{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33144895", "kind": "science-record", "revision": 7, "content_hash": "sha256:c76170c1bf318052560d9f18fad1942e8354fe7d7d037a072c1ab5346ec38678", "created_at": "2026-11-01T15:41:14Z", "updated_at": "2026-11-01T22:02:27Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Differential Intestinal Mucosa Transcriptomic Biomarkers for Ulcerative Colitis by Bioinformatics Analysis.", "doi": "10.1155/2020/8876565", "pmid": "33144895", "authors": ["Fang Cheng", "Qiang Li", "Jinglin Wang", "Fang Zeng", "Kaiping Wang", "Yu Zhang"], "journal": "Disease markers", "year": 2020, "abstract": "BACKGROUND: Ulcerative colitis (UC) is a complicated disease caused by the interaction between genetic and environmental factors that affect mucosal homeostasis and triggers inappropriate immune response. The purpose of the study was to identify significant biomarkers with potential therapeutic targets and the underlying mechanisms.\nMETHODS: The gene expression profiles of GSE48958, GSE73661, and GSE59071 are from the GEO database. Differentially expressed genes (DEGs) were screened by the GEO2R tool. Next, the Database for Annotation, Visualization and Integrated Discovery (DAVID) was applied to analyze gene ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway. Then, protein-protein interaction (PPI) was visualized by Cytoscape with Search Tool for the Retrieval of Interacting Genes (STRING).\nRESULTS: There were a total of 128 common DEGs genes, including 86 upregulated genes enriched in extracellular space, regulation of inflammatory response, chemokine-mediated signaling pathway, response to lipopolysaccharide, and cell proliferation, while 42 downregulated genes enriched in the integral component of the membrane, the integral component of the plasma membrane, apical plasma membrane, symporter activity, and chloride channel activity. The KEGG pathway analysis results demonstrated that DEGs were particularly enriched in cytokine-cytokine receptor interaction, TNF signaling pathway, chemokine signaling pathway, pertussis, and rheumatoid arthritis. 18 central modules of the PPI networks were selected with Cytotype MCODE. Furthermore, 18 genes were found to significantly enrich in the extracellular space, inflammatory response, chemokine-mediated signaling pathway, TNF signaling pathway, regulation of cell proliferation, and immune response via reanalysis of DAVID.\nCONCLUSION: The study identified DEGs, key target genes, functional pathways, and pathway analysis of UC, which may provide potential molecular targets and diagnostic biomarkers for UC.", "claims": [{"id": "claim-method", "statement": "GEO2R was used for data preprocessing and applied to screen DEGs between the following groups: UC vs. control group.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33144895", "locator": "sections[4] \"2.2. Screening of DEGs\" paragraph 2", "quote": "GEO2R was used for data preprocessing and applied to screen DEGs between the following groups: UC vs. control group."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data used are available in https://www.ncbi.nlm.nih.gov/geo/.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33144895", "locator": "sections[17] \"Data Availability\" paragraph 2", "quote": "The data used are available in https://www.ncbi.nlm.nih.gov/geo/."