{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32391563", "kind": "science-record", "revision": 8, "content_hash": "sha256:3ebb923eff0187fb10ac9c0705ad817aaae9d7dfe7e70bb1139ea31193d0b934", "created_at": "2026-11-01T15:41:01Z", "updated_at": "2026-11-01T22:44:50Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Extracellular matrix-related genes play an important role in the progression of NMIBC to MIBC: a bioinformatics analysis study.", "doi": "10.1042/BSR20194192", "pmid": "32391563", "authors": ["Heng Zhang", "Gang Shan", "Jukun Song", "Ye Tian", "Ling-Yue An", "Yong Ban", "Guang-Heng Luo"], "journal": "Bioscience reports", "year": 2020, "abstract": "Bladder cancer is the 11th most common cancer in the world. Bladder cancer can be roughly divided into muscle invasive bladder cancer (MIBC) and non-muscle invasive bladder cancer (NMIBC). The aim of the present study was to identify the key genes and pathways associated with the progression of NMIBC to MIBC and to further analyze its molecular mechanism and prognostic significance. We analyzed microarray data of NMIBC and MIBC gene expression datasets (GSE31684) listed in the Gene Expression Omnibus (GEO) database. After the dataset was analyzed using R software, differentially expressed genes (DEGs) of NMIBC and MIBC were identified. These DEGs were analyzed using Gene Ontology (GO) enrichment, KOBAS-Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis, and protein-protein interaction (PPI) analysis. The effect of these hub genes on the survival of bladder cancer patients was analyzed in The Cancer Genome Atlas (TCGA) database. A total of 389 DEGs were obtained, of which 270 were up-regulated and 119 down-regulated. GO and KEGG pathway enrichment analysis revealed that DEGs were mainly involved in the pathway of protein digestion and absorption, extracellular matrix (ECM) receiver interaction, phantom, toll-like receptor (TLR) signaling pathway, focal adhesion, NF-κB signaling pathway, PI3K/Akt signaling pathway, and other signaling pathways. Top five hub genes COL1A2, COL3A1, COL5A1, POSTN, and COL12A1 may be involved in the development of MIBC. These results may provide us with a further understanding of the occurrence and development of MIBC, as well as new targets for the diagnosis and treatment of MIBC in the future.", "claims": [{"id": "claim-method", "statement": "The limma package for bioconductor (http://www.bioconductor.org/) was used to analyze the progressive gene differential expression between NMIBC and MIBC.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32391563", "locator": "sections[4] \"Data processing\" paragraph 2", "quote": "The limma package for bioconductor (http://www.bioconductor.org/) was used to analyze the progressive gene differential expression between NMIBC and MIBC."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data can be obtained from GEO website.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32391563", "locator": "sections[18] \"Data Availability\" paragraph 2", "quote": "Data can be obtained from GEO website."}], "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:32391563"], "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:GSE31684"], "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:GSE31684"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32391563", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1042/BSR20194192", "sha256": "sha256:85ad59459505a99487a427c9c063602e91b28145437eb114cbb962a5e282e878", "bytes": 29162, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1042/BSR20194192", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7251326", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE31684", "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=GSE31684", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31684", "version": null, "note": "Data can be obtained from GEO website.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data can be obtained from GEO website.