{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28794688", "kind": "science-record", "revision": 5, "content_hash": "sha256:b7d49d17099ecddd539e2a26fb2ad9588b369245780b03020f0841713de80d7a", "created_at": "2026-11-01T15:40:27Z", "updated_at": "2026-11-01T21:59:28Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Aberrantly methylated-differentially expressed genes and pathways in colorectal cancer.", "doi": "10.1186/s12935-017-0444-4", "pmid": "28794688", "authors": ["Jingwei Liu", "Hao Li", "Liping Sun", "Zhenning Wang", "Chengzhong Xing", "Yuan Yuan"], "journal": "Cancer cell international", "year": 2017, "abstract": "BACKGROUND: Methylation plays an important role in the etiology and pathogenesis of colorectal cancer (CRC). This study aimed to identify aberrantly methylated-differentially expressed genes (DEGs) and pathways in CRC by comprehensive bioinformatics analysis.\nMETHODS: Data of gene expression microarrays (GSE68468, GSE44076) and gene methylation microarrays (GSE29490, GSE17648) were downloaded from GEO database. Aberrantly methylated-DEGs were obtained by GEO2R. Functional and enrichment analyses of selected genes were performed using DAVID database. Protein-protein interaction (PPI) network was constructed by STRING and visualized in Cytoscape. MCODE was used for module analysis of the PPI network.\nRESULTS: Totally 411 hypomethylation-high expression genes were identified, which were enriched in biological processes of response to wounding or inflammation, cell proliferation and adhesion. Pathway enrichment showed cytokine-cytokine receptor interaction, p53 signaling and cell cycle. The top 5 hub genes of PPI network were CAD, CCND1, ATM, RB1 and MET. Additionally, 239 hypermethylation-low expression genes were identified, which demonstrated enrichment in biological processes including cell-cell signaling, nerve impulse transmission, etc. Pathway analysis indicated enrichment in calcium signaling, maturity onset diabetes of the young, cell adhesion molecules, etc. The top 5 hub genes of PPI network were EGFR, ACTA1, SST, ESR1 and DNM2. After validation in TCGA database, most hub genes still remained significant.\nCONCLUSION: In summary, our study indicated possible aberrantly methylated-differentially expressed genes and pathways in CRC by bioinformatics analysis, which may provide novel insights for unraveling pathogenesis of CRC. Hub genes including CAD, CCND1, ATM, RB1, MET, EGFR, ACTA1, SST, ESR1 and DNM2 might serve as aberrantly methylation-based biomarkers for precise diagnosis and treatment of CRC in the future.", "claims": [{"id": "claim-method", "statement": "We used GEO2R online software to analysis the raw submitter-supplied data of microarrays and identify DEGs and DMGs.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28794688", "locator": "sections[4] \"Data processing\" paragraph 2", "quote": "We used GEO2R online software to analysis the raw submitter-supplied data of microarrays and identify DEGs and DMGs."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The authors declare that the data supporting the findings of this study are available within the article.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28794688", "locator": "sections[17] \"ack\" paragraph 1", "quote": "The authors declare that the data supporting the findings of this study are available within the article."