{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41197447", "kind": "science-record", "revision": 1, "content_hash": "sha256:6be5f9d53cfaf0fbc2ee68c7902ef2dd694cfe1709bb254286ade00101423f3a", "created_at": "2026-11-01T10:25:53Z", "updated_at": "2026-11-01T10:25:53Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Development of multiple cell death pattern features to predict prognosis and drug sensitivity in gastric adenocarcinoma.", "doi": "10.1016/j.tranon.2025.102584", "pmid": "41197447", "authors": null, "journal": "Translational oncology", "year": 2026, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:41197447"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:41197447", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:41197447' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41197447", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.tranon.2025.102584", "sha256": "sha256:b0c1561eeadfdc8d64b5aac1939e97634484c7e59c704569334ba455c8189c21", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.tranon.2025.102584", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:41197447 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:41197447"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41197447"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "43ea387aabec98b9dd3d7a0baa3b6bfba798d6e81cd93f80c6e7a5ded0390327", "source_hash": "b0c1561eeadfdc8d64b5aac1939e97634484c7e59c704569334ba455c8189c21", "raw_response_sha256": "sha256:47b1ae01ee2e6977d1a33b652a7b5e25f2633fb06f1712e8c8f4949b7bde695a", "raw_response_chars": 2932}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "d715f828e5c489cb5e43047ac1467a9f47995e48c0e779b7ba13105a27faae6b", "source_hash": "b0c1561eeadfdc8d64b5aac1939e97634484c7e59c704569334ba455c8189c21", "raw_response_sha256": "sha256:c211dca088dee5da0cbecf950dd14023337920f1ae6dbebaa238235afea912b3", "raw_response_chars": 45545}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "fabdaaa7bafa726d165520a6bfeb75b7757d3e1ec585015c3862fff4dfc6e8f9", "source_hash": "b0c1561eeadfdc8d64b5aac1939e97634484c7e59c704569334ba455c8189c21", "raw_response": "{\"parent_value\":6,\"unit\":\"RCD-related genes\",\"evidence\":\"Developed and validated a novel prognostic signature (PCD Score) integrating six key RCD-related genes.\",\"target_result\":\"The paper states that its PCD Score integrates six key RCD-related genes.\",\"number_stated\":true}", "reading": {"parent_value": 6, "unit": "RCD-related genes", "evidence": "Developed and validated a novel prognostic signature (PCD Score) integrating six key RCD-related genes.", "target_result": "The paper states that its PCD Score integrates six key RCD-related genes.", "number_stated": true, "source_locator": "chars 351-454 of source sha256 b0c1561eeadfdc8d64b5aac1939e97634484c7e59c704569334ba455c8189c21"}, "recorded_at": "2026-10-31T15:27:04.746171+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "c835788f3ba0cc7e8c4256a441c181cafbf4ca40fdd7503bcdeed1ef8ae2b261", "source_hash": "b0c1561eeadfdc8d64b5aac1939e97634484c7e59c704569334ba455c8189c21", "raw_response": "<think>We need answer JSON only. Need interpret registered target headline numerical result paper states for main finding. Source has many numbers: 26 genes prognostic relevance, two clusters, six-gene model, 190 DEGs. Asked \"single numerical result that a replication of the registered target has to reproduce. Report headline number only: value paper itself states for registered target, not calculated...\" Registered target is \"the headline numerical result the paper states for its main finding.\" Need identify likely headline number perhaps 190 differentially expressed genes? Main finding perhaps PCD score, validation predictive power, but no AUC/C-index number. Need extract claim only. We need decide number_stated perhaps false because no headline numerical performance result stated for main finding? Yet source explicitly says \"Twenty-six RCD-associated genes showed significant prognostic relevance\" and \"A total of 190 differentially expressed genes...