{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29201983", "kind": "science-record", "revision": 8, "content_hash": "sha256:0548d61cb491c96723c34cd807d8ac4ba9da3ee4c9a3c97f23918a284c109f57", "created_at": "2026-11-01T15:40:30Z", "updated_at": "2026-11-01T22:43:10Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Data on novel DNA methylation changes induced by valproic acid in human hepatocytes.", "doi": "10.1016/j.dib.2017.11.031", "pmid": "29201983", "authors": ["JarnoEJ Wolters", "SimoneGJ van Breda", "SandraM Claessen", "TheoMCM de Kok", "JosCS Kleinjans"], "journal": "Data in brief", "year": 2018, "abstract": "Valproic acid (VPA) is a widely prescribed antiepileptic drug in the world. Despite its pharmacological importance, it may cause liver toxicity and steatosis. However the exact mechanism of the steatosis formation is unknown. The data presented in this DIB publication is used to further investigate the VPA-induced mechanisms of steatosis by analyzing changes in patterns of methylation. Therefore, primary human hepatocytes (PHHs) were exposed to VPA at a concentration which was shown to cause steatosis without inducing overt cytotoxicity. VPA was administered for 5 days daily to PHHs. Furthermore, after 5 days VPA-treatment parts of the PHHs were followed for a 3 days washout. Differentially methylated DNA regions (DMRs) were identified by using the 'Methylated DNA Immuno-Precipitation - sequencing' (MeDIP-seq) method. The data presented in this DIB demonstrate induced steatosis pathways by all DMRs during VPA-treatment, covering interesting drug-induced steatosis genes (persistent DMRs upon terminating VPA treatment and the EP300 network). This was illustrated in our associated article (Wolters et al., 2017) [1]. MeDIP-seq raw data are available on ArrayExpress (accession number: E-MTAB-4437).", "claims": [{"id": "claim-method", "statement": "Statistical analysis was performed applying the default parameters of MEDIPS, using the edgeR module, an empirical analysis of digital gene expression data in R that uses Bayes estimation and exact tests based on the negative binomial distribution [8].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29201983", "locator": "sections[15] \"MeDIP-Seq analysis\" paragraph 2", "quote": "Statistical analysis was performed applying the default parameters of MEDIPS, using the edgeR module, an empirical analysis of digital gene expression data in R that uses Bayes estimation and exact tests based on the negative binomial distribution [8]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "MeDIP-seq raw data are available on ArrayExpress (accession number: E-MTAB-4437).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29201983", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "MeDIP-seq raw data are available on ArrayExpress (accession number: E-MTAB-4437)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study identified DMRs using MEDIPS with edgeR, negative-binomial exact tests, and TMM normalization, and the raw MeDIP-seq source data are available through ArrayExpress under accession E-MTAB-4437.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:29201983", "locator": "sections[15] \"MeDIP-Seq analysis\" paragraph 2", "quote": "The MEDIPS package (version 1.16.0, Bioconductor) was used for the analysis of the MeDIP-seq data [4], [5], [6]."}, {"asset": "source:pmid:29201983", "locator": "sections[15] \"MeDIP-Seq analysis\" paragraph 2", "quote": "Statistical analysis was performed applying the default parameters of MEDIPS, using the edgeR module, an empirical analysis of digital gene expression data in R that uses Bayes estimation and exact tests based on the negative binomial distribution [8]."}, {"asset": "source:pmid:29201983", "locator": "sections[15] \"MeDIP-Seq analysis\" paragraph 2", "quote": "Notably, raw count data was normalized using the weighted trimmed mean of M-values (TMM-normalization)."