{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26484266", "kind": "science-record", "revision": 6, "content_hash": "sha256:31b3ac1bab553f05d4580a50d9df3618e3c7fe9fbb969f3c859b590ddc63d8a5", "created_at": "2026-11-01T15:40:13Z", "updated_at": "2026-11-01T21:20:14Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Global gene expression profiling reveals a suppressed immune response pathway associated with 3q amplification in squamous carcinoma of the lung.", "doi": "10.1016/j.gdata.2015.06.014", "pmid": "26484266", "authors": ["Jun Qian", "Yong Zou", "Jing Wang", "Bing Zhang", "Pierre P Massion"], "journal": "Genomics data", "year": 2015, "abstract": "Chromosome 3q26-28 is a critical region of genomic amplification in non-small cell lung cancer (NSCLC), particularly lung squamous cell carcinomas (SCCs). No molecular therapeutic target has shown clinical utility for SCC, in contrast with adenocarcinomas of the lung. To identify novel candidate drivers in this region, we performed both Array Comparative Genomic Hybridization (array CGH, Agilent Human Genome CGH 244A oligo-microarrays) and Gene Expression Microarray (Agilent Human Gene Expression 4 × 44 K microarray) on 24 untreated lung SCC specimens. Using our previously published integrative genomics approach, we identified 12 top amplified driver genes within this region that are highly correlated and overexpressed in lung SCC. We further demonstrated one of the 12 top amplified driver Fragile X mental retardation-related protein 1 (FXR1) as a novel cancer gene in NSCLC and FXR1 executes its regulatory function by forming a novel complex with two other oncogenes, protein kinase C, iota ( PRKCI) and epithelial cell transforming 2 (ECT2) within the same amplicon in lung cancer cell. Here we report that immune response pathways are significantly suppressed in lung SCC and negatively associated with 3q driver gene expression, implying a potential role of 3q drivers in cancer immune-surveillance. In light of the attractive immunotherapy strategy using blockade of negative regulators of T cell function for multiple human cancer including lung SCC, our findings may provide a rationale for targeting 3q drivers in combination of immunotherapies for human tumors harboring the 3q amplicon. The data have been deposited in NCBI's Gene Expression Omnibus and are accessible through GEO Series accession number GSE40089.", "claims": [{"id": "claim-method", "statement": "To identify molecular pathways associated with 3q amplicon in lung SCC, we performed Pearson correlation analysis using 12-gene signature on 3q chromosome against whole genome expression data obtained from 24 SCCs.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26484266", "locator": "sections[4] \"Results\" paragraph 3", "quote": "To identify molecular pathways associated with 3q amplicon in lung SCC, we performed Pearson correlation analysis using 12-gene signature on 3q chromosome against whole genome expression data obtained from 24 SCCs."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data have been deposited in NCBI's Gene Expression Omnibus and are accessible through GEO Series accession number GSE40089.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26484266", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The data have been deposited in NCBI's Gene Expression Omnibus and are accessible through GEO Series accession number GSE40089."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper used Pearson correlation analysis of a 12-gene 3q driver signature against whole-genome expression data from 24 SCCs; the source data were deposited in GEO under accession GSE40089. The headline result was: “Here we report that immune response pathways are significantly suppressed in lung SCC and negatively associated with 3q driver gene expression, implying a potential role of 3q drivers in cancer immune-surveillance.”", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:26484266", "locator": "sections[4] \"Results\" paragraph 3", "quote": "To identify molecular pathways associated with 3q amplicon in lung SCC, we performed Pearson correlation analysis using 12-gene signature on 3q chromosome against whole genome expression data obtained from 24 SCCs."}, {"asset": "source:pmid:26484266", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Here we report that immune response pathways are significantly suppressed in lung SCC and negatively associated with 3q driver gene expression, implying a potential role of 3q drivers in cancer immune-surveillance."}, {"asset": "source:pmid:26484266", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The data have been deposited in NCBI's Gene Expression Omnibus and are accessible through GEO Series accession number GSE40089."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The paper used Pearson correlation analysis of a 12-gene 3q driver signature against whole-genome expression data from 24 SCCs; the source data were deposited in GEO under accession GSE40089. The headline result was: “Here we report that immune response pathways are significantly suppressed in lung SCC and negatively associated with 3q driver gene expression, implying a potential role of 3q drivers in cancer immune-surveillance.”", "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:26484266"], "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:GSE40089"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "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:GSE40089"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26484266", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.gdata.2015.06.014", "sha256": "sha256:4c8f30dd73d3b05548475af82120f92ca0c6b8b975f4e9d3ca93db84ca99c0c6", "bytes": 8401, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.gdata.2015.06.014", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4583673", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE40089", "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=GSE40089", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE40089", "version": null, "note": "The data have been deposited in NCBI's Gene Expression Omnibus and are accessible through GEO Series accession number GSE40089.