{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36817436", "kind": "science-record", "revision": 4, "content_hash": "sha256:84fba13ac7161faa3beefbbae69e3205c9716e1ea8bcae8dbc434fef48306745", "created_at": "2026-11-01T19:01:24Z", "updated_at": "2026-11-01T22:51:18Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Comprehensive analysis to identify the influences of SARS-CoV-2 infections to inflammatory bowel disease.", "doi": "10.3389/fimmu.2023.1024041", "pmid": "36817436", "authors": ["Chengyan Zhang", "Zeyu Ma", "Xi Nan", "Wenhui Wang", "Xianchang Zeng", "Jinming Chen", "Zhijian Cai", "Jianli Wang"], "journal": "Frontiers in immunology", "year": 2023, "abstract": "Background: Coronavirus disease 2019 (COVID-19) and inflammatory bowel disease (IBD) are both caused by a disordered immune response and have direct and profound impacts on health care services. In this study, we implemented transcriptomic and single-cell analysis to detect common molecular and cellular intersections between COVID-19 and IBD that help understand the linkage of COVID-19 to the IBD patients.\nMethods: Four RNA-sequencing datasets (GSE147507, GSE126124, GSE9686 and GSE36807) from Gene Expression Omnibus (GEO) database are extracted to detect mutual differentially expressed genes (DEGs) for IBD patients with the infection of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) to find shared pathways, candidate drugs, hub genes and regulatory networks. Two single-cell RNA sequencing (scRNA-eq) datasets (GSE150728, PRJCA003980) are used to analyze the immune characteristics of hub genes and the proportion of immune cell types, so as to find common immune responses between COVID-19 and IBD.\nResults: A total of 121 common DEGs were identified among four RNA-seq datasets, and were all involved in the functional enrichment analysis related to inflammation and immune response. Transcription factors-DEGs interactions, miRNAs-DEGs coregulatory networks, and protein-drug interactions were identified based on these datasets. Protein-protein interactions (PPIs) was built and 59 hub genes were identified. Moreover, scRNA-seq of peripheral blood monocyte cells (PBMCs) from COVID-19 patients revealed a significant increase in the proportion of CD14+ monocytes, in which 38 of 59 hub genes were highly enriched. These genes, encoding inflammatory cytokines, were also highly expressed in inflammatory macrophages (IMacrophage) of intestinal tissues of IBD patients.\nConclusions: We conclude that COVID-19 may promote the progression of IBD through cytokine storms. The candidate drugs and DEGs-regulated networks may suggest effective therapeutic methods for both COVID-19 and IBD.", "claims": [{"id": "claim-method", "statement": "To acquire DEGs for the datasets GSE147507 and GSE126124, the “limma” package (21) was employed to select DEGs with |log2FC | > 0.585 (22) and p-value < 0.05 (23).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36817436", "locator": "sections[4] \"Identification of DEGs and the common DEGs among COVID-19 and IBD\" paragraph 2", "quote": "To acquire DEGs for the datasets GSE147507 and GSE126124, the “limma” package (21) was employed to select DEGs with |log2FC | > 0.585 (22) and p-value < 0.05 (23)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36817436", "locator": "sections[21] \"Data availability statement\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material ."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The integrated analysis identified 121 differentially expressed genes shared by COVID-19, Crohn's disease, and ulcerative colitis.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:36817436", "locator": "sections[12] \"Identification of the common DEGs between COVID-19 and IBD\" paragraph 2", "quote": "We identified 121 common DEGs between these datasets through a Venn diagram ( Figure 2 and Supplementary Table S1 )."