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:33144895"], "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:GSE48958"], "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:GSE48958"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33144895", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2020/8876565", "sha256": "sha256:44054f2f6a84f52de6370cbba533b57af53018a1c4fc1d5b7e245eac45c882d0", "bytes": 37686, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2020/8876565", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7596466", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE48958", "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=GSE48958", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE48958", "version": null, "note": "The data used are available in https://www.ncbi.nlm.nih.gov/geo/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used are available in https://www.ncbi.nlm.nih.gov/geo/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1187602", "GSM1187603", "GSM1187604", "GSM1187605", "GSM1187606", "GSM1187607", "GSM1187608", "GSM1187609", "GSM1187610", "GSM1187611", "GSM1187612", "GSM1187613", "GSM1187614", "GSM1187615", "GSM1187616", "GSM1187617", "GSM1187618", "GSM1187619", "GSM1187620", "GSM1187621", "GSM1187622"], "sample_count": 21, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Mucosal gene expression profiling in (un)inflamed colon of patients with ulcerative colitis (UC)", "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:GSE59071", "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=GSE59071", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE59071", "version": null, "note": "The data used are available in https://www.ncbi.nlm.nih.gov/geo/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used are available in https://www.ncbi.nlm.nih.gov/geo/.", "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"], "sample_count": 116, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Mucosal gene expression profiling in patients 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:GSE73661", "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=GSE73661", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE73661", "version": null, "note": "The data used are available in https://www.ncbi.nlm.nih.gov/geo/.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used are available in https://www.ncbi.nlm.nih.gov/geo/.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1900148", "GSM1900149", "GSM1900150", "GSM1900151", "GSM1900152", "GSM1900153", "GSM1900154", "GSM1900155", "GSM1900156", "GSM1900157", "GSM1900158", "GSM1900159", "GSM1900160", "GSM1900161", "GSM1900162", "GSM1900163", "GSM1900164", "GSM1900165", "GSM1900166", "GSM1900167", "GSM1900168", "GSM1900169", "GSM1900170", "GSM1900171", "GSM1900172", "GSM1900173", "GSM1900174", "GSM1900175", "GSM1900176", "GSM1900177", "GSM1900178", "GSM1900179", "GSM1900180", "GSM1900181", "GSM1900182", "GSM1900183", "GSM1900184", "GSM1900185", "GSM1900186", "GSM1900187", "GSM1900188", "GSM1900189", "GSM1900190", "GSM1900191", "GSM1900192", "GSM1900193", "GSM1900194", "GSM1900195", "GSM1900196", "GSM1900197", "GSM1900198", "GSM1900199", "GSM1900200", "GSM1900201", "GSM1900202", "GSM1900203", "GSM1900204", "GSM1900205", "GSM1900206", "GSM1900207", "GSM1900208", "GSM1900209", "GSM1900210", "GSM1900211", "GSM1900212", "GSM1900213", "GSM1900214", "GSM1900215", "GSM1900216", "GSM1900217", "GSM1900218", "GSM1900219", "GSM1900220", "GSM1900221", "GSM1900222", "GSM1900223", "GSM1900224", "GSM1900225", "GSM1900226", "GSM1900227", "GSM1900228", "GSM1900229", "GSM1900230", "GSM1900231", "GSM1900232", "GSM1900233", "GSM1900234", "GSM1900235", "GSM1900236", "GSM1900237", "GSM1900238", "GSM1900239", "GSM1900240", "GSM1900241", "GSM1900242", "GSM1900243", "GSM1900244", "GSM1900245", "GSM1900246", "GSM1900247", "GSM1900248", "GSM1900249", "GSM1900250", "GSM1900251", "GSM1900252", "GSM1900253", "GSM1900254", "GSM1900255", "GSM1900256", "GSM1900257", "GSM1900258", "GSM1900259", "GSM1900260", "GSM1900261", "GSM1900262", "GSM1900263", "GSM1900264", "GSM1900265", "GSM1900266", "GSM1900267", "GSM1900268", "GSM1900269", "