{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29962817", "kind": "science-record", "revision": 6, "content_hash": "sha256:3c40baad5aeff5f4968108b493ca345211f667a6815495e0d10234cfcb51f429", "created_at": "2026-11-01T15:40:35Z", "updated_at": "2026-11-01T21:59:54Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Bioinformatics analysis of aberrantly methylated-differentially expressed genes and pathways in hepatocellular carcinoma.", "doi": "10.3748/wjg.v24.i24.2605", "pmid": "29962817", "authors": ["Liang Sang", "Xue-Mei Wang", "Dong-Yang Xu", "Wen-Jing Zhao"], "journal": "World journal of gastroenterology", "year": 2018, "abstract": "AIM: To discover methylated-differentially expressed genes (MDEGs) in hepatocellular carcinoma (HCC) and to explore relevant hub genes and potential pathways.\nMETHODS: The data of expression profiling GSE25097 and methylation profiling GSE57956 were gained from GEO Datasets. We analyzed the differentially methylated genes and differentially expressed genes online using GEO2R. Functional and enrichment analyses of MDEGs were conducted using the DAVID database. A protein-protein interaction (PPI) network was performed by STRING and then visualized in Cytoscape. Hub genes were ranked by cytoHubba, and a module analysis of the PPI network was conducted by MCODE in Cytoscape software.\nRESULTS: In total, we categorized 266 genes as hypermethylated, lowly expressed genes (Hyper-LGs) referring to endogenous and hormone stimulus, cell surface receptor linked signal transduction and behavior. In addition, 161 genes were labelled as hypomethylated, highly expressed genes (Hypo-HGs) referring to DNA replication and metabolic process, cell cycle and division. Pathway analysis illustrated that Hyper-LGs were enriched in cancer, Wnt, and chemokine signalling pathways, while Hypo-HGs were related to cell cycle and steroid hormone biosynthesis pathways. Based on PPI networks, PTGS2, PIK3CD, CXCL1, ESR1, and MMP2 were identified as hub genes for Hyper-LGs, and CDC45, DTL, AURKB, CDKN3, MCM2, and MCM10 were hub genes for Hypo-HGs by combining six ranked methods of cytoHubba.\nCONCLUSION: In the study, we disclose numerous novel genetic and epigenetic regulations and offer a vital molecular groundwork to understand the pathogenesis of HCC. Hub genes, including PTGS2, PIK3CD, CXCL1, ESR1, MMP2, CDC45, DTL, AURKB, CDKN3, MCM2, and MCM10, can be used as biomarkers based on aberrant methylation for the accurate diagnosis and treatment of HCC.", "claims": [{"id": "claim-method", "statement": "We used an online tool, GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r/), to analyze the differential expression by comparing two groups of samples across setup conditions in a GEO series.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29962817", "locator": "sections[5] \"Data processing\" paragraph 2", "quote": "We used an online tool, GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r/), to analyze the differential expression by comparing two groups of samples across setup conditions in a GEO series."