{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32460303", "kind": "science-record", "revision": 9, "content_hash": "sha256:4baa8a7cf46ca54cc8c3b3e3a369256ba9b4bcd8a394452937d0990334539899", "created_at": "2026-11-01T15:41:02Z", "updated_at": "2026-11-01T22:44:53Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Bioinformatics Analysis and Identification of Underlying Biomarkers Potentially Linking Allergic Rhinitis and Asthma.", "doi": "10.12659/MSM.924934", "pmid": "32460303", "authors": ["Zhanfeng Yan", "Lili Liu", "Lulu Jiao", "Xiaohui Wen", "Jianhua Liu", "Ningyu Wang"], "journal": "Medical science monitor : international medical journal of experimental and clinical research", "year": 2020, "abstract": "BACKGROUND Rhinitis is the most common clinical manifestation of allergy, affecting more than 400 million people around the world. Rhinitis increases the risk of developing bronchial hyper-responsiveness and asthma. Previous studies have shown that rhinitis is closely related with the physiology, pathology, and pathogenesis of asthma. We analyzed co-expressed genes to explore the relationships between rhinitis and asthma and to find biomarkers of comorbid rhinitis and asthma. MATERIAL AND METHODS Asthma- and rhinitis-related differentially-expressed genes (DEGs) were identified by bioinformatic analysis of GSE104468 and GSE46171 datasets from the Gene Expression Omnibus (GEO) database. After assessment of Gene Ontology (GO) terms and pathway enrichment for DEGs, a protein-protein interaction (PPI) network was conducted via comprehensive target prediction and network analyses. We also evaluated co-expressed DEGs and corresponding predicted miRNAs involved in the developing process of rhinitis and asthma. RESULTS We identified 687 and 1001 DEGs in bronchial and nasal epithelia samples of asthma patients, respectively. For patients with rhinitis, we found 245 DEGs. The hub-genes of PAX6, NMU, NTS, NMUR1, PMCH, and KRT6A may be associated with rhinitis, while CPA3, CTSG, POSTN, CLCA1, HDC, and MUC5B may be involved in asthma. The co-expressed DEGs of BPIFA1, CCL26, CPA3, and CST1, together with corresponding predicted miRNAs (e.g., miR-195-5p and miR-125a-3p) were found to be significantly correlated with rhinitis and asthma. CONCLUSIONS Rhinitis and asthma are related, and there are significant correlations of BPIFA1, CCL26, CPA3, and CST1 genes with novel biomarkers involved in the comorbidity of rhinitis and asthma.", "claims": [{"id": "claim-method", "statement": "The Bioconductor R packages “limma” [19], was applied to analyze GSE104468 and GSE46171 RAW datasets. Original p-values were corrected using the Benjamini-Hochberg method.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32460303", "locator": "sections[3] \"Data processing\" paragraph 2", "quote": "The Bioconductor R packages “limma” [19], was applied to analyze GSE104468 and GSE46171 RAW datasets. Original p-values were corrected using the Benjamini-Hochberg method."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Additionally, the GSE104468 dataset, including collected nasal epithelia and bronchial epithelia sample from 12 subjects with allergic asthma and 12 control subjects, was used to identify differentially-expressed genes and molecular mechanisms of asthma [17].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32460303", "locator": "sections[2] \"Material and Methods\" paragraph 2", "quote": "Additionally, the GSE104468 dataset, including collected nasal epithelia and bronchial epithelia sample from 12 subjects with allergic asthma and 12 control subjects, was used to identify differentially-expressed genes and molecular mechanisms of asthma [17]."