper": 2.684778505966118 }, "mean": 2.3205128205128207, "missing": { "known-failure": 2 }, "n": 78, "scheduled": 80, "sd": 1.6156184915452998 }, { "counts": [ 71, 7, 0, 1, 0, 0, 0 ], "interval": { "lower": 1.0292313724043076, "upper": 1.2239331845577177 }, "mean": 1.1265822784810127, "missing": { "known-failure": 1 }, "n": 79, "scheduled": 80, "sd": 0.43462594019115985 } ] ], "id": "likelihood", "inference": { "comparisons": [ { "adjustedP": 9.114794351497384e-19, "df": null, "effect": 2.4919871794871793, "exactDenominator": "2889449982408278562837529605317066835833256100", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 2.278698587874346e-19, "second": [ 1, 0 ], "secondN": 78, "significant": true, "sourceContrastEstimate": 2.4919871794871793, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 4.983974358974359, "stars": "***", "statistic": 4.983974358974359, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.3037420881976849e-14, "df": null, "effect": 2.4984177215189876, "exactDenominator": "5778899964816557125675059210634133671666512200", "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 4.34580696065895e-15, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 2.4984177215189876, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 4.9974358974358974, "stars": "***", "statistic": 4.9974358974358974, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 0.00033587149056831336, "df": null, "effect": 1.1875, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 0.00033587149056831336, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 1.1875, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 2.375, "stars": "***", "statistic": 2.375, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.4518953070910794e-10, "df": null, "effect": 1.193930542031808, "exactDenominator": "1463012649320647373588622584970666752320636000", "exactNumerator": null, "first": [ 1, 0 ], "firstN": 78, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 7.259476535455397e-11, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 1.193930542031808, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 2.3884615384615384, "stars": "***", "statistic": 2.3884615384615384, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." } ], "mode": "computed", "sourceBasis": "declared", "terms": [] }, "kind": "scalar", "maximum": 7, "minimum": 1, "samples": [ { "cells": [ [ { "counts": [ 1, 3, 0, 4, 25, 7, 0 ], "interval": { "lower": 4.382488578498059, "upper": 5.117511421501941 }, "mean": 4.75, "missing": {}, "n": 40, "scheduled": 40, "sd": 1.1491356841177722 }, { "counts": [ 19, 3, 0, 5, 0, 3, 10 ], "interval": { "lower": 2.4885503757951724, "upper": 4.1614496242048284 }, "mean": 3.325, "missing": {}, "n": 40, "scheduled": 40, "sd": 2.6154128957747025 } ], [ { "counts": [ 21, 7, 0, 4, 6, 1, 0 ], "interval": { "lower": 1.6921194540363778, "upper": 2.769419007502084 }, "mean": 2.230769230769231, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "sd": 1.6616659120409454 }, { "counts": [ 36, 3, 0, 1, 0, 0, 0 ], "interval": { "lower": 0.9793804801358542, "upper": 1.3206195198641457 }, "mean": 1.15, "missing": {}, "n": 40, "scheduled": 40, "sd": 0.533493565673837 } ] ], "id": "sample-1" }, { "cells": [ [ { "counts": [ 0, 2, 2, 4, 23, 9, 0 ], "interval": { "lower": 4.55775745858319, "upper": 5.19224254141681 }, "mean": 4.875, "missing": {}, "n": 40, "scheduled": 40, "sd": 0.9919548170024474 }, { "counts": [ 13, 6, 0, 3, 2, 2, 14 ], "interval": { "lower": 3.0730175362838446, "upper": 4.7769824637161555 }, "mean": 3.925, "missing": {}, "n": 40, "scheduled": 40, "sd": 2.6639810194134026 } ], [ { "counts": [ 14, 14, 0, 5, 4, 2, 0 ], "interval": { "lower": 1.8965359581997254, "upper": 2.923976862313095 }, "mean": 2.41025641025641, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "sd": 1.584762122577138 }, { "counts": [ 35, 4, 0, 0, 0, 0, 0 ], "interval": { "lower": 1.0029312213664765, "upper": 1.2021969837617288 }, "mean": 1.1025641025641026, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "sd": 0.30735474060472817 } ] ], "id": "sample-2" } ], "sensitivity": [ { "bounds": [ { "condition": [ 0, 0 ], "includedMissing": 0, "lower": 4.8125, "observed": 4.8125, "upper": 4.8125 }, { "condition": [ 0, 1 ], "includedMissing": 0, "lower": 3.625, "observed": 3.625, "upper": 3.625 }, { "condition": [ 1, 0 ], "includedMissing": 0, "lower": 2.3205128205128207, "observed": 2.3205128205128207, "upper": 2.3205128205128207 }, { "condition": [ 1, 1 ], "includedMissing": 0, "lower": 1.1265822784810127, "observed": 1.1265822784810127, "upper": 1.1265822784810127 } ], "id": "registered-grammar", "label": "Registered grammar-only endpoint sensitivity", "scenarios": [ { "id": "all-minimum", "inference": { "comparisons": [ { "adjustedP": 9.114794351497384e-19, "df": null, "effect": 2.4919871794871793, "exactDenominator": "2889449982408278562837529605317066835833256100", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 2.278698587874346e-19, "second": [ 1, 0 ], "secondN": 78, "significant": true, "sourceContrastEstimate": 2.4919871794871793, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 4.983974358974359, "stars": "***", "statistic": 4.983974358974359, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.3037420881976849e-14, "df": null, "effect": 2.4984177215189876, "exactDenominator": "5778899964816557125675059210634133671666512200", "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 4.34580696065895e-15, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 2.4984177215189876, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 4.9974358974358974, "stars": "***", "statistic": 4.9974358974358974, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 0.00033587149056831336, "df": null, "effect": 1.1875, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 0.00033587149056831336, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 1.1875, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 2.375, "stars": "***", "statistic": 2.375, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.4518953070910794e-10, "df": null, "effect": 1.193930542031808, "exactDenominator": "1463012649320647373588622584970666752320636000", "exactNumerator": null, "first": [ 1, 