{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33868461", "kind": "science-record", "revision": 9, "content_hash": "sha256:aba8d4e8a1a1df098f9d59cc2e146e4e3384383ba18ea52123c37662096fa4a8", "created_at": "2026-11-01T15:41:32Z", "updated_at": "2026-11-01T22:46:32Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Cytotoxic T-lymphocyte infiltration and chemokine predict long-term patient survival independently of tumor mutational burden in triple-negative breast cancer.", "doi": "10.1177/17588359211006680", "pmid": "33868461", "authors": ["Eriko Katsuta", "Li Yan", "Mateusz Opyrchal", "Pawel Kalinski", "Kazuaki Takabe"], "journal": "Therapeutic advances in medical oncology", "year": 2021, "abstract": "BACKGROUND: Cytotoxic T-lymphocyte (CTL) infiltration into tumor is a positive prognostic factor in breast cancer. High tumor mutational burden (TMB) is also considered as a predictor of tumor immunogenicity and response to immunotherapy. However, it is unclear whether the infiltration of functional CTL simply reflects the TMB or represents an independent prognostic value.\nMETHODS: Utilizing The Cancer Genome Atlas (TCGA) breast cancer cohort, we established the Functional Hotness Score (FHS). The associations of FHS and breast cancer patient prognosis as well as distinct immunity markers were analyzed in a total of 3011 breast cancer patients using TCGA, METABRIC and metastatic breast cancer (MBC) cohort GSE110590.\nRESULTS: We established FHS, based on CD8A, GZMB and CXCL10 gene expression levels of bulk tumors, which delivered the best prognostic value among some gene combinations. Breast cancer patients with the high-FHS tumors showed significantly better survival. FHS was lower in the MBCs. Triple-negative breast cancer (TNBC) showed the highest FHS among subtypes. FHS predicted patient survival in hormone receptor (HR)-negative, especially in TNBC, but not in HR-positive breast cancer. FHS predicted patient prognosis independently in TNBC. The high-FHS TNBCs showed not only higher CD8+ T cell infiltration, but also enhanced broader type-1 anti-cancer immunity. The patients with the high-FHS tumors showed better prognosis not only in high-TMB tumors but also in low-TMB TNBCs. The combination of high-TMB with high-FHS identified a unique subset of patients who do not recur over time in TNBC.\nCONCLUSION: TNBCs with high FHS based on the expression levels of CD8A, GZMB and CXCL10 showed improved prognosis with enhanced anti-cancer immunity regardless of TMB. FHS constitutes an independent prognostic marker of survival, particularly robustly when combined with TMB in TNBC.", "claims": [{"id": "claim-method", "statement": "The survival analyses were conducted by Kaplan–Meier curve with log-rank test, and univariate and multivariate analyses were conducted by Cox regression model.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33868461", "locator": "sections[6] \"Statistical analysis\" paragraph 2", "quote": "The survival analyses were conducted by Kaplan–Meier curve with log-rank test, and univariate and multivariate analyses were conducted by Cox regression model."}], "state": "complete"}, {"id": "claim-data-access", "statement": "TCGA provisional and METABRIC datasets were downloaded through cBioportal.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33868461", "locator": "sections[3] \"Study design and patient cohorts\" paragraph 2", "quote": "TCGA provisional and METABRIC datasets were downloaded through cBioportal."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:33868461"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE110590"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:group_comparison_wilcoxon", "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE110590"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:group_comparison_wilcoxon"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33868461", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1177/17588359211006680", "sha256": "sha256:a83793b46f5d16e9e362937b54ae3a54e5d3add0599c487d9f7d210be7ea113a", "bytes": 37639, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1177/17588359211006680", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8024454", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE110590", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110590", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE110590", "version": null, "note": "TCGA provisional and METABRIC datasets were downloaded through cBioportal.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "TCGA provisional and METABRIC datasets were downloaded through cBioportal.