}], "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:32460303"], "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:GSE104468"], "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:GSE104468"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32460303", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.12659/MSM.924934", "sha256": "sha256:62c960aa04be153235788f1a6a7cce63e9b1b7feb73bf855aa396998b87d9bea", "bytes": 33592, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.12659/MSM.924934", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7278529", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE104468", "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=GSE104468", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE104468", "version": null, "note": "Additionally, the GSE104468 dataset, including collected nasal epithelia and bronchial epithelia sample from 12 subjects with allergic asthma and 12 control subjects, was used to identify differentially-expressed genes and molecular mechanisms of asthma [17].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Additionally, the GSE104468 dataset, including collected nasal epithelia and bronchial epithelia sample from 12 subjects with allergic asthma and 12 control subjects, was used to identify differentially-expressed genes and molecular mechanisms of asthma [17].", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2800849", "GSM2800850", "GSM2800851", "GSM2800852", "GSM2800853", "GSM2800854", "GSM2800855", "GSM2800856", "GSM2800857", "GSM2800858", "GSM2800859", "GSM2800860", "GSM2800861", "GSM2800862", "GSM2800863", "GSM2800864", "GSM2800865", "GSM2800866", "GSM2800867", "GSM2800868", "GSM2800869", "GSM2800870", "GSM2800871", "GSM2800872", "GSM2800873", "GSM2800874", "GSM2800875", "GSM2800876", "GSM2800877", "GSM2800878", "GSM2800879", "GSM2800880", "GSM2800881", "GSM2800882", "GSM2800883", "GSM2800884", "GSM2800885", "GSM2800886", "GSM2800887", "GSM2800888", "GSM2800889", "GSM2800890", "GSM2800891", "GSM2800892", "GSM2800893", "GSM2800894", "GSM2800895", "GSM2800896", "GSM2800897", "GSM2800898", "GSM2800899", "GSM2800900", "GSM2800901", "GSM2800902", "GSM2800903", "GSM2800904", "GSM2800905", "GSM2800906", "GSM2800907", "GSM2800908", "GSM2800909", "GSM2800910", "GSM2800911", "GSM2800912", "GSM2800913", "GSM2800914", "GSM2800915", "GSM2800916", "GSM2800917", "GSM2800918", "GSM2800919", "GSM2800920"], "sample_count": 72, "group_sizes": null, "group_sizes_basis": null, "platform": "21185", "taxon": "Homo sapiens", "title": "The Nasal Methylome: A Key to Understanding Allergic Asthma [Agilent]", "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:GSE46171", "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=GSE46171", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE46171", "version": null, "note": "Additionally, the GSE104468 dataset, including collected nasal epithelia and bronchial epithelia sample from 12 subjects with allergic asthma and 12 control subjects, was used to identify differentially-expressed genes and molecular mechanisms of asthma [17].", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Additionally, the GSE104468 dataset, including collected nasal epithelia and bronchial epithelia sample from 12 subjects with allergic asthma and 12 control subjects, was used to identify differentially-expressed genes and molecular mechanisms of asthma [17].", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1125390", "GSM1125391", "GSM1125392", "GSM1125393", "GSM1125394", "GSM1125395", "GSM1125396", "GSM1125397", "GSM1125398", "GSM1125399", "GSM1125400", "GSM1125401", "GSM1125402", "GSM1125403", "GSM1125404", "GSM1125405", "GSM1125406", "GSM1125407", "GSM1125408", "GSM1125409", "GSM1125410", "GSM1125411", "GSM1125412", "GSM1125413", "GSM1125414", "GSM1125415", "GSM1125416", "GSM1125417", "GSM1125418", "GSM1125419", "GSM1125420", "GSM1125421", "GSM1125422", "GSM1125423", "GSM1125424", "GSM1125425", "GSM1125426", "GSM1125427", "GSM1125428", "GSM1125429", "GSM1125430", "GSM1125431", "GSM1125432", "GSM1125433", "GSM1125434", "GSM1125435", "GSM1125436", "GSM1125437", "GSM1125438", "GSM1125439", "GSM1125440", "GSM1125441", "GSM1125442", "GSM1125443", "GSM1125444", "GSM1125445", "GSM1125446", "GSM1125447", "GSM1125448", "GSM1125449", "GSM1125450", "GSM1125451", "GSM1125452", "GSM1125453", "GSM1125454", "GSM1125455", "GSM1125456", "GSM1125457", "GSM1125458", "GSM1125459", "GSM1125460", "GSM1125461", "GSM1125462", "GSM1125463", "GSM1125464", "GSM1125465", "GSM1125466", "GSM1125467", "GSM1125468", "GSM1125469", "GSM1125470", "GSM1125471", "GSM1125472", "GSM1125473", "GSM1125474", "GSM1125475", "GSM1125476", "GSM1125477", "GSM1125478", "GSM1125479", "GSM1125480"], "sample_count": 91, "group_sizes": null, "group_sizes_basis": null, "platform": "6480;16981", "taxon": "Homo sapiens", "title": "Asthmatics with exacerbation during acute respiratory illness exhibit unique transcriptional signatures.", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32460303:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:371aefec5b5a0e49dc2b4328f18e181e9011a6ae882038af3c2f624f0c44b529", "bytes": 4928, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#t1-medscimonit-26-e924934", "version": null, "note": "The Gene Ontology (GO) terms enrichment for the co-expressed genes of rhinitis and asthma.", "structure": {"pmcid": "PMC7278529", "section_index": 9, "section_title": "Functional enrichment in co-DEGs", "row_count": 78, "column_count": 4}, "table": {"label": "Table 1", "caption": "The Gene Ontology (GO) terms enrichment for the co-expressed genes of rhinitis and asthma.", "rows": [["Gene/product", "GO class (direct)", "Evidence", "Reference"], ["BPIFA1", "Protein binding", "IPI", "PMID: 25416956"], ["Extracellular region", "IDA", "PMID: 11425234"], ["Extracellular space", "IDA", "PMID: 21805676"], ["Lipid binding", "IEA", "GO_REF: 0000037"], ["Antimicrobial humoral response", "TAS", "Reactome: R-HSA-6803157"], ["Antibacterial humoral response", "IDA", "PMID: 23499554"], ["Innate immune response", "IDA", "PMID: 23499554"], ["Regulation of liquid surface tension", "IDA", "PMID: 23499554"], ["Multicellular organismal water homeostasis", "IDA", "PMID: 24124190"], ["Defense response to virus", "IEP", "PMID: 21805676"], ["Antimicrobial humoral immune response mediated by antimicrobial peptide", "IEP", "PMID: 21805676"], ["Negative regulation of single-species biofilm formation in or on host organism", "IMP", "PMID: 23499554"], ["Regulation of sodium ion transmembrane transport", "IDA", "PMID: 24124190"], ["CCL26", "Positive regulation of endothelial cell proliferation", "IDA", "PMID: 19525930"], ["Monocyte chemotaxis", "IDA", "PMID: 10373330"], ["Protein binding", "IPI", "PMID: 28381538"], ["Extracellular space", "IDA", "PMID: 10373330"], ["Chemotaxis", "TAS", "PMID: 10373330"], ["Signal transduction", "NAS", "PMID: 10373330"], ["Cell–cell signaling", "TAS", "PMID: 10373330"], ["Chemokine activity", "IDA", "PMID: 10373330"], ["T cell chemotaxis", "IDA", "PMID: 10373330"], ["Positive regulation of cell migration", "IDA", "PMID: 19525930"], ["Positive regulation of actin filament