{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40657391", "kind": "science-record", "revision": 1, "content_hash": "sha256:52182a4f3b2a81c2b80a49b759eed460d08fc9346db13e7dac3caf9dd42aa456", "created_at": "2026-11-01T10:25:51Z", "updated_at": "2026-11-01T10:25:51Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Integration of Multi-Scale Profiling and Machine Learning Reveals the Prognostic Role of Extracellular Matrix-Related Cancer-Associated Fibroblasts in Lung Adenocarcinoma.", "doi": "10.7150/ijms.113580", "pmid": "40657391", "authors": null, "journal": "International journal of medical sciences", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 28.0, "unit": "ecafs-related genes", "tolerance": null, "source": "chars 1239-1425 of source sha256 7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8"}, "evidence": [{"asset": "source:pmid:40657391", "locator": "chars 1239-1425 of source sha256 7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8", "quote": "A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts."}]}], "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:40657391"], "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:40657391", "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:40657391' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40657391", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7150/ijms.113580", "sha256": "sha256:7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7150/ijms.113580", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}], "gaps": ["asset:source:pmid:40657391 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:40657391"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40657391"]}, "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": "ceb60bff39d4bb5b450e01b83d017f6206fc92b389b410eafb58d31028ac72fe", "source_hash": "7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8", "raw_response_sha256": "sha256:bce3ee03123343af21b1599245c6ead18ef3596ae74ae089ee62d4a7883c857d", "raw_response_chars": 4770}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "dbda8e8ce30d73d0023a781dc49d04867f4640dbb9311ed66082569f1525e8ed", "source_hash": "7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8", "raw_response_sha256": "sha256:ddcf938c4c4bc98e55cf019eb6f8b1c13a7f9399242fc24c614a60af29bd8d3b", "raw_response_chars": 74662}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "dbbed125bf502f0bbb5fd6e407fc09551c34bd22cfdf41b20356a01994f325dd", "source_hash": "7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8", "raw_response": "{\"parent_value\":28,\"unit\":\"eCAFs-related genes\",\"evidence\":\"A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.\",\"target_result\":\"The paper states that the prognostic model incorporated 28 eCAFs-related genes.\",\"number_stated\":true}", "reading": {"parent_value": 28, "unit": "eCAFs-related genes", "evidence": "A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.", "target_result": "The paper states that the prognostic model incorporated 28 eCAFs-related genes.", "number_stated": true, "source_locator": "chars 1239-1425 of source sha256 7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8"}, "recorded_at": "2026-10-31T15:27:10.281225+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "3a87a2c0c6e291fefb9bdec213f59cb495039763cd7008e065609fe1a33b0736", "source_hash": "7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8", "raw_response": "<think>We need answer JSON only. Need interpret target headline numerical result paper states main finding. Source abstract: prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, stratified groups. What single numerical result replication target has to reproduce? Likely 28 eCAFs-related genes? Registered target \"headline numerical result the paper itself states for its main finding.\" Need infer perhaps headline number from paper title/abstract. Numbers: 15 tumors, cohorts sample sizes, 28 genes, 101 algorithms. Which is headline numerical result? Maybe 28 eCAF-related genes is core main finding. Need quote exact contiguous clause containing number, whole clause. Evidence exact quote. Unit must printed unit. Parent_value 28, unit perhaps \"eCAFs-related genes\". Evidence: \"A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.\" This contains two numerical values, ambiguity perhaps exact clause includes both. They ask single headline number. Could quote \"A prognostic model incorporating 28 eCAFs-related genes\" but that's not clause? Exact contiguous quotation, attribution can be target direct. Need \"headline number only\" and quote whole clause when attribution through wording. This sentence could quote full sentence though includes 101. Does evidence contain number and extra number confuse? Maybe target likely 28. The \"main finding\" is prognostic role, model incorporating 28 genes validated through 101 algorithms. Headline numerical result likely 28 genes. Unit \"eCAFs-related genes.\" Need not overthink.\n\nCould target instead be \"101-machine learning algorithms\" as replication of registered target? Usually prompts in benchmark ask \"single numerical result that replication of registered target has to reproduce\"; registered target generic \"headline numerical result ... main finding\". In abstracts, headline result often e.g. \"model incorporating 28 genes, validated through 101 algorithms\". Which number is main numerical result? 28 eCAFs-related genes is signature size, likely headline. 101 algorithms sounds method. Could headline be \"28 eCAFs-related genes\". Unit should exact printed unit. \"eCAFs-related genes\" plausible. Evidence exact contiguous quote. Target_result perhaps \"28 eCAFs-related genes\" or \"true\". Schema string. Need mention value and unit. Could target_result: \"The prognostic model incorporates 28 eCAFs-related genes.\" But that's paraphrase okay except evidence exact quote. They explicitly ask headline number only, perhaps output parent_value 28, unit \"eCAFs-related genes\", evidence exact, target_result maybe \"28 eCAFs-related genes\". Number stated true.