{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32699530", "kind": "science-record", "revision": 7, "content_hash": "sha256:b65a9ccda40b1531f0fd00efaf3a1f7712dd2cc10f24c433839f50bd4dca95fc", "created_at": "2026-11-01T15:41:06Z", "updated_at": "2026-11-01T22:01:56Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identifying the novel key genes in renal cell carcinoma by bioinformatics analysis and cell experiments.", "doi": "10.1186/s12935-020-01405-6", "pmid": "32699530", "authors": ["Yeda Chen", "Di Gu", "Yaoan Wen", "Shuxin Yang", "Xiaolu Duan", "Yongchang Lai", "Jianan Yang", "Daozhang Yuan", "Aisha Khan", "Wenqi Wu", "Guohua Zeng"], "journal": "Cancer cell international", "year": 2020, "abstract": "BACKGROUND: Although major driver gene have been identified, the complex molecular heterogeneity of renal cell cancer (RCC) remains unclear. Therefore, more relevant genes need to be identified to explain the pathogenesis of renal cancer.\nMETHODS: Microarray datasets GSE781, GSE6344, GSE53000 and GSE68417 were downloaded from Gene Expression Omnibus (GEO) database. The differentially expressed genes (DEGs) were identified by employing GEO2R tool, and function enrichment analyses were performed by using DAVID. The protein-protein interaction network (PPI) was constructed and the module analysis was performed using STRING and Cytoscape. Survival analysis was performed using GEPIA. Differential expression was verified in Oncomine. Cell experiments (cell viability assays, transwell migration and invasion assays, wound healing assay, flow cytometry) were utilized to verify the roles of the hub genes on the proliferation of kidney cancer cells (A498 and OSRC-2 cell lines).\nRESULTS: A total of 215 DEGs were identified from four datasets. Six hub gene (SUCLG1, PCK2, GLDC, SLC12A1, ATP1A1, PDHA1) were identified and the overall survival time of patients with RCC were significantly shorter. The expression levels of these six genes were significantly decreased in six RCC cell lines(A498, OSRC-2, 786- O, Caki-1, ACHN, 769-P) compared to 293t cell line. The expression level of both mRNA and protein of these genes were downregulated in RCC samples compared to those in paracancerous normal tissues. Cell viability assays showed that overexpressions of SUCLG1, PCK2, GLDC significantly decreased proliferation of RCC. Transwell migration, invasion, wound healing assay showed overexpression of three genes(SUCLG1, PCK2, GLDC) significantly inhibited the migration, invasion of RCC. Flow cytometry analysis showed that overexpression of three genes(SUCLG1, PCK2, GLDC) induced G1/S/G2 phase arrest of RCC cells.\nCONCLUSION: Based on our current findings, it is concluded that SUCLG1, PCK2, GLDC may serve as a potential prognostic marker of RCC.", "claims": [{"id": "claim-method", "statement": "The DEGs between ccRCC and non-cancerous samples were screened using GEO2R which is an interactive web tool that allows users to compare two or more datasets in a GEO series for identifying DEGs in experimental conditions. The adjusted P-values (adj. P) and Benjamini and Hochberg false discovery rate were applied to provide a balance between discovery of statistically significant genes and limitations of false-positives. Probe sets without corresponding gene symbols or genes with more than one probe set were removed or averaged, respectively. Adj. P-value < 0.01 and logFC (fold change) > 1 were considered statistically significant.