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM3003762", "GSM3003763", "GSM3003764", "GSM3003765", "GSM3003766", "GSM3003767", "GSM3003768", "GSM3003769", "GSM3003770", "GSM3003771", "GSM3003772", "GSM3003773", "GSM3003774", "GSM3003775", "GSM3003776", "GSM3003777", "GSM3003778", "GSM3003779", "GSM3003780", "GSM3003781", "GSM3003782", "GSM3003783", "GSM3003784", "GSM3003785", "GSM3003786", "GSM3003787", "GSM3003788", "GSM3003789", "GSM3003790", "GSM3003791", "GSM3003792", "GSM3003793", "GSM3003794", "GSM3003795", "GSM3003796", "GSM3003797", "GSM3003798", "GSM3003799", "GSM3003800", "GSM3003801", "GSM3003802", "GSM3003803", "GSM3003804", "GSM3003805", "GSM3003806", "GSM3003807", "GSM3003808", "GSM3003809", "GSM3003810", "GSM3003811", "GSM3003812", "GSM3003813", "GSM3003814", "GSM3003815", "GSM3003816", "GSM3003817", "GSM3003818", "GSM3003819", "GSM3003820", "GSM3003821", "GSM3003822", "GSM3003823", "GSM3003824", "GSM3003825", "GSM3003826", "GSM3003827", "GSM3003828", "GSM3003829", "GSM3003830", "GSM3003831", "GSM3003832", "GSM3003833", "GSM3003834", "GSM3003835", "GSM3003836", "GSM3003837", "GSM3003838", "GSM3003839", "GSM3003840", "GSM3003841", "GSM3003842", "GSM3003843", "GSM3003844"], "sample_count": 83, "group_sizes": null, "group_sizes_basis": null, "platform": "11154;16791", "taxon": "Homo sapiens", "title": "Integrated RNA and DNA sequencing reveals early drivers of metastatic breast cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33868461:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:22d7dd847319f6bfb468ea25ca55b49892af1062ea062713a8be5c9baf3d8d73", "bytes": 929, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#table1-17588359211006680", "version": null, "note": "Patient demographics.", "structure": {"pmcid": "PMC8024454", "section_index": 3, "section_title": "Study design and patient cohorts", "row_count": 34, "column_count": 3}, "table": {"label": "Table 1.", "caption": "Patient demographics.", "rows": [["", "TCGA (n = 1091)", "METABRIC (n = 1904)"], ["Age (years)"], ["Mean ± SD", "58.5 ± 13.2", "61.1 ± 13.0"], ["Menopause"], ["Post", "703", "1493"], ["Pre", "226", "411"], ["Indeterminate", "73", "0"], ["Unknown", "89", "0"], ["ER"], ["ER+", "805", "1459"], ["ER−", "237", "445"], ["Indeterminate", "2", "0"], ["Unknown", "47", "0"], ["PR"], ["PR+", "697", "1009"], ["PR−", "342", "895"], ["Indeterminate", "4", "0"], ["Unknown", "48", "0"], ["HER2"], ["HER2+", "185", "236"], ["HER2−", "767", "1668"], ["Indeterminate", "25", "0"], ["Unknown", "114", "0"], ["Histology"], ["IDC", "781", "1500"], ["ILC", "203", "142"], ["Others", "107", "262"], ["Stage"], ["Stage 0", "0", "4"], ["Stage I", "180", "475"], ["Stage II", "618", "800"], ["Stage III", "249", "115"], ["Stage IV", "20", "9"], ["Stage X", "24", "501"]], "row_count": 34, "column_count": 3, "numeric_cells": 55, "header_rows": 1, "locator": "section[3]/table-wrap[1]#table1-17588359211006680"}}], "gaps": ["asset:data:geo:GSE110590 not downloaded", "asset:data:geo:GSE110590 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The survival analyses were conducted by Kaplan–Meier curve with log-rank test, and univariate and multivariate analyses were conducted by Cox regression model."}}, {"id": "method-2", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "analysis of variance"}}, {"id": "method-3", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Cox regression"}}, {"id": "method-4", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}], "targets": [], "gaps": ["method.group_comparison_wilcoxon"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": false, "required_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: wilcoxon."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE110590"], "resolved_accessions": ["GSE110590"], "statements": ["TCGA provisional and METABRIC datasets were downloaded through cBioportal."], "basis": "The paper names GSE110590 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:33868461", "data:geo:GSE110590", "asset:table:pmid:33868461:1"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "group_comparison_wilcoxon", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE110590"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:29:18Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 29657, "completion_tokens": 2641, "cached_tokens": 784}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:33868461", "type": "paper", "label": "pmid:33868461"}, {"id": "source:pmid:33868461", "type": "manuscript", "label": "PMID 33868461 full text"}, {"id": "data:geo:GSE110590", "type": "dataset", "label": "GEO GSE110590"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33868461", "type": "paper", "label": "pmid:33868461"}, {"id": "source:pmid:33868461", "type": "manuscript", "label": "PMID 33868461 full text"}, {"id": "data:geo:GSE110590", "type": "dataset", "label": "GEO GSE110590"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33868461", "type": "extraction", "used": ["source:pmid:33868461"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE110590", "type": "accession_resolution", "used": ["data:geo:GSE110590"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:33868461", "parent_hash": "sha256:e50961c10e56d2e1eccee97877eb66fb15af7722c6ca562b2692bdf55f8e54e5", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE110590 licence not read", "asset:data:geo:GSE110590 not downloaded", "execution.not_run", "method.group_comparison_wilcoxon", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:group_comparison_wilcoxon"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The survival analyses were conducted by Kaplan–Meier curve with log-rank test, and univariate and multivariate analyses were conducted by Cox regression model."], "order_basis": "analysis_only", "id": "assay:1"}]},"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":"2026-11-04T00:30:49+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}}}