{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34130601", "kind": "science-record", "revision": 7, "content_hash": "sha256:0326737505879760bf98f4c1621bda8a8b96eecb77c59da062d55e3248a84dab", "created_at": "2026-11-01T15:41:39Z", "updated_at": "2026-11-01T22:03:58Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Potential role of a three-gene signature in predicting diagnosis in patients with myocardial infarction.", "doi": "10.1080/21655979.2021.1938498", "pmid": "34130601", "authors": ["Yinhui Yao", "Jingyi Zhao", "Xiaohui Zhou", "Junhui Hu", "Ying Wang"], "journal": "Bioengineered", "year": 2021, "abstract": "In this study, we evaluated the diagnostic value of key genes in myocardial infarction (MI) based on data from the Gene Expression Omnibus (GEO) database. We used data from GSE66360 to identify a set of significant differentially expressed genes (DEGs) between MI and healthy controls. Logistic regression, least absolute shrinkage and selection operator (LASSO) regression, support vector machine recursive feature elimination (SVM-RFE), and SignalP 3.0 server were used to identify the potential role of genes in predicting diagnosis in patients with MI. Principal component analysis (PCA), receiver operating characteristic (ROC) curve analyses, area under the curve (AUC) analyses, and C-index were used to estimate the diagnostic value of genes in patients with MI. The association was validated using six other independent data sets. Subsequently, bioinformatics analysis was conducted based on the aforementioned potential genes. A meta-analysis was performed to evaluate the diagnostic value of the genes in MI. Forty-four DEGs were selected from the GSE66360 dataset. A three-gene signature consisting of CCL20, IL1R2, and ITLN1 could effectively distinguish patients with MI. The three-gene signature was validated in seven independent cohorts. Functional enrichment and Kyoto Encyclopedia of Genes and Genomes (KEGG) analyses were performed to reveal the involvement of the three-gene signature in inflammation-related biological processes and pathways. Moreover, diagnostic meta-analysis results of the three-gene signature showed that the pooled sensitivity, specificity, and AUC for MI were 0.80, 0.90, and 0.93, respectively. These results suggest that the three-gene signature is a novel candidate biomarker for distinguishing MI from healthy controls.", "claims": [{"id": "claim-method", "statement": "Finally, multivariable logistic regression analysis was utilized to build a diagnosis-related gene signature by incorporating the detectable features selected from the peripheral blood of patients in the SignalP 3.0 server.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34130601", "locator": "sections[4] \"Identification of the diagnosis-related gene signature associated with MI\" paragraph 2", "quote": "Finally, multivariable logistic regression analysis was utilized to build a diagnosis-related gene signature by incorporating the detectable features selected from the peripheral blood of patients in the SignalP 3.0 server."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34130601", "locator": "sections[16] \"Data availability\" paragraph 2", "quote": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048)."}], "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:34130601"], "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:GSE109048"], "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:GSE109048"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34130601", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1080/21655979.2021.1938498", "sha256": "sha256:d6a8f8fd0e260e1a24b40669c7b0c2fce48423553dee199054b3c4956d398910", "bytes": 