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32699530", "locator": "sections[4] \"Identification of DEGs\" paragraph 2", "quote": "The DEGs between ccRCC and non-cancerous samples were screened using GEO2R which is an interactive web tool that allows users to compare two or more datasets in a GEO series for identifying DEGs in experimental conditions. The adjusted P-values (adj. P) and Benjamini and Hochberg false discovery rate were applied to provide a balance between discovery of statistically significant genes and limitations of false-positives. Probe sets without corresponding gene symbols or genes with more than one probe set were removed or averaged, respectively. Adj. P-value < 0.01 and logFC (fold change) > 1 were considered statistically significant."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32699530", "locator": "sections[34] \"Availability of data and materials\" paragraph 2", "quote": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request"}], "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:32699530"], "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:GSE53000"], "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:GSE53000"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32699530", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12935-020-01405-6", "sha256": "sha256:7ba8eb8c52897d3d6c6e3419fe06ef3eaae9929829be7c641fbde6655ff4ae30", "bytes": 42310, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12935-020-01405-6", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7372855", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE53000", "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=GSE53000", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53000", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1279951", "GSM1279952", "GSM1279953", "GSM1279954", "GSM1279955", "GSM1279956", "GSM1279957", "GSM1279959", "GSM1279960", "GSM1279962", "GSM1279963", "GSM1279964", "GSM1279965", "GSM1279966", "GSM1279967", "GSM1279968", "GSM1279969", "GSM1279970", "GSM1279971", "GSM1279972", "GSM1279973", "GSM1279974", "GSM1279975", "GSM1279976", "GSM1279977", "GSM1279978", "GSM1279979", "GSM1279980", "GSM1279982", "GSM1279983", "GSM1279984", "GSM1279985", "GSM1279986", "GSM1279987", "GSM1279988", "GSM1279989", "GSM1279990", "GSM1279991", "GSM1279992", "GSM1279993", "GSM1279994", "GSM1279995", "GSM1279996", "GSM1279997", "GSM1279998", "GSM1279999", "GSM1280000", "GSM1280001", "GSM1280002", "GSM1280003", "GSM1280004", "GSM1280005", "GSM1280006", "GSM1280007", "GSM1280010", "GSM1280012", "GSM1280013", "GSM1280014", "GSM1280015", "GSM1280016", "GSM1280017", "GSM1280018"], "sample_count": 62, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Expression data from spatially separated samples of different ccRCC 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:GSE6344", "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=GSE6344", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE6344", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM146778", "GSM146779", "GSM146780", "GSM146781", "GSM146782", "GSM146783", "GSM146784", "GSM146785", "GSM146786", "GSM146787", "GSM146788", "GSM146789", "GSM146790", "GSM146791", "GSM146792", "GSM146793", "GSM146794", "GSM146795", "GSM146796", "GSM146797", "GSM146798", "GSM146799", "GSM146800", "GSM146801", "GSM146802", "GSM146803", "GSM146804", "GSM146805", "GSM146806", "GSM146807", "GSM146808", "GSM146809", "GSM146810", "GSM146811", "GSM146812", "GSM146813", "GSM146814", "GSM146815", "GSM146816", "GSM146817"], "sample_count": 40, "group_sizes": null, "group_sizes_basis": null, "platform": "96;97", "taxon": "Homo sapiens", "title": "Gene expression in Stage 1,2 Normal and Tumor kidney