{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34307447", "kind": "science-record", "revision": 8, "content_hash": "sha256:5935f9bb1c837db1886c17b56668bc5c91ed4fa69e3989259b1438f795978768", "created_at": "2026-11-01T15:41:45Z", "updated_at": "2026-11-01T22:47:10Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "High Expression Levels of CDK1 and CDC20 in Patients With Lung Squamous Cell Carcinoma are Associated With Worse Prognosis.", "doi": "10.3389/fmolb.2021.653805", "pmid": "34307447", "authors": ["Huan Deng", "Qingqing Hang", "Dijian Shen", "Hangjie Ying", "Yibi Zhang", "Xu Qian", "Ming Chen"], "journal": "Frontiers in molecular biosciences", "year": 2021, "abstract": "Purpose: Progress related to the early detection and molecular targeted therapy of lung squamous cell carcinoma (LUSC) remains limited. The goal of our study was to identify key candidate indicators of LUSC. Methods: Three microarray datasets (GSE33532, GSE30219 and GSE19188) were applied to find differentially expressed genes (DEGs). Functional enrichment analyses of DEGs were carried out, and their protein-protein interaction (PPI) network was established. Hub genes were chosen from the PPI network according to their degree scores. Then, overall survival (OS) analyses of hub genes were carried out using Kaplan-Meier plotter, and their GSEA analyses were performed. Public databases were used to verify the expression patterns of CDK1 and CDC20. Furthermore, basic experiments were performed to verify our findings. Results: A total of 1,366 DEGs were identified, containing 669 downregulated and 697 upregulated DEGs. These DEGs were primarily enriched in cell cycle, chromosome centromeric region and nuclear division. Seventeen hub genes were selected from PPI network. Survival analyses demonstrated that CDK1 and CDC20 were closely associated with OS. GSEA analyses revealed that cell cycle, DNA replication, and mismatch repair were associated with CDK1 expression, while spliceosome, RNA degradation and cell cycle were correlated with CDC20 expression. Based on The Cancer Genome Atlas (TCGA) and The Human Protein Atlas (THPA) databases, CDK1 and CDC20 were upregulated in LUSC at the mRNA and protein levels. Moreover, basic experiments also supported the obvious upregulation of CDK1 and CDC20 in LUSC. Conclusion: Our study suggests and validates that CDK1 and CDC20 are potential therapeutic targets and prognostic biomarkers of LUSC.", "claims": [{"id": "claim-method", "statement": "DEGs were selected between LUSC and normal lung tissues using the limma package of R software (Ritchie et al., 2015). To minimize the false discovery rate (FDR), the p-values were adjusted using the Benjamini–Hochberg method.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34307447", "locator": "sections[4] \"Identification of Differentially Expressed Genes\" paragraph 2", "quote": "DEGs were selected between LUSC and normal lung tissues using the limma package of R software (Ritchie et al., 2015). To minimize the false discovery rate (FDR), the p-values were adjusted using the Benjamini–Hochberg method."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34307447", "locator": "sections[20] \"Data Availability Statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors."}], "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:34307447"], "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:GSE19188"], "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": {"fdr_threshold": "with Benjamini–Hochberg false discovery rate adjustment"}, "inputs": ["data:geo:GSE19188"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34307447", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fmolb.2021.653805", "sha256": "sha256:f48fe3aeb5ed2f866a737887340af38972914a788bb8c5f3469f3c5b46d12659", "bytes": 