0 ], "firstN": 78, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 7.259476535455397e-11, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 1.193930542031808, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 2.3884615384615384, "stars": "***", "statistic": 2.3884615384615384, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." } ], "mode": "computed" }, "label": "all-minimum", "modelTerms": { "reason": "No likelihood omnibus model is declared.", "status": "not-declared", "terms": [] } }, { "id": "all-maximum", "inference": { "comparisons": [ { "adjustedP": 9.114794351497384e-19, "df": null, "effect": 2.4919871794871793, "exactDenominator": "2889449982408278562837529605317066835833256100", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 2.278698587874346e-19, "second": [ 1, 0 ], "secondN": 78, "significant": true, "sourceContrastEstimate": 2.4919871794871793, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 4.983974358974359, "stars": "***", "statistic": 4.983974358974359, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.3037420881976849e-14, "df": null, "effect": 2.4984177215189876, "exactDenominator": "5778899964816557125675059210634133671666512200", "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 4.34580696065895e-15, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 2.4984177215189876, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 4.9974358974358974, "stars": "***", "statistic": 4.9974358974358974, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 0.00033587149056831336, "df": null, "effect": 1.1875, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 0.00033587149056831336, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 1.1875, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 2.375, "stars": "***", "statistic": 2.375, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.4518953070910794e-10, "df": null, "effect": 1.193930542031808, "exactDenominator": "1463012649320647373588622584970666752320636000", "exactNumerator": null, "first": [ 1, 0 ], "firstN": 78, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 7.259476535455397e-11, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 1.193930542031808, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 2.3884615384615384, "stars": "***", "statistic": 2.3884615384615384, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." } ], "mode": "computed" }, "label": "all-maximum", "modelTerms": { "reason": "No likelihood omnibus model is declared.", "status": "not-declared", "terms": [] } }, { "id": "least-favourable", "inference": { "comparisons": [ { "adjustedP": 9.114794351497384e-19, "df": null, "effect": 2.4919871794871793, "exactDenominator": "2889449982408278562837529605317066835833256100", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 2.278698587874346e-19, "second": [ 1, 0 ], "secondN": 78, "significant": true, "sourceContrastEstimate": 2.4919871794871793, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 4.983974358974359, "stars": "***", "statistic": 4.983974358974359, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.3037420881976849e-14, "df": null, "effect": 2.4984177215189876, "exactDenominator": "5778899964816557125675059210634133671666512200", "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 4.34580696065895e-15, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 2.4984177215189876, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 4.9974358974358974, "stars": "***", "statistic": 4.9974358974358974, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 0.00033587149056831336, "df": null, "effect": 1.1875, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 0.00033587149056831336, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 1.1875, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 2.375, "stars": "***", "statistic": 2.375, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.4518953070910794e-10, "df": null, "effect": 1.193930542031808, "exactDenominator": "1463012649320647373588622584970666752320636000", "exactNumerator": null, "first": [ 1, 0 ], "firstN": 78, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 7.259476535455397e-11, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 1.193930542031808, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 2.3884615384615384, "stars": "***", "statistic": 2.3884615384615384, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." } ], "mode": "computed" }, "label": "least-favourable", "modelTerms": { "reason": "No likelihood omnibus model is declared.", "status": "not-declared", "terms": [] } } ], "scope": "registered-grammar-only", "status": "available" }, { "bounds": [ { "condition": [ 0, 0 ], "includedMissing": 0, "lower": 4.8125, "observed": 4.8125, "upper": 4.8125 }, { "condition": [ 0, 1 ], "includedMissing": 0, "lower": 3.625, "observed": 3.625, "upper": 3.625 }, { "condition": [ 1, 0 ], "includedMissing": 2, "lower": 2.2875, "observed": 2.3205128205128207, "upper": 2.4375 }, { "condition": [ 1, 1 ], "includedMissing": 1, "lower": 1.125, "observed": 1.1265822784810127, "upper": 1.2 } ], "id": "native-unavailable", "label": "All unavailable scheduled outcomes: native endpoint sensitivity", "scenarios": [ { "id": "all-minimum", "inference": { "comparisons": [ { "adjustedP": 3.1326898861687293e-19, "df": null, "effect": 2.525, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 7.831724715421823e-20, "second": [ 1, 0 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 2.525, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 5.05, "stars": "***", "statistic": 5.05, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 1.1551387771783214e-14, "df": null, "effect": 2.5, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 3.8504625905944045e-15, "second": [ 1, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 2.5, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 5, "stars": "***", "statistic": 5, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 0.00033587149056831336, "df": null, "effect": 1.1875, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 0.00033587149056831336, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 1.1875, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 