GSM1900270", "GSM1900271", "GSM1900272", "GSM1900273", "GSM1900274", "GSM1900275", "GSM1900276", "GSM1900277", "GSM1900278", "GSM1900279", "GSM1900280", "GSM1900281", "GSM1900282", "GSM1900283", "GSM1900284", "GSM1900285", "GSM1900286", "GSM1900287", "GSM1900288", "GSM1900289", "GSM1900290", "GSM1900291", "GSM1900292", "GSM1900293", "GSM1900294", "GSM1900295", "GSM1900296", "GSM1900297", "GSM1900298", "GSM1900299", "GSM1900300", "GSM1900301", "GSM1900302", "GSM1900303", "GSM1900304", "GSM1900305", "GSM1900306", "GSM1900307", "GSM1900308", "GSM1900309", "GSM1900310", "GSM1900311", "GSM1900312", "GSM1900313", "GSM1900314", "GSM1900315", "GSM1900316", "GSM1900317", "GSM1900318", "GSM1900319", "GSM1900320", "GSM1900321", "GSM1900322", "GSM1900323", "GSM1900324", "GSM1900325"], "sample_count": 178, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "The effect of vedolizumab (anti-α4β7-integrin) therapy on colonic mucosal gene expression in patients with ulcerative colitis (UC)", "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:33144895:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f4ef6152d0d71bf7f78a7de9fdee1ee5382f4d27d34ab85aae02da7a64f6b034", "bytes": 1283, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#tab1", "version": null, "note": "86 upregulated commonly differentially expressed genes (DEGs) and 42 downregulated genes in the UC compared to normal tissues.", "structure": {"pmcid": "PMC7596466", "section_index": 9, "section_title": "3.1. Identification of DEGs", "row_count": 3, "column_count": 2}, "table": {"label": "Table 1", "caption": "86 upregulated commonly differentially expressed genes (DEGs) and 42 downregulated genes in the UC compared to normal tissues.", "rows": [["DEGs", "Genes name"], ["Upregulated", "LCN2 CDH3I GHM///IGHG1///IGHD///IGHA2///IGHA1///IGHA2///IGHA1///IGH OSMR TNIP3 CXCL10 ITGA5 C4BPA SAA2 ALDOB TNFAIP6 MXRA5 STEAP4 S100A12 IDO1 GBP5 MMP7 LOC102723407///IGHV431///IGHM///IGHD///IGHA2///LOC102723407///SKAP2///IGHA2///IGHA1///IGH NOS2 SERPINB5 APOL1 SLC7A11 SERPINB3 TNC FCGR3B///FCGR3A UBD VSIG1 VNN2 IL1A AQP9 MMP3 SERPINA3 ICAM1 CCL18 REG3A SOCS3 MMP10 DUOX2 SPINK4 CXCL13 SELP TIMP1 PHLDA1 REG1B PLEK S100A8 CXCR1 ABCA12 PI3 SLC6A14 IGK///IGKC DAPP1 TGM2 CFB C2 CXCL1 CHI3L1 KYNU TCN1 SERPINB7 CCL20 GBP4 PIM2 CD55 CXCL11 MMP1 OLFM4 IGFBP5 REG4 PTGS2 MMP12 SELL IRAK3 CXCL8 CXCL2 CLDN1 REG1A IL1B SELE DMBT1 DUOXA2 CD79A IL1RN MMP9 C3 VNN1"], ["Downregulated", "SLC38A4 CLCA1 TMIGD1 MEP1B PPARGC1A OTOP2 CLDN8 TRPM6 HNF1A-AS1 MT1M ABCG2 BMP3///BMP3 PRKG2 CYP2B6 HMGCS2 SLC26A2 APOBEC3B TMEM236 PCK1 GUCA2A PADI2 SLC16A9 SLC30A10 GUCA2B ADH1C CWH43 PBLD BEST4 CA1 CYP2B7P TMEM63C ABCB1 AQP8 CHP2 BRINP3 SLC22A5 SLC17A4 B4GALNT2 UGT2A3 ACSF2 PHLPP2 DHRS11"]], "row_count": 3, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[9]/table-wrap[1]#tab1"}}, {"id": "asset:table:pmid:33144895:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:afbf9438d6c8ed58260891ab8390d3a569e4ff803805e907cd0d0851664a2777", "bytes": 1518, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#tab2", "version": null, "note": "Gene ontology analysis of 18 central hub genes in UC.", "structure": {"pmcid": "PMC7596466", "section_index": 12, "section_title": "3.4. Module Analysis of the PPI Network", "row_count": 11, "column_count": 6}, "table": {"label": "Table 2", "caption": "Gene ontology analysis of 18 central hub genes in UC.", "rows": [["Category", "Term", "Count", "P value", "Genes", "--log10 (P value)"], ["GOTERM_BP_DIRECT", "GO:0070098~chemokine-mediated signaling pathway", "7", "8.79E-12", "CCL20, CXCL2, CXCR1, CXCL8, CXCL11, CXCL10", "7.977397"], ["GOTERM_BP_DIRECT", "GO:0006954~inflammatory response", "8", "3.40E-09", "CCL20, PTGS2, CXCL2, CXCL8, NOS2, CXCL11, CXCL10", "5.389683"], ["GOTERM_BP_DIRECT", "GO:0042127~regulation