28432, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fmolb.2021.653805", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8292837", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE19188", "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=GSE19188", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19188", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM475656", "GSM475657", "GSM475658", "GSM475659", "GSM475660", "GSM475661", "GSM475662", "GSM475663", "GSM475664", "GSM475665", "GSM475666", "GSM475667", "GSM475668", "GSM475669", "GSM475670", "GSM475671", "GSM475672", "GSM475673", "GSM475674", "GSM475675", "GSM475676", "GSM475677", "GSM475678", "GSM475679", "GSM475680", "GSM475681", "GSM475682", "GSM475683", "GSM475684", "GSM475685", "GSM475686", "GSM475687", "GSM475688", "GSM475689", "GSM475690", "GSM475691", "GSM475692", "GSM475693", "GSM475694", "GSM475695", "GSM475696", "GSM475697", "GSM475698", "GSM475699", "GSM475700", "GSM475701", "GSM475702", "GSM475703", "GSM475704", "GSM475705", "GSM475706", "GSM475707", "GSM475708", "GSM475709", "GSM475710", "GSM475711", "GSM475712", "GSM475713", "GSM475714", "GSM475715", "GSM475716", "GSM475717", "GSM475718", "GSM475719", "GSM475720", "GSM475721", "GSM475722", "GSM475723", "GSM475724", "GSM475725", "GSM475726", "GSM475727", "GSM475728", "GSM475729", "GSM475730", "GSM475731", "GSM475732", "GSM475733", "GSM475734", "GSM475735", "GSM475736", "GSM475737", "GSM475738", "GSM475739", "GSM475740", "GSM475741", "GSM475742", "GSM475743", "GSM475744", "GSM475745", "GSM475746", "GSM475747", "GSM475748", "GSM475749", "GSM475750", "GSM475751", "GSM475752", "GSM475753", "GSM475754", "GSM475755", "GSM475756", "GSM475757", "GSM475758", "GSM475759", "GSM475760", "GSM475761", "GSM475762", "GSM475763", "GSM475764", "GSM475765", "GSM475766", "GSM475767", "GSM475768", "GSM475769", "GSM475770", "GSM475771", "GSM475772", "GSM475773", "GSM475774", "GSM475775", "GSM475776", "GSM475777", "GSM475778", "GSM475779", "GSM475780", "GSM475781", "GSM475782", "GSM475783", "GSM475784", "GSM475785", "GSM475786", "GSM475787", "GSM475788", "GSM475789", "GSM475790", "GSM475791", "GSM475792", "GSM475793", "GSM475794", "GSM475795", "GSM475796", "GSM475797", "GSM475798", "GSM475799", "GSM475800", "GSM475801", "GSM475802", "GSM475803", "GSM475804", "GSM475805", "GSM475806", "GSM475807", "GSM475808", "GSM475809", "GSM475810", "GSM475811"], "sample_count": 156, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data for early stage NSCLC", "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:GSE30219", "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=GSE30219", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE30219", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1465989", "GSM1465990", "GSM1465991", "GSM1465992", "GSM1465993", "GSM1465994", "GSM1465995", "GSM1465996", "GSM1465997", "GSM1465998", "GSM1465999", "GSM748053", "GSM748054", "GSM748055", "GSM748056", "GSM748057", "GSM748058", "GSM748059", "GSM748060", "GSM748061", "GSM748062", "GSM748063", "GSM748064", "GSM748065", "GSM748066", "GSM748067", "GSM748068", "GSM748069", "GSM748070", "GSM748071", "GSM748072", "GSM748073", "GSM748074", "GSM748075", "GSM748076", "GSM748077", "GSM748078", "GSM748079", "GSM748080", "GSM748081", "GSM748083", "GSM748084", "GSM748085", "GSM748086", "GSM748087", "GSM748088", "GSM748089", "GSM748090", "GSM748091", "GSM748092", "GSM748093", "GSM748094", "GSM748095", "GSM748096", "GSM748097", "GSM748098", "GSM748099", "GSM748100", "GSM748101", "GSM748102", "GSM748103", "GSM748104", "GSM748105", "GSM748106", "GSM748107", "GSM748108", "GSM748109", "GSM748110", "GSM748111", "GSM748112", "GSM748113", "GSM748115", "GSM748116", "GSM748117", "GSM748118", "GSM748119", "GSM748120", "GSM748121", "GSM748122", "GSM748123", "GSM748124", "GSM748125", "GSM748126", "GSM748127", "GSM748128", "GSM748129", "GSM748130", "GSM748131", "GSM748132", "GSM748133", "GSM748134", "GSM748135", "GSM748136", "GSM748137", "GSM748138", "GSM748139", "GSM748140", "GSM748141", "GSM748142", "GSM748143", "GSM748144", "GSM748145", "GSM748146", "GSM748147", "