{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32642240", "kind": "science-record", "revision": 8, "content_hash": "sha256:978d7645aaa14e688cd692df185617e1b7bf6621ad01e50650c951d3f2a86037", "created_at": "2026-11-01T15:41:05Z", "updated_at": "2026-11-01T22:01:54Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of key genes for esophageal squamous cell carcinoma via integrated bioinformatics analysis and experimental confirmation.", "doi": "10.21037/jtd.2020.01.33", "pmid": "32642240", "authors": ["Jia Hu", "Rongzhen Li", "Huikai Miao", "Zhesheng Wen"], "journal": "Journal of thoracic disease", "year": 2020, "abstract": "BACKGROUND: Esophageal squamous cell carcinoma (ESCC) as the main subtype of esophageal cancer (EC) is a leading cause of cancer-related death worldwide. Despite advances in early diagnosis and clinical management, the long-term survival of ESCC patients remains disappointing, due to a lack of full understanding of the molecular mechanisms.\nMETHODS: In order to identify the differentially expressed genes (DEGs) in ESCC, the microarray datasets GSE20347 and GSE26886 from Gene Expression Omnibus (GEO) database were analyzed. The enrichment analyses of gene ontology (GO) terms, Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway and Gene Set Enrichment Analysis (GSEA) were performed for the DEGs. The protein-protein interaction (PPI) network of these DEGs was constructed using the Cytoscape software based on the STRING database to select as hub genes for weighted co-expression network analysis (WGCNA) with ESCC samples from TCGA database.\nRESULTS: A total of 746 DEGs were commonly shared in the two datasets including 286 upregulated genes and 460 downregulated genes in ESCC. The DEGs were enriched in biological processes such as extracellular matrix organization, proliferation and keratinocyte differentiation, and were enriched in biological pathways such as ECM-receptor interaction and cell cycle. GSEA analysis also indicated the enrichment of upregulated DEGs in cell cycle. The 40 DEGs were selected as hub genes. The MEblack module was found to be enriched in the cell cycle, Spliceosome, DNA replication and Oocyte meiosis. Among the hub genes correlated with MEblack module, GSEA analysis indicated that DEGs of TCGA samples with DLGAP5 upregulation was enriched in cell cycle. Moreover, the highly endogenous expression of DLGAP5 was confirmed in ESCC cells. DLGAP5 knockdown significantly inhibited the proliferation of ESCC cells.\nCONCLUSIONS: DEGs and hub genes such as DLGAP5 from independent datasets in the current study will provide clues to elucidate the molecular mechanisms involved in development and progression of ESCC.", "claims": [{"id": "claim-method", "statement": "The student’s t test was used to compare the differences among different groups.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32642240", "locator": "sections[10] \"Statistical analysis\" paragraph 2", "quote": "The student’s t test was used to compare the differences among different groups."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original microarray data were downloaded from the GEO database (12). The GSE20347 based on GPL571 platform (Affymetrix Human Genome U133A 2.0 Array) contains 17 paired ESCC samples and normal adjacent esophageal tissues.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32642240", "locator": "sections[3] \"Microarray data collection\" paragraph 2", "quote": "The original microarray data were downloaded from the GEO database (12). The GSE20347 based on GPL571 platform (Affymetrix Human Genome U133A 2.0 Array) contains 17 paired ESCC samples and normal adjacent esophageal tissues."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "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:32642240"], "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:GSE20347"], "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:GSE20347"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32642240", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.21037/jtd.2020.01.33", "sha256": "sha256:f65f0c96e12e00b20705adf9c6a5d76058c9f3dac19a6cb3e9fa8dbb0434a132", "bytes": 25202, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.21037/jtd.2020.01.33", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7330802", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE20347", "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=GSE20347", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE20347", "version": null, "note": "The original microarray data were downloaded from the GEO database (12). The GSE20347 based on GPL571 platform (Affymetrix Human Genome U133A 2.0 Array) contains 17 paired ESCC samples and normal adjacent esophageal tissues.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original microarray data were downloaded from the GEO database (12). The GSE20347 based on GPL571 platform (Affymetrix Human Genome U133A 2.0 Array) contains 17 paired ESCC samples and normal adjacent esophageal tissues.