polymerization", "IDA", "PMID: 19525930"], ["CCR3 chemokine receptor binding", "IDA", "PMID: 11425309"], ["Positive regulation of GTPase activity", "IDA", "PMID: 19525930"], ["Receptor ligand activity", "IDA", "PMID: 11425309"], ["Positive regulation of chemotaxis", "IDA", "PMID: 10373330"], ["Chemokine-mediated signaling pathway", "IDA", "PMID: 10373330"], ["CCR chemokine receptor binding", "IBA", "PMID: 21873635"], ["Positive regulation of GTPase activity", "IBA", "PMID: 21873635"], ["Lymphocyte chemotaxis", "IBA", "PMID: 21873635"], ["Chemokine activity", "IBA", "PMID: 21873635"], ["Monocyte chemotaxis", "IBA", "PMID: 21873635"], ["Cellular response to tumor necrosis factor", "IBA", "PMID: 21873635"], ["Extracellular space", "IBA", "PMID: 21873635"], ["Inflammatory response", "IBA", "PMID: 21873635"], ["Chemokine-mediated signaling pathway", "IBA", "PMID: 21873635"], ["G protein-coupled receptor signaling pathway", "IBA", "PMID: 21873635"], ["Cellular response to interleukin-1", "IBA", "PMID: 21873635"], ["Neutrophil chemotaxis", "IBA", "PMID: 21873635"], ["Positive regulation of ERK1 and ERK2 cascade", "IBA", "PMID: 21873635"], ["Cellular response to interferon-gamma", "IBA", "PMID: 21873635"], ["CPA3", "Angiotensin maturation", "TAS", "Reactome: R-HSA-2028294"], ["Metallocarboxypeptidase activity", "TAS", "PMID: 1629626"], ["Extracellular region", "TAS", "Reactome: R-HSA-2028294"], ["Proteolysis", "TAS", "PMID: 2708524"], ["Zinc ion binding", "IEA", "GO_REF: 0000002"], ["Transport vesicle", "IEA", "GO_REF: 0000039"], ["Secretory granule", "NAS", "PMID: 2594780"], ["Collagen-containing extracellular matrix", "HDA", "PMID: 27559042"], ["Metallocarboxypeptidase activity", "IBA", "PMID: 21873635"], ["Proteolysis", "IBA", "PMID: 21873635"], ["Extracellular space", "IBA", "PMID: 21873635"], ["CST1", "Detection of chemical stimulus involved in sensory perception of bitter taste", "IDA", "PMID: 24248522"], ["Cysteine-type endopeptidase inhibitor activity", "IEA", "GO_REF: 0000037"], ["Protein binding", "IPI", "PMID: 25416956"], ["Extracellular space", "HDA", "PMID: 22664934"], ["Negative regulation of endopeptidase activity", "IEA", "GO_REF: 0000108"], ["Extracellular space", "IBA", "PMID: 21873635"], ["CST2", "Detection of chemical stimulus involved in sensory perception of bitter taste", "IDA", "PMID: 24248522"], ["Cysteine-type endopeptidase inhibitor activity", "IEA", "GO_REF: 0000037"], ["Protein binding", "IPI", "PMID: 25416956"], ["Extracellular space", "HDA", "PMID: 22664934"], ["Negative regulation of endopeptidase activity", "IEA", "GO_REF: 0000108"], ["Extracellular space", "IBA", "PMID: 21873635"], ["FETUB", "Cysteine-type endopeptidase inhibitor activity", "IEA", "GO_REF: 0000002"], ["Single fertilization", "ISS", "GO_REF: 0000024"], ["Binding of sperm to zona pellucida", "ISS", "GO_REF: 0000024"], ["Metalloendopeptidase inhibitor activity", "ISS", "GO_REF: 0000024"], ["Negative regulation of endopeptidase activity", "ISS", "GO_REF: 0000024"], ["Extracellular exosome", "HDA", "PMID: 23533145"], ["Binding of sperm to zona pellucida", "IBA", "PMID: 21873635"], ["Negative regulation of endopeptidase activity", "IBA", "PMID: 21873635"], ["Metalloendopeptidase inhibitor activity", "IBA", "PMID: 21873635"], ["Extracellular region", "IBA", "PMID: 21873635"], ["Endopeptidase inhibitor activity", "IBA", "PMID: 21873635"]], "row_count": 78, "column_count": 4, "numeric_cells": 79, "header_rows": 1, "locator": "section[9]/table-wrap[1]#t1-medscimonit-26-e924934"}}, {"id": "asset:table:pmid:32460303:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:057272956e5a19bcaa8989df646273e22af8fee13ce6e420ec8ccc722246bc79", "bytes": 