GSM748148", "GSM748149", "GSM748150", "GSM748151", "GSM748152", "GSM748153", "GSM748154", "GSM748155", "GSM748156", "GSM748157", "GSM748158", "GSM748159", "GSM748160", "GSM748161", "GSM748162", "GSM748163", "GSM748164", "GSM748165", "GSM748166", "GSM748167", "GSM748168", "GSM748169", "GSM748170", "GSM748171", "GSM748172", "GSM748173", "GSM748174", "GSM748175", "GSM748176", "GSM748177", "GSM748178", "GSM748179", "GSM748180", "GSM748181", "GSM748182", "GSM748183", "GSM748184", "GSM748185", "GSM748186", "GSM748187", "GSM748188", "GSM748189", "GSM748191", "GSM748192", "GSM748193", "GSM748195", "GSM748196", "GSM748197", "GSM748198", "GSM748199", "GSM748200", "GSM748201", "GSM748202", "GSM748203", "GSM748206", "GSM748207", "GSM748209", "GSM748210", "GSM748211", "GSM748212", "GSM748213", "GSM748214", "GSM748215", "GSM748216", "GSM748217", "GSM748218", "GSM748219", "GSM748220", "GSM748221", "GSM748222", "GSM748223", "GSM748224", "GSM748225", "GSM748226", "GSM748227", "GSM748228", "GSM748229", "GSM748232", "GSM748233", "GSM748234", "GSM748235", "GSM748239", "GSM748240", "GSM748242", "GSM748243", "GSM748244", "GSM748245", "GSM748246", "GSM748247", "GSM748248", "GSM748249", "GSM748250", "GSM748251", "GSM748252", "GSM748253", "GSM748254", "GSM748255", "GSM748256", "GSM748257", "GSM748258", "GSM748259", "GSM748260", "GSM748261", "GSM748262", "GSM748263", "GSM748264", "GSM748265", "GSM748266", "GSM748267", "GSM748268", "GSM748269", "GSM748270", "GSM748271", "GSM748272", "GSM748273", "GSM748274", "GSM748275", "GSM748276", "GSM748277", "GSM748278", "GSM748279", "GSM748280", "GSM748281", "GSM748282", "GSM748283", "GSM748284", "GSM748285", "GSM748286", "GSM748287", "GSM748288", "GSM748291", "GSM748292", "GSM748294", "GSM748295", "GSM748296", "GSM748297", "GSM748298", "GSM748299", "GSM748300", "GSM748301", "GSM748302", "GSM748303", "GSM748304", "GSM748305", "GSM748306", "GSM748307", "GSM748308", "GSM748309", "GSM748310", "GSM748311", "GSM748312", "GSM748313", "GSM748314", "GSM748315", "GSM748316", "GSM748317", "GSM748318", "GSM748319", "GSM748320", "GSM748321", "GSM748323", "GSM748324", "GSM748325", "GSM748326", "GSM748327", "GSM748328", "GSM748329", "GSM748330", "GSM748331", "GSM748332", "GSM748333", "GSM748334", "GSM748335", "GSM748336", "GSM748337", "GSM748338", "GSM748339", "GSM748341", "GSM748342", "GSM748343", "GSM748344", "GSM748345", "GSM748346", "GSM748347", "GSM748348", "GSM748349", "GSM748350", "GSM748351", "GSM748352", "GSM748353", "GSM748354", "GSM748355", "GSM748356", "GSM748357", "GSM748358", "GSM748359", "GSM748360", "GSM748361", "GSM748362", "GSM748363", "GSM748364", "GSM748365", "GSM748366"], "sample_count": 307, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "\"Off-context\" gene expression in lung cancer identifies a group of metastatic-prone tumors", "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:GSE33532", "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=GSE33532", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33532", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM835268", "GSM835269", "GSM835270", "GSM835271", "GSM835272", "GSM835273", "GSM835274", "GSM835275", "GSM835276", "GSM835277", "GSM835278", "GSM835279", "GSM835280", "GSM835281", "GSM835282", "GSM835283", "GSM835284", "GSM835285", "GSM835286", "GSM835287", "GSM835288", "GSM835289", "GSM835290", "GSM835291", "GSM835292", "GSM835293", "GSM835294", "GSM835295", "GSM835296", "GSM835297", "GSM835298", "GSM835299", "GSM835300", "GSM835301", "GSM835302", "GSM835303", "GSM835304", "GSM835305", "GSM835306", "GSM835307", "GSM835308", "GSM835309", "GSM835310", "GSM835311", "GSM835312", "GSM835313", "GSM835314", "GSM835315", "GSM835316", "GSM835317", "GSM835318", "GSM835319", "GSM835320", "GSM835321", "GSM835322", "GSM835323", "GSM835324", "GSM835325", "GSM835326", "GSM835327", "GSM835328", "GSM835329", "GSM835330", "GSM835331", "GSM835332", "GSM835333", "GSM835334", "GSM835335", "GSM835336", "GSM835337", "GSM835338", "GSM835339", "GSM835340", "GSM835341", "GSM835342", "GSM835343", "GSM835344", "GSM835345", "GSM835346", "GSM835347", "GSM835348", "GSM835349", "GSM835350", "GSM835351", "GSM835352", "GSM835353", "GSM835354", "GSM835355", "GSM835356", "GSM835357", "GSM835358", "GSM835359", "GSM835360", "GSM835361", "GSM835362", "GSM835363", "GSM835364", "GSM835365", "GSM835366", "GSM835367"], "sample_count": 100, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Intratumor heterogeneity of gene expression profiles in early stage non-small cell lung cancer (NSCLC)", "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:34307447:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:38c377ea89ae4f8c4f9ed8a3df6021d17ab5e2801d2da8fa20dac6105a09914b", "bytes": 517, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "Characteristics of the included datasets from GEO.", "structure": {"pmcid": "PMC8292837", "section_index": 3, "section_title": "The Obtainment of Microarray Datasets", "row_count": 4, "column_count": 7}, "table": {"label": "TABLE 1", "caption": "Characteristics of the included datasets from GEO.", "rows": [["GEO datasets", "Publication year", "Country", "RNA-Seq platforms", "LUSC", "Normal", "Sum"], ["GSE33532 (Meister et al., 2014)", "2014", "Germany", "GPL570", "16", "20", "36"], ["GSE30219 (Rousseaux et al., 2013)", "2013", "France", "GPL570", "61", "14", "75"], ["GSE19188 (Hou et al., 2010)", "2010", "Netherlands", "GPL570", "27", "65", "92"]], "row_count": 4, "column_count": 7, "numeric_cells": 18, "header_rows": 1, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:34307447:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3c0146defde18867e30df1bda6685c630e09f200137c9e64da841743e67543db", "bytes": 2817, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T3", "version": null, "note": "Functional roles of all hub genes with degrees>60.", "structure": {"pmcid": "PMC8292837", "section_index": 6, "section_title": "Construction of the PPI Network and Selection of Hub Genes", "row_count": 18, "column_count": 5}, "table": {"label": "TABLE 3", "caption": "Functional roles of all hub genes with degrees>60.", "rows": [["No", "Gene Symbol", "Degree", "Full name", "Function"], ["1", "CDK1", "123", "Cyclin-dependent kinase 1", "CDK1 regulates the cell cycle progression, apoptosis and carcinogenesis of several cancers"], ["2", "CDC20", "106", "Cell division cycle 20", "CDC20 participates in the pathogenesis of NSCLC, and its higher expression correlates with higher tumor grade"], ["3", "CCNB1", "95", "Cyclin B1", "CCNB1 plays an important role in promoting the transition from G2/M phase, and its high expression predicts worse prognosis in LUSC."], ["4", "CCNB2", "91", "Cyclin B2", "CCNB2 participates in promoting G2/M transition, and its overexpression correlates with the development of LUSC."], ["5", "CCNA2", "83", "Cyclin A2", "CCNA2 promotes the transition from G1 to S phase and G2 to M phase, and it is overexpressed in LUSC."], ["6", "BUB1", "83", "BUB1 mitotic checkpoint serine/threonine kinase", "BUB1 participates in binding kinetochores, and its mutation is correlated with the occurrence of LUSC."], ["7", "AURKB", "82", "Aurora Kinase B", "AURKB closely correlates with the acquired resistance of anti-EGFR treatment in NSCLC."], ["8", "PLK1", "80", "Polo Like Kinase 1", "Abnormal expression of PLK1 is associated with higher stages and aggressive progression of LUSC."], ["9", "MAD2L1", "75", "Mitotic Arrest Deficient 2 Like 1", "MAD2L1 participates in chromosomal instability and substantial aneuploidy, which is correlated with the carcinogenesis of NSCLC."], ["10", "CDCA8", "74", "Cell Division Cycle Associated 8", "Phosphorylation and activation of CDCA8 by AURKB serve an important role in the tumorigenesis of LC."], ["11", "KIF11", "69", "Kinesin Family Member 11", "The overexpression of KIF11 promotes the invasion and adverse prognosis of NSCLC."], ["12", "KIF2C", "69", "Kinesin Family Member 