2.375, "stars": "***", "statistic": 2.375, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 6.267243215820973e-10, "df": null, "effect": 1.1625, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 1, 0 ], "firstN": 80, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 3.1336216079104864e-10, "second": [ 1, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 1.1625, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 2.325, "stars": "***", "statistic": 2.325, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." } ], "mode": "computed" }, "label": "all-minimum", "modelTerms": { "reason": "No likelihood omnibus model is declared.", "status": "not-declared", "terms": [] } }, { "id": "all-maximum", "inference": { "comparisons": [ { "adjustedP": 1.397882385759477e-16, "df": null, "effect": 2.375, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 3.4947059643986925e-17, "second": [ 1, 0 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 2.375, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 4.75, "stars": "***", "statistic": 4.75, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 6.66674278731131e-13, "df": null, "effect": 2.425, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 2.2222475957704367e-13, "second": [ 1, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 2.425, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 4.85, "stars": "***", "statistic": 4.85, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 0.00033587149056831336, "df": null, "effect": 1.1875, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 0.00033587149056831336, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 1.1875, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 2.375, "stars": "***", "statistic": 2.375, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 2.0296006308933338e-08, "df": null, "effect": 1.2375, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 1, 0 ], "firstN": 80, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 1.0148003154466669e-08, "second": [ 1, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 1.2375, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 2.475, "stars": "***", "statistic": 2.475, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." } ], "mode": "computed" }, "label": "all-maximum", "modelTerms": { "reason": "No likelihood omnibus model is declared.", "status": "not-declared", "terms": [] } }, { "id": "least-favourable", "inference": { "comparisons": [ { "adjustedP": 1.397882385759477e-16, "df": null, "effect": 2.375, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 3.4947059643986925e-17, "second": [ 1, 0 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 2.375, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 4.75, "stars": "***", "statistic": 4.75, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 6.66674278731131e-13, "df": null, "effect": 2.425, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 2.2222475957704367e-13, "second": [ 1, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 2.425, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 4.85, "stars": "***", "statistic": 4.85, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 0.00033587149056831336, "df": null, "effect": 1.1875, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 0.00033587149056831336, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 1.1875, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 2.375, "stars": "***", "statistic": 2.375, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." }, { "adjustedP": 2.0296006308933338e-08, "df": null, "effect": 1.2375, "exactDenominator": "11557799929633114251350118421268267343333024400", "exactNumerator": null, "first": [ 1, 0 ], "firstN": 80, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-permutation-mean-difference-stratified-by-sample", "p": 1.0148003154466669e-08, "second": [ 1, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 1.2375, "sourceContrastSE": null, "sourceContrastScale": "outcome units", "sourceContrastStatistic": 2.475, "stars": "***", "statistic": 2.475, "statisticLabel": "Summed within-sample difference in means", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native exact output supplies no SE, t, df, contrast interval or exact tail numerator; its exact allocation count is retained." } ], "mode": "computed" }, "label": "least-favourable", "modelTerms": { "reason": "No likelihood omnibus model is declared.", "status": "not-declared", "terms": [] } } ], "scope": "native-all-unavailable", "status": "available" } ], "title": "Likelihood of buying at 25 US dollars" }, { "cells": [ [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 80, "scheduled": 80, "successes": 10 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 80, "scheduled": 80, "successes": 12 } ], [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 2 }, "n": 78, "scheduled": 80, "successes": 24 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 79, "scheduled": 80, "successes": 49 } ] ], "id": "SHORTFALL", "inference": { "comparisons": [ { "adjustedP": 0.012090766020948456, "df": null, "effect": -0.1826923076923077, "exactDenominator": null, "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-conditional-stratified-by-sample", "p": 0.006045383010474228, "second": [ 1, 0 ], "secondN": 78, "significant": true, "sourceContrastEstimate": -0.1826923076923077, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "*", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." }, { "adjustedP": 3.363581018771396e-09, "df": null, "effect": -0.470253164556962, "exactDenominator": null, "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-conditional-stratified-by-sample", "p": 8.40895254692849e-10, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": -0.470253164556962, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "***", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." }, { "adjustedP": 0.8194101267604893, "df": null, "effect": -0.024999999999999994, "exactDenominator": null, "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-conditional-stratified-by-sample", "p": 0.8194101267604893, "second": [ 0, 1 ], "secondN": 80, "significant": false, "sourceContrastEstimate": -0.024999999999999994, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." }, { "adjustedP": 