{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33714202", "kind": "science-record", "revision": 6, "content_hash": "sha256:7bf6bd7b78f0ec722c586af2bce363dcbd143026ff8153b4da6af5744722388a", "created_at": "2026-11-01T15:41:28Z", "updated_at": "2026-11-01T22:03:18Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Construction of a ceRNA-based lncRNA-mRNA network to identify functional lncRNAs in polycystic ovarian syndrome.", "doi": "10.18632/aging.202659", "pmid": "33714202", "authors": ["Yue Ma", "Linna Ma", "Yurong Cao", "Jun Zhai"], "journal": "Aging", "year": 2021, "abstract": "Polycystic ovary syndrome (PCOS) is a prevalent endocrine and metabolic disorder in women of childbearing age. Recent studies suggest important roles for lncRNAs in PCOS development. Based on the hypothesis that lncRNAs are able to regulate mRNA functions by competitive binding to shared miRNAs, the present work sought to construct a PCOS-related lncRNA-mRNA network (PCLMN) to identify key lncRNAs with dysregulated expression and potential prognostic and therapeutic relevance. A global background network was constructed after retrieving lncRNA-miRNA and miRNA-mRNA pairs from the lncRNASNP2, miRTarBase and StarBase databases. Based on gene expression profiles from ovarian granulosa cells from PCOS patients and controls in the GEO's GSE95728 dataset, the PCLMN was then constructed by applying hypergeometric testing. Using topological analysis, we identified 3 lncRNAs (LINC00667, AC073172.1 and H19) ranking within the top-ten gene lists for all three centrality measures. We then explored their subcellular localization, performed functional module analyses, and identified 4 sex hormone-related transcription factors as potential regulators of their expression. Significant associations with inflammation, oxidative stress, and apoptosis-related processes and pathways were revealed for the key lncRNAs in our PCMLN. Further studies verifying the mRNA/lncRNA relationships identified herein are needed to clarify their clinical significance.", "claims": [{"id": "claim-method", "statement": "Then, lncRNA-miRNA-mRNA interactions were extracted by hypergeometric test with P < 0.01.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33714202", "locator": "sections[15] \"Construction of the PCOS-related lncRNA-mRNA network\" paragraph 2", "quote": "Then, lncRNA-miRNA-mRNA interactions were extracted by hypergeometric test with P < 0.01."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Gene expression data from the GSE95728 dataset, based on the GPL16956 platform (Agilent-045997 Arraystar human lncRNA microarray V3), was downloaded from the Gene Expression Omnibus (GEO) database. GSE95728 included lncRNA and mRNA expression profiles from granulosa cells from seven PCOS patients and seven controls (women with normal ovarian reserve).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33714202", "locator": "sections[13] \"Gene expression profile\" paragraph 2", "quote": "Gene expression data from the GSE95728 dataset, based on the GPL16956 platform (Agilent-045997 Arraystar human lncRNA microarray V3), was downloaded from the Gene Expression Omnibus (GEO) database. GSE95728 included lncRNA and mRNA expression profiles from granulosa cells from seven PCOS patients and seven controls (women with normal ovarian reserve)."}], "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:33714202"], "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:GSE95728"], "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:GSE95728"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33714202", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/aging.202659", "sha256": "sha256:967b38baeca94d22877718ab2d4dc3fc2512f9e5a1de469e974a701984229589", "bytes": 28268, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/aging.202659", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8034915", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE95728", "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=GSE95728", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE95728", "version": null, "note": "Gene expression data from the GSE95728 dataset, based on the GPL16956 platform (Agilent-045997 Arraystar human lncRNA microarray V3), was downloaded from the Gene Expression Omnibus (GEO) database. GSE95728 included lncRNA and mRNA expression profiles from granulosa cells from seven PCOS patients and seven controls (women with normal ovarian reserve).