2C", "Elevated expression of KIF2C is associated with poorer differentiation status and lymph node metastasis in NSCLC."], ["13", "NDC80", "69", "NDC80 Kinetochore Complex Component", "NDC80 is highly expressed in LUAD, and high expression of NDC80 is associated with shorter OS."], ["14", "BIRC5", "66", "Baculoviral IAP Repeat Containing 5", "BIRC5 is highly expressed in LUSC, and the upregulation of BIRC5 indicates worse survival in LUSC."], ["15", "CENPE", "65", "Centromere Protein E", "CENPE is overexpressed in the G2/M phase, and CENPE participates in the cell proliferation in LUAD."], ["16", "TOP2A", "64", "Topoisomerase (DNA) II α", "TOP2A regulates the progress of LUSC, and high expression of TOP2A predicts poor prognosis in LUSC."], ["17", "CENPF", "63", "Centromere Protein F", "High expression of CENPF is associated with larger tumor size and poorer survival in NSCLC."]], "row_count": 18, "column_count": 5, "numeric_cells": 49, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:34307447:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ddceb9a504f115e78ed75b7460aa9b23d28054cc741e00f04383dd9802a3af2e", "bytes": 577, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T2", "version": null, "note": "The primers of GAPDH, CDK1 and CDC20.", "structure": {"pmcid": "PMC8292837", "section_index": 9, "section_title": "The External Validation of Basic Experiments", "row_count": 4, "column_count": 3}, "table": {"label": "TABLE 2", "caption": "The primers of GAPDH, CDK1 and CDC20.", "rows": [["Gene symbol", "Forward (F)", "Reverse (R)"], ["GAPDH", "5′-ACA​ACT​TTG​GTA​TCG​TGG​AAG​G-3′", "5′-GCC​ATC​ACG​CCA​CAG​TTT​C-3′"], ["CDK1", "5′-GGA​TGT​GCT​TAT​GCA​GGA​TTC​C-3′", "5′-CAT​GTA​CTG​ACC​AGG​AGG​GAT​AG-3′"], ["CDC20", "5′-GAC​CAC​TCC​TAG​CAA​ACC​TGG-3′", "5′-GGG​CGT​CTG​GCT​GTT​TTC​A-3′"]], "row_count": 4, "column_count": 3, "numeric_cells": 7, "header_rows": 1, "locator": "section[9]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:34307447:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3c0146defde18867e30df1bda6685c630e09f200137c9e64da841743e67543db", "bytes": 2817, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T3", "version": null, "note": "Functional roles of all hub genes with degrees>60.", "structure": {"pmcid": "PMC8292837", "section_index": 13, "section_title": "Construction of the PPI Network and Selection of Hub Genes", "row_count": 18, "column_count": 5}, "table": {"label": "TABLE 3", "caption": "Functional roles of all hub genes with degrees>60.", "rows": [["No", "Gene Symbol", "Degree", "Full name", "Function"], ["1", "CDK1", "123", "Cyclin-dependent kinase 1", "CDK1 regulates the cell cycle progression, apoptosis and carcinogenesis of several cancers"], ["2", "CDC20", "106", "Cell division cycle 20", "CDC20 participates in the pathogenesis of NSCLC, and its higher expression correlates with higher tumor grade"], ["3", "CCNB1", "95", "Cyclin B1", "CCNB1 plays an important role in promoting the transition from G2/M phase, and its high expression predicts worse prognosis in LUSC."], ["4", "CCNB2", "91", "Cyclin B2", "CCNB2 participates in promoting G2/M transition, and its overexpression correlates with the development of LUSC."], ["5", "CCNA2", "83", "Cyclin A2", "CCNA2 promotes the transition from G1 to S phase and G2 to M phase, and it is overexpressed in LUSC."], ["6", "BUB1", "83", "BUB1 mitotic checkpoint serine/threonine kinase", "BUB1 participates in binding kinetochores, and its mutation is correlated with the occurrence of LUSC."], ["7", "AURKB", "82", "Aurora Kinase B", "AURKB closely correlates with the acquired resistance of anti-EGFR treatment in NSCLC."], ["8", "PLK1", "80", "Polo Like Kinase 1", "Abnormal expression of PLK1 is associated with higher stages and aggressive progression of LUSC."], ["9", "MAD2L1", "75", "Mitotic Arrest Deficient 2 Like 1", "MAD2L1 participates in chromosomal instability and substantial aneuploidy, which is correlated