}], "state": "complete"}, {"id": "claim-data-access", "statement": "One gene expression profiling dataset, GSE25097, and another gene methylation dataset, GSE57956, were downloaded from Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29962817", "locator": "sections[4] \"Microarray data\" paragraph 2", "quote": "One gene expression profiling dataset, GSE25097, and another gene methylation dataset, GSE57956, were downloaded from Gene Expression Omnibus (GEO, 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:29962817"], "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:GSE25097"], "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:GSE25097"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29962817", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3748/wjg.v24.i24.2605", "sha256": "sha256:c60811f9b5cccd1b34707209e1a185bc7480f85bbc9edb98325c803b3c587843", "bytes": 39743, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3748/wjg.v24.i24.2605", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6021769", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE25097", "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=GSE25097", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE25097", "version": null, "note": "One gene expression profiling dataset, GSE25097, and another gene methylation dataset, GSE57956, were downloaded from Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "One gene expression profiling dataset, GSE25097, and another gene methylation dataset, GSE57956, were downloaded from Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM616704", "GSM616705", "GSM616706", "GSM616707", "GSM616708", "GSM616709", "GSM616710", "GSM616711", "GSM616712", "GSM616713", "GSM616714", "GSM616715", "GSM616716", "GSM616717", "GSM616718", "GSM616719", "GSM616720", "GSM616721", "GSM616722", "GSM616723", "GSM616724", "GSM616725", "GSM616726", "GSM616727", "GSM616728", "GSM616729", "GSM616730", "GSM616731", "GSM616732", "GSM616733", "GSM616734", "GSM616735", "GSM616736", "GSM616737", "GSM616738", "GSM616739", "GSM616740", "GSM616741", "GSM616742", "GSM616743", "GSM616744", "GSM616745", "GSM616746", "GSM616747", "GSM616748", "GSM616749", "GSM616750", "GSM616751", "GSM616752", "GSM616753", "GSM616754", "GSM616755", "GSM616756", "GSM616757", "GSM616758", "GSM616759", "GSM616760", "GSM616761", "GSM616762", "GSM616763", "GSM616764", "GSM616765", "GSM616766", "GSM616767", "GSM616768", "GSM616769", "GSM616770", "GSM616771", "GSM616772", "GSM616773", "GSM616774", "GSM616775", "GSM616776", "GSM616777", "GSM616778", "GSM616779", "GSM616780", "GSM616781", "GSM616782", "GSM616783", "GSM616784", "GSM616785", "GSM616786", "GSM616787", "GSM616788", "GSM616789", "GSM616790", "GSM616791", "GSM616792", "GSM616793", "GSM616794", "GSM616795", "GSM616796", "GSM616797", "GSM616798", "GSM616799", "GSM616800", "GSM616801", "GSM616802", "GSM616803", "GSM616804", "GSM616805", "GSM616806", "GSM616807", "GSM616808", "GSM616809", "GSM616810", "GSM616811", "GSM616812", "GSM616813", "GSM616814", "GSM616815", "GSM616816", "GSM616817", "GSM616818", "GSM616819", "GSM616820", "GSM616821", "GSM616822", "GSM616823", "GSM616824", "GSM616825", "GSM616826", "GSM616827", "GSM616828", "GSM616829", "GSM616830", "GSM616831", "GSM616832", "GSM616833", "GSM616834", "GSM616835", "GSM616836", "GSM616837", "GSM616838", "GSM616839", "GSM616840", "GSM616841", "GSM616842", "GSM616843", "GSM616844", "GSM616845", "GSM616846", "GSM616847", "GSM616848", "GSM616849", "GSM616850", "GSM616851", "GSM616852", "GSM616853", "GSM616854", "GSM616855", "GSM616856", "GSM616857", "GSM616858", "GSM616859", "GSM616860", "GSM616861", "GSM616862", "GSM616863", "GSM616864", "GSM616865", "GSM616866", "GSM616867", "GSM616868", "GSM616869", "GSM616870", "GSM616871", "GSM616872", "GSM616873", "GSM616874", "GSM616875", "GSM616876", "GSM616877", "GSM616878", "GSM616879", "GSM616