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM786491", "GSM786492", "GSM786493", "GSM786494", "GSM786495", "GSM786496", "GSM786497", "GSM786498", "GSM786499", "GSM786500", "GSM786501", "GSM786502", "GSM786503", "GSM786504", "GSM786505", "GSM786506", "GSM786507", "GSM786508", "GSM786509", "GSM786510", "GSM786511", "GSM786512", "GSM786513", "GSM786514", "GSM786515", "GSM786516", "GSM786517", "GSM786518", "GSM786519", "GSM786520", "GSM786521", "GSM786522", "GSM786523", "GSM786524", "GSM786525", "GSM786526", "GSM786527", "GSM786528", "GSM786529", "GSM786530", "GSM786531", "GSM786532", "GSM786533", "GSM786534", "GSM786535", "GSM786536", "GSM786537", "GSM786538", "GSM786539", "GSM786540", "GSM786541", "GSM786542", "GSM786543", "GSM786544", "GSM786545", "GSM786546", "GSM786547", "GSM786548", "GSM786549", "GSM786550", "GSM786551", "GSM786552", "GSM786553", "GSM786554", "GSM786555", "GSM786556", "GSM786557", "GSM786558", "GSM786559", "GSM786560", "GSM786561", "GSM786562", "GSM786563", "GSM786564", "GSM786565", "GSM786566", "GSM786567", "GSM786568", "GSM786569", "GSM786570", "GSM786571", "GSM786572", "GSM786573", "GSM786574", "GSM786575", "GSM786576", "GSM786577", "GSM786578", "GSM786579", "GSM786580", "GSM786581", "GSM786582", "GSM786583"], "sample_count": 93, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Combination of a novel gene expression signature with a clinical nomogram improves the prediction of survival in high-risk bladder cancer  ", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32391563:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:aeaf9e0aba1bd924f08167073d9e9945c1fef45a715ab1ef661d470a96aebce1", "bytes": 2765, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T1", "version": null, "note": "Screening DEGs by integrated microarray", "structure": {"pmcid": "PMC7251326", "section_index": 9, "section_title": "Microarray data information and identification of DEGs in MIBC", "row_count": 3, "column_count": 2}, "table": {"label": "Table 1", "caption": "Screening DEGs by integrated microarray", "rows": [["DEGs", "Gene names"], ["Up-regulated", "FHL1 LIPG LOC100128239 IL6 GEM FAM129A MILR1 KDELC1 NID2 ARSJ PLAU TRIM59 ANP32E CCDC109B TNFSF13B OAT TSPAN4 PSPH H2BFS TMEM158 CXorf21 FBXO17 DUSP14 COX7B2 GPR65 MT1H CD14 HLA-DMB GLIPR1 EMILIN1 TAGLN SLIT2 SYNM KIAA0922 SHOX2 CDKN3 SLFN11 TRIP13 KLHL13 COL12A1 MFAP4 SCG5 EVI2A COL6A2 KCND2 RACGAP1 CDC25B ISLR DACT1 C1QC CAP2 MUM1L1 C1R UBE2E2 PRKCDBP LAP3 MMP11 CDH11 C8orf88 FERMT2 EMP3 SERPING1 FXYD6 CHST11 TIMP1 MAMDC2 PDGFC CTSK CYBRD1 CTSV TUBB6 SULF2 NEXN C5orf34 DCLK1 PRTFDC1 PCOLCE PNMA1 SLC7A7 CKS2 BCAT1 COL15A1 OGN KIAA0895 EPB41L3 PTRF CDC20 PBK SHCBP1 CLIC4 PDGFRL LINC01279 SERPINA3 CNN1 JAZF1 SUGCT MRGPRF DPYSL3 HMCN1 FIBIN CEP55 COL8A2 CAV1 PALLD CYP1B1 KIAA1598 TPST1 AHNAK2 CLEC2B MS4A4A OGFRL1 MN1 CNN3 NXN EVI2B ASB5 MT2A ACTG2 TRPS1 GBP5 GPC6 TREM1 FBN1 OSR2 SYNC CD163 IFIT1 SECTM1 PLAGL1 FBLN2 PCDHB5 NR3C1 MT1HL1 CACNA2D1 PLA2G7 SOSTDC1 STEAP1 PCOLCE2 MGC24103 PLSCR4 CXCL12 SGPP1 TMEM200A MT1E C5AR1 ASPN RNASE6 KATNAL1 AAED1 ALDH2 BCL2A1 OLFML3 TNFAIP6 DEPDC7 DSCR8 CRISPLD1 PEG10 ARSI IGF2BP3 CCL4 MT1X NAP1L3 PI3 TIMP2 DEPDC1B GLT8D2 ZNF521 C3orf80 CXCL10 EPYC ANLN KIAA1524 MGP CXCL9 CCL8 MLLT11 CFL2 TUBA1A RAB23 CD109 CHI3L1 FKBP10 FN1 C1QB FCER1G HIST1H3G ITGAM NUF2 CHRDL2 LOC100132891 CENPW LINC01094 PPAPDC1A CCL19 GXYLT2 KIF18A INHBA ADAMDEC1 IFI6 TGFBI HSD17B6 ANXA5 FLNA COL16A1 COLEC12 COL5A1 RARRES2 OLR1 OXCT1 THBS2 SERPINF1 DSC2 IL18 COL6A3 GPR1 SRPX GAS1 LY96 ROR2 DEGS1 COL1A2 S100A8 FNDC1 COL5A2 C1S VCAN LGALS1 LOX CLMP TUBB2A CPVL COL3A1 TMEM45A PRRX1 CXCL11 HS3ST3A1 MMP9 FCGR3B MMP3 EFEMP1 KRT6B AEBP1 SLC16A1 SULF1 SACS MFAP5 SFRP4 PLN ANXA3 GPX8 FAP ZFPM2 PCP4 MIR100HG SGCE SELM EGR2 POSTN COMP GPNMB KRT6A COL10A1 CTHRC1 PCDHB2 COL11A1 SFRP2 CCL18 GREM1"], ["Down-regulated", "SLC14A1 BTBD16 SNX31 CYP4B1 HSD17B2 ANXA10 CLCA4 SPINK1 DHRS2 TOX3 PSCA CYP3A7-CYP3AP1 RNF128 MAL TRIM31 LOC102659288 S100P ADIRF ARL14 HPGD CYP4F8 GPX2 UPK1A FMO9P