}], "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:28794688"], "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:GSE17648"], "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:GSE17648"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28794688", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12935-017-0444-4", "sha256": "sha256:821bdbb131808ec92d5aba3dd2a7d365caa11460a238e1ee58160bf3b54bcd66", "bytes": 29141, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12935-017-0444-4", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5545832", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE17648", "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=GSE17648", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE17648", "version": null, "note": "The authors declare that the data supporting the findings of this study are available within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The authors declare that the data supporting the findings of this study are available within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM440333", "GSM440334", "GSM440335", "GSM440336", "GSM440337", "GSM440338", "GSM440339", "GSM440340", "GSM440341", "GSM440342", "GSM440343", "GSM440344", "GSM440345", "GSM440346", "GSM440347", "GSM440348", "GSM440349", "GSM440350", "GSM440351", "GSM440352", "GSM440353", "GSM440354", "GSM440355", "GSM440356", "GSM440357", "GSM440358", "GSM440359", "GSM440360", "GSM440361", "GSM440362", "GSM440363", "GSM440364", "GSM440365", "GSM440366", "GSM440367", "GSM440368", "GSM440369", "GSM440370", "GSM440371", "GSM440372", "GSM440373", "GSM440374", "GSM440375", "GSM440376"], "sample_count": 44, "group_sizes": null, "group_sizes_basis": null, "platform": "8490", "taxon": "Homo sapiens", "title": "Epigenomic Analysis of Aberrantly Methylated Genes in Colorectal Cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE29490", "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=GSE29490", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29490", "version": null, "note": "The authors declare that the data supporting the findings of this study are available within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The authors declare that the data supporting the findings of this study are available within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM729624", "GSM729625", "GSM729626", "GSM729627", "GSM729628", "GSM729629", "GSM729630", "GSM729631", "GSM729632", "GSM729633", "GSM729634", "GSM729635", "GSM729636", "GSM729637", "GSM729638", "GSM729639", "GSM729640", "GSM729641", "GSM729642", "GSM729643", "GSM729644", "GSM729645", "GSM729646", "GSM729647", "GSM729648", "GSM729649", "GSM729650", "GSM729651", "GSM729652", "GSM729653", "GSM729654", "GSM729655", "GSM729656", "GSM729657", "GSM729658", "GSM729659", "GSM729660", "GSM729661", "GSM729662", "GSM729663", "GSM729664", "GSM729665", "GSM729666", "GSM729667", "GSM729668", "GSM729669", "GSM729670", "GSM729671"], "sample_count": 48, "group_sizes": null, "group_sizes_basis": null, "platform": "8490", "taxon": "Homo sapiens", "title": "A Genome-wide DNA Methylation Study in Colorectal 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:GSE44076", "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=GSE44076", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE44076", "version": null, "note": "The authors declare that the data supporting the findings of this study are available within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The authors declare that the data supporting the findings of this study are available within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1077598", "GSM1077599", "GSM1077600", "GSM1077601", "GSM1077602", "GSM1077603", "GSM1077604", "GSM1077605", "GSM1077606", "GSM1077607", "GSM1077608", "GSM1077609", "GSM1077610", "GSM1077611", "GSM1077612", "GSM1077613", "GSM1077614", "GSM1077615", "GSM1077616", "GSM1077617", "GSM1077618", "GSM1077619", "GSM1077620", "GSM1077621", "GSM1077622", "GSM1077623", "GSM1077624", "GSM1077625", "GSM1077626", "GSM1077627", "GSM1077628", "GSM1077629", "GSM1077630", "GSM1077631", "GSM1077632", "GSM1077633", "GSM1077634", "GSM1077635", "GSM1077636", "GSM1077637", "GSM1077638", "GSM1077639