880", "GSM616881", "GSM616882", "GSM616883", "GSM616884", "GSM616885", "GSM616886", "GSM616887", "GSM616888", "GSM616889", "GSM616890", "GSM616891", "GSM616892", "GSM616893", "GSM616894", "GSM616895", "GSM616896", "GSM616897", "GSM616898", "GSM616899", "GSM616900", "GSM616901", "GSM616902", "GSM616903", "GSM616904", "GSM616905", "GSM616906", "GSM616907", "GSM616908", "GSM616909", "GSM616910", "GSM616911", "GSM616912", "GSM616913", "GSM616914", "GSM616915", "GSM616916", "GSM616917", "GSM616918", "GSM616919", "GSM616920", "GSM616921", "GSM616922", "GSM616923", "GSM616924", "GSM616925", "GSM616926", "GSM616927", "GSM616928", "GSM616929", "GSM616930", "GSM616931", "GSM616932", "GSM616933", "GSM616934", "GSM616935", "GSM616936", "GSM616937", "GSM616938", "GSM616939", "GSM616940", "GSM616941", "GSM616942", "GSM616943", "GSM616944", "GSM616945", "GSM616947", "GSM616948", "GSM616950", "GSM616952", "GSM616953", "GSM616955", "GSM616957", "GSM616959", "GSM616961", "GSM616963", "GSM616965", "GSM616966", "GSM616968", "GSM616970", "GSM616972", "GSM616973", "GSM616975", "GSM616977", "GSM616978", "GSM616980", "GSM616982", "GSM616984", "GSM616986", "GSM616987", "GSM616989", "GSM616990", "GSM616992", "GSM616994", "GSM616995", "GSM616996", "GSM616997", "GSM616998", "GSM616999", "GSM617000", "GSM617001", "GSM617002", "GSM617003", "GSM617004", "GSM617005", "GSM617006", "GSM617007", "GSM617008", "GSM617009", "GSM617010", "GSM617011", "GSM617012", "GSM617013", "GSM617304", "GSM617305", "GSM617306", "GSM617307", "GSM617308", "GSM617309", "GSM617310", "GSM617311", "GSM617312", "GSM617313", "GSM617314", "GSM617315", "GSM617316", "GSM617317", "GSM617318", "GSM617319", "GSM617320", "GSM617321", "GSM617322", "GSM617323", "GSM617324", "GSM617325", "GSM617326", "GSM617327", "GSM617328", "GSM617329", "GSM617330", "GSM617331", "GSM617332", "GSM617333", "GSM617334", "GSM617335", "GSM617336", "GSM617337", "GSM617338", "GSM617339", "GSM617340", "GSM617341", "GSM617342", "GSM617343", "GSM617344", "GSM617345", "GSM617346", "GSM617347", "GSM617348", "GSM617349", "GSM617350", "GSM617351", "GSM617352", "GSM617353", "GSM617354", "GSM617355", "GSM617356", "GSM617357", "GSM617358", "GSM617359", "GSM617360", "GSM617361", "GSM617362", "GSM617363", "GSM617364", "GSM617365", "GSM617366", "GSM617367", "GSM617368", "GSM617369", "GSM617370", "GSM617371", "GSM617372", "GSM617373", "GSM617374", "GSM617375", "GSM617376", "GSM617377", "GSM617378", "GSM617379", "GSM617380", "GSM617381", "GSM617382", "GSM617383", "GSM617384", "GSM617385", "GSM617386", "GSM617387", "GSM617388", "GSM617389", "GSM617390", "GSM617391", "GSM617392", "GSM617393", "GSM617394", "GSM617395", "GSM617396", "GSM617397", "GSM617398", "GSM617399", "GSM617400", "GSM617401", "GSM617402", "GSM617403", "GSM617404", "GSM617405", "GSM617406", "GSM617407", "GSM617408", "GSM617409", "GSM617410", "GSM617411", "GSM617412", "GSM617413", "GSM617414", "GSM617415", "GSM617416", "GSM617417", "GSM617418", "GSM617419", "GSM617420", "GSM617421", "GSM617422", "GSM617423", "GSM617424", "GSM617425", "GSM617426", "GSM617427", "GSM617428", "GSM617429", "GSM617430", "GSM617431", "GSM617432", "GSM617433", "GSM617434", "GSM617435", "GSM617436", "GSM617437", "GSM617438", "GSM617439", "GSM617440", "GSM617441", "GSM617442", "GSM617443", "GSM617444", "GSM617445", "GSM617446", "GSM617447", "GSM617448", "GSM617449", "GSM617450", "GSM617451", "GSM617452", "GSM617453", "GSM617454", "GSM617455", "GSM617456", "GSM617457", "GSM617458", "GSM617