with the carcinogenesis of NSCLC."], ["10", "CDCA8", "74", "Cell Division Cycle Associated 8", "Phosphorylation and activation of CDCA8 by AURKB serve an important role in the tumorigenesis of LC."], ["11", "KIF11", "69", "Kinesin Family Member 11", "The overexpression of KIF11 promotes the invasion and adverse prognosis of NSCLC."], ["12", "KIF2C", "69", "Kinesin Family Member 2C", "Elevated expression of KIF2C is associated with poorer differentiation status and lymph node metastasis in NSCLC."], ["13", "NDC80", "69", "NDC80 Kinetochore Complex Component", "NDC80 is highly expressed in LUAD, and high expression of NDC80 is associated with shorter OS."], ["14", "BIRC5", "66", "Baculoviral IAP Repeat Containing 5", "BIRC5 is highly expressed in LUSC, and the upregulation of BIRC5 indicates worse survival in LUSC."], ["15", "CENPE", "65", "Centromere Protein E", "CENPE is overexpressed in the G2/M phase, and CENPE participates in the cell proliferation in LUAD."], ["16", "TOP2A", "64", "Topoisomerase (DNA) II α", "TOP2A regulates the progress of LUSC, and high expression of TOP2A predicts poor prognosis in LUSC."], ["17", "CENPF", "63", "Centromere Protein F", "High expression of CENPF is associated with larger tumor size and poorer survival in NSCLC."]], "row_count": 18, "column_count": 5, "numeric_cells": 49, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:34307447:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3b7a2cc869cc228b72994474a38cc9f0e19dbd98409749bae1a0a670460430cf", "bytes": 1442, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T4", "version": null, "note": "Relative pathways associated with the expression of CDK1 and CDC20 using GSEA.", "structure": {"pmcid": "PMC8292837", "section_index": 14, "section_title": "Gene Set Enrichment Analysis of CDK1 and CDC20", "row_count": 21, "column_count": 6}, "table": {"label": "TABLE 4", "caption": "Relative pathways associated with the expression of CDK1 and CDC20 using GSEA.", "rows": [["Gene", "Name", "ES", "NES", "NOM p-value", "FDR q-value"], ["CDK1", "KEGG_BASAL_TRANSCRIPTION_FACTORS", "0.57", "1.74", "0.010", "0.033"], ["KEGG_BASE_EXCISION_REPAIR", "0.67", "1.90", "0.000", "0.040"], ["KEGG_CELL_CYCLE", "0.58", "1.88", "0.000", "0.012"], ["KEGG_DNA_REPLICATION", "0.76", "1.85", "0.004", "0.014"], ["KEGG_MISMATCH_REPAIR", "0.77", "1.94", "0.002", "0.016"], ["KEGG_NUCLEOTIDE_EXCISION_REPAIR", "0.61", "1.81", "0.006", "0.017"], ["KEGG_ONE_CARBON_POOL_BY_FOLATE", "0.67", "1.73", "0.002", "0.034"], ["KEGG_RNA_DEGRADATION", "0.56", "1.83", "0.006", "0.016"], ["KEGG_RNA_POLYMERASE", "0.67", "1.88", "0.000", "0.015"], ["KEGG_SPLICEOSOME", "0.55", "1.95", "0.002", "0.020"], ["CDC20", "KEGG_BASAL_TRANSCRIPTION_FACTORS", "0.53", "1.57", "0.033", "0.137"], ["KEGG_BASE_EXCISION_REPAIR", "0.61", "1.70", "0.004", "0.063"], ["KEGG_CELL_CYCLE", "0.59", "1.84", "0.002", "0.030"], ["KEGG_DNA_REPLICATION", "0.78", "1.76", "0.000", "0.044"], ["KEGG_MISMATCH_REPAIR", "0.74", "1.80", "0.004", "0.034"], ["KEGG_NUCLEOTIDE_EXCISION_REPAIR", "0.61", "1.72", "0.006", "0.058"], ["KEGG_OOCYTE_MEIOSIS", "0.43", "1.60", "0.011", "0.126"], ["KEGG_RNA_DEGRADATION", "0.62", "1.94", "0.000", "0.010"], ["KEGG_RNA_POLYMERASE", "0.60", "1.60", "0.031", "0.134"], ["KEGG_SPLICEOSOME", "0.59", "2.03", "0.002", "0.005"]], "row_count": 21, "column_count": 6, "numeric_cells": 81, "header_rows": 1, "locator": "section[14]/table-wrap[1]#T4"}}, {"id": "asset:table:pmid:34307447:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ddceb9a504f115e78ed75b7460aa9b23d28054cc741e00f04383dd9802a3af2e", "bytes": 577, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T2", "version": null, "note": "The primers of GAPDH, CDK1 and CDC20.", "structure": {"pmcid": "PMC8292837", "section_index": 16, "section_title": "The External Validation of Basic Experiments", "row_count": 4, "column_count": 3}, "table": {"label": "TABLE 2", "caption": "The primers of GAPDH, CDK1 and CDC20.", "rows": [["Gene