{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31921802", "kind": "science-record", "revision": 7, "content_hash": "sha256:4663b678cd1b7571faa25e1fae54401c6fb662609893491e7a163f611e28020d", "created_at": "2026-11-01T15:40:54Z", "updated_at": "2026-11-01T22:01:11Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Integrative Bioinformatics Approaches to Map Potential Novel Genes and Pathways Involved in Ovarian Cancer.", "doi": "10.3389/fbioe.2019.00391", "pmid": "31921802", "authors": ["S Udhaya Kumar", "D Thirumal Kumar", "R Siva", "C George Priya Doss", "Hatem Zayed"], "journal": "Frontiers in bioengineering and biotechnology", "year": 2019, "abstract": "Background and aims: Ovarian cancer (OC) is the seventh most commonly detected cancer among women. This study aimed to map the hub and core genes and potential pathways that might be involved in the molecular pathogenesis of OC. Methods: In the present work, we analyzed a microarray dataset (GSE126519) from the Gene Expression Omnibus (GEO) database and used the GEO2R tool to screen OC cells and ovarian SINE-resistant cancer cells for differentially expressed genes (DEGs). For the functional annotation of the DEGs, we conducted Gene Ontology (GO) and pathway enrichment analyses (KEGG) using the DAVID v6.8 online server and GenoGo Metacore™, Cortellis Solution software. Protein-protein interaction (PPI) networks were constructed using the STRING database, and Cytoscape software was used for visualization. The survival analysis was performed using the online platform GEPIA2 to determine the prognostic value of the expression of hub genes in cell lines from OC patients. Results: We identified a total of 809 upregulated and 700 downregulated DEGs. GO analysis revealed that the genes with statistically significant differences in expression were mainly associated with biological processes involved in the cell cycle, the mitotic cell cycle, mitotic nuclear division, organ morphogenesis, cell development, and cell morphogenesis. By using the Analyze Networks (AN) algorithm in GeneGo, we identified the most relevant biological networks involving DEGs that were mainly enriched in the cell cycle (in metaphase checkpoints) and revealed the role of APC in cell cycle regulation pathways. We found 10 hub genes and four core genes (FZD6, FZD8, CDK2, and RBBP8) that are strongly linked to OC. Conclusion: This study sheds light on the molecular pathogenesis of OC and is expected to provide potential molecular biomarkers that are beneficial for the treatment and clinical molecular diagnosis of OC.", "claims": [{"id": "claim-method", "statement": "The p-values were calculated using log-rank statistics.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31921802", "locator": "sections[13] \"Survival Analysis and Expression Levels of Hub Genes\" paragraph 3", "quote": "The p-values were calculated using log-rank statistics."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All datasets generated for this study are included in the article/Supplementary Material.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31921802", "locator": "sections[15] \"Data Availability Statement\" paragraph 2", "quote": "All datasets generated for this study are included in the article/Supplementary Material."}], "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:31921802"], "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:GSE126519"], "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:GSE126519"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31921802", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fbioe.2019.00391", "sha256": "sha256:cde1fcbd45fb8dc385bb21833e0ded365a0698cb12bae37baf55b8cbac372777", "bytes": 40341, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fbioe.2019.00391", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6927934", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE126519", "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=GSE126519", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE126519", "version": null, "note": "All datasets generated for this study are included in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All datasets generated for this study are included in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3602932", "GSM3602933", "GSM3602934", "GSM3602935", "GSM3602936", "GSM3602937"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Analysis of RNA profiles in parent and Selective Inhibitors of Nuclear Export (SINE) resistant ovarian cancer cells", "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:31921802:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:644b03c4a388f175ac0ca432699b38d8ec281f73773389316fb380505ba7c48d", "bytes": 842, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T1", "version": null, "note": "Patients' information in GSE126519 derived from the GEO database.", "structure": {"pmcid": "PMC6927934", "section_index": 9, "section_title": "DEG Identification", "row_count": 7, "column_count": 6}, "table": {"label": "Table 1", "caption": "Patients' information in GSE126519 derived from the GEO database.", "rows": [["Group", "Accession", "Patient no.", "Organism", "Disease state", "Type"], ["OC", "GSM3602932", "Patient 1", "Homo sapiens", "Ovarian cancer", "Human ovarian cancer cell"], ["", "GSM3602933", "Patient 2", "Homo sapiens", "Ovarian cancer", "Human ovarian cancer cell"], ["", "GSM3602934", "Patient 3", "Homo sapiens", "Ovarian cancer", "Human ovarian cancer cell"], ["SINE resistance OC", "GSM3602935", "Patient 4", "Homo sapiens", "Ovarian cancer", "Human ovarian cancer cell"], ["", "GSM3602936", "Patient 5", "Homo sapiens", "Ovarian cancer", "Human ovarian cancer cell"], ["", "GSM3602937", "Patient 6", "Homo sapiens", "Ovarian cancer", "Human ovarian cancer cell"]], "row_count": 7, "column_count": 6, "numeric_cells": 12, "header_rows": 