", "GSM1077640", "GSM1077641", "GSM1077642", "GSM1077643", "GSM1077644", "GSM1077645", "GSM1077646", "GSM1077647", "GSM1077648", "GSM1077649", "GSM1077650", "GSM1077651", "GSM1077652", "GSM1077653", "GSM1077654", "GSM1077655", "GSM1077656", "GSM1077657", "GSM1077658", "GSM1077659", "GSM1077660", "GSM1077661", "GSM1077662", "GSM1077663", "GSM1077664", "GSM1077665", "GSM1077666", "GSM1077667", "GSM1077668", "GSM1077669", "GSM1077670", "GSM1077671", "GSM1077672", "GSM1077673", "GSM1077674", "GSM1077675", "GSM1077676", "GSM1077677", "GSM1077678", "GSM1077679", "GSM1077680", "GSM1077681", "GSM1077682", "GSM1077683", "GSM1077684", "GSM1077685", "GSM1077686", "GSM1077687", "GSM1077688", "GSM1077689", "GSM1077690", "GSM1077691", "GSM1077692", "GSM1077693", "GSM1077694", "GSM1077695", "GSM1077696", "GSM1077697", "GSM1077698", "GSM1077699", "GSM1077700", "GSM1077701", "GSM1077702", "GSM1077703", "GSM1077704", "GSM1077705", "GSM1077706", "GSM1077707", "GSM1077708", "GSM1077709", "GSM1077710", "GSM1077711", "GSM1077712", "GSM1077713", "GSM1077714", "GSM1077715", "GSM1077716", "GSM1077717", "GSM1077718", "GSM1077719", "GSM1077720", "GSM1077721", "GSM1077722", "GSM1077723", "GSM1077724", "GSM1077725", "GSM1077726", "GSM1077727", "GSM1077728", "GSM1077729", "GSM1077730", "GSM1077731", "GSM1077732", "GSM1077733", "GSM1077734", "GSM1077735", "GSM1077736", "GSM1077737", "GSM1077738", "GSM1077739", "GSM1077740", "GSM1077741", "GSM1077742", "GSM1077743", "GSM1077744", "GSM1077745", "GSM1077746", "GSM1077747", "GSM1077748", "GSM1077749", "GSM1077750", "GSM1077751", "GSM1077752", "GSM1077753", "GSM1077754", "GSM1077755", "GSM1077756", "GSM1077757", "GSM1077758", "GSM1077759", "GSM1077760", "GSM1077761", "GSM1077762", "GSM1077763", "GSM1077764", "GSM1077765", "GSM1077766", "GSM1077767", "GSM1077768", "GSM1077769", "GSM1077770", "GSM1077771", "GSM1077772", "GSM1077773", "GSM1077774", "GSM1077775", "GSM1077776", "GSM1077777", "GSM1077778", "GSM1077779", "GSM1077780", "GSM1077781", "GSM1077782", "GSM1077783", "GSM1077784", "GSM1077785", "GSM1077786", "GSM1077787", "GSM1077788", "GSM1077789", "GSM1077790", "GSM1077791", "GSM1077792", "GSM1077793", "GSM1077794", "GSM1077795", "GSM1077796", "GSM1077797", "GSM1077798", "GSM1077799", "GSM1077800", "GSM1077801", "GSM1077802", "GSM1077803", "GSM1077804", "GSM1077805", "GSM1077806", "GSM1077807", "GSM1077808", "GSM1077809", "GSM1077810", "GSM1077811", "GSM1077812", "GSM1077813", "GSM1077814", "GSM1077815", "GSM1077816", "GSM1077817", "GSM1077818", "GSM1077819", "GSM1077820", "GSM1077821", "GSM1077822", "GSM1077823", "GSM1077824", "GSM1077825", "GSM1077826", "GSM1077827", "GSM1077828", "GSM1077829", "GSM1077830", "GSM1077831", "GSM1077832", "GSM1077833", "GSM1077834", "GSM1077835", "GSM1077836", "GSM1077837", "GSM1077838", "GSM1077839", "GSM1077840", "GSM1077841", "GSM1077842", "GSM1077843"], "sample_count": 246, "group_sizes": null, "group_sizes_basis": null, "platform": "13667", "taxon": "Homo sapiens", "title": "Gene expression data from healthy, adjacent normal and tumor colon cells", "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:GSE68468", "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=GSE68468", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE68468", "version": null, "note": "The authors declare that the data supporting the findings of this study are available within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The authors declare that the data supporting the findings of this study are available