cancer", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE68417", "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=GSE68417", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE68417", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1671350", "GSM1671351", "GSM1671352", "GSM1671353", "GSM1671354", "GSM1671355", "GSM1671356", "GSM1671357", "GSM1671358", "GSM1671359", "GSM1671360", "GSM1671361", "GSM1671362", "GSM1671363", "GSM1671364", "GSM1671365", "GSM1671366", "GSM1671367", "GSM1671368", "GSM1671369", "GSM1671370", "GSM1671371", "GSM1671372", "GSM1671373", "GSM1671374", "GSM1671375", "GSM1671376", "GSM1671377", "GSM1671378", "GSM1671379", "GSM1671380", "GSM1671381", "GSM1671382", "GSM1671383", "GSM1671384", "GSM1671385", "GSM1671386", "GSM1671387", "GSM1671388", "GSM1671389", "GSM1671390", "GSM1671391", "GSM1671392", "GSM1671393", "GSM1671394", "GSM1671395", "GSM1671396", "GSM1671397", "GSM1671398"], "sample_count": 49, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Gene expression characterization of high and low grade clear cell renal cell carcinoma", "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:GSE781", "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=GSE781", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE781", "version": null, "note": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM11805", "GSM11810", "GSM11814", "GSM11815", "GSM11823", "GSM11827", "GSM11830", "GSM11832", "GSM12067", "GSM12069", "GSM12075", "GSM12078", "GSM12079", "GSM12083", "GSM12098", "GSM12099", "GSM12100", "GSM12101", "GSM12105", "GSM12106", "GSM12268", "GSM12269", "GSM12270", "GSM12274", "GSM12283", "GSM12287", "GSM12298", "GSM12299", "GSM12300", "GSM12301", "GSM12399", "GSM12412", "GSM12444", "GSM12448"], "sample_count": 34, "group_sizes": null, "group_sizes_basis": null, "platform": "96;97", "taxon": "Homo sapiens", "title": "Normal and Renal Cell Carcinoma Kidney Tissue, Human", "resolution_checked_at": "2026-11-01T15:14:33Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32699530:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4a10292f2373f74ee96c371dbc2aace15df748deb851201306be32fad1776546", "bytes": 2911, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#Tab1", "version": null, "note": "GO and KEGG pathway enrichment analysis of DEGs in KIRC samples", "structure": {"pmcid": "PMC7372855", "section_index": 5, "section_title": "KEGG and GO enrichment analyses of DEGs", "row_count": 45, "column_count": 4}, "table": {"label": "Table 1", "caption": "GO and KEGG pathway enrichment analysis of DEGs in KIRC samples", "rows": [["Term/pathway ID", "Description", "Count in gene set", "P-value"], ["BP"], ["GO:0019752", "Carboxylic acid metabolic process", "45", "1.07E−16"], ["GO:0006082", "Organic acid metabolic process", "47", "1.23E−16"], ["GO:0043436", "Oxoacid metabolic process", "45", "1.33E−16"], ["GO:0044282", "Small molecule catabolic process", "25", "6.84E−12"], ["GO:0001822", "Kidney development", "22", "1.91E−11"], ["GO:0072001", "Renal system development", "22", "5.72E−11"], ["GO:0055114", "Oxidation–reduction process", "40", "8.91E−11"], ["GO:0016054", "Organic acid catabolic process", "19", "3.42E−10"], ["GO:0001655", "Urogenital system development", "22", "5.53E−10"], ["GO:0006811", "Ion transport", "48", "8.49E−10"], ["CC"], ["GO:0070062", "Extracellular exosome", "101", "9.00E−25"], ["GO:1903561", "Extracellular vesicle", "101", "1.34E−24"], ["GO:0043230", "Extracellular organelle", "101", "1.38E−24"], ["GO:0031988", "Membrane-bounded vesicle", "107", "7.12E−20"], ["GO:0044421", "Extracellular region part", "108", "5.23E−18"], ["GO:0005576", "Extracellular region", "113", "1.48E−14"], ["GO:0045177", "Apical part of cell", "26", "1.04E−11"], ["GO:0016323", "Basolateral plasma membrane", "20", "2.35E−11"], ["GO:0016324", "Apical plasma membrane", "23", "4.15E−11"], ["GO:0098590", "Plasma membrane region", "39", "3.45E−10"], ["MF"], ["GO:0048037", "Cofactor binding", "20", "2.23E−09"], ["GO:0050662", "Coenzyme binding", "14", "7.50E−07"], ["GO:0015291", "Secondary active transmembrane