}, {"asset": "source:pmid:29201983", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "MeDIP-seq raw data are available on ArrayExpress (accession number: E-MTAB-4437)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study identified DMRs using MEDIPS with edgeR, negative-binomial exact tests, and TMM normalization, and the raw MeDIP-seq source data are available through ArrayExpress under accession E-MTAB-4437.", "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:29201983"], "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:E-MTAB-4437"], "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:E-MTAB-4437"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29201983", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2017.11.031", "sha256": "sha256:f151e07c703e859065645d9b79cc20cbf853ff88108d96748f7b1dbd284444a4", "bytes": 28965, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2017.11.031", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5702865", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:E-MTAB-4437", "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=E-MTAB-4437", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-4437", "version": null, "note": "MeDIP-seq raw data are available on ArrayExpress (accession number: E-MTAB-4437).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "MeDIP-seq raw data are available on ArrayExpress (accession number: E-MTAB-4437).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:29:00Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:29201983:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:18f54bc4a960e8e7ca6a820403c3d9baa0f794d1795c31d2365fcfee51c5741e", "bytes": 1158, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0020", "version": null, "note": null, "structure": {"pmcid": "PMC5702865", "section_index": 1, "section_title": "p", "row_count": 10, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Biology"], ["More specific subject area", "(Hepato)toxicogenomics"], ["Type of data", "Figure and Tables"], ["How data was acquired", "Illumina HiSeq. 2000 sequencer"], ["Data format", "Differentially methylated DNA regions/genes, pathways, statistical analysis"], ["Experimental factors", "Primary human hepatocytes (PHHs) were treated by valproic acid (VPA) at an incubation concentration of 15 mM for 5 days daily followed by a washout of 3 days"], ["Experimental features", "The treated samples were corrected for time-matched vehicle controls."], ["The persistent changes were identified by determining DNA methylation similarities between samples of 5 days daily VPA-treatment and samples of 3 days washout upon the 5 days daily VPA-treatment"], ["Data source location", "Department of Toxicogenomics, Maastricht University, the Netherlands"], ["Data accessibility", "Methylated DNA Immuno-Precipitation – sequencing (MeDIP-seq) raw data are available on ArrayExpress (accession number: E-MTAB-4437)."]], "row_count": 10, "column_count": 2, "numeric_cells": 4, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t0020"}}, {"id": "asset:table:pmid:29201983:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:18f54bc4a960e8e7ca6a820403c3d9baa0f794d1795c31d2365fcfee51c5741e", "bytes": 1158, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0020", "version": null, "note": null, "structure": {"pmcid": "PMC5702865", "section_index": 2, "section_title": "p", "row_count": 10, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Biology"], ["More specific subject area", "(Hepato)toxicogenomics"], ["Type of data", "Figure and Tables"], ["How data was acquired", "Illumina HiSeq. 