{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31533842", "kind": "science-record", "revision": 8, "content_hash": "sha256:ebdb40b431903c5096aa491f9d48b47cc2e280a970c341b112e2c35c81068514", "created_at": "2026-11-01T15:40:49Z", "updated_at": "2026-11-01T22:44:12Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of key DNA methylation-driven genes in prostate adenocarcinoma: an integrative analysis of TCGA methylation data.", "doi": "10.1186/s12967-019-2065-2", "pmid": "31533842", "authors": ["Ning Xu", "Yu-Peng Wu", "Zhi-Bin Ke", "Ying-Chun Liang", "Hai Cai", "Wen-Ting Su", "Xuan Tao", "Shao-Hao Chen", "Qing-Shui Zheng", "Yong Wei", "Xue-Yi Xue"], "journal": "Journal of translational medicine", "year": 2019, "abstract": "BACKGROUND: Prostate cancer (PCa) remains the second leading cause of deaths due to cancer in the United States in men. The aim of this study was to perform an integrative epigenetic analysis of prostate adenocarcinoma to explore the epigenetic abnormalities involved in the development and progression of prostate adenocarcinoma. The key DNA methylation-driven genes were also identified.\nMETHODS: Methylation and RNA-seq data were downloaded for The Cancer Genome Atlas (TCGA). Methylation and gene expression data from TCGA were incorporated and analyzed using MethylMix package. Methylation data from the Gene Expression Omnibus (GEO) were assessed by R package limma to obtain differentially methylated genes. Pathway analysis was performed on genes identified by MethylMix criteria using ConsensusPathDB. Gene Ontology (GO) term enrichment analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis were also applied for the identification of pathways in which DNA methylation-driven genes significantly enriched. The protein-protein interaction (PPI) network and module analysis in Cytoscape software were used to find the hub genes. Two methylation profile (GSE112047 and GSE76938) datasets were utilized to validate screened hub genes. Immunohistochemistry of these hub genes were evaluated by the Human Protein Atlas.\nRESULTS: A total of 553 samples in TCGA database, 32 samples in GSE112047 and 136 samples in GSE76938 were included in this study. There were a total of 266 differentially methylated genes were identified by MethylMix. Plus, a total of 369 differentially methylated genes and 594 differentially methylated genes were identified by the R package limma in GSE112047 and GSE76938, respectively. GO term enrichment analysis suggested that DNA methylation-driven genes significantly enriched in oxidation-reduction process, extracellular exosome, electron carrier activity, response to reactive oxygen species, and aldehyde dehydrogenase [NAD(P)+] activity. KEGG pathway analysis found DNA methylation-driven genes significantly enriched in five pathways including drug metabolism-cytochrome P450, phenylalanine metabolism, histidine metabolism, glutathione metabolism, and tyrosine metabolism. The validated hub genes were MAOB and RTP4.\nCONCLUSIONS: Methylated hub genes, including MAOB and RTP4, can be regarded as novel biomarkers for accurate PCa diagnosis and treatment. Further studies are needed to draw more attention to the roles of these hub genes in the occurrence and development of PCa.", "claims": [{"id": "claim-data-access", "statement": "All data was obtained from The Cancer Genome Atlas (TCGA, https://tcga-data.nci.nih.gov/tcga/) and Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31533842", "locator": "sections[28] \"notes\" paragraph 1", "quote": "All data was obtained from The Cancer Genome Atlas (TCGA, https://tcga-data.nci.nih.gov/tcga/) and Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/)."