within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1672961", "GSM1672962", "GSM1672963", "GSM1672964", "GSM1672965", "GSM1672966", "GSM1672967", "GSM1672968", "GSM1672969", "GSM1672970", "GSM1672971", "GSM1672972", "GSM1672973", "GSM1672974", "GSM1672975", "GSM1672976", "GSM1672977", "GSM1672978", "GSM1672979", "GSM1672980", "GSM1672981", "GSM1672982", "GSM1672983", "GSM1672984", "GSM1672985", "GSM1672986", "GSM1672987", "GSM1672988", "GSM1672989", "GSM1672990", "GSM1672991", "GSM1672992", "GSM1672993", "GSM1672994", "GSM1672995", "GSM1672996", "GSM1672997", "GSM1672998", "GSM1672999", "GSM1673000", "GSM1673001", "GSM1673002", "GSM1673003", "GSM1673004", "GSM1673005", "GSM1673006", "GSM1673007", "GSM1673008", "GSM1673009", "GSM1673010", "GSM1673011", "GSM1673012", "GSM1673013", "GSM1673014", "GSM1673015", "GSM1673016", "GSM1673017", "GSM1673018", "GSM1673019", "GSM1673020", "GSM1673021", "GSM1673022", "GSM1673023", "GSM1673024", "GSM1673025", "GSM1673026", "GSM1673027", "GSM1673028", "GSM1673029", "GSM1673030", "GSM1673031", "GSM1673032", "GSM1673033", "GSM1673034", "GSM1673035", "GSM1673036", "GSM1673037", "GSM1673038", "GSM1673039", "GSM1673040", "GSM1673041", "GSM1673042", "GSM1673043", "GSM1673044", "GSM1673045", "GSM1673046", "GSM1673047", "GSM1673048", "GSM1673049", "GSM1673050", "GSM1673051", "GSM1673052", "GSM1673053", "GSM1673054", "GSM1673055", "GSM1673056", "GSM1673057", "GSM1673058", "GSM1673059", "GSM1673060", "GSM1673061", "GSM1673062", "GSM1673063", "GSM1673064", "GSM1673065", "GSM1673066", "GSM1673067", "GSM1673068", "GSM1673069", "GSM1673070", "GSM1673071", "GSM1673072", "GSM1673073", "GSM1673074", "GSM1673075", "GSM1673076", "GSM1673077", "GSM1673078", "GSM1673079", "GSM1673080", "GSM1673081", "GSM1673082", "GSM1673083", "GSM1673084", "GSM1673085", "GSM1673086", "GSM1673087", "GSM1673088", "GSM1673089", "GSM1673090", "GSM1673091", "GSM1673092", "GSM1673093", "GSM1673094", "GSM1673095", "GSM1673096", "GSM1673097", "GSM1673098", "GSM1673099", "GSM1673100", "GSM1673101", "GSM1673102", "GSM1673103", "GSM1673104", "GSM1673105", "GSM1673106", "GSM1673107", "GSM1673108", "GSM1673109", "GSM1673110", "GSM1673111", "GSM1673112", "GSM1673113", "GSM1673114", "GSM1673115", "GSM1673116", "GSM1673117", "GSM1673118", "GSM1673119", "GSM1673120", "GSM1673121", "GSM1673122", "GSM1673123", "GSM1673124", "GSM1673125", "GSM1673126", "GSM1673127", "GSM1673128", "GSM1673129", "GSM1673130", "GSM1673131", "GSM1673132", "GSM1673133", "GSM1673134", "GSM1673135", "GSM1673136", "GSM1673137", "GSM1673138", "GSM1673139", "GSM1673140", "GSM1673141", "GSM1673142", "GSM1673143", "GSM1673144", "GSM1673145", "GSM1673146", "GSM1673147", "GSM1673148", "GSM1673149", "GSM1673150", "GSM1673151", "GSM1673152", "GSM1673153", "GSM1673154", "GSM1673155", "GSM1673156", "GSM1673157", "GSM1673158", "GSM1673159", "GSM1673160", "GSM1673161", "GSM1673162", "GSM1673163", "GSM1673164", "GSM1673165", "GSM1673166", "GSM1673167", "GSM1673168", "GSM1673169", "GSM1673170", "GSM1673171", "GSM1673172", "GSM1673173", "GSM1673174", "GSM1673175", "GSM1673176", "GSM1673177", "GSM1673178", "GSM1673179", "GSM1673180", "GSM1673181", "GSM1673182", "GSM1673183", "GSM1673184", "GSM1673185", "GSM1673186", "GSM1673187", "GSM1673188", "GSM1673189", "GSM1673190", "GSM1673191", "GSM1673192", "GSM1673193", "GSM1673194", "GSM1673195", "GSM1673196", "GSM1673197", "GSM1673198", "GSM1673199", "GSM1673200", "GSM1673201", "GSM1673202", "GSM1673203", "GSM1673204", "GSM1673205", "GSM1673206", "GSM1673207", "GSM1673208", "GSM1673209", "GSM1673210", "GSM1673211", "GSM1673212", "GSM1673213", "GSM1673214", "GSM1673215", "GSM1673216", "GSM1673217", "GSM1673218", "GSM1673219", "GSM1673220", "GSM1673221", "GSM1673222", "GSM1673223", "GSM1673224", "GSM1673225", "GSM1673226", "GSM1673227", "GSM1673228", "GSM1673229", "GSM1673230", "GSM1673231", "GSM1673232", "GSM1673233", "GSM1673234", "GSM1673235", "GSM1673236", "GSM1673237", "GSM1673238", "GSM1673239", "GSM1673240", "GSM1673241", "GSM1673242", "GSM1673243", "GSM1673244", "GSM1673245", "GSM1673246", "GSM1673247", "GSM1673248", "GSM1673249", "GSM