0.0003430134950356143, "df": null, "effect": -0.3125608568646543, "exactDenominator": null, "exactNumerator": null, "first": [ 1, 0 ], "firstN": 78, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-conditional-stratified-by-sample", "p": 0.0001143378316785381, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": -0.3125608568646543, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "***", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." } ], "mode": "computed", "sourceBasis": "declared", "terms": [ { "b": -1.6874900566418236, "df": null, "interval": { "lower": -2.2487155843117366, "upper": -1.1262645289719107 }, "intervalMethod": "Reporting-derived individual unadjusted 95% normal/Wald coefficient interval from native b and SE.", "intervalUnavailableReason": null, "method": "wald-z", "p": 3.7876518731152855e-09, "se": 0.28634481658682936, "statistic": -5.893209720910454, "statisticLabel": "z", "term": "rows", "title": "main effect of Frame", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": -0.7606886158671053, "df": null, "interval": { "lower": -1.3214841995382125, "upper": -0.19989303219599808 }, "intervalMethod": "Reporting-derived individual unadjusted 95% normal/Wald coefficient interval from native b and SE.", "intervalUnavailableReason": null, "method": "wald-z", "p": 0.007846973496521874, "se": 0.2861254533729147, "statistic": -2.658584222060385, "statisticLabel": "z", "term": "columns", "title": "main effect of Model", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 1.0977697147871572, "df": null, "interval": { "lower": -0.023731513596894738, "upper": 2.2192709431712094 }, "intervalMethod": "Reporting-derived individual unadjusted 95% normal/Wald coefficient interval from native b and SE.", "intervalUnavailableReason": null, "method": "wald-z", "p": 0.05504888488323878, "se": 0.572205018679073, "statistic": 1.9184901896200468, "statisticLabel": "z", "term": "interaction", "title": "interaction", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." } ] }, "kind": "binary", "maximum": 1, "minimum": 0, "samples": [ { "cells": [ [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 4 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 6 } ], [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "successes": 8 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 26 } ] ], "id": "sample-1" }, { "cells": [ [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 6 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 6 } ], [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "successes": 16 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "successes": 23 } ] ], "id": "sample-2" } ], "sensitivity": [ { "bounds": [ { "condition": [ 0, 0 ], "includedMissing": 0, "lower": 0.125, "observed": 0.125, "upper": 0.125 }, { "condition": [ 0, 1 ], "includedMissing": 0, "lower": 0.15, "observed": 0.15, "upper": 0.15 }, { "condition": [ 1, 0 ], "includedMissing": 0, "lower": 0.3076923076923077, "observed": 0.3076923076923077, "upper": 0.3076923076923077 }, { "condition": [ 1, 1 ], "includedMissing": 0, "lower": 0.620253164556962, "observed": 0.620253164556962, "upper": 0.620253164556962 } ], "id": "registered-coder-grammar", "label": "registered-captured-coder-grammar", "scenarios": [], "scope": "registered-captured-coder-grammar", "status": "available" }, { "bounds": [ { "condition": [ 0, 0 ], "includedMissing": 0, "lower": 0.125, "observed": 0.125, "upper": 0.125 }, { "condition": [ 0, 1 ], "includedMissing": 0, "lower": 0.15, "observed": 0.15, "upper": 0.15 }, { "condition": [ 1, 0 ], "includedMissing": 2, "lower": 0.3, "observed": 0.3076923076923077, "upper": 0.325 }, { "condition": [ 1, 1 ], "includedMissing": 1, "lower": 0.6125, "observed": 0.620253164556962, "upper": 0.625 } ], "id": "native-unavailable", "label": "native-all-unavailable", "scenarios": [], "scope": "native-all-unavailable", "status": "available" } ], "title": "Unprotected share lowers the price" }, { "cells": [ [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 80, "scheduled": 80, "successes": 28 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 80, "scheduled": 80, "successes": 33 } ], [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 2 }, "n": 78, "scheduled": 80, "successes": 16 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 79, "scheduled": 80, "successes": 10 } ] ], "id": "PROTECTION_VALUE", "inference": { "comparisons": [ { "adjustedP": 0.15515081091559954, "df": null, "effect": 0.14487179487179486, "exactDenominator": null, "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-conditional-stratified-by-sample", "p": 0.051716936971866516, "second": [ 1, 0 ], "secondN": 78, "significant": false, "sourceContrastEstimate": 0.14487179487179486, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." }, { "adjustedP": 0.0002655473251622056, "df": null, "effect": 0.2859177215189873, "exactDenominator": null, "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-conditional-stratified-by-sample", "p": 6.63868312905514e-05, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": 0.2859177215189873, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "***", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." }, { "adjustedP": 0.5164608269997968, "df": null, "effect": -0.0625, "exactDenominator": null, "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-conditional-stratified-by-sample", "p": 0.5164608269997968, "second": [ 0, 1 ], "secondN": 80, "significant": false, "sourceContrastEstimate": -0.0625, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." }, { "adjustedP": 0.39986073267908284, "df": null, "effect": 0.07854592664719245, "exactDenominator": null, "exactNumerator": null, "first": [ 1, 0 ], "firstN": 78, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-conditional-stratified-by-sample", "p": 0.19993036633954142, "second": [ 1, 1 ], "secondN": 79, "significant": false, "sourceContrastEstimate": 0.07854592664719245, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." } ], "mode": "computed", "sourceBasis": "declared", "terms": [ { "b": 1.1608814854422163, "df": null, "interval": { "lower": 0.6231351580908108, "upper": 