30821, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1080/21655979.2021.1938498", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8806758", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE109048", "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=GSE109048", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE109048", "version": null, "note": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2928447", "GSM2928448", "GSM2928449", "GSM2928450", "GSM2928451", "GSM2928452", "GSM2928453", "GSM2928454", "GSM2928455", "GSM2928456", "GSM2928457", "GSM2928458", "GSM2928459", "GSM2928460", "GSM2928461", "GSM2928462", "GSM2928463", "GSM2928464", "GSM2928465", "GSM2928466", "GSM2928467", "GSM2928468", "GSM2928469", "GSM2928470", "GSM2928471", "GSM2928472", "GSM2928473", "GSM2928474", "GSM2928475", "GSM2928476", "GSM2928477", "GSM2928478", "GSM2928479", "GSM2928480", "GSM2928481", "GSM2928482", "GSM2928483", "GSM2928484", "GSM2928485", "GSM2928486", "GSM2928487", "GSM2928488", "GSM2928489", "GSM2928490", "GSM2928491", "GSM2928492", "GSM2928493", "GSM2928494", "GSM2928495", "GSM2928496", "GSM2928497", "GSM2928498", "GSM2928499", "GSM2928500", "GSM2928501", "GSM2928502", "GSM2928503"], "sample_count": 57, "group_sizes": null, "group_sizes_basis": null, "platform": "17586", "taxon": "Homo sapiens", "title": "Platelet gene expression profiling of acute myocardial infarction", "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:GSE141512", "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=GSE141512", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE141512", "version": null, "note": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4205353", "GSM4205354", "GSM4205355", "GSM4205356", "GSM4205357", "GSM4205358", "GSM4205359", "GSM4205360", "GSM4205361", "GSM4205362", "GSM4205363", "GSM4205364"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "17586", "taxon": "Homo sapiens", "title": "Expression data for patients with myocardial infarction (MI) vs healthy patients", "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:GSE24519", "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=GSE24519", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE24519", "version": null, "note": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM604559", "GSM604560", "GSM604561", "GSM604562", "GSM604563", "GSM604564", "GSM604565", "GSM604566", "GSM604567", "GSM604568", "GSM604569", "GSM604570", "GSM604571", "GSM604572", "GSM604573", "GSM604574", "GSM604575", "GSM604576", "GSM604577", "GSM604578", "GSM604579", "GSM604580", "GSM604581", "GSM604582", "GSM604583", "GSM604584", "GSM604585", "GSM604586", "GSM604587", "GSM604588", "GSM604589", "GSM604590", "GSM604591", "GSM604592", "GSM604672", "GSM604673", "GSM604674", "GSM604675"], "sample_count": 38, "group_sizes": null, "group_sizes_basis": null, "platform": "2895", "taxon": "Homo sapiens", "title": "Gene expression profiling of patients affected by first acute myocardial infarction (FAMI)", "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:GSE34198", "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=GSE34198", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE34198", "version": null, "note": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM843870", "GSM843871", "GSM843872", "GSM843873", "GSM843874", "GSM843875", "GSM843876", "GSM843877", "GSM843878", "GSM843879", "GSM843880", "GSM843881", "GSM843882", "GSM843883", "GSM843884", "GSM843885", "GSM843886", "GSM843887", "GSM843888", "GSM843889", "GSM843890", "GSM843891", "GSM843892", "GSM843893", "GSM843894", "GSM843895", "GSM843896", "GSM843897", "GSM843898", "GSM843899", "GSM843900", "GSM843901", "GSM843902", "GSM843903", "GSM843904", "GSM843905", "GSM843906", "GSM843907", "GSM843908", "GSM843909", "GSM843910", "GSM843911", "GSM843912", "GSM843913", "GSM843914", "GSM843915", "GSM843916", "GSM843917", "GSM843918", "GSM843919", "GSM843920", "GSM843921", "GSM843922", "GSM843923", "GSM843924", "GSM843925", "GSM843926", "GSM843927", "GSM843928", "GSM843929", "GSM843930", "GSM843931", "GSM843932", "GSM843933", "GSM843934", "GSM843935", "GSM843936", "GSM843937", "GSM843938", "GSM843939", "GSM843940", "GSM843941", "GSM843942", "GSM843943", "GSM843944", "GSM843945", "GSM843946", "GSM843947", "GSM843948", "GSM843949", "GSM843950", "GSM843951", "GSM843952", "GSM843953", "GSM843954", "GSM843955", "GSM843956", "GSM843957", "GSM843958", "GSM843959", "GSM843960", "GSM843961", "GSM843962", "GSM843963", "GSM843964", "GSM843965", "GSM843966"], "sample_count": 