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression data from the GSE95728 dataset, based on the GPL16956 platform (Agilent-045997 Arraystar human lncRNA microarray V3), was downloaded from the Gene Expression Omnibus (GEO) database. GSE95728 included lncRNA and mRNA expression profiles from granulosa cells from seven PCOS patients and seven controls (women with normal ovarian reserve).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2522774", "GSM2522775", "GSM2522776", "GSM2522777", "GSM2522778", "GSM2522779", "GSM2522780", "GSM2522781", "GSM2522782", "GSM2522783", "GSM2522784", "GSM2522785", "GSM2522786", "GSM2522787"], "sample_count": 14, "group_sizes": null, "group_sizes_basis": null, "platform": "16956", "taxon": "Homo sapiens", "title": "Long noncoding RNA expression profiles in granulosa cells from PCOS patients and women with normal ovarian reserve", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33714202:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c72362e74731fcc20159a31380ec9a95f9c9affc4be883a5a03a8ece948871e3", "bytes": 2129, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#t1", "version": null, "note": "Enriched GO terms in the PCLMN.", "structure": {"pmcid": "PMC8034915", "section_index": 6, "section_title": "Hierarchical clustering and functional characteristics of the PCLMN", "row_count": 32, "column_count": 3}, "table": {"label": "Table 1", "caption": "Enriched GO terms in the PCLMN.", "rows": [["GO term", "P-value", "Associated genes (%)"], ["regulation of receptor binding", "2.67E-05", "10.71"], ["T cell selection", "1.64E-04", "5.88"], ["positive T cell selection", "6.78E-05", "7.89"], ["T cell differentiation in thymus", "2.20E-05", "5.06"], ["granulocyte chemotaxis", "4.15E-07", "4.32"], ["neutrophil migration", "2.80E-07", "4.62"], ["neutrophil chemotaxis", "1.09E-07", "5.41"], ["interleukin-12 production", "3.23E-04", "4.69"], ["regulation of interleukin-12 production", "2.94E-04", "4.84"], ["somatic diversification of immune receptors", "4.75E-04", "4.11"], ["somatic cell DNA recombination", "4.75E-04", "4.11"], ["chemokine production", "4.93E-05", "4.12"], ["regulation of cytokine production involved in immune response", "5.56E-05", "4.00"], ["regulation of chemokine production", "4.01E-05", "4.35"], ["regulation of leukocyte apoptotic process", "4.01E-05", "4.35"], ["regulation of lymphocyte apoptotic process", "2.67E-04", "5.00"], ["heterotypic cell-cell adhesion", "3.38E-04", "4.62"], ["chemokine production", "4.93E-05", "4.12"], ["regulation of lipid catabolic process", "3.38E-04", "4.62"], ["leukocyte aggregation", "3.03E-06", "21.43"], ["regulation of reactive oxygen species biosynthetic process", "5.56E-05", "4.00"], ["negative regulation of reactive oxygen species metabolic process", "3.53E-04", "4.55"], ["regulation of cytokine production involved in immune response", "5.56E-05", "4.00"], ["regulation of chemokine production", "4.01E-05", "4.35"], ["regulation of heterotypic cell-cell adhesion", "2.39E-05", "11.11"], ["negative regulation of reactive oxygen species biosynthetic process", "4.42E-05", "9.09"], ["positive regulation of cytokine production involved in immune response", "3.69E-04", "4.48"], ["positive regulation of chemokine production", "4.03E-04", "4.35"], ["positive regulation of heterotypic cell-cell adhesion", "4.65E-06", "18.75"], ["unsaturated fatty acid biosynthetic process", "3.38E-04", "4.62"], ["regulation of lymphocyte apoptotic process", "2.67E-04", "5.00"]], "row_count": 32, "column_count": 3, "numeric_cells": 64, "header_rows": 0, "locator": "section[6]/table-wrap[1]#t1"}}, {"id": "asset:table:pmid:33714202:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6937ee70795e0f619e2eff6e34b5473dca7813d272fc4f41c2349c96423eb6a2", "bytes": 2057, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[2]#t2", "version": null, "note": "Enriched KEGG pathways in the PCLMN.", "structure": {"pmcid": "PMC8034915", "section_index": 6, "section_title": "Hierarchical clustering and functional characteristics of the PCLMN", "row_count": 34, "column_count": 3}, "table": {"label": "Table 2", "caption": "Enriched KEGG pathways in the PCLMN.", "rows": [["GO term", "P-value", "Associated genes%"], ["Hematopoietic cell lineage", "2.09E-04", "4.04"], ["IL-17 signaling pathway", "8.26E-06", "5.32"], ["Intestinal immune network for IgA production", "9.35E-03", "4.08"], ["Chagas disease (American trypanosomiasis)", "5.22E-07", "5.88"], ["African trypanosomiasis", "5.42E-03", "5.41"], ["Malaria", "1.42E-05", "8.00"], ["Bladder cancer", "2.43E-04", "7.32"], ["Asthma", "3.82E-03", "6.45"], ["Allograft