UCA1 UPK2 DUOX2 VSIG2 SIDT1 CYP3A5 ID1 TFF2 CYP4F3 AGAP11 FAM174B FER1L4 CYP4X1 FAM110C ZNF486 C10orf99 CEL ELF3 TFF1 PPARG C8orf4 LCN2 TMEM45B CRH PTPRR LINC00967 ENTPD3 ZNF432 BCAS1 GGT6 GATA3 FOXA1 CDC42EP5 GSTA1 TMPRSS4 FOXQ1 CYP3A43 AGR2 TMEM139 LRP5L ST3GAL5 BMP5 SLC20A1 GPR110 CAPN5 FBP1 CACNA1D CAPNS2 EPS8L3 TMPRSS2 MYCL GRHL3 SEMA6A SYT8 FOSB HMGCS2 DENND2D MAOA RAPGEFL1 MPPED2 AZGP1 GAREM LGALS4 FOS ZSCAN4 PP14571 PPFIBP2 SLC44A3 EMX2 PADI3 FAM162B KLF5 SLC38A11 BHMT BPIFB1 CYP2J2 PLAT EPHB6 TMEM178A SCIN LOC100287525 AQP3 TNFRSF21 CYP4F11 EIF3C SIGLEC15 SORL1 LOC286272 CAMK2N1 TRAK1 GRAMD1C RASSF6 CYP4F12 CXCL17 ZNF440"]], "row_count": 3, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[9]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:32391563:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1dad9d42c3db0833c26118cff4f413834aa34abf3048cb8b757f7aa5a37aad8e", "bytes": 472, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T2", "version": null, "note": "Top ten in PPI network ranked by MCC method", "structure": {"pmcid": "PMC7251326", "section_index": 12, "section_title": "PPI network construction and cytoHubba analysis", "row_count": 11, "column_count": 3}, "table": {"label": "Table 2", "caption": "Top ten in PPI network ranked by MCC method", "rows": [["Rank", "Name", "Score"], ["1", "COL1A2", "3.08E+08"], ["2", "COL3A1", "3.08E+08"], ["3", "COL5A1", "2.96E+08"], ["4", "POSTN", "2.68E+08"], ["5", "COL12A1", "2.55E+08"], ["6", "FBN1", "2.53E+08"], ["7", "COL5A2", "2.52E+08"], ["8", "COL6A3", "2.51E+08"], ["9", "COL6A2", "2.51E+08"], ["10", "FN1", "2.21E+08"]], "row_count": 11, "column_count": 3, "numeric_cells": 21, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T2"}}], "gaps": ["asset:data:geo:GSE31684 not downloaded", "asset:data:geo:GSE31684 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The limma package for bioconductor (http://www.bioconductor.org/) was used to analyze the progressive gene differential expression between NMIBC and MIBC."}}, {"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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE31684"], "resolved_accessions": ["GSE31684"], "statements": ["Data can be obtained from GEO website."], "basis": "The paper names GSE31684 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:32391563", "data:geo:GSE31684", "asset:table:pmid:32391563:1", "asset:table:pmid:32391563:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE31684"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:19:42Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 23817, "completion_tokens": 1373, "cached_tokens": 784}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:32391563", "type": "paper", "label": "pmid:32391563"}, {"id": "source:pmid:32391563", "type": "manuscript", "label": "PMID 32391563 full text"}, {"id": "data:geo:GSE31684", "type": "dataset", "label": "GEO GSE31684"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32391563", "type": "paper", "label": "pmid:32391563"}, {"id": "source:pmid:32391563", "type": "manuscript", "label": "PMID 32391563 full text"}, {"id": "data:geo:GSE31684", "type": "dataset", "label": "GEO GSE31684"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32391563", "type": "extraction", "used": ["source:pmid:32391563"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE31684", "type": "accession_resolution", "used": ["data:geo:GSE31684"], "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:32391563", "parent_hash": "sha256:aff223f9f08040fcc2220b5be85f1b36d236e7e1f1da1c9bbf44229e4339c7e2", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE31684 licence not read", "asset:data:geo:GSE31684 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The limma package for bioconductor (http://www.bioconductor.org/) was used to analyze the progressive gene differential expression between NMIBC and MIBC."], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T04:01:23+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}}}