97, "group_sizes": null, "group_sizes_basis": null, "platform": "6102", "taxon": "Homo sapiens", "title": "Determinants of excess genetic risk of acute myocardial infarction – a matched case-control study", "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:GSE48060", "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=GSE48060", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE48060", "version": null, "note": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1167072", "GSM1167073", "GSM1167074", "GSM1167075", "GSM1167076", "GSM1167077", "GSM1167078", "GSM1167079", "GSM1167080", "GSM1167081", "GSM1167082", "GSM1167083", "GSM1167084", "GSM1167085", "GSM1167086", "GSM1167087", "GSM1167088", "GSM1167089", "GSM1167090", "GSM1167091", "GSM1167092", "GSM1167093", "GSM1167094", "GSM1167095", "GSM1167096", "GSM1167097", "GSM1167098", "GSM1167099", "GSM1167100", "GSM1167101", "GSM1167102", "GSM1167103", "GSM1167104", "GSM1167105", "GSM1167106", "GSM1167107", "GSM1167108", "GSM1167109", "GSM1167110", "GSM1167111", "GSM1167112", "GSM1167113", "GSM1167114", "GSM1167115", "GSM1167116", "GSM1167117", "GSM1167118", "GSM1167119", "GSM1167120", "GSM1167121", "GSM1167122", "GSM1167123"], "sample_count": 52, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Transcriptome from circulating cells suggests dysregulated pathways associated with long-term recurrent events following first-time myocardial infarction.", "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:GSE60993", "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=GSE60993", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE60993", "version": null, "note": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1495313", "GSM1495314", "GSM1495315", "GSM1495316", "GSM1495317", "GSM1495318", "GSM1495319", "GSM1495320", "GSM1495321", "GSM1495322", "GSM1495323", "GSM1495324", "GSM1495325", "GSM1495326", "GSM1495327", "GSM1495328", "GSM1495329", "GSM1495330", "GSM1495331", "GSM1495332", "GSM1495333", "GSM1495334", "GSM1495335", "GSM1495336", "GSM1495337", "GSM1495338", "GSM1495339", "GSM1495340", "GSM1495341", "GSM1495342", "GSM1495343", "GSM1495344", "GSM1495345"], "sample_count": 33, "group_sizes": null, "group_sizes_basis": null, "platform": "6884", "taxon": "Homo sapiens", "title": "Assessment and Diagnostic Relevance of Novel Serum Biomarkers for Early Decision of ST-elevation Myocardial Infarction", "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:GSE66360", "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=GSE66360", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE66360", "version": null, "note": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1620819", "GSM1620820", "GSM1620821", "GSM1620822", "GSM1620823", "GSM1620824", "GSM1620825", "GSM1620826", "GSM1620827", "GSM1620828", "GSM1620829", "GSM1620830", "GSM1620831", "GSM1620832", "GSM1620833", "GSM1620834", "GSM1620835", "GSM1620836", "GSM1620837", "GSM1620838", "GSM1620839", "GSM1620840", "GSM1620841", "GSM1620842", "GSM1620843", "GSM1620844", "GSM1620845", "GSM1620846", "GSM1620847", "GSM1620848", "GSM1620849", "GSM1620850", "GSM1620851", "GSM1620852", "GSM1620853", "GSM1620854", "GSM1620855", "GSM1620856", "GSM1620857", "GSM1620858", "GSM1620859", "GSM1620860", "GSM1620861", "GSM1620862", "GSM1620863", "GSM1620864", "GSM1620865", "GSM1620866", "GSM1620867", "GSM1620868", "GSM1620869", "GSM1620870", "GSM1620871", "GSM1620872", "GSM1620873", "GSM1620874", "GSM1620875", "GSM1620876", "GSM1620877", "GSM1620878", "GSM1620879", "GSM1620880", "GSM1620881", "GSM1620882", "GSM1620883", "GSM1620884", "GSM1620885", "GSM1620886", "GSM1620887", "GSM1620888", "GSM1620889", "GSM1620890", "GSM1620891", "GSM1620892", "GSM1620893", "GSM1620894", "GSM1620895", "GSM1620896", "GSM1620897", "GSM1620898", "GSM1620899", "GSM1620900", "GSM1620901", "GSM1620902", "GSM1620903", "GSM1620904", "GSM1620905", "GSM1620906", "GSM1620907", "GSM1620908", "GSM1620909", "GSM1620910", "GSM1620911", "GSM1620912", "GSM1620913", "GSM1620914", "GSM1620915", "GSM1620916", "GSM1620917"], "sample_count": 99, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "A Whole Blood Molecular Signature for the Identification of Acute Myocardial Infarction Without Relying Upon Myonecrosis (microarray)", "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:34130601:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a2929e2d319eb97c437fecc22bcfc40f151607346486aca7c2dbd3ec3f6bcd1a", "bytes": 678, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#t0001", "version": null, "note": "Information on the included microarray data sets", "structure": {"pmcid": "PMC8806758", "section_index": 3, "section_title": "Data mining based on the GEO database", "row_count": 8, "column_count": 5}, "table": {"label": "Table 1.", "caption": "Information on the included microarray data sets", "rows": [["GEO accession", "Country", "Platform", "Cases/controls", "Source of tissue"], ["GSE141512", "Russia", "GPL17586", "6/6", "Whole blood"], ["GSE24519", "Italy", "GPL2895", "34/4", "Whole blood"], ["GSE34198", "Czech Republic", "GPL6102", "49/48", "Whole blood"], ["GSE48060", "USA", "GPL570", "31/21", "Whole blood"], ["GSE60993", "South Korea", "GPL6884", "17/7", "Whole blood"], ["GSE66360", "USA", "GPL570", "49/50", "CD146+ circulating endothelial cells"], ["GSE109048", "Italy", "GPL17586", "19/19", "Platelets"]], "row_count": 8, "column_count": 5, "numeric_cells": 22, "header_rows": 1, "locator": "section[3]/table-wrap[1]#t0001"}}, {"id": "asset:table:pmid:34130601:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e5c4e325f36bac1dd323633469688fb4e6d4add2ac9645837c4426f33b8aae8b", "bytes": 1269, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#t0002", "version": null, "note": "Sensitivity, specificity, AUC, and C-index of the classification performance of the three-gene signature in six data sets", "structure": {"pmcid": "PMC8806758", "section_index": 10, "section_title": "Validation of the three-gene signature in six independent cohorts", "row_count": 8, "column_count": 9}, "table": {"label": "Table 2.", "caption": "Sensitivity, specificity, AUC, and C-index of the classification performance of the three-gene signature in six data sets", "rows": [["GEO accession", "TP", "FP", "FN", "TN", "Sensitivity (95% CI)", "Specificity (95% CI)", "AUC (95% CI)", "C-index (95% CI)"], ["GSE141512", "3", "1", "3", "5", "0.500 (0.139–0.860)", "0.833 (0.364–0.991)", "0.639 (0.311–0.967)", "0.639 (0.00788–1.00)"], ["GSE24519", "32", "0", "2", "4", "0.941 (0.789–0.989)", "1.00 (0.395–1.000)", "0.978 (0.934–1.00)", "0.978 (0.899–1.00)"], ["GSE34198", "27", "10", "22", "38", "0.551 (0.403–0.691)", "0.79 (0.645–0.890)", "0.652 (0.542–0.762)", "0.652 (0.446–0.857)"], ["GSE48060", "24", "4", "7", "17", "0.774 (0.584–0.897)", "0.809 (0.574–0.937)", "0.78 (0.641–0.920)", "0.78 (0.501–1.00)"], ["GSE60993", "15", "1", "2", "6", "0.824 (0.558–0.953)", "1.00 (0.561–1.00)", "0.882 (0.744–1.000)", "0.882 (0.613–1.00)"], ["GSE66360", "45", "1", "4", "49", "0.918 (0.795–0.973)", "0.980 (0.879–0.998)", "0.975 (0.948–1.000)", "0.975 (0.922–1.00)"], ["GSE109048", "14", "2", "5", "17", "0.736 (0.485–0.898)", "0.894 (0.654–0.981)", "0.867 (0.749–0.985)", "0.867 (0.635–1.00)"]], "row_count": 8, "column_count": 9, "numeric_cells": 67, "header_rows": 1, "locator": "section[10]/table-wrap[1]#t0002"}}, {"id": "asset:table:pmid:34130601:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:540dbb918561761833dceaeb9df4b4b0e9a7ac719b0f07127f6dbe3f10972ee8", "bytes": 6039, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#t0003", "version": null, "note": "GO functional annotation of the three-gene signature", "structure": {"pmcid": "PMC8806758", "section_index": 11, "section_title": "Functional annotation", "row_count": 79, "column_count": 5}, "table": {"label": "Table 3.", "caption": "GO functional annotation of the three-gene signature", "rows": [["Category", "ID", "GO