1673250", "GSM1673251", "GSM1673252", "GSM1673253", "GSM1673254", "GSM1673255", "GSM1673256", "GSM1673257", "GSM1673258", "GSM1673259", "GSM1673260", "GSM1673261", "GSM1673262", "GSM1673263", "GSM1673264", "GSM1673265", "GSM1673266", "GSM1673267", "GSM1673268", "GSM1673269", "GSM1673270", "GSM1673271", "GSM1673272", "GSM1673273", "GSM1673274", "GSM1673275", "GSM1673276", "GSM1673277", "GSM1673278", "GSM1673279", "GSM1673280", "GSM1673281", "GSM1673282", "GSM1673283", "GSM1673284", "GSM1673285", "GSM1673286", "GSM1673287", "GSM1673288", "GSM1673289", "GSM1673290", "GSM1673291", "GSM1673292", "GSM1673293", "GSM1673294", "GSM1673295", "GSM1673296", "GSM1673297", "GSM1673298", "GSM1673299", "GSM1673300", "GSM1673301", "GSM1673302", "GSM1673303", "GSM1673304", "GSM1673305", "GSM1673306", "GSM1673307", "GSM1673308", "GSM1673309", "GSM1673310", "GSM1673311", "GSM1673312", "GSM1673313", "GSM1673314", "GSM1673315", "GSM1673316", "GSM1673317", "GSM1673318", "GSM1673319", "GSM1673320", "GSM1673321", "GSM1673322", "GSM1673323", "GSM1673324", "GSM1673325", "GSM1673326", "GSM1673327", "GSM1673328", "GSM1673329", "GSM1673330", "GSM1673331", "GSM1673332", "GSM1673333", "GSM1673334", "GSM1673335", "GSM1673336", "GSM1673337", "GSM1673338", "GSM1673339", "GSM1673340", "GSM1673341", "GSM1673342", "GSM1673343", "GSM1673344", "GSM1673345", "GSM1673346", "GSM1673347", "GSM1673348", "GSM1673349", "GSM1673350"], "sample_count": 390, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "caArray_notte-00422: Molecular Dissection of Colon Cancer", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:28794688:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:86dd0e6df7c6ccb743d544b7d32fc43df8d3c00f1683a1cc096027b8d91f506b", "bytes": 1018, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Tab4", "version": null, "note": "Validation of the hub genes in TCGA database", "structure": {"pmcid": "PMC5545832", "section_index": 7, "section_title": "Validation of the hub genes in TCGA database", "row_count": 13, "column_count": 6}, "table": {"label": "Table 4", "caption": "Validation of the hub genes in TCGA database", "rows": [["Category", "Hub gene", "Methylation status", "P value", "Expression status", "P value"], ["Hypomethylation and high expression"], ["", "CAD", "Hypomethylation", "5.55E−16", "Up-regulated", "3.88E−18"], ["", "CCND1", "Hypomethylation", "0.032", "Up-regulated", "7.26E−17"], ["", "ATM", "–", "–", "Up-regulated", "0.006"], ["", "RB1", "Hypomethylation", "5.27E−03", "Up-regulated", "1.17E−11"], ["", "DNM2", "Hypomethylation", "1.36E−13", "Up-regulated", "5.23E−08"], ["Hypermethylation and low expression"], ["", "EGFR", "Hypermethylation", "4.65E−14", "Down-regulated", "7.20E−21"], ["", "ACTA1", "Hypermethylation", "1.64E−14", "–", "–"], ["", "SST", "Hypermethylation", "9.67E−14", "Down-regulated", "2.22E−31"], ["", "ESR1", "Hypermethylation", "1.18E−14", "Down-regulated", "9.62E−20"], ["", "DNM2", "Hypermethylation", "5.43E−06", "–", "–"]], "row_count": 13, "column_count": 6, "numeric_cells": 17, "header_rows": 1, "locator": "section[13]/table-wrap[1]#Tab4"}}, {"id": "asset:table:pmid:28794688:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e9ce39be650543542573ec1eb52551d43fc30d1ceb65a822887d3f914000d699", "bytes": 2865, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#Tab1", "version": null, "note": "Gene ontology analysis of aberrantly methylated-differentially expressed genes in colorectal cancer", "structure": {"pmcid": "PMC5545832", "section_index": 10, "section_title": "GO functional enrichment analysis", "row_count": 33, "column_count": 6}, "table": {"label": "Table 1", "caption": "Gene ontology analysis of aberrantly methylated-differentially expressed genes in colorectal cancer", "rows": [["Category", "GO analysis", "Term", "Gene