transporter activity", "15", "1.92E−06"], ["GO:0008509", "Anion transmembrane transporter activity", "14", "2.26E−06"], ["GO:0022804", "Active transmembrane transporter activity", "18", "5.05E−06"], ["GO:0016614", "Oxidoreductase activity, acting on CH–OH group of donors", "11", "1.05E−05"], ["GO:1901681", "Sulfur compound binding", "13", "4.69E−05"], ["GO:0015103", "Inorganic anion transmembrane transporter activity", "10", "5.01E−05"], ["GO:0016709", "Oxidoreductase activity, with incorporation or reduction of molecular oxygen", "6", "2.11E−04"], ["GO:0042802", "Identical protein binding", "34", "2.45E−04"], ["KEGG"], ["hsa01100", "Metabolic pathways", "48", "3.79E−09"], ["hsa01130", "Biosynthesis of antibiotics", "18", "6.50E−08"], ["hsa01200", "Carbon metabolism", "12", "2.45E−06"], ["hsa04960", "Aldosterone-regulated sodium reabsorption", "6", "4.38E−04"], ["hsa00010", "Glycolysis/Gluconeogenesis", "7", "8.33E−04"], ["hsa00280", "Valine, leucine and isoleucine degradation", "6", "1.05E−03"], ["hsa00020", "Citrate cycle (TCA cycle)", "5", "1.45E−03"], ["hsa00260", "Glycine, serine and threonine metabolism", "5", "3.88E−03"], ["hsa04610", "Complement and coagulation cascades", "6", "5.74E−03"], ["hsa04966", "Collecting duct acid secretion", "4", "9.94E−03"]], "row_count": 45, "column_count": 4, "numeric_cells": 120, "header_rows": 1, "locator": "section[20]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:32699530:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:24ed00b3ac0d3a0e3d196e3ed1d6d183bf9ef2014f52949411c6bc4b342b7c87", "bytes": 1973, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[21]/table-wrap[1]#Tab2", "version": null, "note": "GO and KEGG pathway enrichment analysis of DEGs in the most significant module", "structure": {"pmcid": "PMC7372855", "section_index": 6, "section_title": "PPI network construction and module analysis", "row_count": 33, "column_count": 4}, "table": {"label": "Table 2", "caption": "GO and KEGG pathway enrichment analysis of DEGs in the most significant module", "rows": [["Term/Pathway ID", "Description", "Count in gene set", "P-value"], ["BP"], ["GO:0006813", "Potassium ion transport", "4", "2.29E−04"], ["GO:0055082", "Cellular chemical homeostasis", "5", "5.69E−04"], ["GO:0006732", "Coenzyme metabolic process", "4", "7.29E−04"], ["GO:0019752", "Carboxylic acid metabolic process", "5", "9.93E−04"], ["GO:0043436", "Oxoacid metabolic process", "5", "1.02E−03"], ["GO:0019725", "Cellular homeostasis", "5", "1.02E−03"], ["GO:0051186", "Cofactor metabolic process", "4", "1.30E−03"], ["GO:0006082", "Organic acid metabolic process", "5", "1.41E−03"], ["GO:0035383", "Thioester metabolic process", "3", "1.44E−03"], ["GO:0006637", "Acyl-CoA metabolic process", "3", "1.44E−03"], ["CC"], ["GO:0005759", "Mitochondrial matrix", "4", "1.83E−03"], ["GO:0016324", "Apical plasma membrane", "3", "1.33E−02"], ["GO:0070062", "Extracellular exosome", "6", "1.70E−02"], ["GO:1903561", "Extracellular vesicle", "6", "1.74E−02"], ["GO:0043230", "Extracellular organelle", "6", "1.74E−02"], ["GO:0044429", "Mitochondrial part", "4", "1.94E−02"], ["GO:0045177", "Apical part of cell", "3", "1.98E−02"], ["GO:0030315", "T-tubule", "2", "2.63E−02"], ["GO:0014704", "Intercalated disc", "2", "3.06E−02"], ["GO:0044291", "Cell–cell contact zone", "2", "4.08E−02"], ["MF"], ["GO:0022804", "Active transmembrane transporter activity", "3", "2.22E−02"], ["KEGG"], ["hsa00020", "Citrate cycle (TCA cycle)", "3", "5.07E−04"], ["hsa01130", "Biosynthesis of antibiotics", "4", "1.44E−03"], ["hsa01200", "Carbon metabolism", "3", "7.02E−03"], ["hsa04964", "Proximal tubule bicarbonate reclamation", "2", "2.65E−02"], ["hsa01100", "Metabolic pathways", "5", "3.76E−02"], ["hsa00260", "Glycine, serine and