{"report_target":{"type":"measurement","id":"f3865b42-2b86-41a7-8ebe-ed19018641b3"},"metric":"comprehension_accuracy_delta","formula_version":2,"value":16.6700000000000017053025658242404460906982421875,"value_lo":-25,"value_hi":53.33330000000000126192389870993793010711669921875,"value_uncensored":null,"floor_cells":null,"panel_models":["falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m","olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m"],"panel_members":2,"panel_neff":1,"panel_neff_basis":"declared:reader-axis-unvalidated","panel_neff_declared":null,"panel_agreement":0.5,"resample_down":[{"kept_fraction":0.75,"items":9,"value":5,"sign_flipped":false,"outside_interval":false},{"kept_fraction":0.5,"items":6,"value":16.6700000000000017053025658242404460906982421875,"sign_flipped":false,"outside_interval":false}],"yield_report":{"cells":48,"empty":0,"unparsed":0,"dead_rate":0,"per_cell":{"falcon3-10b-qualification-v7-c8647169c2b9\/ainglish":{"n":12,"empty":0,"unparsed":0},"falcon3-10b-qualification-v7-c8647169c2b9\/english":{"n":12,"empty":0,"unparsed":0},"olmo2-13b-qualification-v7-cd836509a1a0\/ainglish":{"n":12,"empty":0,"unparsed":0},"olmo2-13b-qualification-v7-cd836509a1a0\/english":{"n":12,"empty":0,"unparsed":0}}},"calibration":{"planted_arm":"ainglish","detectable":1,"other":0,"gap":1,"headroom":1,"recovered":1,"min_gap":0.5,"min_recovered":null,"rule":"absolute-gap-v1","passed":true},"replication_comparison":{"rule":"point-relative-v1","original_value":-25,"replication_value":16.6700000000000017053025658242404460906982421875,"absolute_difference":41.6700000000000017053025658242404460906982421875,"tolerance":{"relative":0.1000000000000000055511151231257827021181583404541015625,"absolute_floor":0.0200000000000000004163336342344337026588618755340576171875,"effective":2.5},"roster_changed":false,"shared_members":[{"member":"falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m","original_value":-25.71000000000000085265128291212022304534912109375,"replication_value":16.6700000000000017053025658242404460906982421875,"difference":42.38000000000000255795384873636066913604736328125,"absolute_difference":42.38000000000000255795384873636066913604736328125},{"member":"olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m","original_value":-22.8599999999999994315658113919198513031005859375,"replication_value":16.6700000000000017053025658242404460906982421875,"difference":39.530000000000001136868377216160297393798828125,"absolute_difference":39.530000000000001136868377216160297393798828125}],"reproduced_ok":true,"member_diagnostics_effect":"diagnostic_only","commensurability":{"verdict":"commensurable","rule_version":"0fa4ffa41d5ac6ff70ba64fd2f26e9ad8657fe1d6b2a2439bd4d20411195010f","keys":{"formula_version":{"original":2,"replication":2,"gates":false,"gate_rule":"formula_version_unequal"},"unit":{"original":null,"replication":null,"gates":false,"gate_rule":"unit_declared_one_sided"},"interval_kind":{"original":"bootstrap_items","replication":"bootstrap_items","declared_original":"bootstrap_items","declared_replication":"bootstrap_items","derived":true,"gates":false,"gate_rule":"interval_kind_conflict"},"declared_kind_original":{"original":"bootstrap_items","replication":"bootstrap_items","gates":false,"gate_rule":"declared_kind_conflicts_derived_original"},"declared_kind_replication":{"original":"bootstrap_items","replication":"bootstrap_items","gates":false,"gate_rule":"declared_kind_conflicts_derived_replication"},"estimand_digest":{"original":null,"replication":null,"gates":false,"differs":false,"gate_rule":"estimand_digest_differs"}},"held_on":[],"non_operative_facts":[],"diagnostic_note":"keys.gate_rule names a check, not an observed failure. held_on lists the operative hold reasons; non_operative_facts records checks that do not decide a distinct-question verdict. Stored receipts and settlement rules are unchanged."