1.6986278127936218 }, "intervalMethod": "Reporting-derived individual unadjusted 95% normal/Wald coefficient interval from native b and SE.", "intervalUnavailableReason": null, "method": "wald-z", "p": 2.3249853733753103e-05, "se": 0.27436541262649716, "statistic": 4.231150983387848, "statisticLabel": "z", "term": "rows", "title": "main effect of Frame", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": 0.15499533683395325, "df": null, "interval": { "lower": -0.38253048487453145, "upper": 0.692521158542438 }, "intervalMethod": "Reporting-derived individual unadjusted 95% normal/Wald coefficient interval from native b and SE.", "intervalUnavailableReason": null, "method": "wald-z", "p": 0.5719685032373087, "se": 0.2742529076801512, "statistic": 0.5651547622412716, "statisticLabel": "z", "term": "columns", "title": "main effect of Model", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." }, { "b": -0.8437967641075264, "df": null, "interval": { "lower": -1.9188756536215446, "upper": 0.23128212540649185 }, "intervalMethod": "Reporting-derived individual unadjusted 95% normal/Wald coefficient interval from native b and SE.", "intervalUnavailableReason": null, "method": "wald-z", "p": 0.12397132155357926, "se": 0.5485197166856653, "statistic": -1.5383161961907605, "statisticLabel": "z", "term": "interaction", "title": "interaction", "unavailableQuantities": "Interval is reporting-derived, individual and unadjusted; the native record did not emit this interval." } ] }, "kind": "binary", "maximum": 1, "minimum": 0, "samples": [ { "cells": [ [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 16 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 15 } ], [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "successes": 4 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 4 } ] ], "id": "sample-1" }, { "cells": [ [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 12 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 18 } ], [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "successes": 12 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "successes": 6 } ] ], "id": "sample-2" } ], "sensitivity": [ { "bounds": [ { "condition": [ 0, 0 ], "includedMissing": 0, "lower": 0.35, "observed": 0.35, "upper": 0.35 }, { "condition": [ 0, 1 ], "includedMissing": 0, "lower": 0.4125, "observed": 0.4125, "upper": 0.4125 }, { "condition": [ 1, 0 ], "includedMissing": 0, "lower": 0.20512820512820512, "observed": 0.20512820512820512, "upper": 0.20512820512820512 }, { "condition": [ 1, 1 ], "includedMissing": 0, "lower": 0.12658227848101267, "observed": 0.12658227848101267, "upper": 0.12658227848101267 } ], "id": "registered-coder-grammar", "label": "registered-captured-coder-grammar", "scenarios": [], "scope": "registered-captured-coder-grammar", "status": "available" }, { "bounds": [ { "condition": [ 0, 0 ], "includedMissing": 0, "lower": 0.35, "observed": 0.35, "upper": 0.35 }, { "condition": [ 0, 1 ], "includedMissing": 0, "lower": 0.4125, "observed": 0.4125, "upper": 0.4125 }, { "condition": [ 1, 0 ], "includedMissing": 2, "lower": 0.2, "observed": 0.20512820512820512, "upper": 0.225 }, { "condition": [ 1, 1 ], "includedMissing": 1, "lower": 0.125, "observed": 0.12658227848101267, "upper": 0.1375 } ], "id": "native-unavailable", "label": "native-all-unavailable", "scenarios": [], "scope": "native-all-unavailable", "status": "available" } ], "title": "Some protection is worth paying for" }, { "cells": [ [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 80, "scheduled": 80, "successes": 0 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 80, "scheduled": 80, "successes": 0 } ], [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 2 }, "n": 78, "scheduled": 80, "successes": 0 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 79, "scheduled": 80, "successes": 0 } ] ], "id": "FRAME_EQUIVALENCE", "inference": { "comparisons": [ { "adjustedP": 1, "df": null, "effect": 0, "exactDenominator": null, "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-conditional-stratified-by-sample", "p": 1, "second": [ 1, 0 ], "secondN": 78, "significant": false, "sourceContrastEstimate": 0, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." }, { "adjustedP": 1, "df": null, "effect": 0, "exactDenominator": null, "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-conditional-stratified-by-sample", "p": 1, "second": [ 1, 1 ], "secondN": 79, "significant": false, "sourceContrastEstimate": 0, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." }, { "adjustedP": 1, "df": null, "effect": 0, "exactDenominator": null, "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-conditional-stratified-by-sample", "p": 1, "second": [ 0, 1 ], "secondN": 80, "significant": false, "sourceContrastEstimate": 0, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." }, { "adjustedP": 1, "df": null, "effect": 0, "exactDenominator": null, "exactNumerator": null, "first": [ 1, 0 ], "firstN": 78, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-conditional-stratified-by-sample", "p": 1, "second": [ 1, 1 ], "secondN": 79, "significant": false, "sourceContrastEstimate": 0, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." } ], "mode": "computed", "sourceBasis": "preregistered-fallback", "terms": [ { "b": -0.01869980074549593, "df": null, "interval": null, "intervalMethod": null, "intervalUnavailableReason": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval.", "method": "firth-penalized-likelihood-ratio", "p": 0.9894609375363246, "se": null, "statistic": 0.00017448138203768337, "statisticLabel": "Likelihood-ratio chi-square", "term": "rows", "title": "main effect of Frame", "unavailableQuantities": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval." }, { "b": 0.006273767015803958, "df": null, "interval": null, "intervalMethod": null, "intervalUnavailableReason": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval.", "method": "firth-penalized-likelihood-ratio", "p": 0.9964640396908726, "se": null, "statistic": 1.963981909280932e-05, "statisticLabel": "Likelihood-ratio chi-square", "term": "columns", "title": "main effect of