count", "%", "P value"], ["Hypomethylation and high expression"], ["", "GOTERM_BP_FAT", "GO:0009611~response to wounding", "37", "9.00", "9.44E−08"], ["", "GOTERM_BP_FAT", "GO:0006954~inflammatory response", "25", "6.08", "3.48E−06"], ["", "GOTERM_BP_FAT", "GO:0008283~cell proliferation", "29", "7.06", "7.95E−06"], ["", "GOTERM_BP_FAT", "GO:0007155~cell adhesion", "37", "9.00", "5.54E−05"], ["", "GOTERM_BP_FAT", "GO:0022610~biological adhesion", "37", "9.00", "5.55E−05"], ["", "GOTERM_CC_FAT", "GO:0005576~extracellular region", "92", "22.38", "2.01E−08"], ["", "GOTERM_CC_FAT", "GO:0044421~extracellular region part", "55", "13.38", "3.78E−08"], ["", "GOTERM_CC_FAT", "GO:0005615~extracellular space", "42", "10.22", "4.12E−07"], ["", "GOTERM_CC_FAT", "GO:0005578~proteinaceous extracellular matrix", "21", "5.11", "2.45E−04"], ["", "GOTERM_CC_FAT", "GO:0005625~soluble fraction", "20", "4.87", "5.01E−04"], ["", "GOTERM_MF_FAT", "GO:0042802~identical protein binding", "35", "8.52", "8.25E−05"], ["", "GOTERM_MF_FAT", "GO:0005125~cytokine activity", "15", "3.65", "6.69E−04"], ["", "GOTERM_MF_FAT", "GO:0004175~endopeptidase activity", "21", "5.11", "2.33E−03"], ["", "GOTERM_MF_FAT", "GO:0030674~protein binding, bridging", "9", "2.19", "3.39E−03"], ["", "GOTERM_MF_FAT", "GO:0008201~heparin binding", "9", "2.19", "5.90E−03"], ["Hypermethylation and low expression"], ["", "GOTERM_BP_FAT", "GO:0007267~cell–cell signaling", "29", "12.13", "3.32E−07"], ["", "GOTERM_BP_FAT", "GO:0019226~transmission of nerve impulse", "18", "7.53", "4.70E−05"], ["", "GOTERM_BP_FAT", "GO:0031644~regulation of neurological system process", "11", "4.60", "1.72E−04"], ["", "GOTERM_BP_FAT", "GO:0007610~behavior", "20", "8.37", "1.90E−04"], ["", "GOTERM_BP_FAT", "GO:0030182~neuron differentiation", "19", "7.95", "2.35E−04"], ["", "GOTERM_CC_FAT", "GO:0044459~plasma membrane part", "64", "26.78", "2.13E−09"], ["", "GOTERM_CC_FAT", "GO:0005886~plasma membrane", "84", "35.15", "5.38E−07"], ["", "GOTERM_CC_FAT", "GO:0043005~neuron projection", "19", "7.95", "1.13E−06"], ["", "GOTERM_CC_FAT", "GO:0005887~integral to plasma membrane", "38", "15.90", "1.67E−06"], ["", "GOTERM_CC_FAT", "GO:0031226~intrinsic to plasma membrane", "38", "15.90", "2.85E−06"], ["", "GOTERM_MF_FAT", "GO:0003700~transcription factor activity", "38", "15.90", "2.48E−07"], ["", "GOTERM_MF_FAT", "GO:0022836~gated channel activity", "16", "6.69", "9.15E−05"], ["", "GOTERM_MF_FAT", "GO:0015267~channel activity", "18", "7.53", "2.17E−04"], ["", "GOTERM_MF_FAT", "GO:0022803~passive transmembrane transporter activity", "18", "7.53", "2.23E−04"], ["", "GOTERM_MF_FAT", "GO:0005216~ion channel activity", "17", "7.11", "3.17E−04"]], "row_count": 33, "column_count": 6, "numeric_cells": 120, "header_rows": 1, "locator": "section[10]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:28794688:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:cd134a2b3300a6669fcb41788f2ac574d8f1dcaff21265aeed3f2ed877bda71a", "bytes": 1615, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#Tab2", "version": null, "note": "KEGG pathway analysis of aberrantly methylated-differentially expressed genes in colorectal cancer", "structure": {"pmcid": "PMC5545832", "section_index": 10, "section_title": "GO functional enrichment analysis", "row_count": 12, "column_count": 6}, "table": {"label": "Table 2", "caption": "KEGG pathway analysis of aberrantly methylated-differentially expressed genes in colorectal cancer", "rows": [["Pathway ID", "Pathway name", "Gene no.", "%", "P value", "Genes"], ["Hypomethylation and high expression"], ["hsa04060", "Cytokine–cytokine receptor interaction", "20", "4.87", "5.86E−04", "CXCL1, IL2RA, LTBR, CXCL3, IL21R, CXCL2, MET, CXCL9, TNFSF15, TNFRSF4, CCL18, LIF, INHBA, TNFRSF9, TNFSF11, IL23A, PRLR, CCL20, IL20RA, ACVR1"], ["hsa04115", "p53 