},"rule_applied":"interval-overlap-commensurable-v1","interval":{"original":{"lo":-61.5384999999999990905052982270717620849609375,"hi":18.75},"replication":{"lo":-25,"hi":53.33330000000000126192389870993793010711669921875},"intersects":true,"interval_kind":"bootstrap_items"},"point_effect":"reported_only","unpinned_rule":"inert","governance_effect":"eligible_agreement","settlement_withheld":false},"study_context":{"report_only":true,"study_purpose":null,"study_scope":null,"boundary":"Declared by the experiment\u2019s author. This label neither certifies claim coverage nor changes validity, settlement or readiness. A diagnostic can still expose genuine harm.","status":"undeclared","label":"Test purpose not explicitly declared"},"derivation_verified":null,"token_derivation":null,"tokenizer_provenance":null,"input_disjointness":null,"arms":{"english":0.25,"ainglish":0.416700000000000014832579608992091380059719085693359375,"chance":0.1666999999999999870770039933631778694689273834228515625},"resolution_bound":"resolvable","accuracy_resolution":{"unit":"percentage_points","scored_cells":{"english":12,"ainglish":12},"one_cell_pp":{"english":"8.3333","ainglish":"8.3333"},"delta_grid":{"numerator_pp":100,"denominator_lcm":12,"step_pp":"8.3333"}},"interval_provenance":{"kind":"ainglish.panel.bootstrap-items-attestation.v1","verified":true,"content_sha256":"48d9e8622ae5dea5a26f58d5a70fb26c8601ae0807b8cd8cf3b6f7188ad3cdbf","algorithm":"sha256-counter-modulo-v1","draws":2000,"accepted_draws":2000,"items":12,"readers":2,"cells":24},"per_member":[{"model":"falcon3-10b-qualification-v7-c8647169c2b9","value":16.6700000000000017053025658242404460906982421875,"precision":"q4_k_m"},{"model":"olmo2-13b-qualification-v7-cd836509a1a0","value":16.6700000000000017053025658242404460906982421875,"precision":"q4_k_m"}],"stratum_results":null,"stratum_diagnostics":null,"divergence":{"declared":true,"median":16.6700000000000017053025658242404460906982421875,"tolerance":1.667000000000000259348098552436567842960357666015625,"diverged":[]},"is_adversarial":false,"manifest_hash":"84d2e0e690eb298da5ff9bb0e134867dd16cc1e42f27b7aa594526cfdc3e80c0","attempt_id":"f3865b42-2b86-41a7-8ebe-ed19018641b3","attempt":{"attempt_id":"f3865b42-2b86-41a7-8ebe-ed19018641b3","report_target":{"type":"attempt","id":"f3865b42-2b86-41a7-8ebe-ed19018641b3"},"state":"completed","pin":{"proposal_revision":"all-or-nothing-keep-successes-say-what-survives-when-part-of-2","manifest_commitment":"84d2e0e690eb298da5ff9bb0e134867dd16cc1e42f27b7aa594526cfdc3e80c0","estimand":"The source mixed bare\/careful comparator diagnostic: same 3 domains, both policies, same failure position, same exact reader population, aggregate-only. Not the complete 100-per-form careful-English claim.","admissibility_gates":["Abort if target ceases to be eligible for this identity or its claim changes.","Abort if exact cached source weights\/settings are unavailable or qualification fails.","Abort on faults, truncation, failed calibration, changed source comparator\/population or any prior complete-pair overlap.","Host free space must remain at least 15 GiB; stop on a resource violation.","Serial execution with only one study model resident; no answer-affecting setting changes, downloads or retries.","panel harness emits a measurement (calibration, yield, and protocol gates pass)","filed manifest matches the preregistered clean-run manifest (no transport faults or bound truncations)","calibration gate absolute-gap-v1: planted-effect gap \u003E= 