Model", "unavailableQuantities": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval." }, { "b": -0.012547534031609277, "df": null, "interval": null, "intervalMethod": null, "intervalUnavailableReason": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval.", "method": "firth-penalized-likelihood-ratio", "p": 0.9964640396908726, "se": null, "statistic": 1.963981909280932e-05, "statisticLabel": "Likelihood-ratio chi-square", "term": "interaction", "title": "interaction", "unavailableQuantities": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval." } ] }, "kind": "binary", "maximum": 1, "minimum": 0, "samples": [ { "cells": [ [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 0 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 0 } ], [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "successes": 0 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 0 } ] ], "id": "sample-1" }, { "cells": [ [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 0 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 0 } ], [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "successes": 0 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "successes": 0 } ] ], "id": "sample-2" } ], "sensitivity": [ { "bounds": [ { "condition": [ 0, 0 ], "includedMissing": 0, "lower": 0, "observed": 0, "upper": 0 }, { "condition": [ 0, 1 ], "includedMissing": 0, "lower": 0, "observed": 0, "upper": 0 }, { "condition": [ 1, 0 ], "includedMissing": 0, "lower": 0, "observed": 0, "upper": 0 }, { "condition": [ 1, 1 ], "includedMissing": 0, "lower": 0, "observed": 0, "upper": 0 } ], "id": "registered-coder-grammar", "label": "registered-captured-coder-grammar", "scenarios": [], "scope": "registered-captured-coder-grammar", "status": "available" }, { "bounds": [ { "condition": [ 0, 0 ], "includedMissing": 0, "lower": 0, "observed": 0, "upper": 0 }, { "condition": [ 0, 1 ], "includedMissing": 0, "lower": 0, "observed": 0, "upper": 0 }, { "condition": [ 1, 0 ], "includedMissing": 2, "lower": 0, "observed": 0, "upper": 0.025 }, { "condition": [ 1, 1 ], "includedMissing": 1, "lower": 0, "observed": 0, "upper": 0.0125 } ], "id": "native-unavailable", "label": "native-all-unavailable", "scenarios": [], "scope": "native-all-unavailable", "status": "available" } ], "title": "Framing recognised" }, { "cells": [ [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 80, "scheduled": 80, "successes": 79 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 80, "scheduled": 80, "successes": 69 } ], [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 2 }, "n": 78, "scheduled": 80, "successes": 49 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 79, "scheduled": 80, "successes": 63 } ] ], "id": "REFERENCE_PRICE", "inference": { "comparisons": [ { "adjustedP": 2.0527605323601377e-09, "df": null, "effect": 0.35929487179487185, "exactDenominator": null, "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-conditional-stratified-by-sample", "p": 5.131901330900344e-10, "second": [ 1, 0 ], "secondN": 78, "significant": true, "sourceContrastEstimate": 0.35929487179487185, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "***", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." }, { "adjustedP": 0.29974530864653215, "df": null, "effect": 0.06503164556962027, "exactDenominator": null, "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-conditional-stratified-by-sample", "p": 0.29974530864653215, "second": [ 1, 1 ], "secondN": 79, "significant": false, "sourceContrastEstimate": 0.06503164556962027, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." }, { "adjustedP": 0.014255786892747827, "df": null, "effect": 0.125, "exactDenominator": null, "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-conditional-stratified-by-sample", "p": 0.004751928964249276, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": 0.125, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "*", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." }, { "adjustedP": 0.04190797781558908, "df": null, "effect": -0.16926322622525158, "exactDenominator": null, "exactNumerator": null, "first": [ 1, 0 ], "firstN": 78, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-conditional-stratified-by-sample", "p": 0.02095398890779454, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": -0.16926322622525158, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "*", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." } ], "mode": "computed", "sourceBasis": "preregistered-fallback", "terms": [ { "b": 1.9652162471900556, "df": null, "interval": null, "intervalMethod": null, "intervalUnavailableReason": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval.", "method": "firth-penalized-likelihood-ratio", "p": 1.2981260948441463e-07, "se": null, "statistic": 27.86900614439213, "statisticLabel": "Likelihood-ratio chi-square", "term": "rows", "title": "main effect of Frame", "unavailableQuantities": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval." }, { "b": 0.6671593608720148, "df": null, "interval": null, "intervalMethod": null, "intervalUnavailableReason": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval.", "method": "firth-penalized-likelihood-ratio", "p": 0.12244722454233381, "se": null, "statistic": 2.3857358303432648, "statisticLabel": "Likelihood-ratio chi-square", "term": "columns", "title": "main effect of Model", "unavailableQuantities": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval." }, { "b": 3.0262855980605514, "df": null, "interval": null, "intervalMethod": null, "intervalUnavailableReason": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval.", "method": "firth-penalized-likelihood-ratio", "p": 0.00012168354822853048, "se": null, "statistic": 14.766415043124994, "statisticLabel": "Likelihood-ratio chi-square", "term": "interaction", "title": "interaction", "unavailableQuantities": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval." } ] }, "kind": "binary", "maximum": 1, "minimum": 0, "samples": [ { "cells": [ [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 39 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 34 } ], [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "successes": 19 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 32 } ] ], "id": "sample-1" }, { "cells": [ [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 40 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 35 } ], [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "successes": 30 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "successes": 31 } ] ], "id": "sample-2" } ], "sensitivity": [ { "bounds": [ { "condition": [ 0, 0 ], "includedMissing": 0, "lower": 0.9875, "observed": 0.9875, "upper": 0.9875 }, { "condition": [ 0, 1 ], "includedMissing": 0, "lower": 0.8625, "observed": 0.8625, "upper": 0.8625 }, { "condition": [ 1, 0 ], "includedMissing": 0, "lower": 0.6282051282051282, "observed": 0.6282051282051282, "upper": 0.6282051282051282 }, { "condition": [ 1, 1 ], "includedMissing": 0, "lower": 0.7974683544303798, "observed": 0.7974683544303798, "upper": 0.7974683544303798 } ], "id": "registered-coder-grammar", "label": "registered-captured-coder-grammar", "scenarios": [], "scope": "registered-captured-coder-grammar", "status": "available" }, { "bounds": [ { "condition": [ 0, 0 ], "includedMissing": 0, "lower": 0.9875, "observed": 0.9875, "upper": 0.9875 }, { "condition": [ 0, 1 ], "includedMissing": 0, "lower": 0.8625, "observed": 0.8625, "upper": 0.8625 }, { "condition": [ 1, 0 ], "includedMissing": 2, "lower": 0.6125, "observed": 0.6282051282051282, "upper": 0.6375 }, { "condition": [ 1, 1 ], "includedMissing": 1, "lower": 0.7875, "observed": 0.7974683544303798, "upper": 0.8 } ], "id": "native-unavailable", "label": "native-all-unavailable", "scenarios": [], "scope": "native-all-unavailable", "status": "available" } ], "title": "Price set by the 25 dollar reference" }, { "cells": [ [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 80, "scheduled": 80, "successes": 1 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 80, "scheduled": 80, "successes": 28 } ], [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 2 }, "n": 78, "scheduled": 80, "successes": 29 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 79, "scheduled": 80, "successes": 62 } ] ], "id": "CALCULATED_PRICE", "inference": { "comparisons": [ { "adjustedP": 2.615331128185833e-09, "df": null, "effect": -0.3592948717948718, "exactDenominator": null, "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-8191d902-091c-4fa8-8bd8-81e33a32db6c:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-conditional-stratified-by-sample", "p": 6.538327820464583e-10, "second": [ 1, 0 ], "secondN": 78, "significant": true, "sourceContrastEstimate": -0.3592948717948718, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "***", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-6 Sol in Gain frame against GPT-6 Sol in Loss frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." }, { "adjustedP": 7.454433464226342e-08, "df": null, "effect": -0.43481012658227847, "exactDenominator": null, "exactNumerator": null, "first": [ 0, 1 ], "firstN": 80, "id": "level-51e3661d-e80f-4ce6-b173-fb62e95131f3:level-1e375993-4668-4c7f-88c7-3a32a8047b32-level-ac901b6d-18ea-4ed2-8b57-57168d7f542c", "method": "exact-conditional-stratified-by-sample", "p": 3.727216732113171e-08, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": -0.43481012658227847, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "***", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-5.6 Terra in Gain frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." }, { "adjustedP": 2.4128326204879457e-08, "df": null, "effect": -0.33749999999999997, "exactDenominator": null, "exactNumerator": null, "first": [ 0, 0 ], "firstN": 80, "id": "level-1e375993-4668-4c7f-88c7-3a32a8047b32:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-conditional-stratified-by-sample", "p": 8.042775401626486e-09, "second": [ 0, 1 ], "secondN": 80, "significant": true, "sourceContrastEstimate": -0.33749999999999997, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "***", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-6 Sol in Gain frame against GPT-5.6 Terra in Gain frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." }, { "adjustedP": 1.5513970234239955e-07, "df": null, "effect": -0.41301525478740664, "exactDenominator": null, "exactNumerator": null, "first": [ 1, 0 ], "firstN": 78, "id": "level-ac901b6d-18ea-4ed2-8b57-57168d7f542c:level-8191d902-091c-4fa8-8bd8-81e33a32db6c-level-51e3661d-e80f-4ce6-b173-fb62e95131f3", "method": "exact-conditional-stratified-by-sample", "p": 1.5513970234239955e-07, "second": [ 1, 1 ], "secondN": 79, "significant": true, "sourceContrastEstimate": -0.41301525478740664, "sourceContrastSE": null, "sourceContrastScale": "proportion difference", "sourceContrastStatistic": null, "stars": "***", "statistic": null, "statisticLabel": "Not exported by native conditional comparison", "title": "GPT-6 Sol in Loss frame against GPT-5.6 Terra in Loss frame", "unavailableQuantities": "Native conditional pairwise output supplies no test statistic, SE, df, contrast interval or exact tail numerator/denominator." } ], "mode": "computed", "sourceBasis": "preregistered-fallback", "terms": [ { "b": -2.6784303260059663, "df": null, "interval": null, "intervalMethod": null, "intervalUnavailableReason": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval.", "method": "firth-penalized-likelihood-ratio", "p": 1.0301929119670965e-16, "se": null, "statistic": 68.91079668267116, "statisticLabel": "Likelihood-ratio chi-square", "term": "rows", "title": "main effect of Frame", "unavailableQuantities": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval." }, { "b": -2.584480597768607, "df": null, "interval": null, "intervalMethod": null, "intervalUnavailableReason": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval.", "method": "firth-penalized-likelihood-ratio", "p": 2.0896376032460836e-15, "se": null, "statistic": 62.97860852454443, "statisticLabel": "Likelihood-ratio chi-square", "term": "columns", "title": "main effect of Model", "unavailableQuantities": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval." }, { "b": -1.5696209153339578, "df": null, "interval": null, "intervalMethod": null, "intervalUnavailableReason": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval.", "method": "firth-penalized-likelihood-ratio", "p": 0.05223482548292413, "se": null, "statistic": 