term", "P-value", "Gene"], ["BP", "GO:0071347", "cellular response to interleukin-1", "0.00014", "CCL20, IL1R2"], ["BP", "GO:0070555", "response to interleukin-1", "0.00020", "CCL20, IL1R2"], ["BP", "GO:0050711", "negative regulation of interleukin-1 secretion", "0.0025", "IL1R2"], ["BP", "GO:1900016", "negative regulation of cytokine production involved in inflammatory response", "0.0031", "IL1R2"], ["BP", "GO:0035584", "calcium-mediated signaling using intracellular calcium source", "0.0035", "CCL20"], ["BP", "GO:0032692", "negative regulation of interleukin-1 production", "0.0045", "IL1R2"], ["BP", "GO:2000406", "positive regulation of T cell migration", "0.0048", "CCL20"], ["BP", "GO:0070207", "protein homotrimerization", "0.0052", "ITLN1"], ["BP", "GO:0046326", "positive regulation of glucose import", "0.0053", "ITLN1"], ["BP", "GO:2000403", "positive regulation of lymphocyte migration", "0.0058", "CCL20"], ["BP", "GO:0010955", "negative regulation of protein processing", "0.0061", "IL1R2"], ["BP", "GO:1903318", "negative regulation of protein maturation", "0.0061", "IL1R2"], ["BP", "GO:0010828", "positive regulation of glucose transmembrane transport", "0.0064", "ITLN1"], ["BP", "GO:1900015", "regulation of cytokine production involved in inflammatory response", "0.0064", "IL1R2"], ["BP", "GO:2000404", "regulation of T cell migration", "0.0064", "CCL20"], ["BP", "GO:0002534", "cytokine production involved in inflammatory response", "0.0069", "IL1R2"], ["BP", "GO:0050704", "regulation of interleukin-1 secretion", "0.0079", "IL1R2"], ["BP", "GO:0070206", "protein trimerization", "0.0087", "ITLN1"], ["BP", "GO:0046324", "regulation of glucose import", "0.0088", "ITLN1"], ["BP", "GO:0070498", "interleukin-1-mediated signaling pathway", "0.0088", "IL1R2"], ["BP", "GO:0001960", "negative regulation of cytokine-mediated signaling pathway", "0.0090", "IL1R2"], ["BP", "GO:0050701", "interleukin-1 secretion", "0.0090", "IL1R2"], ["BP", "GO:0072678", "T cell migration", "0.0095", "CCL20"], ["BP", "GO:2000401", "regulation of lymphocyte migration", "0.0095", "CCL20"], ["BP", "GO:0060761", "negative regulation of response to cytokine stimulus", "0.0097", "IL1R2"], ["BP", "GO:0002532", "production of molecular mediator involved in inflammatory response", "0.010", "IL1R2"], ["BP", "GO:0046323", "glucose import", "0.010", "ITLN1"], ["BP", "GO:0048247", "lymphocyte chemotaxis", "0.010", "CCL20"], ["BP", "GO:0002548", "monocyte chemotaxis", "0.010", "CCL20"], ["BP", "GO:0050710", "negative regulation of cytokine secretion", "0.010", "IL1R2"], ["BP", "GO:0010827", "regulation of glucose transmembrane transport", "0.011", "ITLN1"], ["BP", "GO:0032652", "regulation of interleukin-1 production", "0.012", "IL1R2"], ["BP", "GO:0071674", "mononuclear cell migration", "0.013", "CCL20"], ["BP", "GO:0032612", "interleukin-1 production", "0.014", "IL1R2"], ["BP", "GO:0070098", "chemokine-mediated signaling pathway", "0.014", "CCL20"], ["BP", "GO:1990868", "response to chemokine", "0.015", "CCL20"], ["BP", "GO:1990869", "cellular response to chemokine", "0.015", "CCL20"], ["BP", "GO:0030593", "neutrophil chemotaxis", "0.016", "CCL20"], ["BP", "GO:1904659", "glucose transmembrane transport", "0.016", "ITLN1"], ["BP", "GO:0072676", "lymphocyte migration", "0.016", "CCL20"], ["BP", "GO:0008645", "hexose transmembrane transport", "0.017", "ITLN1"], ["BP", "GO:0015749", "monosaccharide transmembrane transport", "0.017", "ITLN1"], ["BP", "GO:0034219", "carbohydrate transmembrane transport", "0.018", "ITLN1"], ["BP", "GO:1990266", "neutrophil migration", "0.018", "CCL20"], ["BP", "GO:0019730", "antimicrobial humoral response", "0.019", "ITLN1"], ["BP", "GO:0071621", "granulocyte chemotaxis", "0.019", "CCL20"], ["BP", "GO:0002687", "positive regulation of leukocyte migration", "0.019", "CCL20"], ["BP", "GO:0050709", "negative regulation of protein secretion", "0.020", "IL1R2"], ["BP", "GO:0097530", "granulocyte migration", "0.021", "CCL20"], ["BP", "GO:0002792", "negative regulation of peptide