2000 sequencer"], ["Data format", "Differentially methylated DNA regions/genes, pathways, statistical analysis"], ["Experimental factors", "Primary human hepatocytes (PHHs) were treated by valproic acid (VPA) at an incubation concentration of 15 mM for 5 days daily followed by a washout of 3 days"], ["Experimental features", "The treated samples were corrected for time-matched vehicle controls."], ["The persistent changes were identified by determining DNA methylation similarities between samples of 5 days daily VPA-treatment and samples of 3 days washout upon the 5 days daily VPA-treatment"], ["Data source location", "Department of Toxicogenomics, Maastricht University, the Netherlands"], ["Data accessibility", "Methylated DNA Immuno-Precipitation – sequencing (MeDIP-seq) raw data are available on ArrayExpress (accession number: E-MTAB-4437)."]], "row_count": 10, "column_count": 2, "numeric_cells": 4, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t0020"}}, {"id": "asset:table:pmid:29201983:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8362607f585827fe84b98783a7b872ec4ae2ef16328be52828ffeaddcaee9581", "bytes": 3362, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#t0005", "version": null, "note": "Names and functions of the 20 persistently hypermethylated DMRs annotated to 15 unique Entrez Genes (A) and the 11 hypomethylated DMRs annotated to 9 unique Entrez Genes (B) of the MEDIP-seq analysis after the exposure of PHHs for 5 days daily to VPA followed by 3 days washout. PHHs, primary human hepatocytes; VPA, valproic acid; DMRs, differentially methylated DNA regions.", "structure": {"pmcid": "PMC5702865", "section_index": 3, "section_title": "Data", "row_count": 31, "column_count": 4}, "table": {"label": "Table 1", "caption": "Names and functions of the 20 persistently hypermethylated DMRs annotated to 15 unique Entrez Genes (A) and the 11 hypomethylated DMRs annotated to 9 unique Entrez Genes (B) of the MEDIP-seq analysis after the exposure of PHHs for 5 days daily to VPA followed by 3 days washout. PHHs, primary human hepatocytes; VPA, valproic acid; DMRs, differentially methylated DNA regions.", "rows": [["A) 20 persistently hypermethylated DMRs annotated to 15 unique Entrez Genes"], ["Entrez Gene ID", "Gene Symbol", "Gene Name", "NCBI Gene Function"], ["114", "ADCY8", "adenylate cyclase 8 (brain)", "membrane bound enzyme that catalyses the formation of cyclic AMP from ATP"], ["5099", "PCDH7", "protocadherin 7", "The gene product is an integral membrane protein that is thought to function in cell-cell recognition and adhesion"], ["7625", "ZNF74", "zinc finger protein 74", "–"], ["23078", "VWA8", "von Willebrand factor A domain containing 8", "–"], ["55591", "VEZT", "vezatin, adherens junctions transmembrane protein", "This gene encodes a transmembrane protein which has been localized to adherens junctions and shown to bind to myosin VIIA"], ["57521", "RPTOR", "regulatory associated protein of MTOR, complex 1", "encodes a component of a signaling pathway that regulates cell growth in response to nutrient and insulin levels"], ["79755", "ZNF750", "zinc finger protein 750", "This gene encodes a protein with a nuclear localization site and a C2H2 zinc finger domain. Mutations in this gene have been associated with seborrhea-like dermatitis with psoriasiform elements."], ["80757", "TMEM121", "transmembrane protein 121", "–"], ["114784", "CSMD2", "CUB and Sushi multiple domains 2", "–"], ["122706", "PSMB11", "proteasome (prosome, macropain) subunit, beta type, 11", "Proteasomes generate peptides that are presented by major histocompatibility complex (MHC) I molecules to other cells of the immune system."], ["254827", "NAALADL2", "N-acetylated alpha-linked acidic dipeptidase-like 2", "–"], ["338707", "B4GALNT4", "beta-1,4-N-acetyl-galactosaminyl transferase 4", "–"], ["388228", "SBK1", "SH3 domain binding kinase 1", "–"], ["440073", "IQSEC. 3", "IQ motif and Sec. 7 domain 3", "–"], ["100507290", "ZNF865", "zinc finger protein 865", "–"], [""], ["B) 11 persistently hypomethylated DMRs annotated to 9 unique Entrez Genes"], [""], ["Entrez Gene ID", "Gene Symbol", "Gene Name", "NCBI Gene Function"], [""], ["290", "ANPEP", "alanyl (membrane) aminopeptidase", "Aminopeptidase N is located in the small-intestinal and renal microvillar membrane, and also in other plasma membranes. In the small intestine aminopeptidase N plays a role in the final digestion of peptides generated from hydrolysis of proteins by gastric and pancreatic proteases."], ["29982", "NRBF2", "nuclear receptor binding factor 2", "–"], ["136051", "ZNF786", "zinc finger