}], "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:31533842"], "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:GSE112047"], "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:GSE112047"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31533842", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12967-019-2065-2", "sha256": "sha256:3b7a2e077e4a1421fbc11f0e304d7ae8c22939048006a114333f67d24bed3fb6", "bytes": 33636, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12967-019-2065-2", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6751626", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE112047", "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=GSE112047", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE112047", "version": null, "note": "All data was obtained from The Cancer Genome Atlas (TCGA, https://tcga-data.nci.nih.gov/tcga/) and Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data was obtained from The Cancer Genome Atlas (TCGA, https://tcga-data.nci.nih.gov/tcga/) and Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3053769", "GSM3053770", "GSM3053771", "GSM3053772", "GSM3053773", "GSM3053774", "GSM3053775", "GSM3053776", "GSM3053777", "GSM3053778", "GSM3053779", "GSM3053780", "GSM3053781", "GSM3053782", "GSM3053783", "GSM3053784", "GSM3053785", "GSM3053786", "GSM3053787", "GSM3053788", "GSM3053789", "GSM3053790", "GSM3053791", "GSM3053792", "GSM3053793", "GSM3053794", "GSM3053795", "GSM3053796", "GSM3053797", "GSM3053798", "GSM3053799", "GSM3053800", "GSM3053801", "GSM3053802", "GSM3053803", "GSM3053804", "GSM3053805", "GSM3053806", "GSM3053807", "GSM3053808", "GSM3053809", "GSM3053810", "GSM3053811", "GSM3053812", "GSM3053813", "GSM3053814", "GSM3053815"], "sample_count": 47, "group_sizes": null, "group_sizes_basis": null, "platform": "13534", "taxon": "Homo sapiens", "title": "Genome-Wide DNA methylation analysis of tumor and adjacent normal prostate tissues", "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:GSE76938", "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=GSE76938", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE76938", "version": null, "note": "All data was obtained from The Cancer Genome Atlas (TCGA, https://tcga-data.nci.nih.gov/tcga/) and Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data was obtained from The Cancer Genome Atlas (TCGA, https://tcga-data.nci.nih.gov/tcga/) and Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2041110", "GSM2041111", "GSM2041112", "GSM2041113", "GSM2041114", "GSM2041115", "GSM2041116", "GSM2041117", "GSM2041118", "GSM2041119", "GSM2041120", "GSM2041121", "GSM2041122", "GSM2041123", "GSM2041124", "GSM2041125", "GSM2041126", "GSM2041127", "GSM2041128", "GSM2041129", "GSM2041130", "GSM2041131", "GSM2041132", "GSM2041133", "GSM2041134", "GSM2041135", "GSM2041136", "GSM2041137", "GSM2041138", "GSM2041139", "GSM2041140", "GSM2041141", "GSM2041142", "GSM2041143", "GSM2041144", "GSM2041145", "GSM2041146", "GSM2041147", "GSM2041148", "GSM2041149", "GSM2041150", "GSM2041151", "GSM2041152", "GSM2041153", "GSM2041154", "GSM2041155", "GSM2041156", "GSM2041157", "GSM2041158", "GSM2041159", "GSM2041160", "GSM2041161", "GSM2041162", "GSM2041163", "GSM2041164", "GSM2041165", "GSM2041166", "GSM2041167", "GSM2041168", "GSM2041169", "GSM2041170", "GSM2041171", "GSM2041172", "GSM2041173", "GSM2041174", "GSM2041175", "GSM2041176", "GSM2041177", "GSM2041178", "GSM2041179", "GSM2041180", "GSM2041181", "GSM2041182", "GSM2041183", "GSM2041184", "GSM2041185", "GSM2041186", "GSM2041187", "GSM2041188", "GSM2041189", "GSM2041190", "GSM2041191", "GSM2041192", "GSM2041193", "GSM2041194", "GSM2041195", "GSM2041196", "GSM2041197", "GSM2041198", "GSM2041199", "GSM2041200", "GSM2041201", "GSM2041202", "GSM2041203", "GSM2041204", "GSM2041205", "GSM2041206", "GSM2041207", "GSM2041208", "GSM2041209", "GSM2041210", "GSM2041211", "GSM2041212", "GSM2041213", "GSM2041214", "GSM2041215", "GSM2041216", "GSM2041217", "GSM2041218", "GSM2041219", "GSM2041220", "GSM2041221", "GSM2041222", "GSM2041223", "GSM2041224", "GSM2041225", "GSM2041226", "GSM2041227", "GSM2041228", "GSM2041229", "GSM2041230", "GSM2041231", "GSM2041232", "GSM2041233", "GSM2041234", "GSM2041235", "GSM2041236", "GSM2041237", "GSM2041238", "GSM2041239", "GSM2041240", "GSM2041241", "GSM2041242", "GSM2041243", "GSM2041244", "GSM2041245"], "sample_count": 136, "group_sizes": null, "group_sizes_basis": null, "platform": "13534", "taxon": "Homo sapiens", "title": "Illumina M450 profiling of human prostate cancer tissue and benign prostate tissue", "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:31533842:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2dbe3c51f56448581f0f08bd69acc6208cbe1499e7336694efe6bca871d2c3c5", "bytes": 526, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "Clinical dada of prostate cancer patients from TCGA", "structure": {"pmcid": "PMC6751626", "section_index": 3, "section_title": "Identification of DNA methylation-driven genes", "row_count": 15, "column_count": 2}, "table": {"label": "Table 1", "caption": "Clinical dada of prostate cancer patients from TCGA", "rows": [["Characteristic", "Total"], ["Cohort sizea", "500"], ["Mean age, years", "61.01 ± 6.823"], ["T stage"], ["pT2a", "13 (2.6%)"], ["pT2b", "10 (2%)"], ["pT2c", "165 (33%)"], ["pT3a", "159 (31.8%)"], ["pT3b", "136 (27.2%)"], ["pT4", "10 (2%)"], ["Unknown", "7 (1.4%)"], ["N stage"], ["N0", "348 (69.6%)"], ["N1", "79 (15.8%)"], ["Unknown", "73 (14.6%)"]], "row_count": 15, "column_count": 2, "numeric_cells": 12, "header_rows": 1, "locator": "section[3]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:31533842:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:08c7727aa2306ea4ff63707933ff230eff0d2703a6ceddc00743aa89f76143b3", "bytes": 2481, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#Tab2", "version": null, "note": "Top 10 hypomethylated genes and hypermethylated genes in patients with prostate cancer", "structure": {"pmcid": "PMC6751626", "section_index": 3, "section_title": "Identification of DNA methylation-driven genes", "row_count": 23, "column_count": 8}, "table": {"label": "Table 2", "caption": "Top 10 hypomethylated genes and hypermethylated genes in patients with prostate cancer", "rows": [["Gene", "Normal mean", "Tumor mean", "Log FC", "p value", "Adjust p", "Cor", "Cor p value"], ["Top 10 hypomethylated genes"], ["TAF1D", "0.298851771", "0.17046481", "− 0.809956148", "5.12E−22", "1.61E−19", "− 0.515133904", "3.62E−35"], ["TMEM87A", "0.36898334", "0.219989007", "− 0.746124244", "2.40E−22", "7.57E−20", "− 0.415783216", "2.80E−22"], ["KLK2", "0.42230197", "0.252663444", "− 0.741058027", "2.34E−25", "7.36E−23", "− 0.424469057", "3.03E−23"], ["MARS", "0.661117252", "0.407190703", "− 0.69920154", "2.88E−18", "9.08E−16", "− 0.402813221", "6.87E−21"], ["SLC10A5", "0.682378547", "0.421046571", "-0.696592477", "1.19E−16", "3.76E−14", "− 0.320114016", "2.36E−13"], ["KLK3", "0.528659515", "0.348234132", "− 0.602281232", "2.38E−22", "7.50E−20", "− 0.352378214", "4.92E−16"], ["MPC2", "0.847716806", "0.573604393", "− 0.563526315", "3.24E−22", "1.02E−19", "− 