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The integrated analysis identified 121 differentially expressed genes shared by COVID-19, Crohn's disease, and ulcerative colitis.", "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:36817436"], "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:GSE126124"], "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:GSE126124"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36817436", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fimmu.2023.1024041", "sha256": "sha256:b11e4805a6fceac4510e56cfc8f517d191a530e8d2ac1331c2f930c737535d0b", "bytes": 53772, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fimmu.2023.1024041", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9936160", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE126124", "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=GSE126124", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE126124", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3591886", "GSM3591887", "GSM3591888", "GSM3591889", "GSM3591890", "GSM3591891", "GSM3591892", "GSM3591893", "GSM3591894", "GSM3591895", "GSM3591896", "GSM3591897", "GSM3591898", "GSM3591899", "GSM3591900", "GSM3591901", "GSM3591902", "GSM3591903", "GSM3591904", "GSM3591905", "GSM3591906", "GSM3591907", "GSM3591908", "GSM3591909", "GSM3591910", "GSM3591911", "GSM3591912", "GSM3591913", "GSM3591914", "GSM3591915", "GSM3591916", "GSM3591917", "GSM3591918", "GSM3591919", "GSM3591920", "GSM3591921", "GSM3591922", "GSM3591923", "GSM3591924", "GSM3591925", "GSM3591926", "GSM3591927", "GSM3591928", "GSM3591929", "GSM3591930", "GSM3591931", "GSM3591932", "GSM3591933", "GSM3591934", "GSM3591935", "GSM3591936", "GSM3591937", "GSM3591938", "GSM3591939", "GSM3591940", "GSM3591941", "GSM3591942", "GSM3591943", "GSM3591944", "GSM3591945", "GSM3591946", "GSM3591947", "GSM3591948", "GSM3591949", "GSM3591950", "GSM3591951", "GSM3591952", "GSM3591953", "GSM3591954", "GSM3591955", "GSM3591956", "GSM3591957", "GSM3591958", "GSM3591959", "GSM3591960", "GSM3591961", "GSM3591962", "GSM3591963", "GSM3591964", "GSM3591965", "GSM3591966", "GSM3591967", "GSM3591968", "GSM3591969", "GSM3591970", "GSM3591971", "GSM3591972", "GSM3591973", "GSM3591974", "GSM3591975", "GSM3591976", "GSM3591977", "GSM3591978", "GSM3591979", "GSM3591980", "GSM3591981", "GSM3591982", "GSM3591983", "GSM3591984", "GSM3591985", "GSM3591986", "GSM3591987", "GSM3591988", "GSM3591989", "GSM3591990", "GSM3591991", "GSM3591992", "GSM3591993", "GSM3591994", "GSM3591995", "GSM3591996", "GSM3591997", "GSM3591998", "GSM3591999", "GSM3592000", "GSM3592001", "GSM3592002", "GSM3592003", "GSM3592004", "GSM3592005", "GSM3592006", "GSM3592007", "GSM3592008", "GSM3592009", "GSM3592010", "GSM3592011", "GSM3592012", "GSM3592013", "GSM3592014", "GSM3592015", "GSM3592016", "GSM3592017", "GSM3592018", "GSM3592019", "GSM3592020", "GSM3592021", "GSM3592022", "GSM3592023", "GSM3592024", "GSM3592025", "GSM3592026", "GSM3592027", "GSM3592028", "GSM3592029", "GSM3592030", "GSM3592031", "GSM3592032", "GSM3592033", "GSM3592034", "GSM3592035", "GSM3592036", "GSM3592037", "GSM3592038", "GSM3592039", "GSM3592040", "GSM3592041", "GSM3592042", "GSM3592043", "GSM3592044", "GSM3592045", "GSM3592046", "GSM3592047", "GSM3592048", "GSM3592049", "GSM3592050", "GSM3592051", "GSM3592052", "GSM3592053", "GSM3592054", "GSM3592055", "GSM3592056", "GSM3592057", "GSM3592058", "GSM3592059", "GSM3592060", "GSM3592061"], "sample_count": 176, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Concordance between gene expression in peripheral whole blood and colonic tissue in children with inflammatory bowel