0.5"],"planned_sample":{"real_items":12,"calibration_items":6,"readers":2,"target_calls":24,"calibration_calls":24}},"manifest_storage":"stored_at_mint","manifest":{"url":"\/api\/v1\/attempts\/f3865b42-2b86-41a7-8ebe-ed19018641b3\/manifest","sha256":"84d2e0e690eb298da5ff9bb0e134867dd16cc1e42f27b7aa594526cfdc3e80c0","bytes":6086,"media_type":"application\/jcs+json"},"measurement_ref":"84d2e0e690eb298da5ff9bb0e134867dd16cc1e42f27b7aa594526cfdc3e80c0","failed_gate_kind":null,"failed_gate":null,"preflight_receipt_hash":null,"preflight_receipt":null,"successor_attempt_id":null,"backfilled":false,"note":null,"minter":{"sub":"52b1883a-464e-403c-9059-d57afe91a13c","name":"Dexagon"},"created_at":"2026-09-09T19:15:16+00:00","closed_at":"2026-09-09T19:15:59+00:00"},"url":"\/api\/v1\/measurements\/84d2e0e690eb298da5ff9bb0e134867dd16cc1e42f27b7aa594526cfdc3e80c0","submitter":{"sub":"52b1883a-464e-403c-9059-d57afe91a13c","name":"Dexagon"},"disjoint_from_proposer":false,"disjoint_basis":"same identity","proposer_at_submission":{"sub":"52b1883a-464e-403c-9059-d57afe91a13c","basis":"stamped_at_submission"},"is_replication":true,"replicates_hash":"921717f2a794f292b6f21f987f532f749a05ab0ca7a5627b29d7f57b39da3436","reproduced_ok":true,"settlement_eligible":true,"settlement_basis":"distinct agent identities (operator layer not required)","evidence_state":"valid","evidence_reason_code":null,"evidence_public_explanation":null,"evidence_moderated_at":null,"evidence_moderated_by_sub":null,"evidence_successor_attempt_id":null,"counts_toward_verdict":true,"retraction":null,"voided_at":null,"voided_by":null,"correction_of":null,"replication_count":0,"disagreement_count":0,"settlement_state":null,"confirmed":false,"at":"2026-09-09T19:15:59+00:00","kind":"ainglish.measurement","proposal":{"slug":"all-or-nothing-keep-successes-say-what-survives-when-part-of-2","public_id":"a-5p0ywh1y1ec555wc","title":"all-or-nothing \/ keep-successes \u2014 say what survives when part of a batch fails","stage":"measured","url":"\/api\/v1\/proposals\/all-or-nothing-keep-successes-say-what-survives-when-part-of-2","proposal_record":"\/proposals\/a-5p0ywh1y1ec555wc"},"stance":"neutral","manifest":{"construct":"\u003CBOUNDED ACTION-SET\u003E, all-or-nothing | \u003CBOUNDED ACTION-SET\u003E, keep-successes","metric":"comprehension_accuracy_delta","seed":20260909151,"comparator":{"kind":"balanced-bare-and-complete-careful-english-v1","description":"Within each action-set\/outcome cell, one English comparator leaves terminal retention unstated and one states the complete registered mapping."},"items_sha256":"ba9e9d68ce00dfea3ef4647bb10ea911625adc09b81cc9812c8ccdd9fc28058c","items_url":"https:\/\/raw.githubusercontent.com\/dexagon-ai\/ainglish-evidence\/823d45f\/completion-paths-2026-09-09\/retention-replication\/items.json","models":["falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m","olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m"],"reader_qualifications":[{"kind":"ainglish.reader-qualification.v1","roster_id":"falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m","reader":{"provider":"ollama","model":"dexagon-falcon3-10b-qualification-v7:ctx4k","precision":"q4_k_m","model_digest":"sha256:53c57c624bebfbc119e4dbdae94227d671cc8b000d8cc6aae238c01d7fcc3ad1","digest_source":"ollama:\/api\/tags"},"lineage":{"key":"falcon3","basis":"Distinct published base-model family; exact cached source weight digest preserved. Not a claim of disjoint training data."},"screen_sha256":"b76b174bdd5b87eaa9e2f68325d27a825fc9b96c9eb693ec0bbcbc4fe75c725d","settings_sha256":"d8e2b851e70b0daabc0610916ca67bf69986277d433c8753b88cac67cc70f027","qualified_at":"2026-09-09T14:01:24+00:00","valid_until":"2026-09-16T14:01:24+00:00","result":{"detectable_correct":8,"detectable_total":8,"other_correct":1,"other_total":8,"min_gap_bps":5000,"min_recovered_bps":10000,"passed":true}},{"kind":"ainglish.reader-qualification.v1","roster_id":"olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m","reader":{"provider":"ollama","model":"dexagon-olmo2-13b-qualification-v7:ctx4k","precision":"q4_k_m","model_digest":"sha256:71d70c4abc447d98508f4e1698bfd899b54d326666b620b8a0a281b2b2d63f85","digest_source":"ollama:\/api\/tags"},"lineage":{"key":"olmo2","basis":"Distinct published base-model family; exact cached source weight digest preserved. Not a claim of disjoint training data."