1, "locator": "section[9]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:31921802:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a6b5f07ee5e68b56b723fe55f1b672fcbd850e3f7f61d0fbfa1d565a67be70e0", "bytes": 664, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T2", "version": null, "note": "Topological parameters for the upregulated and downregulated PPI network.", "structure": {"pmcid": "PMC6927934", "section_index": 10, "section_title": "Construction of the PPI Network", "row_count": 9, "column_count": 4}, "table": {"label": "Table 2", "caption": "Topological parameters for the upregulated and downregulated PPI network.", "rows": [["S. no.", "Topological parameters", "Comprehended values"], ["", "", "Upregulated genes", "Downregulated genes"], ["(1)", "Number of nodes", "794", "676"], ["(2)", "Clustering co-efficient", "0.321", "0.192"], ["(3)", "Network density", "0.023", "0.003"], ["(4)", "Network centralization", "0.169", "0.081"], ["(5)", "Network heterogeneity", "1.748", "1.893"], ["(6)", "Characteristic path length", "3.295", "4.509"], ["(7)", "Average number of neighbors", "18.544", "2.257"]], "row_count": 9, "column_count": 4, "numeric_cells": 21, "header_rows": 2, "locator": "section[10]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:31921802:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2a4f1deb49fb430d9a6313b980aa3cb40ea834e8bc9dae1939c4fa20a789db3b", "bytes": 1258, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T3", "version": null, "note": "Most relevant biological networks were generated using GeneGo Analyze Networks (AN) algorithm.", "structure": {"pmcid": "PMC6927934", "section_index": 12, "section_title": "Enrichment Analysis Using Metacore™ Software", "row_count": 4, "column_count": 9}, "table": {"label": "Table 3", "caption": "Most relevant biological networks were generated using GeneGo Analyze Networks (AN) algorithm.", "rows": [["S. no.", "Network name", "Processes", "Size", "Target", "Pathways", "p-value", "z score", "g score"], ["1", "TCF7L2 (TCF4), Tcf(Lef), Frizzled, RUNX2, p21", "Canonical Wnt signaling pathway (50.0%), regulation of Wnt signaling pathway (58.0%), cell-cell signaling by Wnt (56.0%), Wnt signaling pathway (56.0%), regulation of canonical Wnt signaling pathway (50.0%)", "50", "17", "262", "1.12e-20", "21.47", "348.97"], ["2", "CDC25A, CDK2, Brca1, ATM, RBBP8 (CtIP)", "Mitotic cell cycle (57.1%), mitotic cell cycle process (53.1%), mitotic cell cycle phase transition (42.9%), cell cycle phase transition (42.9%), positive regulation of cell cycle (46.9%)", "50", "32", "24", "2.61e-49", "41.10", "71.10"], ["3", "KRMP1, FAM83D, LMO1, CBWD1, PSF1", "cGMP catabolic process (6.4%), response to macrophage colony-stimulating factor (6.4%), cellular response to macrophage colony-stimulating factor stimulus (6.4%), purine ribonucleotide catabolic process (8.5%), ribonucleotide catabolic process (8.5%)", "50", "35", "0", "5.36e-56", "45.03", "45.03"]], "row_count": 4, "column_count": 9, "numeric_cells": 27, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T3"}}], "gaps": ["asset:data:geo:GSE126519 not downloaded", "asset:data:geo:GSE126519 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "The p-values were calculated using log-rank statistics."}}, {"id": "method-2", "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-3", "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": 0.7, "band": "medium", "quote": "pathway enrichment"}}], "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": ["logrank_test"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: log_rank_test."}, "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": ["GSE126519"], "resolved_accessions": ["GSE126519"], "statements": ["All datasets generated for this study are included in the article/Supplementary Material."], "basis": "The paper names GSE126519 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": ["logrank_test"], "assets": ["source:pmid:31921802", "data:geo:GSE126519", "asset:table:pmid:31921802:1", "asset:table:pmid:31921802:2", "asset:table:pmid:31921802:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE126519"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:17:51Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 29092, "completion_tokens": 1645, "cached_tokens": 18944}}, "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:31921802", "type": "paper", "label": "pmid:31921802"}, {"id": "source:pmid:31921802", "type": "manuscript", "label": "PMID 31921802 full text"}, {"id": "data:geo:GSE126519", "type": "dataset", "label": "GEO GSE126519"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31921802", "type": "paper", "label": "pmid:31921802"}, {"id": "source:pmid:31921802", "type": "manuscript", "label": "PMID 31921802 full text"}, {"id": "data:geo:GSE126519", "type": "dataset", "label": "GEO GSE126519"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31921802", "type": "extraction", "used": ["source:pmid:31921802"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE126519", "type": "accession_resolution", "used": ["data:geo:GSE126519"], "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:31921802", "parent_hash": "sha256:08539297af087eaa1fa95ba7c801b3b01398a52700b90f8218bc345efe4d225e", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE126519 licence not read", "asset:data:geo:GSE126519 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": 0.93, "evidence": ["Methods: In the present work, we analyzed a microarray dataset (GSE126519) from the Gene Expression"], "order_basis": "paper_text_order:337", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["logrank_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The p-values were calculated using log-rank statistics."], "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":"2026-11-04T02:11:13+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}}}