disease.", "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:GSE147507", "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=GSE147507", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE147507", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4432378", "GSM4432379", "GSM4432380", "GSM4432381", "GSM4432382", "GSM4432383", "GSM4432384", "GSM4432385", "GSM4432386", "GSM4432387", "GSM4432388", "GSM4432389", "GSM4432390", "GSM4432391", "GSM4432392", "GSM4432393", "GSM4432394", "GSM4432395", "GSM4432396", "GSM4432397", "GSM4462336", "GSM4462337", "GSM4462338", "GSM4462339", "GSM4462340", "GSM4462341", "GSM4462342", "GSM4462343", "GSM4462344", "GSM4462345", "GSM4462346", "GSM4462347", "GSM4462348", "GSM4462349", "GSM4462350", "GSM4462351", "GSM4462352", "GSM4462353", "GSM4462354", "GSM4462355", "GSM4462356", "GSM4462357", "GSM4462358", "GSM4462359", "GSM4462360", "GSM4462361", "GSM4462362", "GSM4462363", "GSM4462364", "GSM4462365", "GSM4462366", "GSM4462367", "GSM4462368", "GSM4462369", "GSM4462370", "GSM4462371", "GSM4462372", "GSM4462373", "GSM4462374", "GSM4462375", "GSM4462376", "GSM4462377", "GSM4462378", "GSM4462379", "GSM4462380", "GSM4462381", "GSM4462382", "GSM4462383", "GSM4462384", "GSM4462385", "GSM4462386", "GSM4462387", "GSM4462388", "GSM4462389", "GSM4462390", "GSM4462391", "GSM4462392", "GSM4462393", "GSM4462394", "GSM4462395", "GSM4462396", "GSM4462397", "GSM4462398", "GSM4462399", "GSM4462400", "GSM4462401", "GSM4462402", "GSM4462403", "GSM4462404", "GSM4462405", "GSM4462406", "GSM4462407", "GSM4462408", "GSM4462409", "GSM4462410", "GSM4462411", "GSM4462412", "GSM4462413", "GSM4462414", "GSM4462415", "GSM4462416", "GSM4486157", "GSM4486158", "GSM4486159", "GSM4486160", "GSM4486161", "GSM4486162", "GSM4486163", "GSM4486164", "GSM4486165"], "sample_count": 110, "group_sizes": null, "group_sizes_basis": null, "platform": "18573;28369", "taxon": "Mustela putorius furo; Homo sapiens", "title": "Transcriptional response to SARS-CoV-2 infection", "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:GSE150728", "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=GSE150728", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE150728", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4557327", "GSM4557328", "GSM4557329", "GSM4557330", "GSM4557331", "GSM4557332", "GSM4557333", "GSM4557334", "GSM4557335", "GSM4557336", "GSM4557337", "GSM4557338", "GSM4557339"], "sample_count": 13, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "A single-cell atlas of the peripheral immune response to severe COVID-19", "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:GSE157103", "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=GSE157103", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE157103", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4753021", "GSM4753022", "GSM4753023", "GSM4753024", "GSM4753025", "GSM4753026", "GSM4753027", "GSM4753028", "GSM4753029", "GSM4753030", "GSM4753031", "GSM4753032", "GSM4753033", "GSM4753034", "GSM4753035", "GSM4753036", "GSM4753037", "GSM4753038", "GSM4753039", "GSM4753040", "GSM4753041", "GSM4753042", "GSM4753043", "GSM4753044", "GSM4753045", "GSM4753046", "GSM4753047", "GSM4753048", "GSM4753049", "GSM4753050", "GSM4753051", "GSM4753052", "GSM4753053", "GSM4753054", "GSM4753055", "GSM4753056", "GSM4753057", "GSM4753058", "GSM4753059", "GSM4753060", "GSM4753061", "GSM4753062", "GSM4753063", "GSM4753064", "GSM4753065", "GSM4753066", "GSM4753067", "GSM4753068", "GSM4753069", "GSM4753070", "GSM4753071", "GSM4753072", "GSM4753073", "GSM4753074", "GSM4753075", "GSM4753076", "GSM4753077", "GSM4753078", "GSM4753079", "GSM4753080", "GSM4753081", "GSM4753082", "GSM4753083", "GSM4753084", "GSM4753085", "GSM4753086", "GSM4753087", "GSM4753088", "GSM4753089", "GSM4753090", "GSM4753091", "GSM4753092", "GSM4753093", "GSM4753094", "GSM4753095", "GSM4753096", "GSM4753097", "GSM4753098", "GSM4753099", "GSM4753100", "GSM4753101", "GSM4753102", "GSM4753103", "GSM4753104", "GSM4753105", "GSM4753106", "GSM4753107", "GSM4753108", "GSM4753109", "GSM4753110", "GSM4753111", "GSM4753112", "GSM4753113", "GSM4753114", "GSM4753115", "GSM4753116", "GSM4753117", "GSM4753118", "GSM4753119", "GSM4753120", "GSM4753121", "GSM4753122", "GSM4753123", "GSM4753124", "GSM4753125", "GSM4753126", "GSM4753127", "GSM4753128", "GSM4753129", "GSM4753130", "GSM4753131", "GSM4753132", "GSM4753133", "GSM4753134", "GSM4753135", "GSM4753136", "GSM4753137", "GSM4753138", "GSM4753139", "GSM4753140", "GSM4753141", "GSM4753142", "GSM4753143", "GSM4753144", "GSM4753145", "GSM4753146"], "sample_count": 126, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "Large-scale Multi-omic Analysis of COVID-19 Severity", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE16879", "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=GSE16879", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE16879", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM364627", "GSM364628", "GSM364629", "GSM364630", "GSM364631", "GSM364632", "GSM364633", "GSM364634", "GSM364635", "GSM364636", "GSM364637", "GSM364638", "GSM364639", "GSM364640", "GSM364641", "GSM364642", "GSM364643", "GSM364644", "GSM364645", "GSM364646", "GSM364647", "GSM364648", "GSM364649", "GSM364650", "GSM364651", "GSM364652", "GSM364653", "GSM364654", "GSM364655", "GSM364656", "GSM422963", "GSM422965", "GSM422967", "GSM422969", "GSM422971", "GSM422973", "GSM422975", "GSM422977", "GSM422979", "GSM422981", "GSM422983", "GSM422985", "GSM422987", "GSM422989", "GSM422991", "GSM422993", "GSM422995", "GSM422997", "GSM422999", "GSM423001", "GSM423003", "GSM423005", "GSM423007", "GSM423009", "GSM423010", "GSM423011", "GSM423012", "GSM423013", "GSM423014", "GSM423015", "GSM423016", "GSM423017", "GSM423018", "GSM423019", "GSM423020", "GSM423021", "GSM423022", "GSM423023", "GSM423024", "GSM423025", "GSM423026", "GSM423027", "GSM423028", "GSM423029", "GSM423030", "GSM423031", "GSM423032", "GSM423033", "GSM423034", "GSM423035", "GSM423036", "GSM423037", "GSM423038", "GSM423039", "GSM423040", "GSM423041", "GSM423042", "GSM423043", "GSM423044", "GSM423045", "GSM423046", "GSM423047", "GSM423048", "GSM423049", "GSM423050", "GSM423051", "GSM423052", "GSM423053", "GSM423054", "GSM423055", "GSM423056", "GSM423057", "GSM423058", "GSM423059", "GSM423060", "GSM423061", "GSM423062", "GSM423063", "GSM423064", "GSM423065", "GSM423066", "GSM423067", "GSM423068", "GSM423069", "GSM423070", "GSM423071", "GSM423072", "GSM423073", "GSM423074", "GSM423075", "GSM423076", "GSM423077", "GSM423078", "GSM423079", "GSM423080", "GSM423081", "GSM423082", "GSM423083", "GSM423084", "GSM423085", "GSM423086", "GSM423087", "GSM423088"], "sample_count": 133, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Mucosal expression profiling in patients with inflammatory bowel disease before and after first infliximab treatment", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE36807", "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=GSE36807", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE36807", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM901319", "GSM901320", "GSM901321", "GSM901322", "GSM901323", "GSM901324", "GSM901325", "GSM901326", "GSM901327", "GSM901328", "GSM901329", "GSM901330", "GSM901331", "GSM901332", "GSM901333", "GSM901334", "GSM901335", "GSM901336", "GSM901337", "GSM901338", "GSM901339", "GSM901340", "GSM901341", "GSM901342", "GSM901343", "GSM901344", "GSM901345", "GSM901346", "GSM901347", "GSM901348", "GSM901349", "GSM901350", "GSM901351", "GSM901352", "GSM901353"], "sample_count": 35, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Genome-wide analysis of Crohn's disease and ulcerative colitis biopsy samples.", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE75214", "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=GSE75214", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE75214", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1426071", "GSM1426072", "GSM1426073", "GSM1426074", "GSM1426075", "GSM1426076", "GSM1426077", "GSM1426078", "GSM1426079", "GSM1426080", "GSM1426081", "GSM1426082", "GSM1426083", "GSM1426084", "GSM1426085", "GSM1426086", "GSM1426087", "GSM1426088", "GSM1426089", "GSM1426090", "GSM1426091", "GSM1426092", "GSM1426093", "GSM1426094", "GSM1426095", "GSM1426096", "GSM1426097", "GSM1426098", "GSM1426099", "GSM1426100", "GSM1426101", "GSM1426102", "GSM1426103", "GSM1426104", "GSM1426105", "GSM1426106", "GSM1426107", "GSM1426108", "GSM1426109", "GSM1426110", "GSM1426111", "GSM1426112", "GSM1426113", "GSM1426114", "GSM1426115", "GSM1426116", "GSM1426117", "GSM1426118", "GSM1426119", "GSM1426120", "GSM1426