2768, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#t2-medscimonit-26-e924934", "version": null, "note": "The Gene Ontology (GO) terms and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways enrichment among predicted miRNAs and co-DEGs.", "structure": {"pmcid": "PMC7278529", "section_index": 11, "section_title": "Identification of functional and pathway enrichment among predicted miRNAs and co-DEGs", "row_count": 45, "column_count": 5}, "table": {"label": "Table 2", "caption": "The Gene Ontology (GO) terms and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways enrichment among predicted miRNAs and co-DEGs.", "rows": [["Genes", "Predicted miRNAs", "Category", "", "P value"], ["BPIFA1", "hsa-miR-195-5p", "KEGG pathway", "Fatty acid biosynthesis", "1.04E-07"], ["hsa-miR-16-5p", "Adherens junction", "1.70E-07"], ["hsa-miR-424-5p", "TGF-beta signaling pathway", "3.28E-05"], ["hsa-miR-497-5p", "GO terms", "Neurotrophin TRK receptor signaling pathway", "1.79E-31"], ["hsa-miR-15b-5p", "cell death", "1.41E-28"], ["Response to stress", "1.41E-28"], ["Blood coagulation", "1.84E-25"], ["Fc-epsilon receptor signaling pathway", "5.45E-19"], ["Immune system process", "3.87E-15"], ["Activation of signaling protein activity involved in unfolded protein response", "3.77E-14"], ["Toll-like receptor 10 signaling pathway", "1.22E-13"], ["Epidermal growth factor receptor signaling pathway", "1.82E-13"], ["Toll-like receptor TLR1: TLR2 signaling pathway", "1.06E-12"], ["Toll-like receptor TLR6: TLR2 signaling pathway", "1.06E-12"], ["CCL26", "hsa-miR-326", "KEGG pathway", "Steroid biosynthesis", "8.04E-10"], ["hsa-miR-615-5p", "ECM-receptor interaction", "3.39E-08"], ["hsa-miR-559", "GO terms", "Neurotrophin TRK receptor signaling pathway", "5.30E-26"], ["hsa-miR-335-5p", "Small molecule metabolic process", "5.89E-21"], ["hsa-miR-548d-5p", "Blood coagulation", "8.06E-18"], ["Cellular protein modification process", "4.43E-15"], ["Fc-epsilon receptor signaling pathway", "3.94E-13"], ["Cellular nitrogen compound metabolic process", "3.94E-13"], ["Immune system process", "7.59E-11"], ["CPA3", "hsa-miR-125a-3p", "KEGG pathway", "Adherens junction", "2.60E-07"], ["hsa-miR-155-5p", "Hippo signaling pathway", "1.21E-05"], ["hsa-miR-196a-5p", "TGF-beta signaling pathway", "1.96E-05"], ["hsa-miR-196b-5p", "Lysine degradation", "4.43E-05"], ["GO terms", "cellular nitrogen compound metabolic process", "6.05E-108"], ["gene expression", "7.55E-68"], ["biosynthetic process", "8.95E-64"], ["cellular protein modification process", "8.70E-52"], ["CST1", "hsa-miR-452-5p", "KEGG pathway", "ECM-receptor interaction", "0.000132"], ["hsa-miR-608", "Hippo signaling pathway", "0.00019"], ["hsa-miR-138-5p", "Adherens junction", "0.00019"], ["hsa-miR-4685-5p", "Apoptosis", "0.005037"], ["hsa-miR-1321", "Focal adhesion", "0.005037"], ["GO terms", "Cellular nitrogen compound metabolic process", "2.81E-42"], ["Gene expression", "2.91E-40"], ["Biosynthetic process", "7.87E-34"], ["mRNA metabolic process", "8.00E-21"], ["Response to stress", "8.00E-21"], ["RNA metabolic process", "1.38E-17"], ["Symbiosis, encompassing mutualism through parasitism", "1.97E-17"], ["Cellular component assembly", "2.11E-17"]], "row_count": 45, "column_count": 5, "numeric_cells": 65, "header_rows": 1, "locator": "section[11]/table-wrap[1]#t2-medscimonit-26-e924934"}}, {"id": "asset:table:pmid:32460303:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:cefca4b5ae53fa565008fac6d868f63aa556c46717c0f4a0a9dcc55fc2d69275", "bytes": 