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM509787", "GSM509788", "GSM509789", "GSM509790", "GSM509791", "GSM509792", "GSM509793", "GSM509794", "GSM509795", "GSM509796", "GSM509797", "GSM509798", "GSM509799", "GSM509800", "GSM509801", "GSM509802", "GSM509803", "GSM509804", "GSM509805", "GSM509806", "GSM509807", "GSM509808", "GSM509809", "GSM509810", "GSM509811", "GSM509812", "GSM509813", "GSM509814", "GSM509815", "GSM509816", "GSM509817", "GSM509818", "GSM509819", "GSM509820"], "sample_count": 34, "group_sizes": null, "group_sizes_basis": null, "platform": "571", "taxon": "Homo sapiens", "title": "Analysis of gene expression in esophageal squamous cell carcinoma (ESCC)", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE26886", "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=GSE26886", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE26886", "version": null, "note": "The original microarray data were downloaded from the GEO database (12). The GSE20347 based on GPL571 platform (Affymetrix Human Genome U133A 2.0 Array) contains 17 paired ESCC samples and normal adjacent esophageal tissues.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original microarray data were downloaded from the GEO database (12). The GSE20347 based on GPL571 platform (Affymetrix Human Genome U133A 2.0 Array) contains 17 paired ESCC samples and normal adjacent esophageal tissues.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM661721", "GSM661722", "GSM661723", "GSM661724", "GSM661725", "GSM661726", "GSM661727", "GSM661728", "GSM661729", "GSM661730", "GSM661731", "GSM661732", "GSM661733", "GSM661734", "GSM661735", "GSM661736", "GSM661737", "GSM661738", "GSM661739", "GSM661740", "GSM661741", "GSM661742", "GSM661743", "GSM661744", "GSM661745", "GSM661746", "GSM661747", "GSM661748", "GSM661749", "GSM661750", "GSM661751", "GSM661752", "GSM661753", "GSM661754", "GSM661755", "GSM661756", "GSM661757", "GSM661758", "GSM661759", "GSM661760", "GSM661761", "GSM661762", "GSM661763", "GSM661764", "GSM661765", "GSM661766", "GSM661767", "GSM661768", "GSM661769", "GSM661770", "GSM661771", "GSM661772", "GSM661773", "GSM661774", "GSM661775", "GSM661776", "GSM661777", "GSM661778", "GSM661779", "GSM661780", "GSM661781", "GSM661782", "GSM661783", "GSM661784", "GSM661785", "GSM661786", "GSM661787", "GSM661788", "GSM661789"], "sample_count": 69, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiling of Barrett's esophagus, adenocarcinoma, esophageal squamous epithelium and squamous cell carcinoma", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE20347 not downloaded", "asset:data:geo:GSE20347 licence not read", "asset:data:geo:GSE26886 not downloaded", "asset:data:geo:GSE26886 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-2", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "Student’s t test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The student’s t test was used to compare the differences among different groups."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": ["GSE20347", "GSE26886"], "resolved_accessions": ["GSE20347", "GSE26886"], "statements": ["The original microarray data were downloaded from the GEO database (12). The GSE20347 based on GPL571 platform (Affymetrix Human Genome U133A 2.0 Array) contains 17 paired ESCC samples and normal adjacent esophageal tissues."], "basis": "The paper names GSE20347, GSE26886 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:32642240", "data:geo:GSE20347"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE20347"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:01Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 18828, "completion_tokens": 1540, "cached_tokens": 776}}, "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:32642240", "type": "paper", "label": "pmid:32642240"}, {"id": "source:pmid:32642240", "type": "manuscript", "label": "PMID 32642240 full text"}, {"id": "data:geo:GSE20347", "type": "dataset", "label": "GEO GSE20347"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32642240", "type": "paper", "label": "pmid:32642240"}, {"id": "source:pmid:32642240", "type": "manuscript", "label": "PMID 32642240 full text"}, {"id": "data:geo:GSE20347", "type": "dataset", "label": "GEO GSE20347"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32642240", "type": "extraction", "used": ["source:pmid:32642240"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE20347", "type": "accession_resolution", "used": ["data:geo:GSE20347"], "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:32642240", "parent_hash": "sha256:1612ec602fce01932ac12fab8d5a70f67849fc92afab0b8c4388b72f9911fa11", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE20347 licence not read", "asset:data:geo:GSE20347 not downloaded", "asset:data:geo:GSE26886 licence not read", "asset:data:geo:GSE26886 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": 0.93, "evidence": ["entially expressed genes (DEGs) in ESCC, the microarray datasets GSE20347 and GSE26886 from Gene Exp"], "order_basis": "paper_text_order:520", "id": "assay:1"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["f DLGAP5 was confirmed in ESCC cells. DLGAP5 knockdown significantly inhibited the proliferation of", "e.org/gsea/index.jsp) (17). Cell culture and transfection ESCC cell lines including TE-1, KYSE30 and K", "with DLGAP5 knockdown, TE-1 and KYSE410 were transfected with psi-LVRU6GP vectors with DLGAP5 shRNAs", "', sh-3#: 5'- CCATATTTCAGAAATATCCTC-3'). The transfection was performed using Lipofectamine 3000 (Invi"], "order_basis": "paper_text_order:1887", "id": "assay:2"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["KYSE30 and KYSE410, KYSE180 and KYSE520 were cultured in RPMI-1640 or DMEM medium (Gibco, Carlsbad, C"], "order_basis": "paper_text_order:2987", "id": "assay:3"}, {"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"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":"2026-11-04T01:42:57+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}}}