protein 786", "–"], ["414763", "BMS1P18", "BMS1 ribosome biogenesis factor pseudogene 18", "–"], ["643955", "ZNF733P", "zinc finger protein 733, pseudogene", "–"], ["646096", "CHEK2P2", "checkpoint kinase 2 pseudogene 2", "–"], ["647121", "EMBP1", "embigin pseudogene 1", "–"], ["100101266", "HAVCR1P1", "hepatitis A virus cellular receptor 1 pseudogene 1", "–"], ["101927554", "LINC01250", "long intergenic non-protein coding RNA 1250", "–"]], "row_count": 31, "column_count": 4, "numeric_cells": 58, "header_rows": 2, "locator": "section[3]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:29201983:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c6f21f6213cb8cc77cd1a615eb078d7ef244d8e9a81be872f33d60ef4d672509", "bytes": 10824, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#t0010", "version": null, "note": "The ‘enriched pathway-based sets’ from the HOMER annotated genes of the 3006 hypermethylated DMRs and the 3077 hypomethylated DMRs after the exposure of PHHs for 5 days daily to VPA. PHHs, primary human hepatocytes; VPA, valproic acid; DMRs, differentially methylated DNA regions.", "structure": {"pmcid": "PMC5702865", "section_index": 3, "section_title": "Data", "row_count": 120, "column_count": 6}, "table": {"label": "Table 2", "caption": "The ‘enriched pathway-based sets’ from the HOMER annotated genes of the 3006 hypermethylated DMRs and the 3077 hypomethylated DMRs after the exposure of PHHs for 5 days daily to VPA. PHHs, primary human hepatocytes; VPA, valproic acid; DMRs, differentially methylated DNA regions.", "rows": [["Pathway name", "Set size", "Candidates, contained", "p-value", "q-value", "Pathway source"], ["Developmental Biology", "586", "129 (22.0%)", "3.23E-10", "8.02E-07", "Reactome"], ["Axon guidance", "459", "101 (22.0%)", "3.06E-08", "3.81E-05", "Reactome"], ["Wnt signaling pathway - Homo sapiens (human)", "140", "36 (25.7%)", "3.17E-05", "0.0262", "KEGG"], ["Axon guidance - Homo sapiens (human)", "127", "33 (26.0%)", "5.33E-05", "0.0331", "KEGG"], ["Signalling by NGF", "386", "76 (19.7%)", "9.86E-05", "0.0447", "Reactome"], ["Signaling by SCF-KIT", "264", "56 (21.2%)", "0.000108", "0.0447", "Reactome"], ["Hippo signaling pathway - Homo sapiens (human)", "154", "36 (23.4%)", "0.000257", "0.0914", "KEGG"], ["Diseases of signal transduction", "180", "40 (22.2%)", "0.000373", "0.097", "Reactome"], ["Regulation of lipid metabolism by Peroxisome proliferator-activated receptor alpha (PPARalpha)", "20", "9 (45.0%)", "0.00044", "0.097", "Reactome"], ["Oxytocin signaling pathway - Homo sapiens (human)", "159", "36 (22.6%)", "0.000494", "0.097", "KEGG"], ["BMP2 signaling TGF-beta MV", "56", "17 (30.4%)", "0.000501", "0.097", "INOH"], ["Fc gamma R-mediated phagocytosis - Homo sapiens (human)", "92", "24 (26.1%)", "0.000502", "0.097", "KEGG"], ["effects of calcineurin in keratinocyte differentiation", "13", "7 (53.8%)", "0.000508", "0.097", "BioCarta"], ["NOTCH1 Intracellular Domain Regulates Transcription", "47", "15 (31.9%)", "0.000587", "0.104", "Reactome"], ["Calcium signaling pathway - Homo sapiens (human)", "180", "39 (21.7%)", "0.000741", "0.118", "KEGG"], ["Signaling by ERBB4", "263", "52 (19.8%)", "0.00107", "0.118", "Reactome"], ["Signaling by PDGF", "301", "58 (19.3%)", "0.0011", "0.118", "Reactome"], ["Signaling by FGFR3", "270", "53 (19.6%)", "0.00114", "0.118", "Reactome"], ["Signaling by FGFR4", "270", "53 (19.6%)", "0.00114", "0.118", "Reactome"], ["Signaling by FGFR1", "271", "53 (19.6%)", "0.00125", "0.118", "Reactome"], ["Extrinsic Pathway of Fibrin Clot Formation", "5", "4 (80.0%)", "0.00126", "0.118", "Reactome"], ["G alpha (12/13) signalling events", "76", "20 (26.3%)", "0.00127", "0.118", "Reactome"], ["alk in cardiac myocytes", "27", "10 (37.0%)", "0.00134", "0.118", "BioCarta"], ["TGF-beta super family signaling pathway canonical", "115", "27 (23.5%)", "0.00135", "0.118", "INOH"], ["nuclear receptors coordinate the activities of chromatin remodeling complexes and coactivators to facilitate initiation of transcription in carcinoma