459", "GSM617460", "GSM617461", "GSM617462", "GSM617463", "GSM617464", "GSM617465", "GSM617466", "GSM617467", "GSM617468", "GSM617469", "GSM617470", "GSM617471", "GSM617472", "GSM617473", "GSM617474", "GSM617475", "GSM617476", "GSM617477", "GSM617478", "GSM617479", "GSM617480", "GSM617481", "GSM617482", "GSM617483", "GSM617484", "GSM617485", "GSM617486", "GSM617487", "GSM617488", "GSM617489", "GSM617490", "GSM617491", "GSM617492", "GSM617493", "GSM617494", "GSM617495", "GSM617496", "GSM617497", "GSM617498", "GSM617499", "GSM617500", "GSM617501", "GSM617502", "GSM617503", "GSM617504", "GSM617505", "GSM617506", "GSM617507", "GSM617508", "GSM617509", "GSM617510", "GSM617511", "GSM617512", "GSM617513", "GSM617514", "GSM617515", "GSM617516", "GSM617517", "GSM617518", "GSM617519", "GSM617520", "GSM617521", "GSM617522", "GSM617523", "GSM617524", "GSM617525", "GSM617526", "GSM617527", "GSM617528", "GSM617529", "GSM617530", "GSM617531", "GSM617532", "GSM617533", "GSM617534", "GSM617535", "GSM617536", "GSM617537", "GSM617538", "GSM617539", "GSM617540", "GSM617541", "GSM617542", "GSM617543", "GSM617544", "GSM617545", "GSM617546", "GSM617547", "GSM617548", "GSM617549", "GSM617550", "GSM617551", "GSM617552", "GSM617553", "GSM617554", "GSM617555", "GSM617556", "GSM617557", "GSM617558", "GSM617559", "GSM617560", "GSM617561", "GSM617562", "GSM617563", "GSM617564", "GSM617565", "GSM617566", "GSM617567", "GSM617568", "GSM617569", "GSM617570", "GSM617571"], "sample_count": 557, "group_sizes": null, "group_sizes_basis": null, "platform": "10687", "taxon": "Homo sapiens", "title": "Study of gene expression of human liver Hepatocellular carcinoma", "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:GSE57956", "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=GSE57956", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE57956", "version": null, "note": "One gene expression profiling dataset, GSE25097, and another gene methylation dataset, GSE57956, were downloaded from Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "One gene expression profiling dataset, GSE25097, and another gene methylation dataset, GSE57956, were downloaded from Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1398525", "GSM1398526", "GSM1398527", "GSM1398528", "GSM1398529", "GSM1398530", "GSM1398531", "GSM1398532", "GSM1398533", "GSM1398534", "GSM1398535", "GSM1398536", "GSM1398537", "GSM1398538", "GSM1398539", "GSM1398540", "GSM1398541", "GSM1398542", "GSM1398543", "GSM1398544", "GSM1398545", "GSM1398546", "GSM1398547", "GSM1398548", "GSM1398549", "GSM1398550", "GSM1398551", "GSM1398552", "GSM1398553", "GSM1398554", "GSM1398555", "GSM1398556", "GSM1398557", "GSM1398558", "GSM1398559", "GSM1398560", "GSM1398561", "GSM1398562", "GSM1398563", "GSM1398564", "GSM1398565", "GSM1398566", "GSM1398567", "GSM1398568", "GSM1398569", "GSM1398570", "GSM1398571", "GSM1398572", "GSM1398573", "GSM1398574", "GSM1398575", "GSM1398576", "GSM1398577", "GSM1398578", "GSM1398579", "GSM1398580", "GSM1398581", "GSM1398582", "GSM1398583", "GSM1398584", "GSM1398585", "GSM1398586", "GSM1398587", "GSM1398588", "GSM1398589", "GSM1398590", "GSM1398591", "GSM1398592", "GSM1398593", "GSM1398594", "GSM1398595", "GSM1398596", "GSM1398597", "GSM1398598", "GSM1398599", "GSM1398600", "GSM1398601", "GSM1398602", "GSM1398603", "GSM1398604", "GSM1398605", "GSM1398606", "GSM1398607", "GSM1398608", "GSM1398609", "GSM1398610", "GSM1398611", "GSM1398612", "GSM1398613", "GSM1398614", "GSM1398615", "GSM1398616", "GSM1398617", "GSM1398618", "GSM1398619", "GSM1398620", "GSM1398621", "GSM1398622", "GSM1398623", "GSM1398624", "GSM1398625", "GSM1398626", "GSM1398627", "GSM1398628", "GSM1398629", "GSM1398630", "GSM1398631", "GSM1398632", "GSM1398633", "GSM1398634", "GSM1398635", "GSM1398636", "GSM1398637", "GSM1398638", "GSM1398639", "GSM1398640", "GSM1398641", "GSM1398642", "GSM1398643", "GSM1398644"], "sample_count": 