3.7682317486101056, "statisticLabel": "Likelihood-ratio chi-square", "term": "interaction", "title": "interaction", "unavailableQuantities": "Native Firth penalized likelihood-ratio terms do not supply the standard error or profile-likelihood interval required for a supported interval; do not fabricate a Wald interval." } ] }, "kind": "binary", "maximum": 1, "minimum": 0, "samples": [ { "cells": [ [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 1 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 15 } ], [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "successes": 19 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 31 } ] ], "id": "sample-1" }, { "cells": [ [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 0 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": {}, "n": 40, "scheduled": 40, "successes": 13 } ], [ { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "successes": 10 }, { "interval": null, "invalidCapturedCoderReply": 0, "missing": { "known-failure": 1 }, "n": 39, "scheduled": 40, "successes": 31 } ] ], "id": "sample-2" } ], "sensitivity": [ { "bounds": [ { "condition": [ 0, 0 ], "includedMissing": 0, "lower": 0.0125, "observed": 0.0125, "upper": 0.0125 }, { "condition": [ 0, 1 ], "includedMissing": 0, "lower": 0.35, "observed": 0.35, "upper": 0.35 }, { "condition": [ 1, 0 ], "includedMissing": 0, "lower": 0.3717948717948718, "observed": 0.3717948717948718, "upper": 0.3717948717948718 }, { "condition": [ 1, 1 ], "includedMissing": 0, "lower": 0.7848101265822784, "observed": 0.7848101265822784, "upper": 0.7848101265822784 } ], "id": "registered-coder-grammar", "label": "registered-captured-coder-grammar", "scenarios": [], "scope": "registered-captured-coder-grammar", "status": "available" }, { "bounds": [ { "condition": [ 0, 0 ], "includedMissing": 0, "lower": 0.0125, "observed": 0.0125, "upper": 0.0125 }, { "condition": [ 0, 1 ], "includedMissing": 0, "lower": 0.35, "observed": 0.35, "upper": 0.35 }, { "condition": [ 1, 0 ], "includedMissing": 2, "lower": 0.3625, "observed": 0.3717948717948718, "upper": 0.3875 }, { "condition": [ 1, 1 ], "includedMissing": 1, "lower": 0.775, "observed": 0.7848101265822784, "upper": 0.7875 } ], "id": "native-unavailable", "label": "native-all-unavailable", "scenarios": [], "scope": "native-all-unavailable", "status": "available" } ], "title": "Price derived by arithmetic" } ], "provenance": { "analysisSha": "sha256:a8bb0432c101ec03b5453c29ff40bc0074f5e8f4ad0ea4ba7f68d90fbdec9d9b", "collectionSha": "sha256:7cb1c2d50725b3dbe4e5b4feee4c596b5ede638742d5941388f4030bbc84bbf2", "planSha": "sha256:b92d77b84ce933657d8fc5f5ce6cbbaaa6400a063c78cda69b66cb97e4e4b2e4", "sourceRegistrationSha": "sha256:aebe13dacaa6a318667ebb25e917f67b4daa3ed2fb2dde56eebfee746efb3790", "specificationSha": "sha256:ab81ec56cfb716fb5d496e2484ee42a8feeda1a0d8ab1de4dcb1f148c9911258" }, "recordType": "price03-public-residual-aggregate-report", "reportingProvenance": { "codingCoverage": { "allCapturedRationalesCoded": true, "auditOnlyCandidates": 3, "capturedCandidates": 320, "eligibleScientificRationales": 317, "invalidCoderReplies": 0, "unavailableCoderReplies": 0, "validCoderReplies": 320 }, "coefficientEnrichmentSha": "sha256:ecf00e40bcb076c9bb7c6dae71f52473d0d87900c21cd79ac09b287a84cd4e87", "coefficientMethodReviewSha": "sha256:1a732270f788b3d8b4b5cf909488154c77dc56025aca9c2abbc3ef3cb06ff9fd", "coefficientMethodSha": "sha256:c25d4b0d8177baedd6f0a319a53546c1d9d8b1efe4143c6a4d6b41148e822de8", "collectionMetadataSha": "sha256:09372489de657a1f7dec13d4806ed88931972a44db1b9568deb9d927fa84847a", "comparison": "Four separately pinned descriptive PRICE-02/PRICE-03 summaries. Reporting-only Welch intervals are computed by the existing renderer; no cross-study test, pooling, equivalence or replication classification is added.", "comparisonSources": { "historicalLimitations": [ "PRICE-02 coding, final recording and app integration remain pending.", "Original strict numerical verification remains failed; its independently documented reporting-precision characterization passed with no failures at the declared tolerance.", "The frozen native numerical values are retained; their maximum independently checked mean-CI discrepancy was about 2.18e-9.", "This reference does not grant scientific recording or publication authority." ], "historicalReportingPrecisionStatus": "passed-reporting-precision-with-documented-strict-discrepancies", "historicalScope": "Previously published PRICE-02 scalar aggregate reference only. No PRICE-03 observations or cross-study tests. Gain-minus-loss Welch intervals will be reporting-derived using the prior prospective supplement.", "historicalStrictAuditStatus": "failed", "originalAdapterReceiptSha": "sha256:fe6433ecaf04488321f969275e31c41cf0af2090a1d9201fea6e024b070d636c", "originalAggregateByteSha": "sha256:cf6cbb99e90b236e3107dabb761015782278e3165c4711043bb05dbbd7216f6a", "price02ReferenceByteSha": "sha256:9bf48da869b409072f1363e6b30ee59e6e7c91e60c2a66ec61d27b9645c47334", "price02ReferenceReviewByteSha": "sha256:1cc03fc3063a756ee90621e989038969cc422e60d9d1cd534592afcce0fc5e2b", "price02ReferenceReviewSha": "sha256:635248bada26e5ed81c82779c1ff24634ec64567a4c6087638897439c78c1a19", "price02ReferenceSha": "sha256:b8d7ce68ee2c2ea43202524d0fe6072589a08510c748599499e9304024c4e1b9" }, "evidenceAnalysisSha": "sha256:1b4c871c5a3ee87eb0e413ae7cec05d6e62f39887fc34fb0f9c3330a9acb0c10", "modelCoding": { "coefficientIntervals": "individual unadjusted reporting-derived; unchanged source b, SE, df, p and method", "columns": [ { "code": 0.5, "title": "GPT-6 Sol" }, { "code": -0.5, "title": "GPT-5.6 Terra" } ], "rows": [ { "code": 0.5, "title": "Gain frame" }, { "code": -0.5, "title": "Loss frame" } ], "sampleHandling": "pooled-with-sample-block", "sampleIntercepts": "one per sample" }, "preparedSha": "sha256:bc128a029a4b3d3ddea06d0e82d959215d72c14e47ab538f22b0c0600917b464", "sensitivityEnrichmentSha": "sha256:1ef40476a4ef380e4f1806630b139efa4a2427cf8e6f877284e3eedb810582d8" }, "schemaVersion": 3, "status": { "analysis": "all-outcome-inference", "appIntegration": "pending", "coding": "complete", "finalRecord": "complete" }, "studyId": "PRICE03-SOL-TERRA-20261007-E2" }