121", "GSM1426122", "GSM1426123", "GSM1426124", "GSM1426125", "GSM1426126", "GSM1426127", "GSM1426128", "GSM1426129", "GSM1426130", "GSM1426131", "GSM1426132", "GSM1426133", "GSM1426134", "GSM1426135", "GSM1426136", "GSM1426137", "GSM1426138", "GSM1426139", "GSM1426140", "GSM1426141", "GSM1426142", "GSM1426143", "GSM1426144", "GSM1426145", "GSM1426146", "GSM1426147", "GSM1426148", "GSM1426149", "GSM1426150", "GSM1426151", "GSM1426152", "GSM1426153", "GSM1426154", "GSM1426155", "GSM1426156", "GSM1426157", "GSM1426158", "GSM1426159", "GSM1426160", "GSM1426161", "GSM1426162", "GSM1426163", "GSM1426164", "GSM1426165", "GSM1426166", "GSM1426167", "GSM1426168", "GSM1426169", "GSM1426170", "GSM1426171", "GSM1426172", "GSM1426173", "GSM1426174", "GSM1426175", "GSM1426176", "GSM1426177", "GSM1426178", "GSM1426179", "GSM1426180", "GSM1426181", "GSM1426182", "GSM1426183", "GSM1426184", "GSM1426185", "GSM1426186", "GSM1945759", "GSM1945760", "GSM1945761", "GSM1945762", "GSM1945763", "GSM1945764", "GSM1945765", "GSM1945766", "GSM1945767", "GSM1945768", "GSM1945769", "GSM1945770", "GSM1945771", "GSM1945772", "GSM1945773", "GSM1945774", "GSM1945775", "GSM1945776", "GSM1945777", "GSM1945778", "GSM1945779", "GSM1945780", "GSM1945781", "GSM1945782", "GSM1945783", "GSM1945784", "GSM1945785", "GSM1945786", "GSM1945787", "GSM1945788", "GSM1945789", "GSM1945790", "GSM1945791", "GSM1945792", "GSM1945793", "GSM1945794", "GSM1945795", "GSM1945796", "GSM1945797", "GSM1945798", "GSM1945799", "GSM1945800", "GSM1945801", "GSM1945802", "GSM1945803", "GSM1945804", "GSM1945805", "GSM1945806", "GSM1945807", "GSM1945808", "GSM1945809", "GSM1945810", "GSM1945811", "GSM1945812", "GSM1945813", "GSM1945814", "GSM1945815", "GSM1945816", "GSM1945817", "GSM1945818", "GSM1945819", "GSM1945820", "GSM1945821", "GSM1945822", "GSM1945823", "GSM1945824", "GSM1945825", "GSM1945826", "GSM1945827", "GSM1945828", "GSM1945829", "GSM1945830", "GSM1945831", "GSM1945832", "GSM1945833", "GSM1945834", "GSM1945835", "GSM1945836"], "sample_count": 194, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Mucosal gene expression profiling in patients with inflammatory bowel disease study", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE9686", "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=GSE9686", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE9686", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM244745", "GSM244746", "GSM244747", "GSM244748", "GSM244749", "GSM244750", "GSM244751", "GSM244752", "GSM244753", "GSM244754", "GSM244755", "GSM244756", "GSM244757", "GSM244758", "GSM244759", "GSM244760", "GSM244761", "GSM244762", "GSM244763", "GSM244764", "GSM244765", "GSM244766", "GSM244767", "GSM244768", "GSM244769", "GSM244770", "GSM244771", "GSM244772", "GSM244773", "GSM244774", "GSM244775", "GSM244776", "GSM244777"], "sample_count": 33, "group_sizes": null, "group_sizes_basis": null, "platform": "5760", "taxon": "Homo sapiens", "title": "Human colon expression in healthy, CD, treated CD, and UC", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE126124 not downloaded", "asset:data:geo:GSE126124 licence not read", "asset:data:geo:GSE147507 not downloaded", "asset:data:geo:GSE147507 licence not read", "asset:data:geo:GSE150728 not downloaded", "asset:data:geo:GSE150728 licence not read", "asset:data:geo:GSE157103 not downloaded", "asset:data:geo:GSE157103 licence not read", "asset:data:geo:GSE16879 not downloaded", "asset:data:geo:GSE16879 licence not read", "asset:data:geo:GSE36807 not downloaded", "asset:data:geo:GSE36807 licence not read", "asset:data:geo:GSE75214 not downloaded", "asset:data:geo:GSE75214 licence not read", "asset:data:geo:GSE9686 not downloaded", "asset:data:geo:GSE9686 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To acquire DEGs for the datasets GSE147507 and GSE126124, the “limma” package (21) was employed to select DEGs with |log2FC | > 0.585 (22) and p-value < 0.05 (23)."