0.509873152", "2.25E−34"], ["ALDH1A3", "0.390659331", "0.266302408", "− 0.552845598", "6.96E−20", "2.19E−17", "− 0.500862763", "4.78E−33"], ["CLDN8", "0.556942422", "0.387056997", "− 0.524982157", "1.24E−14", "3.91E−12", "− 0.339347771", "6.50E−15"], ["PMEPA1", "0.427234317", "0.301507194", "− 0.50283511", "1.93E−21", "6.07E−19", "− 0.559861766", "1.65E−42"], ["Top 10 hypermethylated genes"], ["HIST1H2BH", "0.073047", "0.264894", "1.858512", "1.40E−15", "4.41E−13", "− 0.37138", "9.15E−18"], ["FAM200A", "0.052277", "0.163374", "1.643934", "1.78E−18", "5.60E−16", "− 0.32491", "9.86E−14"], ["ZFP36L2", "0.101664", "0.293078", "1.527482", "1.59E−13", "5.02E−11", "− 0.47382", "2.72E−29"], ["WFDC2", "0.125846", "0.347072", "1.463575", "2.89E−24", "9.09E−22", "− 0.46874", "1.27E−28"], ["SMIM10", "0.169555", "0.460955", "1.44287", "1.29E−18", "4.06E−16", "− 0.52098", "4.58E−36"], ["RIPPLY2", "0.06161", "0.166659", "1.435669", "4.35E−23", "1.37E−20", "− 0.33215", "2.57E−14"], ["RTP4", "0.102519", "0.273692", "1.416666", "4.91E−19", "1.55E−16", "− 0.51074", "1.67E−34"], ["FBXO27", "0.048294", "0.126663", "1.391093", "3.13E−12", "9.85E−10", "− 0.64419", "7.67E−60"], ["ZNF492", "0.057359", "0.147069", "1.358401", "3.63E−20", "1.14E−17", "− 0.33472", "1.58E−14"], ["HPDL", "0.14249", "0.356177", "1.321732", "5.48E−20", "1.73E−17", "− 0.54417", "8.31E−40"]], "row_count": 23, "column_count": 8, "numeric_cells": 149, "header_rows": 1, "locator": "section[3]/table-wrap[2]#Tab2"}}, {"id": "asset:table:pmid:31533842:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3df6af4ea6ff618a0418ebb6e6e4cdfbf90e8d91680705a305bd2caba5ae3a88", "bytes": 1644, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#Tab3", "version": null, "note": "The top 8 GO terms enriched by the 266 DNA methylation driven genes in prostate cancer", "structure": {"pmcid": "PMC6751626", "section_index": 4, "section_title": "Gene ontology terms analysis of DNA methylation-driven genes obtained from TCGA database", "row_count": 9, "column_count": 5}, "table": {"label": "Table 3", "caption": "The top 8 GO terms enriched by the 266 DNA methylation driven genes in prostate cancer", "rows": [["Category", "Term", "Count", "p value", "Genes"], ["BP", "GO:0055114 ~ oxidation–reduction process", "25", "2.13E−06", "STEAP4, ME3, OXA1L, GLUD1, DUOX1, PAH, HPDL, ALDH3A1, ALDH1A3, GPX3, HAAO, FASN, GPX7, DHCR24, FAXDC2, MAOB, CRYZ, CDO1, RDH5, CYBA, CYP27A1, AKR1B1, TMLHE, AOX1, CYBRD1"], ["CC", "GO:0070062 ~ extracellular exosome", "66", "6.38E−06", "STEAP4, RARRES2, RPS2, SYNGR2, CANT1, GSTM2, DES, APOD, GPX3, LTF, PI15, ZDHHC1, BST2, CFTR, EEF2, CD40, CD38, KRT17, KRT15, TMEM106A, CYBRD1, HSPB1, SERPINB1, NEU1, CSTA, MFAP4, WFDC2, GSTP1, ACP5, PAH, CD74, B3GNT8, KRT5, ITGB8, KRT7, ALDH1A3, ENTPD5, FASN, RPL3, HAAO, ANGPTL1, RPL7A, MARS, BHMT2, S100A16, LGALS3, KLK2, KLK3, HIST1H2BH, MAOB, KLK1, CRYZ, ANXA2, PROM1, ORM1, ACSM1, C1ORF116, PKP1, PHB2, RAB34, AKR1B1, CAPG, AOX1, ALDH2, SLC46A3, PON3"], ["MF", "GO:0009055 ~ electron carrier activity", "7", "0.001504105", "ACOX2, CYBA, AOX1, AKR1B1, MAOB, ALDH2, HAAO"], ["BP", "GO:0000302 ~ response to reactive oxygen species", "5", "0.0019364", "CYBA, APOD, GPX3, GPX7, GSTP1"], ["MF", "GO:0004030 ~ aldehyde dehydrogenase [NAD(P)+] activity", "3", "0.002720156", "ALDH1A3, ALDH2, ALDH3A1"], ["MF", "GO:0004602 ~ glutathione peroxidase activity", "4", "0.002838234", "GSTM2, GPX3, GPX7, GSTP1"], ["BP", "GO:0042178 ~ xenobiotic catabolic process", "3", "0.003748861", "GSTM1, GSTM2, CRYZ"], ["BP", "GO:0060349 ~ bone morphogenesis", "4", "0.005820424", "SP5, LTF, ACP5, RIPPLY2"]], "row_count": 