of cell proliferation", "7", "1.41E-08", "PTGS2, CXCL2, CXCL8, NOS2, CXCL11, CXCL10", "4.772917"], ["GOTERM_BP_DIRECT", "GO:0006955~immune response", "7", "1.42E-07", "CXCL2, IL1B, CXCL8, CXCL11, IL1A, CXCL10", "3.770405"], ["GOTERM_BP_DIRECT", "GO:0006935~chemotaxis", "5", "3.20E-07", "CCL20, CXCR1, CXCL11, CXCL10", "3.415649"], ["GOTERM_BP_DIRECT", "GO:0032496~response to lipopolysaccharide", "5", "2.71E-06", "CXCL2, CXCL8, CXCL11, CXCL10", "2.488617"], ["GOTERM_BP_DIRECT", "GO:0060326~cell chemotaxis", "4", "2.42E-05", "CCL20, CXCL2, CXCL10, ICAM1,", "1.537263"], ["GOTERM_CC_DIRECT", "GO:0005615~extracellular space", "13", "1.26E-11", "CCL20, MMP9, IL1RN, CXCL2, IL1B, CXCL8,CXCL11,SELE,IL1A, CXCL10, TIMP1", "7.981942"], ["GOTERM_MF_DIRECT", "GO:0008009~chemokine activity", "6", "7.11E-10", "CCL20, CXCL2, CXCL8, CXCL11, CXCL10", "6.189676"], ["GOTERM_MF_DIRECT", "GO:0045236~CXCR chemokine receptor binding", "4", "2.98E-07", "CXCL2, CXCL8, CXCL10", "3.567109"]], "row_count": 11, "column_count": 6, "numeric_cells": 51, "header_rows": 1, "locator": "section[12]/table-wrap[1]#tab2"}}], "gaps": ["asset:data:geo:GSE48958 not downloaded", "asset:data:geo:GSE48958 licence not read", "asset:data:geo:GSE59071 not downloaded", "asset:data:geo:GSE59071 licence not read", "asset:data:geo:GSE73661 not downloaded", "asset:data:geo:GSE73661 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": 0.8, "band": "high", "quote": "GO enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "GEO2R differential expression analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "GEO2R was used for data preprocessing and applied to screen DEGs between the following groups: UC vs. control group."}}], "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": ["GSE48958", "GSE73661", "GSE59071"], "resolved_accessions": ["GSE48958", "GSE73661", "GSE59071"], "statements": ["The data used are available in https://www.ncbi.nlm.nih.gov/geo/."], "basis": "The paper names GSE48958, GSE73661, GSE59071 in NCBI-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:33144895", "data:geo:GSE48958", "asset:table:pmid:33144895:1", "asset:table:pmid:33144895:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE48958"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:23:50Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 29772, "completion_tokens": 1418, "cached_tokens": 520}}, "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:33144895", "type": "paper", "label": "pmid:33144895"}, {"id": "source:pmid:33144895", "type": "manuscript", "label": "PMID 33144895 full text"}, {"id": "data:geo:GSE48958", "type": "dataset", "label": "GEO GSE48958"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33144895", "type": "paper", "label": "pmid:33144895"}, {"id": "source:pmid:33144895", "type": "manuscript", "label": "PMID 33144895 full text"}, {"id": "data:geo:GSE48958", "type": "dataset", "label": "GEO GSE48958"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33144895", "type": "extraction", "used": ["source:pmid:33144895"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE48958", "type": "accession_resolution", "used": ["data:geo:GSE48958"], "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:33144895", "parent_hash": "sha256:6e69601237fa81eebfc653c53a52a49b3b1698edeb6efa983f7800ee8fb2d746", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE48958 licence not read", "asset:data:geo:GSE48958 not downloaded", "asset:data:geo:GSE59071 licence not read", "asset:data:geo:GSE59071 not downloaded", "asset:data:geo:GSE73661 licence not read", "asset:data:geo:GSE73661 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":"2026-11-04T02:38:37+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}}}