}}, {"id": "method-2", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "PPI"}}, {"id": "method-3", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE147507", "GSE126124", "GSE9686", "GSE36807", "GSE157103", "GSE75214", "GSE150728", "GSE16879"], "resolved_accessions": ["GSE147507", "GSE126124", "GSE9686", "GSE36807", "GSE157103", "GSE75214", "GSE150728", "GSE16879"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/ Supplementary Material ."], "basis": "The paper names GSE147507, GSE126124, GSE9686, GSE36807, GSE157103, GSE75214, GSE150728, GSE16879 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:36817436", "data:geo:GSE126124"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE126124"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:28:08Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 16022, "completion_tokens": 2590, "cached_tokens": 128}}, "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:36817436", "type": "paper", "label": "pmid:36817436"}, {"id": "source:pmid:36817436", "type": "manuscript", "label": "PMID 36817436 full text"}, {"id": "data:geo:GSE126124", "type": "dataset", "label": "GEO GSE126124"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36817436", "type": "paper", "label": "pmid:36817436"}, {"id": "source:pmid:36817436", "type": "manuscript", "label": "PMID 36817436 full text"}, {"id": "data:geo:GSE126124", "type": "dataset", "label": "GEO GSE126124"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36817436", "type": "extraction", "used": ["source:pmid:36817436"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE126124", "type": "accession_resolution", "used": ["data:geo:GSE126124"], "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:36817436", "parent_hash": "sha256:eceeb0e7041aae5f8caec64b45b2f7045ef6ccb6deb3a433c3b0bc1c54a41c09", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE126124 licence not read", "asset:data:geo:GSE126124 not downloaded", "asset:data:geo:GSE147507 licence not read", "asset:data:geo:GSE147507 not downloaded", "asset:data:geo:GSE150728 licence not read", "asset:data:geo:GSE150728 not downloaded", "asset:data:geo:GSE157103 licence not read", "asset:data:geo:GSE157103 not downloaded", "asset:data:geo:GSE16879 licence not read", "asset:data:geo:GSE16879 not downloaded", "asset:data:geo:GSE36807 licence not read", "asset:data:geo:GSE36807 not downloaded", "asset:data:geo:GSE75214 licence not read", "asset:data:geo:GSE75214 not downloaded", "asset:data:geo:GSE9686 licence not read", "asset:data:geo:GSE9686 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["COVID-19 to the IBD patients. Methods: Four RNA-sequencing datasets (GSE147507, GSE126124, GSE9686 and", "f 121 common DEGs were identified among four RNA-seq datasets, and were all involved in the funct", "nes and regulatory networks. Two single-cell RNA sequencing (scRNA-eq) datasets (GSE150728, PRJCA003980)", "care services. In this study, we implemented transcriptomic and single-cell analysis to detect common mo"], "order_basis": "paper_text_order:286", "id": "assay:1"}, {"role": "data_generation", "definition_id": "scrna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "unsupported", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["rugs, hub genes and regulatory networks. Two single-cell RNA sequencing (scRNA-eq) datasets (GSE150728, PRJCA003980)", "and 59 hub genes were identified. Moreover, scRNA-seq of peripheral blood monocyte cells (PBMCs) f", "flammation-related DEGs (IRGs) identified in scRNA-seq data, we downloaded RNA-seq data (GSE16879)"], "order_basis": "paper_text_order:848", "id": "assay:2"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["after treatment using the platform of GPL570 Affymetrix Human Genome U133 Plus 2.0 Array. The ‘heatm"], "order_basis": "paper_text_order:3341", "id": "assay:3"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["To acquire DEGs for the datasets GSE147507 and GSE126124, the “limma” package (21) was employed to select DEGs with |log2FC | > 0.585 (22) and p-value < 0.05 (23)."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T04:13:39+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}}}