9, "column_count": 5, "numeric_cells": 26, "header_rows": 1, "locator": "section[4]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:31533842:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9acd3658af768b7d3242dc33133afa1705f1e1fb800d1bff03ce876e21775e97", "bytes": 1161, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#Tab4", "version": null, "note": "Pathway enriched by the 266 DNA methylation driven genes", "structure": {"pmcid": "PMC6751626", "section_index": 5, "section_title": "KEGG pathway analysis of DNA methylation-driven genes obtained from TCGA", "row_count": 9, "column_count": 6}, "table": {"label": "Table 4", "caption": "Pathway enriched by the 266 DNA methylation driven genes", "rows": [["Pathway", "External_id", "Members_input_overlap", "p-value", "q-value", "Size"], ["Drug metabolism—cytochrome P450", "hsa00982", "AOX1; GSTM1; GSTM2; ALDH3A1; MAOB; GSTP1; ALDH1A3", "6.59E−05", "0.003828899", "70"], ["Phenylalanine metabolism", "hsa00360", "PAH; MAOB; ALDH3A1; ALDH1A3", "9.23E−05", "0.003828899", "17"], ["Histidine metabolism", "hsa00340", "MAOB; ALDH3A1; ALDH2; ALDH1A3", "0.000320403", "0.008864472", "23"], ["Glutathione metabolism", "hsa00480", "GSTM1; GSTM2; GPX3; GSTP1; GPX7", "0.00114281", "0.023713299", "54"], ["Tyrosine metabolism", "hsa00350", "AOX1; ALDH3A1; ALDH1A3; MAOB", "0.001836818", "0.030491186", "36"], ["Tryptophan metabolism", "hsa00380", "MAOB; HAAO; ALDH2; AOX1", "0.002722806", "0.037665486", "40"], ["Metabolism of xenobiotics by cytochrome P450", "hsa00980", "GSTM1; GSTM2; ALDH3A1; GSTP1; ALDH1A3", "0.00433977", "0.051457275", "74"], ["Chemical carcinogenesis", "hsa05204", "GSTM1; GSTM2; ALDH3A1; GSTP1; ALDH1A3", "0.007094498", "0.073605418", "82"]], "row_count": 9, "column_count": 6, "numeric_cells": 34, "header_rows": 1, "locator": "section[5]/table-wrap[1]#Tab4"}}, {"id": "asset:table:pmid:31533842:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0eae6c3c3988cf053c9a0974aa260bf8cdc9c504b5ca94a3c09037214297af5b", "bytes": 1886, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#Tab5", "version": null, "note": "GO terms enriched in GSE112047 and GSE76938 datasets", "structure": {"pmcid": "PMC6751626", "section_index": 8, "section_title": "Gene ontology terms analysis of DNA methylation-driven genes obtained from GEO database", "row_count": 20, "column_count": 7}, "table": {"label": "Table 5", "caption": "GO terms enriched in GSE112047 and GSE76938 datasets", "rows": [["Gene set", "Description", "Size", "Expect", "Ratio", "p value", "FDR"], ["GSE112047"], ["GO:0045595", "Regulation of cell differentiation", "1699", "28.866", "2.1479", "5.48E−09", "0.0001"], ["GO:0031012", "Extracellular matrix", "496", "8.4271", "3.3226", "3.00E−08", "0.0002"], ["GO:0007155", "Cell adhesion", "1369", "23.259", "2.1067", "5.21E−07", "0.0016"], ["GO:0061061", "Muscle structure development", "610", "10.364", "2.7982", "6.40E−07", "0.0016"], ["GO:0030182", "Neuron differentiation", "1313", "22.308", "2.1069", "9.19E−07", "0.0016"], ["GO:0005540", "Hyaluronic acid binding", "22", "0.3738", "16.052", "1.3596E−06", "0.0021"], ["GO:2000026", "Regulation of multicellular organismal development", "1908", "32.417", "1.82", "3.8179E−06", "0.0046"], ["GSE76938"], ["GO:0043062", "Extracellular structure organization", "400", "11.623", "2.8392", "7.43E−08", "0"], ["GO:0031012", "Extracellular matrix", "496", "14.412", "3.1223", "1.20E−11", "1.56E−08"], ["GO:0021953", "Central nervous system neuron differentiation", "179", "5.2012", "4.2298", "1.19E−08", "7.73E−06"], ["GO:0001505", "Regulation of