signaling pathway", "8", "1.95", "5.54E−03", "CCND1, SERPINB5, CD82, RRM2, TSC2, CASP8, PMAIP1, ATM"], ["hsa04110", "Cell cycle", "9", "2.19", "0.045", "CCND1, PKMYT1, PRKDC, RB1, CDC16, CDC27, ATM, WEE1, TFDP1"], ["Hypermethylation and low expression"], ["hsa04020", "Calcium signaling pathway", "12", "5.02", "7.80E−04", "EGFR, EDNRB, ADCY2, PTGER3, PDE1B, PDE1C, DRD5, GRIN2A, PLCD1, ITPKB, CAMK2B, PTGFR"], ["hsa04950", "Maturity onset diabetes of the young", "5", "2.09", "1.45E−03", "HHEX, NEUROD1, HNF4G, NEUROG3, NKX2-2"], ["hsa04514", "Cell adhesion molecules (CAMs)", "8", "3.35", "0.017", "NCAM1, CD8A, ITGA8, NLGN4X, CNTN1, ITGA4, JAM2, HLA-G"], ["hsa04080", "Neuroactive ligand-receptor interaction", "11", "4.60", "0.033", "EDNRB, SSTR2, PTGER3, GABRB3, GRIK1, GRIK2, DRD5, GRIN2A, GRIA3, PTGFR, VIPR2"], ["hsa04062", "Chemokine signaling pathway", "9", "3.77", "0.035", "DOCK2, ADCY2, CXCL14, TIAM1, HCK, PIK3CD, CCR10, RAP1A, ELMO1"], ["hsa04666", "Fc gamma R-mediated phagocytosis", "6", "2.51", "0.043", "DOCK2, HCK, PIK3CD, ARF6, AMPH, DNM2"]], "row_count": 12, "column_count": 6, "numeric_cells": 42, "header_rows": 1, "locator": "section[10]/table-wrap[2]#Tab2"}}, {"id": "asset:table:pmid:28794688:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:bb4cd6a79a63adf8db5840c4ee91f6ce0e840cc81f2859c31a9761e79993bd21", "bytes": 1330, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#Tab3", "version": null, "note": "Module analysis of the protein–protein interaction network", "structure": {"pmcid": "PMC5545832", "section_index": 12, "section_title": "PPI network construction, module analysis and hub gene selection", "row_count": 13, "column_count": 6}, "table": {"label": "Table 3", "caption": "Module analysis of the protein–protein interaction network", "rows": [["Category", "Module", "Function description", "FDR", "Nodes", "Genes"], ["Hypomethylation and high expression"], ["", "1", "Chemokine signaling pathway", "1.14E−10", "6", "CCL18, CXCL2, CXCL1, CCL20, CXCL9, CXCL3"], ["", "2", "Ribosome", "6.80E−04", "5", "RPL31, PABPC1, UPF3A, RPS15A, RPS15"], ["", "3", "Nucleic acid binding", "0.0195", "9", "DDX49, AHR, GSTP1, RB1, AATF, DDX56, NOC2L, IMP4, DDX52"], ["", "4", "Carbon metabolism", "3.43E−04", "5", "GNPDA1, PFKM, ENO1, ME1, HK3"], ["", "5", "Cell cycle", "3.01E−10", "8", "CDC16, PKMYT1, CDC27, TFDP1, SMARCAL1, ATM, RECQL5, WEE1"], ["", "6", "Proteasome", "0.0344", "8", "FGFR1, SOX9, PSMD6, FOXD1, CCND1, MSX1, PSMF1, FOXA2"], ["Hypermethylation and low expression"], ["", "1", "Synaptic transmission", "1.04E−07", "7", "KCND3, KCNG1, KCNB1, HCN2, KCNK3, KCNA5, KCNA3"], ["", "2", "Gastric acid secretion", "2.19E−04", "6", "SST, NPY, SSTR2, CCR10, PTGER3, ADCY2"], ["", "3", "Glutamatergic synapse", "1.09E−06", "5", "GRIK1, GRIK2, GRIA3, GRIN2A, CAMK2B"], ["", "4", "Cell fate specification", "9.20E−03", "15", "ARHGEF16, RHOH, TIAM1, ABR, RAP1A, NEUROD1, AR, ESR1, EGFR, TF, FEV, INPP5B, SOX17, FGD2, NKX2-2"]], "row_count": 13, "column_count": 6, "numeric_cells": 36, "header_rows": 1, "locator": "section[12]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:28794688:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:86dd0e6df7c6ccb743d544b7d32fc43df8d3c00f1683a1cc096027b8d91f506b", "bytes": 1018, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Tab4", "version": null, "note": "Validation of the hub genes in TCGA database", "structure": {"pmcid": "PMC5545832", "section_index": 13, "section_title": "Validation of the hub genes in TCGA database", "row_count": 13, "column_count": 6}, "table": {"label": "Table 4", "caption": "Validation of the hub genes in TCGA database", "rows": [["Category", "Hub gene", "Methylation status", "P value", "Expression status", "P value"], ["Hypomethylation and high