threonine metabolism", "2", "4.45E−02"], ["hsa00620", "Pyruvate metabolism", "2", "4.56E−02"]], "row_count": 33, "column_count": 4, "numeric_cells": 84, "header_rows": 1, "locator": "section[21]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:32699530:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4a10292f2373f74ee96c371dbc2aace15df748deb851201306be32fad1776546", "bytes": 2911, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#Tab1", "version": null, "note": "GO and KEGG pathway enrichment analysis of DEGs in KIRC samples", "structure": {"pmcid": "PMC7372855", "section_index": 20, "section_title": "KEGG and GO enrichment analyses of DEGs", "row_count": 45, "column_count": 4}, "table": {"label": "Table 1", "caption": "GO and KEGG pathway enrichment analysis of DEGs in KIRC samples", "rows": [["Term/pathway ID", "Description", "Count in gene set", "P-value"], ["BP"], ["GO:0019752", "Carboxylic acid metabolic process", "45", "1.07E−16"], ["GO:0006082", "Organic acid metabolic process", "47", "1.23E−16"], ["GO:0043436", "Oxoacid metabolic process", "45", "1.33E−16"], ["GO:0044282", "Small molecule catabolic process", "25", "6.84E−12"], ["GO:0001822", "Kidney development", "22", "1.91E−11"], ["GO:0072001", "Renal system development", "22", "5.72E−11"], ["GO:0055114", "Oxidation–reduction process", "40", "8.91E−11"], ["GO:0016054", "Organic acid catabolic process", "19", "3.42E−10"], ["GO:0001655", "Urogenital system development", "22", "5.53E−10"], ["GO:0006811", "Ion transport", "48", "8.49E−10"], ["CC"], ["GO:0070062", "Extracellular exosome", "101", "9.00E−25"], ["GO:1903561", "Extracellular vesicle", "101", "1.34E−24"], ["GO:0043230", "Extracellular organelle", "101", "1.38E−24"], ["GO:0031988", "Membrane-bounded vesicle", "107", "7.12E−20"], ["GO:0044421", "Extracellular region part", "108", "5.23E−18"], ["GO:0005576", "Extracellular region", "113", "1.48E−14"], ["GO:0045177", "Apical part of cell", "26", "1.04E−11"], ["GO:0016323", "Basolateral plasma membrane", "20", "2.35E−11"], ["GO:0016324", "Apical plasma membrane", "23", "4.15E−11"], ["GO:0098590", "Plasma membrane region", "39", "3.45E−10"], ["MF"], ["GO:0048037", "Cofactor binding", "20", "2.23E−09"], ["GO:0050662", "Coenzyme binding", "14", "7.50E−07"], ["GO:0015291", "Secondary active transmembrane transporter activity", "15", "1.92E−06"], ["GO:0008509", "Anion transmembrane transporter activity", "14", "2.26E−06"], ["GO:0022804", "Active transmembrane transporter activity", "18", "5.05E−06"], ["GO:0016614", "Oxidoreductase activity, acting on CH–OH group of donors", "11", "1.05E−05"], ["GO:1901681", "Sulfur compound binding", "13", "4.69E−05"], ["GO:0015103", "Inorganic anion transmembrane transporter activity", "10", "5.01E−05"], ["GO:0016709", "Oxidoreductase activity, with incorporation or reduction of molecular oxygen", "6", "2.11E−04"], ["GO:0042802", "Identical protein binding", "34", "2.45E−04"], ["KEGG"], ["hsa01100", "Metabolic pathways", "48", "3.79E−09"], ["hsa01130", "Biosynthesis of antibiotics", "18", "6.50E−08"], ["hsa01200", "Carbon metabolism", "12", "2.45E−06"], ["hsa04960", "Aldosterone-regulated sodium reabsorption", "6", "4.38E−04"], ["hsa00010", "Glycolysis/Gluconeogenesis", "7", "8.33E−04"], ["hsa00280", "Valine, leucine and isoleucine degradation", "6", "1.05E−03"], ["hsa00020", "Citrate cycle (TCA cycle)", "5", "1.45E−03"], ["hsa00260", "Glycine, serine and threonine metabolism", "5", "3.88E−03"], ["hsa04610", "Complement and coagulation cascades", "6", "5.74E−03"], ["hsa04966", "Collecting duct acid secretion", "4", "9.94E−03"]], "row_count": 45, "column_count": 4, "numeric_cells": 120, "header_rows": 