neurotransmitter levels", "335", "9.7341", "2.9792", "1.70E−07", "0.0001"], ["GO:0045165", "Cell fate commitment", "249", "7.2352", "3.3171", "2.86E−07", "0.0001"], ["GO:1990351", "Transporter complex", "332", "9.6469", "2.9025", "4.73E−07", "0.0001"], ["GO:0050769", "Positive regulation of neurogenesis", "447", "12.989", "2.5407", "9.50E−07", "0.0002"], ["GO:0043025", "Neuronal cell body", "486", "14.122", "2.4076", "2.17E−06", "0.0004"], ["GO:0005201", "Extracellular matrix structural constituent", "158", "4.591", "3.7029", "3.55E−06", "0.0005"], ["GO:0042391", "Regulation of membrane potential", "414", "12.03", "2.4938", "4.34E−06", "0.0005"]], "row_count": 20, "column_count": 7, "numeric_cells": 104, "header_rows": 1, "locator": "section[8]/table-wrap[1]#Tab5"}}, {"id": "asset:table:pmid:31533842:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d4ad6e7f78008a5ce445327d815af1332406b13f456c7bd44ea91ed79ba86b80", "bytes": 1915, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#Tab6", "version": null, "note": "Pathways enriched in GSE112047 and GSE76938 datasets", "structure": {"pmcid": "PMC6751626", "section_index": 9, "section_title": "KEGG pathway analysis of DNA methylation-driven genes obtained from GEO", "row_count": 23, "column_count": 7}, "table": {"label": "Table 6", "caption": "Pathways enriched in GSE112047 and GSE76938 datasets", "rows": [["Gene set", "Description", "Size", "Expect", "Ratio", "p value", "FDR"], ["GSE112047"], ["hsa04728", "Dopaminergic synapse", "131", "2.3422", "3.8426", "0.0005", "0.1734"], ["hsa05033", "Nicotine addiction", "40", "0.7152", "5.5931", "0.0054", "0.5917"], ["hsa05031", "Amphetamine addiction", "68", "1.2158", "4.1126", "0.0072", "0.5917"], ["hsa05146", "Amoebiasis", "96", "1.7164", "3.4957", "0.0073", "0.5917"], ["hsa04512", "ECM-receptor interaction", "82", "1.4661", "3.4104", "0.0154", "0.8913"], ["hsa05323", "Rheumatoid arthritis", "90", "1.6091", "3.1073", "0.0222", "0.8913"], ["hsa00604", "Glycosphingolipid biosynthesis", "15", "0.2682", "7.4574", "0.0286", "0.8913"], ["hsa04933", "AGE-RAGE signaling pathway in diabetic complications", "99", "1.77", "2.8248", "0.0318", "0.8913"], ["hsa00380", "Tryptophan metabolism", "40", "0.7152", "4.1948", "0.0341", "0.8913"], ["hsa00360", "Phenylalanine metabolism", "17", "0.3039", "6.5801", "0.0362", "0.8913"], ["GSE76938"], ["hsa05033", "Nicotine addiction", "40", "1.1993", "9.1721", "1.47E−08", "4.8E−06"], ["hsa05032", "Morphine addiction", "91", "2.7284", "4.7647", "2.68E−06", "0.0004"], ["hsa04723", "Retrograde endocannabinoid signaling", "148", "4.4374", "3.3804", "0", "0.0029"], ["hsa04933", "AGE-RAGE signaling pathway in diabetic complications", "99", "2.9682", "4.0428", "0", "0.0029"], ["hsa04080", "Neuroactive ligand-receptor interaction", "277", "8.305", "2.5286", "0.0001", "0.0051"], ["hsa05146", "Amoebiasis", "96", "2.8783", "3.8217", "0.0001", "0.007"], ["hsa04727", "GABAergic synapse", "88", "2.6384", "3.7901", "0.0003", "0.013"], ["hsa04728", "Dopaminergic synapse", "131", "3.9277", "3.0553", "0.0005", "0.0191"], ["hsa05144", "Malaria", "49", "1.4691", "4.7647", "0.0006", "0.0191"], ["hsa04724", "Glutamatergic synapse", "114", "3.418", "3.2183", "0.0006", "0.0191"]], "row_count": 23, "column_count": 7, "numeric_cells": 122, "header_rows": 1, "locator": "section[9]/table-wrap[1]#Tab6"}}, {"id": "asset:table:pmid:31533842:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2dbe3c51f56448581f0f08bd69acc6208cbe1499e7336694efe6bca871d2c3c5", "bytes": 526, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "Clinical dada of prostate cancer