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data have been deposited in NCBI's Gene Expression Omnibus and are accessible through GEO Series accession number GSE40089.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM984306", "GSM984307", "GSM984308", "GSM984309", "GSM984310", "GSM984311", "GSM984312", "GSM984313", "GSM984314", "GSM984315", "GSM984316", "GSM984317", "GSM984318", "GSM984319", "GSM984320", "GSM984321", "GSM984322", "GSM984323", "GSM984324", "GSM984325", "GSM984326", "GSM984327", "GSM984328", "GSM984329", "GSM984686", "GSM984687", "GSM984688", "GSM984689", "GSM984690", "GSM984691", "GSM984692", "GSM984693", "GSM984694", "GSM984695", "GSM984696", "GSM984697", "GSM984698", "GSM984699", "GSM984700", "GSM984701", "GSM984702", "GSM984703", "GSM984704", "GSM984705", "GSM984706", "GSM984707", "GSM984708", "GSM984709"], "sample_count": 48, "group_sizes": null, "group_sizes_basis": null, "platform": "6480;9128", "taxon": "Homo sapiens", "title": "Squamous cell carcinoma of the lung", "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:26484266:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3e66a4a0a188b8da5fe14b535420e7533c143c2ad03f78a4d9175fabe27b47d7", "bytes": 910, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0010", "version": null, "note": null, "structure": {"pmcid": "PMC4583673", "section_index": 1, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Specifications"], ["Organism/cell line/tissue", "Homo sapiens"], ["Sex", "Male and female"], ["Sequencer or array type", "Agilent Human Genome CGH 244A oligo-microarrays and Agilent Human Gene Expression 4 × 44 K microarray"], ["Data format", "Raw and normalized data were provided"], ["Experimental factors", "24 untreated primary lung squamous tumors were fresh-frozen, with efforts made to use samples with tumor content > 70%."], ["Experimental features", "Both aCGH and expression microarrays were performed on the same tumors to identify novel amplified driver genes in 3q26–29."], ["Consent", "All patients consented before starting the study in written form"], ["Sample source location", "Thoracic Program, Vanderbilt Ingram Cancer Center, Nashville, TN 37232, USA"]], "row_count": 9, "column_count": 2, "numeric_cells": 4, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t0010"}}], "gaps": ["asset:data:geo:GSE40089 not downloaded", "asset:data:geo:GSE40089 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To identify molecular pathways associated with 3q amplicon in lung SCC, we performed Pearson correlation analysis using 12-gene signature on 3q chromosome against whole genome expression data obtained from 24 SCCs."}}], "targets": [], "gaps": []}, "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": true, "required_operations": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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": ["GSE40089"], "resolved_accessions": ["GSE40089"], "statements": ["The data have been deposited in NCBI's Gene Expression Omnibus and are accessible through GEO Series accession number GSE40089."], "basis": "The paper names GSE40089 in NCBI's Gene Expression Omnibus and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pearson_r"], "assets": ["source:pmid:26484266", "data:geo:GSE40089", "asset:table:pmid:26484266:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE40089"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:25:51Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 19586, "completion_tokens": 2646, "cached_tokens": 1816}}, "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:26484266", "type": "paper", "label": "pmid:26484266"}, {"id": "source:pmid:26484266", "type": "manuscript", "label": "PMID 26484266 full text"}, {"id": "data:geo:GSE40089", "type": "dataset", "label": "GEO GSE40089"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26484266", "type": "paper", "label": "pmid:26484266"}, {"id": "source:pmid:26484266", "type": "manuscript", "label": "PMID 26484266 full text"}, {"id": "data:geo:GSE40089", "type": "dataset", "label": "GEO GSE40089"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26484266", "type": "extraction", "used": ["source:pmid:26484266"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE40089", "type": "accession_resolution", "used": ["data:geo:GSE40089"], "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:26484266", "parent_hash": "sha256:f3a0cb7d77f88e820c38bdd2943af730239dc7c60409366a3dc3a78e74d62c9a", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE40089 licence not read", "asset:data:geo:GSE40089 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["244A oligo-microarrays) and Gene Expression Microarray (Agilent Human Gene Expression 4 × 44 K micr", "rray (Agilent Human Gene Expression 4 × 44 K microarray) on 24 untreated lung SCC specimens. Using o", "g the Agilent Human Gene Expression 4 × 44 K Microarray platform using manufacturer-recommended proc", "sing manufacturer-recommended procedures for microarray-based one-color assay. The array was scanned"], "order_basis": "paper_text_order:562", "id": "assay:1"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["To identify molecular pathways associated with 3q amplicon in lung SCC, we performed Pearson correlation analysis using 12-gene signature on 3q chromosome against whole genome expression data obtained from 24 SCCs."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T03:32:53+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}}}