1, "locator": "section[20]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:32699530:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:24ed00b3ac0d3a0e3d196e3ed1d6d183bf9ef2014f52949411c6bc4b342b7c87", "bytes": 1973, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[21]/table-wrap[1]#Tab2", "version": null, "note": "GO and KEGG pathway enrichment analysis of DEGs in the most significant module", "structure": {"pmcid": "PMC7372855", "section_index": 21, "section_title": "PPI network construction and module analysis", "row_count": 33, "column_count": 4}, "table": {"label": "Table 2", "caption": "GO and KEGG pathway enrichment analysis of DEGs in the most significant module", "rows": [["Term/Pathway ID", "Description", "Count in gene set", "P-value"], ["BP"], ["GO:0006813", "Potassium ion transport", "4", "2.29E−04"], ["GO:0055082", "Cellular chemical homeostasis", "5", "5.69E−04"], ["GO:0006732", "Coenzyme metabolic process", "4", "7.29E−04"], ["GO:0019752", "Carboxylic acid metabolic process", "5", "9.93E−04"], ["GO:0043436", "Oxoacid metabolic process", "5", "1.02E−03"], ["GO:0019725", "Cellular homeostasis", "5", "1.02E−03"], ["GO:0051186", "Cofactor metabolic process", "4", "1.30E−03"], ["GO:0006082", "Organic acid metabolic process", "5", "1.41E−03"], ["GO:0035383", "Thioester metabolic process", "3", "1.44E−03"], ["GO:0006637", "Acyl-CoA metabolic process", "3", "1.44E−03"], ["CC"], ["GO:0005759", "Mitochondrial matrix", "4", "1.83E−03"], ["GO:0016324", "Apical plasma membrane", "3", "1.33E−02"], ["GO:0070062", "Extracellular exosome", "6", "1.70E−02"], ["GO:1903561", "Extracellular vesicle", "6", "1.74E−02"], ["GO:0043230", "Extracellular organelle", "6", "1.74E−02"], ["GO:0044429", "Mitochondrial part", "4", "1.94E−02"], ["GO:0045177", "Apical part of cell", "3", "1.98E−02"], ["GO:0030315", "T-tubule", "2", "2.63E−02"], ["GO:0014704", "Intercalated disc", "2", "3.06E−02"], ["GO:0044291", "Cell–cell contact zone", "2", "4.08E−02"], ["MF"], ["GO:0022804", "Active transmembrane transporter activity", "3", "2.22E−02"], ["KEGG"], ["hsa00020", "Citrate cycle (TCA cycle)", "3", "5.07E−04"], ["hsa01130", "Biosynthesis of antibiotics", "4", "1.44E−03"], ["hsa01200", "Carbon metabolism", "3", "7.02E−03"], ["hsa04964", "Proximal tubule bicarbonate reclamation", "2", "2.65E−02"], ["hsa01100", "Metabolic pathways", "5", "3.76E−02"], ["hsa00260", "Glycine, serine and threonine metabolism", "2", "4.45E−02"], ["hsa00620", "Pyruvate metabolism", "2", "4.56E−02"]], "row_count": 33, "column_count": 4, "numeric_cells": 84, "header_rows": 1, "locator": "section[21]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:32699530:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:bc7d9e20be376092692a84cf316b78e76f003670d875f63e8f9761ab93995434", "bytes": 2338, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[22]/table-wrap[1]#Tab3", "version": null, "note": "Functional roles of 11 hub genes with betweenness degrees ≥ 10", "structure": {"pmcid": "PMC7372855", "section_index": 22, "section_title": "Hub gene selection and analysis", "row_count": 12, "column_count": 4}, "table": {"label": "Table 3", "caption": "Functional roles of 11 hub genes with betweenness degrees ≥ 10", "rows": [["No.", "Gene symbol", "Full name", "Function"], ["1", "ANK2", "Ankyrin 2", "Attaches integral membrane proteins to cytoskeletal elements.Also binds to cytoskeletal proteins. Plays a role in endocytosis and intracellular protein transport"], ["2", "SUCLG1", "Succinate-CoA Ligase Alpha Subunit", "Succinyl-CoA synthetase functions in the citric acid cycle, coupling the hydrolysis of succinyl-CoA to the synthesis of either ATP or GTP"], ["3", "GLDC", "Glycine Decarboxylase", "The P protein (GLDC) binds the alpha-amino group of glycine through its pyridoxal phosphate cofactor; CO2 is released and the remaining methylamine moiety