secretion", "0.021", "IL1R2"], ["BP", "GO:0050728", "negative regulation of inflammatory response", "0.022", "IL1R2"], ["BP", "GO:0008643", "carbohydrate transport", "0.022", "ITLN1"], ["BP", "GO:0001959", "regulation of cytokine-mediated signaling pathway", "0.024", "IL1R2"], ["BP", "GO:0060759", "regulation of response to cytokine stimulus", "0.026", "IL1R2"], ["BP", "GO:0070613", "regulation of protein processing", "0.027", "IL1R2"], ["BP", "GO:1903317", "regulation of protein maturation", "0.027", "IL1R2"], ["BP", "GO:0071346", "cellular response to interferon-gamma", "0.028", "CCL20"], ["BP", "GO:0002685", "regulation of leukocyte migration", "0.028", "CCL20"], ["BP", "GO:0051224", "negative regulation of protein transport", "0.029", "IL1R2"], ["BP", "GO:0050707", "regulation of cytokine secretion", "0.029", "IL1R2"], ["BP", "GO:1904950", "negative regulation of establishment of protein localization", "0.029", "IL1R2"], ["BP", "GO:0034764", "positive regulation of transmembrane transport", "0.030", "ITLN1"], ["BP", "GO:1903531", "negative regulation of secretion by cell", "0.031", "IL1R2"], ["BP", "GO:0034341", "response to interferon-gamma", "0.031", "CCL20"], ["BP", "GO:0031348", "negative regulation of defense response", "0.031", "IL1R2"], ["BP", "GO:0097529", "myeloid leukocyte migration", "0.031", "CCL20"], ["BP", "GO:0050663", "cytokine secretion", "0.033", "IL1R2"], ["BP", "GO:0030595", "leukocyte chemotaxis", "0.034", "CCL20"], ["BP", "GO:0019722", "calcium-mediated signaling", "0.035", "CCL20"], ["BP", "GO:0051048", "negative regulation of secretion", "0.035", "IL1R2"], ["BP", "GO:0071356", "cellular response to tumor necrosis factor", "0.037", "CCL20"], ["MF", "GO:0070492", "oligosaccharide binding", "0.0025", "ITLN1"], ["MF", "GO:0048020", "CCR chemokine receptor binding", "0.0072", "CCL20"], ["MF", "GO:0008009", "chemokine activity", "0.0083", "CCL20"], ["MF", "GO:0042379", "chemokine receptor binding", "0.011", "CCL20"], ["MF", "GO:0004896", "cytokine receptor activity", "0.015", "IL1R2"], ["MF", "GO:0019955", "cytokine binding", "0.021", "IL1R2"], ["MF", "GO:0019838", "growth factor binding", "0.023", "IL1R2"]], "row_count": 79, "column_count": 5, "numeric_cells": 195, "header_rows": 1, "locator": "section[11]/table-wrap[1]#t0003"}}, {"id": "asset:table:pmid:34130601:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fdadc1e6be9ad04d54e564c4b5485c8124cc5647c26bc354cb22a2ae69e54780", "bytes": 915, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#t0004", "version": null, "note": "KEGG pathway analysis of the three-gene signature", "structure": {"pmcid": "PMC8806758", "section_index": 11, "section_title": "Functional annotation", "row_count": 12, "column_count": 4}, "table": {"label": "Table 4.", "caption": "KEGG pathway analysis of the three-gene signature", "rows": [["ID", "KEGG term", "P-value", "Gene"], ["hsa04060", "Cytokine-cytokine receptor interaction", "0.0010", "CCL20,IL1R2"], ["hsa05323", "Rheumatoid arthritis", "0.023", "CCL20"], ["hsa04657", "IL-17 signaling pathway", "0.023", "CCL20"], ["hsa05215", "Prostate cancer", "0.024", "IL1R2"], ["hsa04640", "Hematopoietic cell lineage", "0.024", "IL1R2"], ["hsa04061", "Viral protein interaction with cytokine and cytokine receptor", "0.025", "CCL20"], ["hsa05146", "Amoebiasis", "0.025", "IL1R2"], ["hsa04668", "TNF signaling pathway", "0.028", "CCL20"], ["hsa05418", "Fluid shear stress and atherosclerosis", "0.034", "IL1R2"], ["hsa04062", "Chemokine signaling pathway", "0.046", "CCL20"], ["hsa05202", "Transcriptional misregulation in cancer", "0.047", "IL1R2"]], "row_count": 12, "column_count": 4, "numeric_cells": 29, "header_rows": 1, "locator": "section[11]/table-wrap[2]#t0004"}}], "gaps": ["asset:data:geo:GSE109048 not downloaded", "asset:data:geo:GSE109048 licence not read", "asset:data:geo:GSE141512 not downloaded", "asset:data:geo:GSE141512 licence not read", "asset:data:geo:GSE24519 not downloaded", "asset:data:geo:GSE24519 licence not read", "asset:data:geo:GSE34198 not downloaded", "asset:data:geo:GSE34198 licence not read", "asset:data:geo:GSE48060 not downloaded", "asset:data:geo:GSE48060 licence not read", "asset:data:geo:GSE60993 not downloaded", "asset:data:geo:GSE60993 licence not read", "asset:data:geo:GSE66360 not downloaded", "asset:data:geo:GSE66360 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Finally, multivariable logistic regression analysis was utilized to build a diagnosis-related gene signature by incorporating the detectable features selected from the peripheral blood of patients in the SignalP 3.0 server."