\" Which is \"headline numerical result\" perhaps the main finding. Registered target wording generic. Need infer expected benchmark extraction. The task asks find single numerical result replication of registered target has to reproduce. \"REGISTERED TARGET: the headline numerical result the paper states for its main finding\". Source likely adapted paper and perhaps abstract omitted key numeric AUC? We must report headline number only. Need use exact contiguous quote containing number, unit paper prints. Which numerical result is the headline for main finding?\n\nLet's parse source. Title. Summary:\n- Established prognostic framework.\n- Identified two molecular clusters...\n- Developed and validated novel prognostic signature PCD Score integrating six key genes.\n- Revealed immune...\n- Predicted temozolomide.\nResults:\n- Twenty-six RCD-associated genes showed significant prognostic relevance.\n- Two clusters identified, B better OS.\n- signature genes...\n- validation strong predictive power.\n...\nThen supplemental detailed:\n- 190 DEGs identified between high/low based threshold.\n- Conclusion: validated six-gene model.\n\nQuestion specifically \"single numerical result that a replication of the registered target has to reproduce.\" Registered target is abstract target, not named metric. \"headline numerical result the paper itself states for its main finding\". Main finding = \"Twenty-six RCD-associated genes showed significant prognostic relevance.\" That likely headline numerical result. Could be 26 RCD-associated genes. Unit perhaps \"genes\". Evidence exact quote: \"Twenty-six RCD-associated genes showed significant prognostic relevance.\" parent_value 26, unit \"genes\". This sounds likely.\n\nBut perhaps main finding is PCD Score with six genes, headline numerical result = six key RCD-related genes. Yet \"a replication of registered target has to reproduce\" maybe extraction benchmark where target can be specific claim, and asks headline numerical result. Here registered target wording is intentionally semantic, likely answer from paper abstract/result. They want a number only and evidence. Need determine which is headline. \"the headline numerical result the paper states for its main finding\" singular. The first Results sentence is \"Twenty-six RCD-associated genes showed significant prognostic relevance.\" That's a numerical finding. The model itself integrates six genes, repeatedly emphasized. \"headline numerical result\" might be 26 genes discovered. Need assess likely expected.\n\nCould answer 26 genes with evidence exact sentence. They demand evidence exact contiguous quotation. Unit must paper prints. Paper prints \"Twenty-six\" word, but parent numeric 26. Unit paper prints \"genes\". They say value paper itself states, no converted. Number is spelled out \"Twenty-six\"—does numeric JSON 26 count converted? Usually extraction accepts number from word. \"The unit must be the unit the paper prints.\" Evidence exact. \"number the paper itself states\" perhaps can normalize spelled number to 26. parent_value number required. Fine.\n\nCould unit be \"RCD-associated genes\" rather than \"genes\"? They ask unit printed. Likely \"genes\". target_result perhaps \"Twenty-six RCD-associated genes showed significant prognostic relevance.\" Maybe number_stated true.\n\nNeed not mention alternatives. JSON valid, no markdown.\n\nLet's investigate clues. They explicitly mention \"Attribution may be carried by text's own wording: a number may be attached to target by a parenthetical list, by word respectively, or by words that name target directly. When that is how text links them, quote whole clause...\" Here target generic, and source sentence directly names \"Twenty-six RCD-associated genes\". The instruction designed to prevent fabricated metric from paper. \"registered target: headline numerical result paper states for its main finding.\" We need choose.\n\nCould \"headline numerical result\" refer 190 DEGs as a central Results subsection, but that's later and not main finding. Main finding is prognostic model based on 26 RCD genes. The abstract-like top says \"Twenty-six RCD-associated genes showed significant prognostic relevance.\" Thus 26 likely.\n\nMaybe there is an original paper with headline \"26 RCD-related genes associated with prognosis...