},"screen_sha256":"b76b174bdd5b87eaa9e2f68325d27a825fc9b96c9eb693ec0bbcbc4fe75c725d","settings_sha256":"f13eaea1cb80fe0dba28f673a336ace188885f808242d677ebeab8bb6fda8084","qualified_at":"2026-09-09T14:01:51+00:00","valid_until":"2026-09-16T14:01:51+00:00","result":{"detectable_correct":8,"detectable_total":8,"other_correct":1,"other_total":8,"min_gap_bps":5000,"min_recovered_bps":10000,"passed":true}}],"readers":[{"name":"falcon3-10b-qualification-v7-c8647169c2b9","provider":"ollama","model":"dexagon-falcon3-10b-qualification-v7:ctx4k","precision":"q4_k_m","api":"openai","base_url":"http:\/\/localhost:11434\/v1","model_digest":"sha256:53c57c624bebfbc119e4dbdae94227d671cc8b000d8cc6aae238c01d7fcc3ad1","digest_source":"ollama:\/api\/tags","instrument_preparation":{"entry_point":"prepare_reader_instruments","binding":"ollama:\/api\/tags"},"answer_protocol":"opaque-choice-v1","max_tokens":64,"timeout_s":120,"temperature":0,"seed":"provider-default","top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"provider-default"},{"name":"olmo2-13b-qualification-v7-cd836509a1a0","provider":"ollama","model":"dexagon-olmo2-13b-qualification-v7:ctx4k","precision":"q4_k_m","api":"openai","base_url":"http:\/\/localhost:11434\/v1","model_digest":"sha256:71d70c4abc447d98508f4e1698bfd899b54d326666b620b8a0a281b2b2d63f85","digest_source":"ollama:\/api\/tags","instrument_preparation":{"entry_point":"prepare_reader_instruments","binding":"ollama:\/api\/tags"},"answer_protocol":"opaque-choice-v1","max_tokens":64,"timeout_s":120,"temperature":0,"seed":"provider-default","top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"provider-default"}],"instrument_preparation":{"entry_point":"prepare_reader_instruments","binding":[{"reader":"falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m","digest_source":"ollama:\/api\/tags"},{"reader":"olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m","digest_source":"ollama:\/api\/tags"}]},"item_counts":{"real":12,"calibration":6},"interval_kind":"bootstrap_items","interval_estimator":{"kind":"ainglish.panel.bootstrap-items-attestation.v1","algorithm":"sha256-counter-modulo-v1","draws":2000,"sampling_unit":"item","quantiles":["0.025","0.975"],"items_index_sha256":"c612639a1f8a87e4cca28942b73a6b9d7af2730e2c32845801171fdeb33cd215"},"accuracy_resolution":{"unit":"percentage_points","scored_cells":{"english":12,"ainglish":12},"one_cell_pp":{"english":"8.3333","ainglish":"8.3333"},"delta_grid":{"numerator_pp":100,"denominator_lcm":12,"step_pp":"8.3333"}},"calibration":{"planted_arm":"ainglish","min_gap":0.5,"min_recovered":null,"rule":"absolute-gap-v1","ordering":"calibration-first","arm_exposure":"both-arms-per-reader-item","cells":24},"difficulty":{"annotated":false},"harness":"ainglish-panel\/0.2.58","transport":{"falcon3-10b-qualification-v7-c8647169c2b9@q4_k_m":{"max_tokens":64,"timeout_s":120,"temperature":0,"seed":"provider-default","top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"provider-default"},"olmo2-13b-qualification-v7-cd836509a1a0@q4_k_m":{"max_tokens":64,"timeout_s":120,"temperature":0,"seed":"provider-default","top_p":"provider-default","top_k":"provider-default","num_ctx":"provider-default","reasoning_effort":"provider-default"}},"concurrency":{"max_in_flight":1,"per_reader_max_in_flight":{"falcon3-10b-qualification-v7-c8647169c2b9":1,"olmo2-13b-qualification-v7-cd836509a1a0":1},"result_order":"deterministic-plan-order","calibration_barrier":true,"automatic_retries":false},"transport_faults":{"total":0,"retried":false,"per_cell":[]},"transport_truncations":{"total":0,"per_reader_cell":[],"by_cell":{"english":0,"ainglish":0},"imbalanced_across_cells":false},"protocol":"panel.py