is then transferred to the lipoamide cofactor of the H protein (GCSH)"], ["4", "SLC12A1", "Solute Carrier Family 12 Member 1", "Mediates sodium and chloride reabsorption. Plays a vital role in the regulation of ionic balance and cell volume"], ["5", "PIPOX", "Pipecolic Acid And Sarcosine Oxidase", "Metabolizes sarcosine, L-pipecolic acid and l-proline"], ["6", "KNG1", "Kininogen 1", "Kininogens 1 is inhibitors of thiol proteases; plays an important role in blood coagulation; inhibits the thrombin- and plasmin-induced aggregation of thrombocytes"], ["7", "SLC9A2", "Solute Carrier Family 9 Member A2", "Involved in pH regulation to eliminate acids generated by active metabolism or to counter adverse environmental conditions"], ["8", "PCK2", "Phosphoenolpyruvate Carboxykinase 2", "Catalyzes the conversion of oxaloacetate to phosphoenolpyruvate"], ["9", "XPNPEP2", "X-Prolyl Aminopeptidase 2", "Membrane-bound metalloprotease which catalyzes the removal of a penultimate prolyl residue from the N-termini of peptides. May play a role in the metabolism of the vasodilator bradykinin"], ["10", "ATP1A1", "ATPase Na+/K+ Transporting Subunit Alpha 1", "This action creates the electrochemical gradient of sodium and potassium ions, providing the energy for active transport of various nutrients"], ["11", "PDHA1", "Pyruvate Dehydrogenase E1 Alpha 1 Subunit", "The pyruvate dehydrogenase complex catalyzes the overall conversion of pyruvate to acetyl-CoA and CO2, and thereby links the glycolytic pathway to the tricarboxylic cycle."]], "row_count": 12, "column_count": 4, "numeric_cells": 21, "header_rows": 1, "locator": "section[22]/table-wrap[1]#Tab3"}}], "gaps": ["asset:data:geo:GSE53000 not downloaded", "asset:data:geo:GSE53000 licence not read", "asset:data:geo:GSE6344 not downloaded", "asset:data:geo:GSE6344 licence not read", "asset:data:geo:GSE68417 not downloaded", "asset:data:geo:GSE68417 licence not read", "asset:data:geo:GSE781 not downloaded", "asset:data:geo:GSE781 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "analysis of variance"}}, {"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": null, "specific": null, "label": "GEO2R, using adjusted P-values with Benjamini–Hochberg false discovery rate, with a significance threshold of adjusted P-value < 0.01 and logFC > 1; source data were obtained from the GEO datasets GSE781, GSE6344, GSE53000 and GSE68417.", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The DEGs between ccRCC and non-cancerous samples were screened using GEO2R which is an interactive web tool that allows users to compare two or more datasets in a GEO series for identifying DEGs in experimental conditions. The adjusted P-values (adj. P) and Benjamini and Hochberg false discovery rate were applied to provide a balance between discovery of statistically significant genes and limitations of false-positives. Probe sets without corresponding gene symbols or genes with more than one probe set were removed or averaged, respectively. Adj. P-value < 0.01 and logFC (fold change) > 1 were considered statistically significant."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["GSE781", "GSE6344", "GSE53000", "GSE68417"], "resolved_accessions": ["GSE781", "GSE6344", "GSE53000", "GSE68417"], "statements": ["The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request"], "basis": "The paper names GSE781, GSE6344, GSE53000, GSE68417 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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:32699530", "data:geo:GSE53000", "asset:table:pmid:32699530:1", "asset:table:pmid:32699530:2", "asset:table:pmid:32699530:3", "asset:table:pmid:32699530:4", "asset:table:pmid:32699530:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE53000"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:30Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 