3154, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#t3-medscimonit-26-e924934", "version": null, "note": "The relationship between co-expressed genes and respiratory system diseases based on the CTD database.", "structure": {"pmcid": "PMC7278529", "section_index": 14, "section_title": "Supplementary Data", "row_count": 27, "column_count": 8}, "table": {"label": "Supplementary Table 1", "caption": "The relationship between co-expressed genes and respiratory system diseases based on the CTD database.", "rows": [["Gene symbol", "Gene ID", "Disease name", "Disease ID", "Direct evidence", "Inference network", "Inference score", "Reference count"], ["BPIFA1", "51297", "Rhinitis", "MESH: D012220", "", "Particulate Matter | Tobacco Smoke Pollution | Vehicle Emissions", "12.67", "3"], ["BPIFA1", "51297", "Rhinitis, allergic", "MESH: D065631", "", "Particulate Matter | Soot", "8.45", "2"], ["BPIFA1", "51297", "Rhinitis, allergic, seasonal", "MESH: D006255", "", "Particulate Matter", "3.57", "1"], ["BPIFA1", "51297", "Asthma", "MESH: D001249", "", "Acetaminophen | Arsenic | Particulate Matter | Soot | Tobacco Smoke Pollution | Vehicle Emissions", "21.02", "29"], ["BPIFA1", "51297", "Asthma, occupational", "MESH: D059366", "", "Silicon Dioxide", "3.35", "1"], ["BPIFA1", "51297", "Nose diseases", "MESH: D009668", "", "Propylthiouracil | Tobacco Smoke Pollution", "9.59", "4"], ["CCL26", "10344", "Asthma", "MESH: D001249", "", "Aerosols | Antigens, Dermatophagoides | Arsenic | Cadmium | Dexamethasone | Ozone | Resveratrol | Tobacco Smoke Pollution | Zinc", "27.99", "28"], ["CCL26", "10344", "Rhinitis, allergic, perennial", "MESH: D012221", "", "Ozone", "3.73", "1"], ["CCL26", "10344", "Rhinitis, allergic", "MESH: D065631", "", "Atrazine", "2.83", "1"], ["CCL26", "10344", "Rhinitis", "MESH: D012220", "", "Tobacco Smoke Pollution", "2.6", "1"], ["CCL26", "10344", "Nose diseases", "MESH: D009668", "", "Lipopolysaccharides | Propylthiouracil | Tobacco Smoke Pollution", "14.31", "5"], ["CCL26", "10344", "Sinusitis", "MESH: D012852", "", "Tobacco Smoke Pollution", "2.9", "1"], ["CPA3", "1359", "Rhinitis", "MESH: D012220", "", "Tobacco Smoke Pollution | Vehicle Emissions", "6.86", "2"], ["CPA3", "1359", "Asthma", "MESH: D001249", "", "Acetaminophen | Decitabine | epigallocatechin gallate | Tobacco Smoke Pollution | trimellitic anhydride | Vehicle Emissions", "18.84", "19"], ["CPA3", "1359", "Nose diseases", "MESH: D009668", "", "Tobacco Smoke Pollution", "3.4", "2"], ["CPA3", "1359", "Sinusitis", "MESH: D012852", "", "Acetaminophen | Tobacco Smoke Pollution", "7.83", "2"], ["CST1", "1469", "Rhinitis, allergic, seasonal", "MESH: D006255", "Marker/mechanism", "", "1"], ["CST1", "1469", "Rhinitis, allergic", "MESH: D065631", "", "Air Pollutants", "3.83", "1"], ["CST1", "1469", "Rhinitis", "MESH: D012220", "", "Air Pollutants", "3.6", "1"], ["CST1", "1469", "Asthma", "MESH: D001249", "", "Air Pollutants | Methotrexate | Tretinoin", "9.41", "14"], ["CST1", "1469", "Asthma, occupational", "MESH: D059366", "", "Silicon Dioxide", "3.45", "1"], ["CST2", "1470", "Asthma, occupational", "MESH: D059366", "", "Silicon Dioxide", "3.85", "1"], ["FETUB", "26998", "Rhinitis", "MESH: D012220", "", "Tobacco Smoke Pollution | Vehicle Emissions", "5.71", "2"], ["FETUB", "26998", "Rhinitis, allergic", "MESH: D065631", "", "Atrazine", "2.66", "1"], ["FETUB", "26998", "Nose diseases", "MESH: D009668", "", "cobaltous chloride | Tobacco Smoke Pollution", "7.86", "3"], ["FETUB", "26998", "Sinusitis", "MESH: D012852", "", "Acetaminophen | Tobacco Smoke Pollution", "6.66", "2"]], "row_count": 27, "column_count": 8, "numeric_cells": 109, "header_rows": 