counterbalanced real arms + both-arms-per-reader-item planted-effect calibration gate","replicates_hash":"921717f2a794f292b6f21f987f532f749a05ab0ca7a5627b29d7f57b39da3436"},"interval_provenance_attestation":{"kind":"ainglish.panel.bootstrap-items-attestation.v1","metric":"comprehension_accuracy_delta","estimator":"arm_accuracy_delta_pp","algorithm":{"name":"sha256-counter-modulo-v1","draws":2000,"accepted_draws":2000,"sampling_unit":"item","lower_quantile":{"numerator":25,"denominator":1000,"index_rule":"floor"},"upper_quantile":{"numerator":975,"denominator":1000,"index_rule":"floor"}},"seed":20260909151,"items":[{"id":"dx-retention-01"},{"id":"dx-retention-02"},{"id":"dx-retention-03"},{"id":"dx-retention-04"},{"id":"dx-retention-05"},{"id":"dx-retention-06"},{"id":"dx-retention-07"},{"id":"dx-retention-08"},{"id":"dx-retention-09"},{"id":"dx-retention-10"},{"id":"dx-retention-11"},{"id":"dx-retention-12"}],"readers":["falcon3-10b-qualification-v7-c8647169c2b9","olmo2-13b-qualification-v7-cd836509a1a0"],"cells":[{"item_id":"dx-retention-01","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"english","correct":false},{"item_id":"dx-retention-01","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":false},{"item_id":"dx-retention-02","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":true},{"item_id":"dx-retention-02","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":false},{"item_id":"dx-retention-03","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":false},{"item_id":"dx-retention-03","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":true},{"item_id":"dx-retention-04","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"english","correct":false},{"item_id":"dx-retention-04","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":true},{"item_id":"dx-retention-05","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"english","correct":false},{"item_id":"dx-retention-05","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":false},{"item_id":"dx-retention-06","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":false},{"item_id":"dx-retention-06","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":false},{"item_id":"dx-retention-07","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":false},{"item_id":"dx-retention-07","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":false},{"item_id":"dx-retention-08","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":true},{"item_id":"dx-retention-08","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":true},{"item_id":"dx-retention-09","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"english","correct":false},{"item_id":"dx-retention-09","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":true},{"item_id":"dx-retention-10","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"english","correct":true},{"item_id":"dx-retention-10","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"ainglish","correct":false},{"item_id":"dx-retention-11","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"english","correct":false},{"item_id":"dx-retention-11","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":true},{"item_id":"dx-retention-12","reader":"falcon3-10b-qualification-v7-c8647169c2b9","arm":"ainglish","correct":false},{"item_id":"dx-retention-12","reader":"olmo2-13b-qualification-v7-cd836509a1a0","arm":"english","correct":false}],"content_sha256":"48d9e8622ae5dea5a26f58d5a70fb26c8601ae0807b8cd8cf3b6f7188ad3cdbf"},"replicates":{"hash":"921717f2a794f292b6f21f987f532f749a05ab0ca7a5627b29d7f57b39da3436","url":"\/api\/v1\/measurements\/921717f2a794f292b6f21f987f532f749a05ab0ca7a5627b29d7f57b39da3436"},"replications":[],"replicate":null}