\n\nNeed ensure no markdown. Exact quote: In abstract: \"A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.\" Full exact. Unit printed \"eCAFs-related genes\". Could quote whole sentence. parent_value number 28.\n\nBut maybe \"101-machine learning algorithms\" is headline number because replication of main finding must reproduce 28 genes? Let's parse wording: \"find the single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target\". REGISTERED TARGET: \"the headline numerical result the paper itself states for its main finding\". It may be task to identify result in source. Main finding includes eCAFs dominant and poor survival, but no quantitative result. Then model incorporates 28 genes. The headline numerical result perhaps 28. They ask \"If the text states no number for the registered target, set false...\" Since target main finding maybe no numerical value attached to eCAFs poor prognosis. But likely source selected because abstract has clear headline number 28. We need distinguish target definition deliberately broad and perhaps asks exact source. \"A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms...\" Both numbers. Which is headline? Perhaps 28 is main finding (signature size), 101 is validation method count. Unit for 28 genes. Could they expect 28.\n\nCould evidence be narrower: \"A prognostic model incorporating 28 eCAFs-related genes\" exact contiguous. User says \"When that is how the text links them, quote the whole clause so a reader can check attribution for themselves.\" Full clause extends through cohorts. Better full sentence. Yet extra number 101 may violate \"headline number only\"? Evidence can include extra contextual number, but ideally exact phrase. They demand \"exact, contiguous quotation ... contains the number; do not shorten it, do not add ellipsis and do not paraphrase it.\" \"do not shorten it\" likely means quote source passage fully, not just a fragment? They say \"When that is how the text links them, quote the whole clause\". So full sentence safest.\n\nCould target_result be \"The paper states that its prognostic model incorporates 28 eCAFs-related genes.\" But headline only perhaps target_result just \"28 eCAFs-related genes\". Need JSON proper escaped apostrophes no issue.\n\nUnit \"eCAFs-related genes\" printed. Does unit need simply \"genes\"? They say unit must be unit paper prints. It prints \"28 eCAFs-related genes\"; count's unit is genes, qualifier part of target. Likely unit \"genes\". They may expect \"eCAFs-related genes\". Usually schema expects e.g. parent_value 28, unit \"genes\". Better unit \"genes\" because unit is noun. But wording says unit the paper prints, and exact phrase is \"eCAFs-related genes.\" Could set \"eCAFs-related genes\" to preserve identity. Parent_value 28.\n\nLet's formulate:\n{\n \"parent_value\":28,\n \"unit\":\"eCAFs-related genes\",\n \"evidence\":\"A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.\",\n \"target_result\":\"28 eCAFs-related genes\",\n \"number_stated\":true\n}\nWould \"headline number only\" target_result include text? They specifically schema includes target_result likely narrative. But \"Report headline number only\" means no explanations. target_result can \"28 eCAFs-related genes\". Good.\n\nNeed answer only JSON.</think>\n\n{\"parent_value\":28,\"unit\":\"eCAFs-related genes\",\"evidence\":\"A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.\",\"target_result\":\"28 eCAFs-related genes\",\"number_stated\":true}", "reading": {"parent_value": 28, "unit": "eCAFs-related genes", "evidence": "A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.", "target_result": "28 eCAFs-related genes", "number_stated": true, "source_locator": "chars 1239-1425 of source sha256 7788e5098a964daa3f06d3a727fa664a872a057286a2d759e21a4969735e05d8"}, "recorded_at": "2026-10-31T15:27:20.092778+00:00"}], "agreement": false, "disagreements": {"target_result": {"minimax": "A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, stratified patients into high- and low-risk groups across cohorts.", "minimax_alt": "A prognostic model incorporating 28 eCAFs-related genes, validated through 101-machine learning algorithms, effectively stratified patients into high- and low-risk groups across cohorts.", "decisive": false}, "analysis_methods": {"minimax": ["single-cell RNA sequencing", "CIBERSORTx deconvolution", "Kaplan-Meier survival analysis", "Slingshot pseudotime trajectory analysis", "Gene Set Variation Analysis (GSVA)", "machine learning algorithms"], "minimax_alt": ["101-machine learning algorithms for prognostic-model validation", "CIBERSORTx deconvolution algorithm in absolute mode", "High-infiltration and low-infiltration stratification based on relative cellular-subset abundance", "Kaplan-Meier (KM) survival analysis", "Slingshot pseudotime trajectory analysis", "Gene Set Variation Analysis (GSVA)", "Gene Ontology (GO) enrichment analysis", "FindMarkers"], "decisive": false}, "statistical_method": {"minimax": "Kaplan-Meier (KM) survival analysis", "minimax_alt": "101-machine learning algorithms", "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:494af632873c165735a882ebc6f314967ebf4c2a6da806bdfa99696ccef0dcf4", "type": "sep_package", "label": "SEP v1 package for pmid:40657391"}], "activities": [{"id": "activity:conversion:pmid:40657391", "type": "conversion", "used": ["package:494af632873c165735a882ebc6f314967ebf4c2a6da806bdfa99696ccef0dcf4"], "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": "0d3899d3-dc7a-4f58-a713-05e8a2982f87", "parent_hash": "494af632873c165735a882ebc6f314967ebf4c2a6da806bdfa99696ccef0dcf4", "fork_of": null, "generation": 1}, "gaps": ["abstract", "asset:source:pmid:40657391 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:40657391' 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":"2026-11-04T03:12:36+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}}}