symbol", "Forward (F)", "Reverse (R)"], ["GAPDH", "5′-ACA​ACT​TTG​GTA​TCG​TGG​AAG​G-3′", "5′-GCC​ATC​ACG​CCA​CAG​TTT​C-3′"], ["CDK1", "5′-GGA​TGT​GCT​TAT​GCA​GGA​TTC​C-3′", "5′-CAT​GTA​CTG​ACC​AGG​AGG​GAT​AG-3′"], ["CDC20", "5′-GAC​CAC​TCC​TAG​CAA​ACC​TGG-3′", "5′-GGG​CGT​CTG​GCT​GTT​TTC​A-3′"]], "row_count": 4, "column_count": 3, "numeric_cells": 7, "header_rows": 1, "locator": "section[9]/table-wrap[1]#T2"}}], "gaps": ["asset:data:geo:GSE19188 not downloaded", "asset:data:geo:GSE19188 licence not read", "asset:data:geo:GSE30219 not downloaded", "asset:data:geo:GSE30219 licence not read", "asset:data:geo:GSE33532 not downloaded", "asset:data:geo:GSE33532 licence not read"]}, "analysis": {"state": "partial", "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": {"fdr_threshold": "with Benjamini–Hochberg false discovery rate adjustment"}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "DEGs were selected between LUSC and normal lung tissues using the limma package of R software (Ritchie et al., 2015). To minimize the false discovery rate (FDR), the p-values were adjusted using the Benjamini–Hochberg method."}}, {"id": "method-2", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-3", "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"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["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": ["GSE33532", "GSE30219", "GSE19188"], "resolved_accessions": ["GSE33532", "GSE30219", "GSE19188"], "statements": ["The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors."], "basis": "The paper names GSE33532, GSE30219, GSE19188 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:34307447", "data:geo:GSE19188", "asset:table:pmid:34307447:1", "asset:table:pmid:34307447:2", "asset:table:pmid:34307447:3", "asset:table:pmid:34307447:4", "asset:table:pmid:34307447:5", "asset:table:pmid:34307447:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE19188"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:32:48Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 21652, "completion_tokens": 1865, "cached_tokens": 776}}, "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:34307447", "type": "paper", "label": "pmid:34307447"}, {"id": "source:pmid:34307447", "type": "manuscript", "label": "PMID 34307447 full text"}, {"id": "data:geo:GSE19188", "type": "dataset", "label": "GEO GSE19188"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34307447", "type": "paper", "label": "pmid:34307447"}, {"id": "source:pmid:34307447", "type": "manuscript", "label": "PMID 34307447 full text"}, {"id": "data:geo:GSE19188", "type": "dataset", "label": "GEO GSE19188"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34307447", "type": "extraction", "used": ["source:pmid:34307447"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE19188", "type": "accession_resolution", "used": ["data:geo:GSE19188"], "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:34307447", "parent_hash": "sha256:c478d10b424ccb890704368bbf197791673754bb2682b59a8aa1105491482ff4", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE19188 licence not read", "asset:data:geo:GSE19188 not downloaded", "asset:data:geo:GSE30219 licence not read", "asset:data:geo:GSE30219 not downloaded", "asset:data:geo:GSE33532 licence not read", "asset:data:geo:GSE33532 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "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": ["candidate indicators of LUSC. Methods: Three microarray datasets (GSE33532, GSE30219 and GSE19188) w"], "order_basis": "paper_text_order:302", "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": ["DEGs were selected between LUSC and normal lung tissues using the limma package of R software (Ritchie et al., 2015). To minimize the false discovery rate (FDR), the p-values were adjusted 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":"2026-11-04T00:32:15+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}}}