cells", "8", "5 (62.5%)", "0.00145", "0.118", "BioCarta"], ["Signaling by FGFR2", "273", "53 (19.4%)", "0.00148", "0.118", "Reactome"], ["Interleukin-3, 5 and GM-CSF signaling", "211", "43 (20.4%)", "0.00152", "0.118", "Reactome"], ["Downstream signaling of activated FGFR2", "267", "52 (19.5%)", "0.00152", "0.118", "Reactome"], ["Downstream signaling of activated FGFR1", "267", "52 (19.5%)", "0.00152", "0.118", "Reactome"], ["Downstream signaling of activated FGFR3", "267", "52 (19.5%)", "0.00152", "0.118", "Reactome"], ["Downstream signaling of activated FGFR4", "267", "52 (19.5%)", "0.00152", "0.118", "Reactome"], ["Signaling by FGFR", "274", "53 (19.3%)", "0.00161", "0.118", "Reactome"], ["Hypertrophic cardiomyopathy (HCM) - Homo sapiens (human)", "83", "21 (25.3%)", "0.00167", "0.118", "KEGG"], ["Signaling by Insulin receptor", "262", "51 (19.5%)", "0.0017", "0.118", "Reactome"], ["Androgen receptor signaling pathway", "89", "22 (24.7%)", "0.00181", "0.118", "Wikipathways"], ["Signaling by NOTCH1", "73", "19 (26.0%)", "0.00191", "0.118", "Reactome"], ["Ectoderm Differentiation", "141", "31 (22.0%)", "0.00194", "0.118", "Wikipathways"], ["Signaling by ERBB2", "277", "53 (19.1%)", "0.00206", "0.118", "Reactome"], ["Interleukin-2 signaling", "202", "41 (20.3%)", "0.00209", "0.118", "Reactome"], ["HTLV-I infection - Homo sapiens (human)", "259", "50 (19.3%)", "0.00224", "0.118", "KEGG"], ["Arrhythmogenic Right Ventricular Cardiomyopathy", "74", "19 (25.7%)", "0.00227", "0.118", "Wikipathways"], ["Arrhythmogenic right ventricular cardiomyopathy (ARVC) - Homo sapiens (human)", "74", "19 (25.7%)", "0.00227", "0.118", "KEGG"], ["Constitutive Signaling by NOTCH1 HD+PEST Domain Mutants", "53", "15 (28.3%)", "0.0023", "0.118", "Reactome"], ["Constitutive Signaling by NOTCH1 PEST Domain Mutants", "53", "15 (28.3%)", "0.0023", "0.118", "Reactome"], ["Signaling by NOTCH1 PEST Domain Mutants in Cancer", "53", "15 (28.3%)", "0.0023", "0.118", "Reactome"], ["Signaling by NOTCH1 HD+PEST Domain Mutants in Cancer", "53", "15 (28.3%)", "0.0023", "0.118", "Reactome"], ["Signaling by NOTCH1 in Cancer", "53", "15 (28.3%)", "0.0023", "0.118", "Reactome"], ["Platelet activation - Homo sapiens (human)", "131", "29 (22.1%)", "0.00239", "0.118", "KEGG"], ["Adipogenesis", "131", "29 (22.1%)", "0.00239", "0.118", "Wikipathways"], ["Downstream signal transduction", "279", "53 (19.0%)", "0.00242", "0.118", "Reactome"], ["Signaling by EGFR", "292", "55 (18.8%)", "0.00246", "0.118", "Reactome"], ["Regulation of nuclear beta catenin signaling and target gene transcription", "80", "20 (25.0%)", "0.00248", "0.118", "PID"], ["Validated nuclear estrogen receptor alpha network", "64", "17 (26.6%)", "0.00257", "0.118", "PID"], ["NCAM signaling for neurite out-growth", "223", "44 (19.7%)", "0.0026", "0.118", "Reactome"], ["Downstream signaling events of B Cell Receptor (BCR)", "120", "27 (22.5%)", "0.0026", "0.118", "Reactome"], ["BMP signaling Dro", "34", "11 (32.4%)", "0.00275", "0.122", "INOH"], ["Signaling by Leptin", "193", "39 (20.2%)", "0.00287", "0.124", "Reactome"], ["Inactivation of Cdc42 and Rac", "9", "5 (55.6%)", "0.00291", "0.124", "Reactome"], ["DAP12 signaling", "282", "53 (18.8%)", "0.00306", "0.129", "Reactome"], ["Mesodermal Commitment Pathway", "76", "19 (25.0%)", "0.00314", "0.129", "Wikipathways"], ["Insulin receptor signalling cascade", "238", "46 (19.3%)", "0.00321", "0.129", "Reactome"], ["regulation of pgc-1a", "21", "8 (38.1%)", "0.00332", "0.129", "BioCarta"], ["EPH-ephrin mediated repulsion of cells", "30", "10 (33.3%)", "0.00332", "0.129", "Reactome"], ["Retinoic acid receptors-mediated signaling", "30", "10 (33.3%)", "0.00332", "0.129", "PID"], ["FoxO signaling pathway - Homo sapiens (human)", "134", "29 (21.6%)", "0.0034", "0.13", "KEGG"], ["Interleukin receptor SHC signaling", "195", "39 (20.0%)", "0.00346", "0.13", "Reactome"], ["NGF signalling via TRKA from the plasma membrane", "310", "57 (18.4%)", "0.00361", "0.133", "Reactome"], ["NRAGE signals death through JNK", "45", "13 (28.9%)", "0.00363", "0.133", "Reactome"], ["Constitutive Signaling by Aberrant PI3K in Cancer", "61", "16 (26.2%)", "0.00389", "0.14", "Reactome"], ["AMPK signaling pathway - Homo sapiens (human)", "124", "27 (21.8%)", "0.00422", "0.148", "KEGG"], ["MAPK1/MAPK3 signaling", "191", "38 (19.9%)", "0.00424", "0.148", "Reactome"], ["Signaling by VEGF", "274", "51 (18.6%)", "0.00444", "0.149", "Reactome"], ["Wnt Signaling Pathway and Pluripotency", "101", "23 (22.8%)", "0.00445", "0.149", "Wikipathways"], ["VEGFR2 mediated cell proliferation", "198", "39 (19.7%)", "0.00455", "0.149", "Reactome"], ["FRS-mediated FGFR2 signaling", "186", "37 (19.9%)", "0.00475", "0.149", "Reactome"], ["FRS-mediated FGFR1 signaling", "186", "37 (19.9%)", "0.00475", "0.149", "Reactome"], ["FRS-mediated FGFR3 signaling", "186", "37 (19.9%)", "0.00475", "0.149", "Reactome"], ["FRS-mediated FGFR4 signaling", "186", "37 (19.9%)", "0.00475", "0.149", "Reactome"], ["Dilated cardiomyopathy - Homo sapiens (human)", "90", "21 (23.3%)", "0.00475", "0.149", "KEGG"], ["repression of WNT target genes", "10", "5 (50.0%)", "0.00519", "0.16", "Reactome"], ["MAPK family signaling cascades", "225", "43 (19.1%)", "0.00529", "0.16", "Reactome"], ["MAPK signaling pathway - Homo sapiens (human)", "257", "48 (18.7%)", "0.00529", "0.16", "KEGG"], ["transcription regulation by methyltransferase of carm1", "14", "6 (42.9%)", "0.00556", "0.16", "BioCarta"], ["Netrin-1 signaling", "37", "11 (29.7%)", "0.0057", "0.16", "Reactome"], ["IRS-related events triggered by IGF1R", "239", "45 (18.8%)", "0.00583", "0.16", "Reactome"], ["IGF1R signaling cascade", "239", "45 (18.8%)", "0.00583", "0.16", "Reactome"], ["Signaling by Type 1 Insulin-like Growth Factor 1 Receptor (IGF1R)", "239", "45 (18.8%)", "0.00583", "0.16", "Reactome"], ["Neuronal System", "291", "53 (18.2%)", "0.00595", "0.16", "Reactome"], ["DAP12 interactions", "298", "54 (18.1%)", "0.00614", "0.16", "Reactome"], ["Gastric acid secretion - Homo sapiens (human)", "75", "18 (24.0%)", "0.00631", "0.16", "KEGG"], ["Fatty acid, triacylglycerol, and ketone body metabolism", "98", "22 (22.4%)", "0.00637", "0.16", "Reactome"], ["PIP3 activates AKT signaling", "98", "22 (22.4%)", "0.00637", "0.16", "Reactome"], ["PI-3K cascade:FGFR2", "98", "22 (22.4%)", "0.00637", "0.16", "Reactome"], ["PI-3K cascade:FGFR1", "98", "22 (22.4%)", "0.00637", "0.16", "Reactome"], ["PI-3K cascade:FGFR3", "98", "22 (22.4%)", "0.00637", "0.16", "Reactome"], ["PI-3K cascade:FGFR4", "98", "22 (22.4%)", "0.00637", "0.16", "Reactome"], ["PI3K events in ERBB4 signaling", "98", "22 (22.4%)", "0.00637", "0.16", "Reactome"], ["PI3K events in ERBB2 signaling", "98", "22 (22.4%)", "0.00637", "0.16", "Reactome"], ["VEGFA-VEGFR2 Pathway", "266", "49 (18.4%)", "0.00639", "0.16", "Reactome"], ["Collagen biosynthesis and modifying enzymes", "64", "16 (25.0%)", "0.00644", "0.16", "Reactome"], ["IRS-mediated signalling", "235", "44 (18.7%)", "0.00704", "0.173", "Reactome"], ["O-linked glycosylation", "105", "23 (21.9%)", "0.00731", "0.173", "Reactome"], ["RAF/MAP kinase cascade", "185", "36 (19.5%)", "0.00759", "0.173", "Reactome"], ["SHC1 events in EGFR signaling", "185", "36 (19.5%)", "0.00759", "0.173", "Reactome"], ["SOS-mediated signalling", "185", "36 (19.5%)", "0.00759", "0.173", "Reactome"], ["GRB2 events in EGFR signaling", "185", "36 (19.5%)", "0.00759", "0.173", "Reactome"], ["SHC1 events in ERBB2 signaling", "185", "36 (19.5%)", "0.00759", "0.173", "Reactome"], ["SHC1 events in ERBB4 signaling", "185", "36 (19.5%)", "0.00759", "0.173", "Reactome"], ["GRB2 events in ERBB2 signaling", "185", "36 (19.5%)", "0.00759", "0.173", "Reactome"], ["Regulation of Commissural axon pathfinding by Slit and Robo", "4", "3 (75.0%)", "0.00784", "0.175", "Reactome"], ["Fosphenytoin (Antiarrhythmic) Metabolism Pathway", "4", "3 (75.0%)", "0.00784", "0.175", "SMPDB"], ["Ephrin B reverse signaling", "24", "8 (33.3%)", "0.0084", "0.186", "PID"], ["Signaling by Interleukins", "270", "49 (18.1%)", "0.00851", "0.186", "Reactome"], ["Transport of organic