120, "group_sizes": null, "group_sizes_basis": null, "platform": "8490", "taxon": "Homo sapiens", "title": "Methylation profile of Hepatocellular Carcinoma", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:29962817:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:23895c7f821a511e723b9b4e22c94e3c1103e6735b6fd35b84a54ff1e4c48d23", "bytes": 2775, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T1", "version": null, "note": "GO enrichment analysis of methylated-differentially expressed genes related with hepatocellular carcinoma", "structure": {"pmcid": "PMC6021769", "section_index": 10, "section_title": "GO functional enrichment analysis", "row_count": 32, "column_count": 6}, "table": {"label": "Table 1", "caption": "GO enrichment analysis of methylated-differentially expressed genes related with hepatocellular carcinoma", "rows": [["Category", "Term", "Count", "%", "P value"], ["Hyper-LGs", "GOTERM_BP_FAT", "GO:0048545~response to steroid hormone stimulus", "18", "6.79", "1.51E-08"], ["", "GOTERM_BP_FAT", "GO:0009725~response to hormone stimulus", "24", "9.06", "3.15E-08"], ["", "GOTERM_BP_FAT", "GO:0007166~cell surface receptor linked signal transduction", "60", "22.64", "1.75E-07"], ["", "GOTERM_BP_FAT", "GO:0009719~response to endogenous stimulus", "24", "9.06", "1.89E-07"], ["", "GOTERM_BP_FAT", "GO:0007610~behavior", "25", "9.43", "6.76E-07"], ["", "GOTERM_CC_FAT", "GO:0044421~extracellular region part", "48", "18.11", "1.97E-11"], ["", "GOTERM_CC_FAT", "GO:0005886~plasma membrane", "107", "40.38", "9.53E-10"], ["", "GOTERM_CC_FAT", "GO:0005576~extracellular region", "68", "25.66", "1.10E-08"], ["", "GOTERM_CC_FAT", "GO:0044459~plasma membrane part", "71", "26.79", "3.27E-08"], ["", "GOTERM_CC_FAT", "GO:0031226~intrinsic to plasma membrane", "47", "17.74", "1.22E-07"], ["", "GOTERM_MF_FAT", "GO:0005539~glycosaminoglycan binding", "11", "4.15", "7.78E-05"], ["", "GOTERM_MF_FAT", "GO:0004714~transmembrane receptor protein tyrosine kinase activity", "8", "3.02", "8.88E-05"], ["", "GOTERM_MF_FAT", "GO:0001871~pattern binding", "11", "4.15", "1.72E-04"], ["", "GOTERM_MF_FAT", "GO:0030247~polysaccharide binding", "11", "4.15", "1.72E-04"], ["", "GOTERM_MF_FAT", "GO:0004713~protein tyrosine kinase activity", "11", "4.15", "3.15E-04"], ["", "", "", "", "", ""], ["Hypo-HGs", "GOTERM_BP_FAT", "GO:0006260~DNA replication", "10", "6.25", "6.22E-05"], ["", "GOTERM_BP_FAT", "GO:0051301~cell division", "12", "7.50", "8.37E-05"], ["", "GOTERM_BP_FAT", "GO:0051276~chromosome organization", "15", "9.38", "1.41E-04"], ["", "GOTERM_BP_FAT", "GO:0006259~DNA metabolic process", "15", "9.38", "2.19E-04"], ["", "GOTERM_BP_FAT", "GO:0007049~cell cycle", "19", "11.88", "2.44E-04"], ["", "GOTERM_CC_FAT", "GO:0005694~chromosome", "14", "8.75", "3.77E-04"], ["", "GOTERM_CC_FAT", "GO:0044427~chromosomal part", "12", "7.50", "1.01E-03"], ["", "GOTERM_CC_FAT", "GO:0000793~condensed chromosome", "7", "4.38", "1.34E-03"], ["", "GOTERM_CC_FAT", "GO:0000785~chromatin", "8", "5.00", "2.77E-03"], ["", "GOTERM_CC_FAT", "GO:0044421~extracellular