1, "locator": "section[14]/table-wrap[1]#t3-medscimonit-26-e924934"}}, {"id": "asset:table:pmid:32460303:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ed542b1c4c27519b6b81a0c17bf41aec77c62e0997602be95ab0be8607a51894", "bytes": 3153, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#db_ds_table-wrap1_reqid_", "version": null, "note": "The relationship between co-expressed genes and respiratory system diseases based on the CTD database.", "structure": {"pmcid": "PMC7278529", "section_index": 19, "section_title": "Supplementary Materials", "row_count": 27, "column_count": 8}, "table": {"label": "Supplementary Table 1", "caption": "The relationship between co-expressed genes and respiratory system diseases based on the CTD database.", "rows": [["Gene symbol", "Gene ID", "Disease name", "Disease ID", "Direct evidence", "Inference network", "Inference score", "Reference count"], ["BPIFA1", "51297", "Rhinitis", "MESH: D012220", "", "Particulate Matter | Tobacco Smoke Pollution | Vehicle Emissions", "12.67", "3"], ["BPIFA1", "51297", "Rhinitis, allergic", "MESH: D065631", "", "Particulate Matter | Soot", "8.45", "2"], ["BPIFA1", "51297", "Rhinitis, allergic, seasonal", "MESH: D006255", "", "Particulate Matter", "3.57", "1"], ["BPIFA1", "51297", "Asthma", "MESH: D001249", "", "Acetaminophen | Arsenic | Particulate Matter | Soot | Tobacco Smoke Pollution | Vehicle Emissions", "21.02", "29"], ["BPIFA1", "51297", "Asthma, occupational", "MESH: D059366", "", "Silicon Dioxide", "3.35", "1"], ["BPIFA1", "51297", "Nose diseases", "MESH: D009668", "", "Propylthiouracil | Tobacco Smoke Pollution", "9.59", "4"], ["CCL26", "10344", "Asthma", "MESH: D001249", "", "Aerosols | Antigens, Dermatophagoides | Arsenic | Cadmium | Dexamethasone | Ozone | Resveratrol | Tobacco Smoke Pollution | Zinc", "27.99", "28"], ["CCL26", "10344", "Rhinitis, allergic, perennial", "MESH: D012221", "", "Ozone", "3.73", "1"], ["CCL26", "10344", "Rhinitis, allergic", "MESH: D065631", "", "Atrazine", "2.83", "1"], ["CCL26", "10344", "Rhinitis", "MESH: D012220", "", "Tobacco Smoke Pollution", "2.6", "1"], ["CCL26", "10344", "Nose diseases", "MESH: D009668", "", "Lipopolysaccharides | Propylthiouracil | Tobacco Smoke Pollution", "14.31", "5"], ["CCL26", "10344", "Sinusitis", "MESH: D012852", "", "Tobacco Smoke Pollution", "2.9", "1"], ["CPA3", "1359", "Rhinitis", "MESH: D012220", "", "Tobacco Smoke Pollution | Vehicle Emissions", "6.86", "2"], ["CPA3", "1359", "Asthma", "MESH: D001249", "", "Acetaminophen | Decitabine | epigallocatechin gallate | Tobacco Smoke Pollution | trimellitic anhydride | Vehicle Emissions", "18.84", "19"], ["CPA3", "1359", "Nose diseases", "MESH: D009668", "", "Tobacco Smoke Pollution", "3.4", "2"], ["CPA3", "1359", "Sinusitis", "MESH: D012852", "", "Acetaminophen | Tobacco Smoke Pollution", "7.83", "2"], ["CST1", "1469", "Rhinitis, allergic, seasonal", "MESH: D006255", "Marker/mechanism", "", "1"], ["CST1", "1469", "Rhinitis, allergic", "MESH: D065631", "", "Air Pollutants", "3.83", "1"], ["CST1", "1469", "Rhinitis", "MESH: D012220", "", "Air Pollutants", "3.6", "1"], ["CST1", "1469", "Asthma", "MESH: D001249", "", "Air Pollutants | Methotrexate | Tretinoin", "9.41", "14"], ["CST1", "1469", "Asthma, occupational", "MESH: D059366", "", "Silicon Dioxide", "3.45", "1"], ["CST2", "1470", "Asthma, occupational", "MESH: D059366", "", "Silicon Dioxide", "3.85", "1"], ["FETUB", "26998", "Rhinitis", "MESH: D012220", "", "Tobacco Smoke Pollution | Vehicle Emissions", "5.71", "2"], ["FETUB", "26998", "Rhinitis, allergic", "MESH: D065631", "", "Atrazine", "2.66", "1"], ["FETUB", "26998", "Nose