expression"], ["", "CAD", "Hypomethylation", "5.55E−16", "Up-regulated", "3.88E−18"], ["", "CCND1", "Hypomethylation", "0.032", "Up-regulated", "7.26E−17"], ["", "ATM", "–", "–", "Up-regulated", "0.006"], ["", "RB1", "Hypomethylation", "5.27E−03", "Up-regulated", "1.17E−11"], ["", "DNM2", "Hypomethylation", "1.36E−13", "Up-regulated", "5.23E−08"], ["Hypermethylation and low expression"], ["", "EGFR", "Hypermethylation", "4.65E−14", "Down-regulated", "7.20E−21"], ["", "ACTA1", "Hypermethylation", "1.64E−14", "–", "–"], ["", "SST", "Hypermethylation", "9.67E−14", "Down-regulated", "2.22E−31"], ["", "ESR1", "Hypermethylation", "1.18E−14", "Down-regulated", "9.62E−20"], ["", "DNM2", "Hypermethylation", "5.43E−06", "–", "–"]], "row_count": 13, "column_count": 6, "numeric_cells": 17, "header_rows": 1, "locator": "section[13]/table-wrap[1]#Tab4"}}], "gaps": ["asset:data:geo:GSE17648 not downloaded", "asset:data:geo:GSE17648 licence not read", "asset:data:geo:GSE29490 not downloaded", "asset:data:geo:GSE29490 licence not read", "asset:data:geo:GSE44076 not downloaded", "asset:data:geo:GSE44076 licence not read", "asset:data:geo:GSE68468 not downloaded", "asset:data:geo:GSE68468 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": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "Pathway enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "GEO2R differential expression and differential methylation analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We used GEO2R online software to analysis the raw submitter-supplied data of microarrays and identify DEGs and DMGs."}}], "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": ["GSE68468", "GSE44076", "GSE29490", "GSE17648"], "resolved_accessions": ["GSE68468", "GSE44076", "GSE29490", "GSE17648"], "statements": ["The authors declare that the data supporting the findings of this study are available within the article."], "basis": "The paper names GSE68468, GSE44076, GSE29490, GSE17648 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:28794688", "data:geo:GSE17648", "asset:table:pmid:28794688:1", "asset:table:pmid:28794688:2", "asset:table:pmid:28794688:3", "asset:table:pmid:28794688:4", "asset:table:pmid:28794688:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE17648"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": null, "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "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:28794688", "type": "paper", "label": "pmid:28794688"}, {"id": "source:pmid:28794688", "type": "manuscript", "label": "PMID 28794688 full text"}, {"id": "data:geo:GSE17648", "type": "dataset", "label": "GEO GSE17648"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28794688", "type": "paper", "label": "pmid:28794688"}, {"id": "source:pmid:28794688", "type": "manuscript", "label": "PMID 28794688 full text"}, {"id": "data:geo:GSE17648", "type": "dataset", "label": "GEO GSE17648"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28794688", "type": "extraction", "used": ["source:pmid:28794688"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE17648", "type": "accession_resolution", "used": ["data:geo:GSE17648"], "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:28794688", "parent_hash": "sha256:373e0016da7108a9c342ed88f88af4c6b521553328b0b6c16aa6656f92fcdc0b", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE17648 licence not read", "asset:data:geo:GSE17648 not downloaded", "asset:data:geo:GSE29490 licence not read", "asset:data:geo:GSE29490 not downloaded", "asset:data:geo:GSE44076 licence not read", "asset:data:geo:GSE44076 not downloaded", "asset:data:geo:GSE68468 licence not read", "asset:data:geo:GSE68468 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":"2026-11-04T02:38:18+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}}}