anions", "11", "5 (45.5%)", "0.00852", "0.186", "Reactome"], ["Rho GTPase cycle", "125", "26 (20.8%)", "0.00914", "0.194", "Reactome"], ["PI3K/AKT activation", "101", "22 (21.8%)", "0.00918", "0.194", "Reactome"], ["Thyroid hormone signaling pathway - Homo sapiens (human)", "119", "25 (21.0%)", "0.0092", "0.194", "KEGG"], ["Signaling by NOTCH", "107", "23 (21.5%)", "0.00923", "0.194", "Reactome"], ["Cell death signalling via NRAGE, NRIF and NADE", "61", "15 (24.6%)", "0.0096", "0.2", "Reactome"]], "row_count": 120, "column_count": 6, "numeric_cells": 489, "header_rows": 1, "locator": "section[3]/table-wrap[2]#t0010"}}, {"id": "asset:table:pmid:29201983:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e78853399a1c568de357199c8a538754a6fb4926905f7241b56431765a03fa06", "bytes": 3733, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[3]#t0015", "version": null, "note": "Names and FCs of the 33 neighbors of the EntrezGene ID 2033 (see Fig. 1) after the exposure of PHHs for 5 days daily to VPA. PHHs, primary human hepatocytes; VPA, valproic acid; FCs, fold changes.", "structure": {"pmcid": "PMC5702865", "section_index": 3, "section_title": "Data", "row_count": 53, "column_count": 5}, "table": {"label": "Table 3", "caption": "Names and FCs of the 33 neighbors of the EntrezGene ID 2033 (see Fig. 1) after the exposure of PHHs for 5 days daily to VPA. PHHs, primary human hepatocytes; VPA, valproic acid; FCs, fold changes.", "rows": [["Entrez Gene ID", "Gene Symbol", "Gene Name", "MeDIP-seq FCs", "Steatosis-related pathway(s)"], ["354", "KLK3", "kallikrein-related peptidase 3", "1.9", "–"], ["595", "CCND1", "cyclin D1", "2.1", "–"], ["864", "RUNX3", "runt-related transcription factor 3", "2", "–"], ["", "", "", "", ""], ["1026", "CDKN1A", "cyclin-dependent kinase inhibitor 1 A (p21, Cip1)", "-3.5", "Adipogenesis"], ["Signaling events mediated by HDAC Class III"], ["", "", "", "", ""], ["1387", "CREBBP", "CREB binding protein", "-3.2", "Signaling events mediated by HDAC Class III"], ["Transcriptional regulation of white adipocyte differentiation"], ["Regulation of lipid metabolism by Peroxisome proliferator-activated receptor alpha (PPARalpha)"], ["Signaling events mediated by HDAC Class I"], ["Fatty acid, triacylglycerol, and ketone body metabolism"], ["1488", "CTBP2", "C-terminal binding protein 2", "-3.9", "–"], ["1844", "DUSP2", "dual specificity phosphatase 2", "2.4", "–"], ["1958", "EGR1", "early growth response 1", "-3.6", "–"], ["", "", "", "", ""], ["2033", "EP300", "E1A binding protein p300", "-5.2", "Signaling events mediated by HDAC Class III"], ["Transcriptional regulation of white adipocyte differentiation"], ["Signaling events mediated by HDAC Class I"], ["2309", "FOXO3", "forkhead box O3", "2.2", "Signaling events mediated by HDAC Class III"], ["2353", "FOS", "FBJ murine osteosarcoma viral oncogene homolog", "-3.5", "–"], ["2626", "GATA4", "GATA binding protein 4", "2.5", "Adipogenesis"], ["4088", "SMAD3", "SMAD family member 3", "2.4", "Adipogenesis"], ["4205", "MEF2A", "myocyte enhancer factor 2 A", "2.2", "Adipogenesis"], ["4772", "NFATC1", "nuclear factor of activated T-cells, cytoplasmic, calcineurin-dependent 1", "1.8", "–"], ["5594", "MAPK1", "mitogen-activated protein kinase 1", "2.3", "–"], ["5914", "RARA", "retinoic acid receptor, alpha", "-3.8", "Adipogenesis"], ["6095", "RORA", "RAR-related orphan receptor A", "-4", "Adipogenesis"], ["", "", "", "", ""], ["6256", "RXRA", "retinoid X receptor, alpha", "-3.8", "Adipogenesis"], ["Transcriptional regulation of white adipocyte differentiation"], ["Regulation of lipid metabolism by Peroxisome proliferator-activated receptor alpha (PPARalpha)"], ["Fatty acid, triacylglycerol, and ketone body metabolism"], ["6670", "SP3", "Sp3 transcription factor", "-4.1", "–"], ["6776", "STAT5A", "signal transducer and activator of transcription 5 A", "2.2", "Adipogenesis"], ["6925", "TCF4", "transcription factor 4", "-4", "–"], ["6929", "TCF3", "transcription factor 3", "2.1", "–"], ["6934", "TCF7L2", "transcription factor 7-like 2 (T-cell