region part", "19", "11.88", "3.60E-03"], ["", "GOTERM_MF_FAT", "GO:0030414~peptidase inhibitor activity", "6", "3.75", "1.24E-02"], ["", "GOTERM_MF_FAT", "GO:0016849~phosphorus-oxygen lyase activity", "3", "1.88", "1.65E-02"], ["", "GOTERM_MF_FAT", "GO:0009975~cyclase activity", "3", "1.88", "1.80E-02"], ["", "GOTERM_MF_FAT", "GO:0004857~enzyme inhibitor activity", "7", "4.38", "3.53E-02"], ["", "GOTERM_MF_FAT", "GO:0008092~cytoskeletal protein binding", "10", "6.25", "3.83E-02"]], "row_count": 32, "column_count": 6, "numeric_cells": 120, "header_rows": 1, "locator": "section[10]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:29962817:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:907d270e0b136de43b2cbd11da731419208a1f9d4341cbf19495caf8ef1beff6", "bytes": 1264, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T2", "version": null, "note": "KEGG pathway analysis of methylated-differentially expressed genes related with hepatocellular carcinoma", "structure": {"pmcid": "PMC6021769", "section_index": 11, "section_title": "KEGG pathway analysis", "row_count": 8, "column_count": 7}, "table": {"label": "Table 2", "caption": "KEGG pathway analysis of methylated-differentially expressed genes related with hepatocellular carcinoma", "rows": [["Category", "Term", "Count", "%", "P value", "Gene"], ["Hyper-LGs", "KEGG_PATHWAY", "hsa04610:Complement and coagulation cascades", "7", "2.64", "6.62E-03", "C7, CR1, CD55, THBD, MASP1, SERPINE1, PLAUR"], ["", "KEGG_PATHWAY", "hsa05414:Dilated cardiomyopathy", "7", "2.64", "2.50E-02", "LAMA2, ITGA9, ADCY1, ADRB1, ITGB8, ADCY5, TGFB3"], ["", "KEGG_PATHWAY", "hsa05200:Pathways in cancer", "15", "5.66", "2.94E-02", "FGFR2, PTGS2, FLT3, PIK3CD, FZD1, TGFB3, MMP2, WNT2, LAMA2, RAC2, NKX3-1, LAMC2, WNT11, HHIP, GSTP1"], ["", "KEGG_PATHWAY", "hsa04310:Wnt signaling pathway", "9", "3.40", "3.16E-02", "WNT2, SFRP5, NKD2, RAC2, PRICKLE1, SFRP1, FZD1, WNT11, FOSL1"], ["", "KEGG_PATHWAY", "hsa04062:Chemokine signaling pathway", "10", "3.77", "3.97E-02", "CXCL1, ADCY1, DOCK2, CCL23, RAC2, TIAM1, ADCY5, PIK3CD, CCL19, CXCL6"], ["Hypo-HGs", "KEGG_PATHWAY", "hsa04110:Cell cycle", "7", "4.38", "2.32E-03", "CCNE2, E2F2, PRKDC, CDC20, MCM2, SFN, PTTG1"], ["", "KEGG_PATHWAY", "hsa00140:Steroid hormone biosynthesis", "3", "1.88", "9.07E-02", "CYP17A1, CYP7A1, UGT2B11"]], "row_count": 8, "column_count": 7, "numeric_cells": 34, "header_rows": 1, "locator": "section[11]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:29962817:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9c05af79f86a0ac35cb9d9aaa6153c671d6951a23e6643ff5a82abe117aae344", "bytes": 829, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T3", "version": null, "note": "Hub genes for hypermethylated, lowly expressed genes ranked in cytoHubba", "structure": {"pmcid": "PMC6021769", "section_index": 12, "section_title": "PPI network construction and cytoHubba analysis", "row_count": 12, "column_count": 7}, "table": {"label": "Table 3", "caption": "Hub genes for hypermethylated, lowly expressed genes ranked in cytoHubba", "rows": [["Catelogy", "Rank methods in cytoHubba"], ["MNC", "Degree", "EPC", "Closeness", "Radiality", "Stress"], ["Gene symbol top 