diseases", "MESH: D009668", "", "cobaltous chloride | Tobacco Smoke Pollution", "7.86", "3"], ["FETUB", "26998", "Sinusitis", "MESH: D012852", "", "Acetaminophen | Tobacco Smoke Pollution", "6.66", "2"]], "row_count": 27, "column_count": 8, "numeric_cells": 109, "header_rows": 1, "locator": "section[19]/table-wrap[1]#db_ds_table-wrap1_reqid_"}}], "gaps": ["asset:data:geo:GSE104468 not downloaded", "asset:data:geo:GSE104468 licence not read", "asset:data:geo:GSE46171 not downloaded", "asset:data:geo:GSE46171 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": "The Bioconductor R packages “limma” [19], was applied to analyze GSE104468 and GSE46171 RAW datasets. Original p-values were corrected using the Benjamini-Hochberg method."}}, {"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": "protein-protein interaction"}}, {"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": 0.7, "band": "medium", "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": ["GSE104468", "GSE46171"], "resolved_accessions": ["GSE104468", "GSE46171"], "statements": ["Additionally, the GSE104468 dataset, including collected nasal epithelia and bronchial epithelia sample from 12 subjects with allergic asthma and 12 control subjects, was used to identify differentially-expressed genes and molecular mechanisms of asthma [17]."], "basis": "The paper names GSE104468, GSE46171 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:32460303", "data:geo:GSE104468", "asset:table:pmid:32460303:1", "asset:table:pmid:32460303:2", "asset:table:pmid:32460303:3", "asset:table:pmid:32460303:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE104468"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:20:04Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 29031, "completion_tokens": 1805, "cached_tokens": 528}}, "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:32460303", "type": "paper", "label": "pmid:32460303"}, {"id": "source:pmid:32460303", "type": "manuscript", "label": "PMID 32460303 full text"}, {"id": "data:geo:GSE104468", "type": "dataset", "label": "GEO GSE104468"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32460303", "type": "paper", "label": "pmid:32460303"}, {"id": "source:pmid:32460303", "type": "manuscript", "label": "PMID 32460303 full text"}, {"id": "data:geo:GSE104468", "type": "dataset", "label": "GEO GSE104468"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32460303", "type": "extraction", "used": ["source:pmid:32460303"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE104468", "type": "accession_resolution", "used": ["data:geo:GSE104468"], "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:32460303", "parent_hash": "sha256:77404babfdeb6c04a959648c5b6393d27739b9d5b59475074f75fa8edd317dfe", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE104468 licence not read", "asset:data:geo:GSE104468 not downloaded", "asset:data:geo:GSE46171 licence not read", "asset:data:geo:GSE46171 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["gilent-072363 SurePrint G3 Human GE v3 8×60K Microarray (Agilent, Santa Clara, CA) and GPL6480 Agile", "nd GPL6480 Agilent-014850 Whole Human Genome Microarray 4×44K G4112F (Agilent, Santa Clara, CA), res"], "order_basis": "paper_text_order:2057", "id": "assay:1"}, {"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": ["The Bioconductor R packages “limma” [19], was applied to analyze GSE104468 and GSE46171 RAW datasets. Original p-values were corrected using the Benjamini-Hochberg method."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T02:25:30+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}}}