\" and PCD score. Search mental recognition? Title perhaps actual Front Oncol / Scientific Reports. Could abstract include:\n\"Twenty-six RCD-related genes were screened for prognostic significance in STAD. Consensus clustering analysis divided patients into two molecular subtypes...\" \nMaybe key result has \"PCD Score accurately predicted overall survival (AUC = 0.7...)\" But supplied text omitted detailed values. They ask only source. Number 26 is first main numerical result.\n\nLet's ensure exact quote contiguous: \"Twenty-six RCD-associated genes showed significant prognostic relevance.\" Yes. Unit \"genes\". parent 26. target_result perhaps \"The paper reports 26 RCD-associated genes with significant prognostic relevance.\" But they said report headline number only perhaps target_result should be minimal, maybe \"Twenty-six RCD-associated genes showed significant prognostic relevance.\" Evidence same exact quote. Number stated true. Should target_result include number and claim. JSON.\n\nNeed maybe unit \"RCD-associated genes\" to be exact. Unit usually unit printed next to number: \"RCD-associated genes\". Parent_value 26. I think unit could be \"RCD-associated genes\". The prompt: \"The unit must be the unit the paper prints.\" If \"26 genes\", unit genes. They may expect \"genes\". Evidence.\n\nCould target_result be \"26 RCD-associated genes showed significant prognostic relevance.\" We can use exact source wording in evidence, and target result own wording. Since says report headline number only perhaps no extraneous. Let's answer.</think>\n\n{\"parent_value\":26,\"unit\":\"RCD-associated genes\",\"evidence\":\"Twenty-six RCD-associated genes showed significant prognostic relevance.\",\"target_result\":\"Twenty-six RCD-associated genes showed significant prognostic relevance.\",\"number_stated\":true}", "reading": {"parent_value": 26, "unit": "RCD-associated genes", "evidence": "Twenty-six RCD-associated genes showed significant prognostic relevance.", "target_result": "Twenty-six RCD-associated genes showed significant prognostic relevance.", "number_stated": true, "source_locator": "chars 1374-1446 of source sha256 b0c1561eeadfdc8d64b5aac1939e97634484c7e59c704569334ba455c8189c21"}, "recorded_at": "2026-10-31T15:27:12.587563+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "A prognostic signature (PCD Score) integrating six key RCD-related genes.", "minimax_alt": "A validated six-gene PCD Score prognostic signature (CTSV, GCSH, LZTS1, SERPINE1, DDIAS, TRAF2) for stratifying STAD patients by survival risk.", "decisive": false}, "analysis_methods": {"minimax": ["limma", "ConsensusClusterPlus", "Cox regression", "ROC curves", "C-index", "multivariate analyses", "ssGSEA", "GSVA", "oncoPredict"], "minimax_alt": ["Cox regression for risk scoring", "ROC curves, C-index, and multivariate analyses for prognostic validation", "limma for differential expression analysis", "ConsensusClusterPlus for unsupervised clustering", "ssGSEA for immune infiltration", "GSVA for pathway scoring", "clusterProfiler (v4.8.2) for GO and KEGG enrichment analysis", "maftools (v2.14.0) for somatic mutation profiling", "oncoPredict with GDSC pharmacogenomic data for drug-sensitivity prediction"], "decisive": false}, "parent_value": {"minimax": 6, "minimax_alt": 26, "decisive": true}, "unit": {"minimax": "RCD-related genes", "minimax_alt": "RCD-associated genes", "decisive": true}}, "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": []}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:f2b68a2f5e1394bc4c7e88b2f4ca65abf2460a10b6011ffcbf71f2456199e378", "type": "sep_package", "label": "SEP v1 package for pmid:41197447"}], "activities": [{"id": "activity:conversion:pmid:41197447", "type": "conversion", "used": ["package:f2b68a2f5e1394bc4c7e88b2f4ca65abf2460a10b6011ffcbf71f2456199e378"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "4768e430-d8ed-4837-9f8c-2cbe16d2a9a9", "parent_hash": "f2b68a2f5e1394bc4c7e88b2f4ca65abf2460a10b6011ffcbf71f2456199e378", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:41197447 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:41197447' does not resolve to a declared asset", "targets"]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:11:55+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}