34132, "completion_tokens": 1968, "cached_tokens": 785}}, "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:32699530", "type": "paper", "label": "pmid:32699530"}, {"id": "source:pmid:32699530", "type": "manuscript", "label": "PMID 32699530 full text"}, {"id": "data:geo:GSE53000", "type": "dataset", "label": "GEO GSE53000"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32699530", "type": "paper", "label": "pmid:32699530"}, {"id": "source:pmid:32699530", "type": "manuscript", "label": "PMID 32699530 full text"}, {"id": "data:geo:GSE53000", "type": "dataset", "label": "GEO GSE53000"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32699530", "type": "extraction", "used": ["source:pmid:32699530"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE53000", "type": "accession_resolution", "used": ["data:geo:GSE53000"], "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:32699530", "parent_hash": "sha256:9f1e2296bcd42c82e8277d44a24df34739598772bb84d3334967d391fc30b57f", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE53000 licence not read", "asset:data:geo:GSE53000 not downloaded", "asset:data:geo:GSE6344 licence not read", "asset:data:geo:GSE6344 not downloaded", "asset:data:geo:GSE68417 licence not read", "asset:data:geo:GSE68417 not downloaded", "asset:data:geo:GSE781 licence not read", "asset:data:geo:GSE781 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": 0.93, "evidence": ["n the pathogenesis of renal cancer. METHODS: Microarray datasets GSE781, GSE6344, GSE53000 and GSE68"], "order_basis": "paper_text_order:308", "id": "assay:1"}, {"role": "data_generation", "definition_id": "flow_cytometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["on and invasion assays, wound healing assay, flow cytometry) were utilized to verify the roles of the hu", "ly inhibited the migration, invasion of RCC. Flow cytometry analysis showed that overexpression of three"], "order_basis": "paper_text_order:901", "id": "assay:2"}, {"role": "data_generation", "definition_id": "clinical_cohort", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.85, "evidence": ["identified and the overall survival time of patients with RCC were significantly shorter. The expressi"], "order_basis": "paper_text_order:1215", "id": "assay:3"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Materials and methods Cell culture and transfection Human renal carcinoma cell lines OSRC-2 and", "in 6-well plates or 60 mm2 medium dishes and transfected with over expressed plasmids and negative co", "ghai GenePharma Co., Ltd. (Shanghai, China). Transfection was conducted using Lipofectamine® 3000 (The", "nc.). The cells were harvested at 48 h after transfection for reverse transcription-quantitative polym"], "order_basis": "paper_text_order:2159", "id": "assay:4"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Academy of Sciences (Shanghai, China), were cultured in RPMI-1640 medium supplemented with 10% FBS,", "ent experiments. OS-RC-2 and A498 cells were cultured in 6-well plates or 60 mm2 medium dishes and tr"], "order_basis": "paper_text_order:2300", "id": "assay:5"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["tion-quantitative polymerase chain reaction (RT-qPCR) analysis. Statistical analysis All data wer", "n-quantitative polymerase chain reaction (RT-qPCR) analysis. Statistical analysis All data wer"], "order_basis": "paper_text_order:2905", "id": "assay:6"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["analysis of variance"], "order_basis": "consumes_earlier_output", "id": "assay:7"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T04:15:25+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}}}