patients from TCGA", "structure": {"pmcid": "PMC6751626", "section_index": 15, "section_title": "Identification of DNA methylation-driven genes", "row_count": 15, "column_count": 2}, "table": {"label": "Table 1", "caption": "Clinical dada of prostate cancer patients from TCGA", "rows": [["Characteristic", "Total"], ["Cohort sizea", "500"], ["Mean age, years", "61.01 ± 6.823"], ["T stage"], ["pT2a", "13 (2.6%)"], ["pT2b", "10 (2%)"], ["pT2c", "165 (33%)"], ["pT3a", "159 (31.8%)"], ["pT3b", "136 (27.2%)"], ["pT4", "10 (2%)"], ["Unknown", "7 (1.4%)"], ["N stage"], ["N0", "348 (69.6%)"], ["N1", "79 (15.8%)"], ["Unknown", "73 (14.6%)"]], "row_count": 15, "column_count": 2, "numeric_cells": 12, "header_rows": 1, "locator": "section[3]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:31533842:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:08c7727aa2306ea4ff63707933ff230eff0d2703a6ceddc00743aa89f76143b3", "bytes": 2481, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#Tab2", "version": null, "note": "Top 10 hypomethylated genes and hypermethylated genes in patients with prostate cancer", "structure": {"pmcid": "PMC6751626", "section_index": 15, "section_title": "Identification of DNA methylation-driven genes", "row_count": 23, "column_count": 8}, "table": {"label": "Table 2", "caption": "Top 10 hypomethylated genes and hypermethylated genes in patients with prostate cancer", "rows": [["Gene", "Normal mean", "Tumor mean", "Log FC", "p value", "Adjust p", "Cor", "Cor p value"], ["Top 10 hypomethylated genes"], ["TAF1D", "0.298851771", "0.17046481", "− 0.809956148", "5.12E−22", "1.61E−19", "− 0.515133904", "3.62E−35"], ["TMEM87A", "0.36898334", "0.219989007", "− 0.746124244", "2.40E−22", "7.57E−20", "− 0.415783216", "2.80E−22"], ["KLK2", "0.42230197", "0.252663444", "− 0.741058027", "2.34E−25", "7.36E−23", "− 0.424469057", "3.03E−23"], ["MARS", "0.661117252", "0.407190703", "− 0.69920154", "2.88E−18", "9.08E−16", "− 0.402813221", "6.87E−21"], ["SLC10A5", "0.682378547", "0.421046571", "-0.696592477", "1.19E−16", "3.76E−14", "− 0.320114016", "2.36E−13"], ["KLK3", "0.528659515", "0.348234132", "− 0.602281232", "2.38E−22", "7.50E−20", "− 0.352378214", "4.92E−16"], ["MPC2", "0.847716806", "0.573604393", "− 0.563526315", "3.24E−22", "1.02E−19", "− 0.509873152", "2.25E−34"], ["ALDH1A3", "0.390659331", "0.266302408", "− 0.552845598", "6.96E−20", "2.19E−17", "− 0.500862763", "4.78E−33"], ["CLDN8", "0.556942422", "0.387056997", "− 0.524982157", "1.24E−14", "3.91E−12", "− 0.339347771", "6.50E−15"], ["PMEPA1", "0.427234317", "0.301507194", "− 0.50283511", "1.93E−21", "6.07E−19", "− 0.559861766", "1.65E−42"], ["Top 10 hypermethylated genes"], ["HIST1H2BH", "0.073047", "0.264894", "1.858512", "1.40E−15", "4.41E−13", "− 0.37138", "9.15E−18"], ["FAM200A", "0.052277", "0.163374", "1.643934", "1.78E−18", "5.60E−16", "− 0.32491", "9.86E−14"], ["ZFP36L2", "0.101664", "0.293078", "1.527482", "1.59E−13", "5.02E−11", "− 0.47382", "2.72E−29"], ["WFDC2", "0.125846", "0.347072", "1.463575", "2.89E−24", "9.09E−22", "− 0.46874", "1.27E−28"], ["SMIM10", "0.169555", "0.460955", "1.44287", "1.29E−18", "4.06E−16", "− 0.52098", "4.58E−36"], ["RIPPLY2", "0.06161", "0.166659", "1.435669", "4.35E−23", "1.37E−20", "− 0.33215", "2.57E−14"], ["RTP4", "0.102519", "0.273692", "1.416666", "4.91E−19", "1.55E−16", "− 0.51074", "1.67E−34"], ["FBXO27", "0.048294", "0.126663", "1.391093", "3.13E−12", "9.85E−10", "− 0.64419", "7.67E−60"], ["ZNF492", "0.057359", "0.147069", "1.358401", "3.63E−20", "1.14E−17", "− 0.33472", "1.58E−14"], ["HPDL", "0.14249", "0.356177", "1.321732", "5.48E−20", "1.73E−17", "− 