10", "PTGS2", "ADCY5", "PTGS2", "PIK3CD", "PIK3CD", "PTGS2"], ["PIK3CD", "MMP2", "PIK3CD", "PTGS2", "PTGS2", "PIK3CD"], ["ADCY5", "PTGS2", "MMP2", "MMP2", "MMP2", "MMP2"], ["ADCY1", "PIK3CD", "ADCY5", "ESR1", "ESR1", "PRKG1"], ["CXCL1", "PRKG1", "ADCY1", "PRKG1", "TLR2", "ESR1"], ["ESR1", "ADCY1", "ESR1", "TLR2", "SERPINE1", "FYN"], ["MMP2", "ESR1", "CXCL1", "FYN", "PRKG1", "RAC2"], ["FYN", "FYN", "TLR2", "CXCL1", "SNAI1", "SERPINE1"], ["TLR2", "CXCL1", "CALCA", "SERPINE1", "CRP", "CXCL1"], ["SERPINE1", "TLR2", "PTGER2", "ADCY5", "CXCL1", "ADCY5"]], "row_count": 12, "column_count": 7, "numeric_cells": 1, "header_rows": 2, "locator": "section[12]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:29962817:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6d358c1d731b8728696a9dc8f50eb5c5a095a75151e5e8b35f99e810f3e9e49a", "bytes": 821, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#T4", "version": null, "note": "Hub genes for hypomethylated, highly expressed genes ranked in cytoHubba", "structure": {"pmcid": "PMC6021769", "section_index": 12, "section_title": "PPI network construction and cytoHubba analysis", "row_count": 12, "column_count": 7}, "table": {"label": "Table 4", "caption": "Hub genes for hypomethylated, highly expressed genes ranked in cytoHubba", "rows": [["Catelogy", "Rank methods in cytoHubba"], ["MCC", "MNC", "Degree", "EPC", "Closeness", "Radiality"], ["Gene symbol top 10", "CDC45", "CDC45", "CDC45", "CDC45", "CDKN3", "CDKN3"], ["DTL", "AURKB", "AURKB", "AURKB", "CDC45", "PRKDC"], ["RACGAP1", "DTL", "CDKN3", "CDKN3", "AURKB", "CDC45"], ["AURKB", "RACGAP1", "DTL", "DTL", "PTTG1", "PTTG1"], ["CDC20", "CDC20", "RACGAP1", "RACGAP1", "DTL", "MCM10"], ["CDKN3", "CDKN3", "CDC20", "CDC20", "MCM2", "BRCA1"], ["RRM2", "MCM2", "MCM2", "MCM2", "MCM10", "PI3"], ["MCM2", "PTTG1", "PTTG1", "PTTG1", "RACGAP1", "AURKB"], ["MCM10", "RRM2", "RRM2", "RRM2", "CDC20", "MCM2"], ["MKI67", "MCM10", "MCM10", "MCM10", "RRM2", "DTL"]], "row_count": 12, "column_count": 7, "numeric_cells": 19, "header_rows": 2, "locator": "section[12]/table-wrap[2]#T4"}}, {"id": "asset:table:pmid:29962817:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fee801fcebe6cdf53655765c94a2398020d3ed2d6500748e1b199a2dc318d91d", "bytes": 1843, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T5", "version": null, "note": "Modules analysis of the protein–protein interaction network", "structure": {"pmcid": "PMC6021769", "section_index": 13, "section_title": "Module analysis", "row_count": 22, "column_count": 6}, "table": {"label": "Table 5", "caption": "Modules analysis of the protein–protein interaction network", "rows": [["Category", "Module", "Score", "Nodes", "Enrichment and pathway description", "Genes"], ["Hyper-LGs", "1", "10.00", "10", "GO.0005886: plasma membrane", "ADRB1, VIPR1, PTGDR, SCTR, CALCA, GPR83, ADCY1, ADCY5, PTGER2, PTGER4"], ["GO.0007187: G-protein coupled receptor signaling pathway"], ["GO.0004016: adenylate cyclase activity"], ["has04080: Neuroactive ligand-receptor interaction"], ["2", "6.00", "6", "GO.0051953: negative regulation of amine transport", "CCL19, ADRA2B, P2RY12, CXCL6, NPY5R, CXCL1"], ["GO.0008009: chemokine activity"], ["has04062: Chemokine signaling pathway"], ["3", "5.68", "20", "GO.0005886: plasma membrane", "OXT, SERPINE1, EDNRB, PTGS2, ADRA1A, IL18, CRP, SOCS3, EFNB3, MMP2, EPHB1, TIAM1, EFNA5, TBXA2R, EPHA2, TLR2, SNAI1, FYN, GNA14, PROK2"], ["GO.0005003: ephrin receptor activity"], ["GO.0051240: positive regulation of multicellular organismal process"], ["hsa04360: Axon guidance"], ["4", "4.50", "5", "GO.0005605: basal lamina", "ITGA9, ITGB8, COL6A2, LAMC2, LAMA2"], ["GO.0030198: extracellular matrix organization"], ["hsa04512: ECM-receptor