rejection", "5.71E-03", "5.26"], ["Primary immunodeficiency", "5.71E-03", "5.26"], ["Phosphorylation of CD3 and TCR zeta chains", "1.93E-03", "9.09"], ["Translocation of ZAP-70 to Immunological synapse", "1.44E-03", "10.53"], ["Generation of second messenger molecules", "4.59E-03", "5.88"], ["PD-1 signaling", "2.11E-03", "8.70"], ["Interleukin-10 signaling", "1.11E-05", "8.51"], ["FCGR3A-mediated IL10 synthesis", "7.26E-03", "4.65"], ["Nucleotide-binding Oligomerization Domain (NOD) pathway", "6.62E-03", "4.88"], ["Allograft Rejection", "1.44E-04", "4.44"], ["Bladder Cancer", "2.43E-04", "7.32"], ["IL-3 Signaling Pathway", "9.35E-03", "4.08"], ["IL1 and megakaryocytes in obesity", "2.50E-03", "8.00"], ["Photodynamic therapy-induced NF-kB survival signaling", "5.56E-08", "14.29"], ["Lung fibrosis", "8.64E-04", "4.76"], ["Hepatitis C and Hepatocellular Carcinoma", "9.72E-03", "4.00"], ["T-Cell antigen Receptor pathway during Staphylococcus aureus infection", "8.25E-04", "4.84"], ["Development and heterogeneity of the ILC family", "4.07E-03", "6.25"], ["Platelet-mediated interactions with vascular and circulating cells", "1.15E-03", "11.76"], ["LTF danger signal response pathway", "2.71E-05", "15.00"], ["Cancer immunotherapy by PD-1 blockade", "2.30E-03", "8.33"], ["Pathogenesis of SARS-CoV-2 Mediated by nsp9/nsp10 Complex", "1.93E-03", "9.09"], ["COVID-19 AOP", "9.07E-08", "26.67"], ["Cytokines and Inflammatory Response", "2.91E-03", "7.41"], ["Type II interferon signaling (IFNG)", "5.42E-03", "5.41"]], "row_count": 34, "column_count": 3, "numeric_cells": 75, "header_rows": 0, "locator": "section[6]/table-wrap[2]#t2"}}], "gaps": ["asset:data:geo:GSE95728 not downloaded", "asset:data:geo:GSE95728 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "centrality", "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": "centrality"}}, {"id": "method-2", "family": null, "specific": null, "label": "Hypergeometric test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Then, lncRNA-miRNA-mRNA interactions were extracted by hypergeometric test with P < 0.01."}}], "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: centrality."}, "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": ["GSE95728"], "resolved_accessions": ["GSE95728"], "statements": ["Gene expression data from the GSE95728 dataset, based on the GPL16956 platform (Agilent-045997 Arraystar human lncRNA microarray V3), was downloaded from the Gene Expression Omnibus (GEO) database. GSE95728 included lncRNA and mRNA expression profiles from granulosa cells from seven PCOS patients and seven controls (women with normal ovarian reserve)."], "basis": "The paper names GSE95728 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": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:33714202", "data:geo:GSE95728", "asset:table:pmid:33714202:1", "asset:table:pmid:33714202:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE95728"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:27:55Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 21269, "completion_tokens": 1241, "cached_tokens": 520}}, "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:33714202", "type": "paper", "label": "pmid:33714202"}, {"id": "source:pmid:33714202", "type": "manuscript", "label": "PMID 33714202 full text"}, {"id": "data:geo:GSE95728", "type": "dataset", "label": "GEO GSE95728"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33714202", "type": "paper", "label": "pmid:33714202"}, {"id": "source:pmid:33714202", "type": "manuscript", "label": "PMID 33714202 full text"}, {"id": "data:geo:GSE95728", "type": "dataset", "label": "GEO GSE95728"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33714202", "type": "extraction", "used": ["source:pmid:33714202"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE95728", "type": "accession_resolution", "used": ["data:geo:GSE95728"], "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:33714202", "parent_hash": "sha256:3b574eb3800966ecf9b9d4d41092e01b8a4694ff3e860dd2890c651809736fd5", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE95728 licence not read", "asset:data:geo:GSE95728 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["ons with inflammation, oxidative stress, and apoptosis-related processes and pathways were revealed"], "order_basis": "paper_text_order:1308", "id": "assay:1"}, {"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": ["centrality"], "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":"2026-11-04T03:13:25+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}}}