0.54417", "8.31E−40"]], "row_count": 23, "column_count": 8, "numeric_cells": 149, "header_rows": 1, "locator": "section[3]/table-wrap[2]#Tab2"}}], "gaps": ["asset:data:geo:GSE112047 not downloaded", "asset:data:geo:GSE112047 licence not read", "asset:data:geo:GSE76938 not downloaded", "asset:data:geo:GSE76938 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": "reordered", "quote": "“For the data from TCGA, the R package MethylMix was applied to perform an analysis integrating gene expression data and methylation data.” “For the data from GEO, the R package limma was applied to perform analysis to identify the DMEs.”"}}, {"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"}}], "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": ["GSE112047", "GSE76938"], "resolved_accessions": ["GSE112047", "GSE76938"], "statements": ["All data was obtained from The Cancer Genome Atlas (TCGA, https://tcga-data.nci.nih.gov/tcga/) and Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/)."], "basis": "The paper names GSE112047, GSE76938 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:31533842", "data:geo:GSE112047", "asset:table:pmid:31533842:1", "asset:table:pmid:31533842:2", "asset:table:pmid:31533842:3", "asset:table:pmid:31533842:4", "asset:table:pmid:31533842:5", "asset:table:pmid:31533842:6", "asset:table:pmid:31533842:7", "asset:table:pmid:31533842:8"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE112047"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:16:11Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 28932, "completion_tokens": 2326, "cached_tokens": 9736}}, "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:31533842", "type": "paper", "label": "pmid:31533842"}, {"id": "source:pmid:31533842", "type": "manuscript", "label": "PMID 31533842 full text"}, {"id": "data:geo:GSE112047", "type": "dataset", "label": "GEO GSE112047"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31533842", "type": "paper", "label": "pmid:31533842"}, {"id": "source:pmid:31533842", "type": "manuscript", "label": "PMID 31533842 full text"}, {"id": "data:geo:GSE112047", "type": "dataset", "label": "GEO GSE112047"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31533842", "type": "extraction", "used": ["source:pmid:31533842"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE112047", "type": "accession_resolution", "used": ["data:geo:GSE112047"], "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:31533842", "parent_hash": "sha256:bd4b80bfdd20d2198c76e1df20abee6dfd2d1ff1dcdbaf7a2bd4654e74b72d10", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE112047 licence not read", "asset:data:geo:GSE112047 not downloaded", "asset:data:geo:GSE76938 licence not read", "asset:data:geo:GSE76938 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["re also identified. METHODS: Methylation and RNA-seq data were downloaded for The Cancer Genome A"], "order_basis": "paper_text_order:499", "id": "assay:1"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ere utilized to validate screened hub genes. Immunohistochemistry of these hub genes were evaluated by the Hum"], "order_basis": "paper_text_order:1347", "id": "assay:2"}, {"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": ["“For the data from TCGA, the R package MethylMix was applied to perform an analysis integrating gene expression data and methylation data.” “For the data from GEO, the R package limma was applied to perform analysis to identify the DMEs.”"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T00:47:27+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}}}