interaction"], ["Hypo-HGs", "1", "17.56", "19", "GO.0022402: cell cycle process", "CDCA5, KIF14, BRCA1, CENPF, RACGAP1, NEK2, CDKN3, DTL, MCM2, MCM10, CDC45, PTTG1, ANLN, CDC20, RRM2, AURKB, MKI67, STIL, CCNE2"], ["GO.0015630: microtubule cytoskeleton"], ["GO.0003688: DNA replication origin binding"], ["hsa04110: Cell cycle"], ["2", "5.00", "5", "GO.0007188: adenylate cyclase-modulating G-protein coupled receptor signaling pathway", "CNR1, CCL20, ADCY6, HTR1D, CCL25"], ["hsa04062: Chemokine signaling pathway"], ["3", "4.50", "5", "GO.0005615: extracellular space", "REN, PLA2G1B, TIMP1, MMP9, VWF"]], "row_count": 22, "column_count": 6, "numeric_cells": 47, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T5"}}], "gaps": ["asset:data:geo:GSE25097 not downloaded", "asset:data:geo:GSE25097 licence not read", "asset:data:geo:GSE57956 not downloaded", "asset:data:geo:GSE57956 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-2", "family": null, "specific": null, "label": "GEO2R differential expression and methylation analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We used an online tool, GEO2R (http://www.ncbi.nlm.nih.gov/geo/geo2r/), to analyze the differential expression by comparing two groups of samples across setup conditions in a GEO series."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: ppi_network."}, "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": ["GSE25097", "GSE57956"], "resolved_accessions": ["GSE25097", "GSE57956"], "statements": ["One gene expression profiling dataset, GSE25097, and another gene methylation dataset, GSE57956, were downloaded from Gene Expression Omnibus (GEO, www.ncbi.nlm.nih.gov/geo/)."], "basis": "The paper names GSE25097, GSE57956 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "assets": ["source:pmid:29962817", "data:geo:GSE25097", "asset:table:pmid:29962817:1", "asset:table:pmid:29962817:2", "asset:table:pmid:29962817:3", "asset:table:pmid:29962817:4", "asset:table:pmid:29962817:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE25097"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": null, "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 0, "usage": {}}, "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:29962817", "type": "paper", "label": "pmid:29962817"}, {"id": "source:pmid:29962817", "type": "manuscript", "label": "PMID 29962817 full text"}, {"id": "data:geo:GSE25097", "type": "dataset", "label": "GEO GSE25097"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29962817", "type": "paper", "label": "pmid:29962817"}, {"id": "source:pmid:29962817", "type": "manuscript", "label": "PMID 29962817 full text"}, {"id": "data:geo:GSE25097", "type": "dataset", "label": "GEO GSE25097"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29962817", "type": "extraction", "used": ["source:pmid:29962817"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE25097", "type": "accession_resolution", "used": ["data:geo:GSE25097"], "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:29962817", "parent_hash": "sha256:5bb9ad0618f5c33420f0caf0d42a591f74425ac5b16edb5f44f14c61e80010a2", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE25097 licence not read", "asset:data:geo:GSE25097 not downloaded", "asset:data:geo:GSE57956 licence not read", "asset:data:geo:GSE57956 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["protein-protein interaction"], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:43:48+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}}}