specific, HMG-box)", "-3.4", "–"], ["6938", "TCF12", "transcription factor 12", "2.12", "–"], ["7026", "NR2F2", "nuclear receptor subfamily 2, group F, member 2", "2.6", "–"], ["7161", "TP73", "tumor protein p73", "2.5", "–"], ["9252", "RPS6KA5", "ribosomal protein S6 kinase, 90 kDa, polypeptide 5", "-3.9", "–"], ["9314", "9314", "Kruppel-like factor 4 (gut)", "2.7", "–"], ["", "", "", "", ""], ["9611", "NCOR1", "nuclear receptor corepressor 1", "-3.4", "Adipogenesis"], ["Transcriptional regulation of white adipocyte differentiation"], ["Regulation of lipid metabolism by Peroxisome proliferator-activated receptor alpha (PPARalpha)"], ["Signaling events mediated by HDAC Class I"], ["Fatty acid, triacylglycerol, and ketone body metabolism"], ["10365", "KLF2", "Kruppel-like factor 2", "-3.3", "Signaling events mediated by HDAC Class III"], ["23411", "SIRT1", "sirtuin 1", "-3.5", ""], ["90427", "BMF", "Bcl2 modifying facto", "2.2", ""]], "row_count": 53, "column_count": 5, "numeric_cells": 94, "header_rows": 1, "locator": "section[3]/table-wrap[3]#t0015"}}], "gaps": ["asset:data:geo:E-MTAB-4437 not downloaded", "asset:data:geo:E-MTAB-4437 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "edger", "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": "Statistical analysis was performed applying the default parameters of MEDIPS, using the edgeR module, an empirical analysis of digital gene expression data in R that uses Bayes estimation and exact tests based on the negative binomial distribution [8]."}}], "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: edger."}, "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": ["E-MTAB-4437"], "resolved_accessions": ["E-MTAB-4437"], "statements": ["MeDIP-seq raw data are available on ArrayExpress (accession number: E-MTAB-4437)."], "basis": "The paper names E-MTAB-4437 in ArrayExpress 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:29201983", "data:geo:E-MTAB-4437", "asset:table:pmid:29201983:1", "asset:table:pmid:29201983:2", "asset:table:pmid:29201983:3", "asset:table:pmid:29201983:4", "asset:table:pmid:29201983:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:E-MTAB-4437"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:32:59Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 70803, "completion_tokens": 2692, "cached_tokens": 1832}}, "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:29201983", "type": "paper", "label": "pmid:29201983"}, {"id": "source:pmid:29201983", "type": "manuscript", "label": "PMID 29201983 full text"}, {"id": "data:geo:E-MTAB-4437", "type": "dataset", "label": "GEO E-MTAB-4437"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29201983", "type": "paper", "label": "pmid:29201983"}, {"id": "source:pmid:29201983", "type": "manuscript", "label": "PMID 29201983 full text"}, {"id": "data:geo:E-MTAB-4437", "type": "dataset", "label": "GEO E-MTAB-4437"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29201983", "type": "extraction", "used": ["source:pmid:29201983"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-E-MTAB-4437", "type": "accession_resolution", "used": ["data:geo:E-MTAB-4437"], "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:29201983", "parent_hash": "sha256:6221264eefdb6a472fbebce8fab02587c0ec1a37704c1a33ea658282b3d422be", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:E-MTAB-4437 licence not read", "asset:data:geo:E-MTAB-4437 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["riability in susceptibility to toxicants and cultured in 6-well plates in a collagen sandwich [2], ac"], "order_basis": "paper_text_order:1590", "id": "assay:1"}, {"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": ["Statistical analysis was performed applying the default parameters of MEDIPS, using the edgeR module, an empirical analysis of digital gene expression data in R that uses Bayes estimation and exact tests based on the negative binomial distribution [8]."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:12:32+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}}}