}}, {"id": "method-2", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Principal component analysis"}}, {"id": "method-3", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "support vector machine"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": ["glm_logit_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: logistic."}, "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": ["GSE66360", "GSE141512", "GSE24519", "GSE34198", "GSE48060", "GSE60993", "GSE109048"], "resolved_accessions": ["GSE66360", "GSE141512", "GSE24519", "GSE34198", "GSE48060", "GSE60993", "GSE109048"], "statements": ["The data supporting the findings of this study are available in the Gene Expression Omnibus (GEO) database (GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, and GSE109048)."], "basis": "The paper names GSE66360, GSE141512, GSE24519, GSE34198, GSE48060, GSE60993, GSE109048 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": ["glm_logit_fit"], "assets": ["source:pmid:34130601", "data:geo:GSE109048", "asset:table:pmid:34130601:1", "asset:table:pmid:34130601:2", "asset:table:pmid:34130601:3", "asset:table:pmid:34130601:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE109048"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:30:52Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 24329, "completion_tokens": 2179, "cached_tokens": 792}}, "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:34130601", "type": "paper", "label": "pmid:34130601"}, {"id": "source:pmid:34130601", "type": "manuscript", "label": "PMID 34130601 full text"}, {"id": "data:geo:GSE109048", "type": "dataset", "label": "GEO GSE109048"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34130601", "type": "paper", "label": "pmid:34130601"}, {"id": "source:pmid:34130601", "type": "manuscript", "label": "PMID 34130601 full text"}, {"id": "data:geo:GSE109048", "type": "dataset", "label": "GEO GSE109048"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34130601", "type": "extraction", "used": ["source:pmid:34130601"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE109048", "type": "accession_resolution", "used": ["data:geo:GSE109048"], "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:34130601", "parent_hash": "sha256:9543dfc9326a30183fa8a714d50fa598f05f6178ab6c9ca72da4c8546403b898", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE109048 licence not read", "asset:data:geo:GSE109048 not downloaded", "asset:data:geo:GSE141512 licence not read", "asset:data:geo:GSE141512 not downloaded", "asset:data:geo:GSE24519 licence not read", "asset:data:geo:GSE24519 not downloaded", "asset:data:geo:GSE34198 licence not read", "asset:data:geo:GSE34198 not downloaded", "asset:data:geo:GSE48060 licence not read", "asset:data:geo:GSE48060 not downloaded", "asset:data:geo:GSE60993 licence not read", "asset:data:geo:GSE60993 not downloaded", "asset:data:geo:GSE66360 licence not read", "asset:data:geo:GSE66360 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "regression_modelling", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["glm_logit_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Finally, multivariable logistic regression analysis was utilized to build a diagnosis-related gene signature by incorporating the detectable features selected from the peripheral blood of patients in the SignalP 3.0 server."], "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":"2026-11-04T02:37:28+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}}}