{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31088477", "kind": "science-record", "revision": 7, "content_hash": "sha256:87e82743797e5516b8ee4c9753167e663f4044c24ad73fe5bb22224ef80a40d0", "created_at": "2026-11-01T15:40:45Z", "updated_at": "2026-11-01T22:00:33Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A robust six-gene prognostic signature for prediction of both disease-free and overall survival in non-small cell lung cancer.", "doi": "10.1186/s12967-019-1899-y", "pmid": "31088477", "authors": ["Shuguang Zuo", "Min Wei", "Hailin Zhang", "Anxian Chen", "Junhua Wu", "Jiwu Wei", "Jie Dong"], "journal": "Journal of translational medicine", "year": 2019, "abstract": "BACKGROUND: The high mortality of patients with non-small cell lung cancer (NSCLC) emphasizes the necessity of identifying a robust and reliable prognostic signature for NSCLC patients. This study aimed to identify and validate a prognostic signature for the prediction of both disease-free survival (DFS) and overall survival (OS) of NSCLC patients by integrating multiple datasets.\nMETHODS: We firstly downloaded three independent datasets under the accessing number of GSE31210, GSE37745 and GSE50081, and then performed an univariate regression analysis to identify the candidate prognostic genes from each dataset, and identified the gene signature by overlapping the candidates. Then, we built a prognostic model to predict DFS and OS using a risk score method. Kaplan-Meier curve with log-rank test was used to determine the prognostic significance. Univariate and multivariate Cox proportional hazard regression models were implemented to evaluate the influences of various variables on DFS and OS. The robustness of the prognostic gene signature was evaluated by re-sampling tests based on the combined GEO dataset (GSE31210, GSE37745 and GSE50081). Furthermore, a The Cancer Genome Atlas (TCGA)-NSCLC cohort was utilized to validate the prediction power of the gene signature. Finally, the correlation of the risk score of the gene signature and the Gene set variation analysis (GSVA) score of cancer hallmark gene sets was investigated.\nRESULTS: We identified and validated a six-gene prognostic signature in this study. This prognostic signature stratified NSCLC patients into the low-risk and high-risk groups. Multivariate regression and stratification analyses demonstrated that the six-gene signature was an independent predictive factor for both DFS and OS when adjusting for other clinical factors. Re-sampling analysis implicated that this six-gene signature for predicting prognosis of NSCLC patients is robust. Moreover, the risk score of the gene signature is correlated with the GSVA score of 7 cancer hallmark gene sets.\nCONCLUSION: This study provided a robust and reliable gene signature that had significant implications in the prediction of both DFS and OS of NSCLC patients, and may provide more effective treatment strategies and personalized therapies.", "claims": [{"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:31088477", "locator": "sections[23] \"notes\" paragraph 1", "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:31088477"], "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:GSE31210"], "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:GSE31210"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31088477", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12967-019-1899-y", "sha256": "sha256:c0d1349dfa7d64955145381e1d992140755fc2a75497b86f2d9d2683323733e6", "bytes": 39589, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12967-019-1899-y", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6515678", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE31210", "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=GSE31210", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31210", "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": ["GSM773540", "GSM773541", "GSM773542", "GSM773543", "GSM773544", "GSM773545", "GSM773546", "GSM773547", "GSM773548", "GSM773549", "GSM773550", "GSM773551", "GSM773552", "GSM773553", "GSM773554", "GSM773555", "GSM773556", "GSM773557", "GSM773558", "GSM773559", "GSM773560", "GSM773561", "GSM773562", "GSM773563", "GSM773564", "GSM773565", "GSM773566", "GSM773567", "GSM773568", "GSM773569", "GSM773570", "GSM773571", "GSM773572", "GSM773573", "GSM773574", "GSM773575", "GSM773576", "GSM773577", "GSM773578", "GSM773579", "GSM773580", "GSM773581", "GSM773582", "GSM773583", "GSM773584", "GSM773585", "GSM773586", "GSM773587", "GSM773588", "GSM773589", "GSM773590", "GSM773591", "GSM773592", "GSM773593", "GSM773594", "GSM773595", "GSM773596", "GSM773597", "GSM773598", "GSM773599", "GSM773600", "GSM773601", "GSM773602", "GSM773603", "GSM773604", "GSM773605", "GSM773606", "GSM773607", "GSM773608", "GSM773609", "GSM773610", "GSM773611", "GSM773612", "GSM773613", "GSM773614", "GSM773615", "GSM773616", "GSM773617", "GSM773618", "GSM773619", "GSM773620", "GSM773621", "GSM773622", "GSM773623", "GSM773624", "GSM773625", "GSM773626", "GSM773627", "GSM773628", "GSM773629", "GSM773630", "GSM773631", "GSM773632", "GSM773633", "GSM773634", "GSM773635", "GSM773636", "GSM773637", "GSM773638", "GSM773639", "GSM773640", "GSM773641", "GSM773642", "GSM773643", "GSM773644", "GSM773645", "GSM773646", "GSM773647", "GSM773648", "GSM773649", "GSM773650", "GSM773651", "GSM773652", "GSM773653", "GSM773654", "GSM773655", "GSM773656", "GSM773657", "GSM773658", "GSM773659", "GSM773660", "GSM773661", "GSM773662", "GSM773663", "GSM773664", "GSM773665", "GSM773666", "GSM773667", "GSM773668", "GSM773669", "GSM773670", "GSM773671", "GSM773672", "GSM773673", "GSM773674", "GSM773675", "GSM773676", "GSM773677", "GSM773678", "GSM773679", "GSM773680", "GSM773681", "GSM773682", "GSM773683", "GSM773684", "GSM773685", "GSM773686", "GSM773687", "GSM773688", "GSM773689", "GSM773690", "GSM773691", "GSM773692", "GSM773693", "GSM773694", "GSM773695", "GSM773696", "GSM773697", "GSM773698", "GSM773699", "GSM773700", "GSM773701", "GSM773702", "GSM773703", "GSM773704", "GSM773705", "GSM773706", "GSM773707", "GSM773708", "GSM773709", "GSM773710", "GSM773711", "GSM773712", "GSM773713", "GSM773714", "GSM773715", "GSM773716", "GSM773717", "GSM773718", "GSM773719", "GSM773720", "GSM773721", "GSM773722", "GSM773723", "GSM773724", "GSM773725", "GSM773726", "GSM773727", "GSM773728", "GSM773729", "GSM773730", "GSM773731", "GSM773732", "GSM773733", "GSM773734", "GSM773735", "GSM773736", "GSM773737", "GSM773738", "GSM773739", "GSM773740", "GSM773741", "GSM773742", "GSM773743", "GSM773744", "GSM773745", "GSM773746", "GSM773747", "GSM773748", "GSM773749", "GSM773750", "GSM773751", "GSM773752", "GSM773753", "GSM773754", "GSM773755", "GSM773756", "GSM773757", "GSM773758", "GSM773759", "GSM773760", "GSM773761", "GSM773762", "GSM773763", "GSM773764", "GSM773765", "GSM773766", "GSM773767", "GSM773768", "GSM773769", "GSM773770", "GSM773771", "GSM773772", "GSM773773", "GSM773774", "GSM773775", "GSM773776", "GSM773777", "GSM773778", "GSM773779", "GSM773780", "GSM773781", "GSM773782", "GSM773783", "GSM773784", "GSM773785"], "sample_count": 246, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression data for pathological stage I-II lung adenocarcinomas", "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:GSE37745", "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=GSE37745", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE37745", "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": ["GSM1019138", "GSM1019139", "GSM1019140", "GSM1019141", "GSM1019142", "GSM1019143", "GSM1019144", "GSM1019145", "GSM1019146", "GSM1019147", "GSM1019148", "GSM1019149", "GSM1019150", "GSM1019151", "GSM1019152", "GSM1019153", "GSM1019154", "GSM1019155", "GSM1019156", "GSM1019157", "GSM1019158", "GSM1019159", "GSM1019160", "GSM1019161", "GSM1019162", "GSM1019163", "GSM1019164", "GSM1019165", "GSM1019166", "GSM1019167", "GSM1019168", "GSM1019169", "GSM1019170", "GSM1019171", "GSM1019172", "GSM1019173", "GSM1019174", "GSM1019175", "GSM1019176", "GSM1019177", "GSM1019178", "GSM1019179", "GSM1019180", "GSM1019181", "GSM1019182", "GSM1019183", "GSM1019184", "GSM1019185", "GSM1019186", "GSM1019187", "GSM1019188", "GSM1019189", "GSM1019190", "GSM1019191", "GSM1019192", "GSM1019193", "GSM1019194", "GSM1019195", "GSM1019196", "GSM1019197", "GSM1019198", "GSM1019199", "GSM1019200", "GSM1019201", "GSM1019202", "GSM1019203", "GSM1019204", "GSM1019205", "GSM1019206", "GSM1019207", "GSM1019208", "GSM1019209", "GSM1019210", "GSM1019211", "GSM1019212", "GSM1019213", "GSM1019214", "GSM1019215", "GSM1019216", "GSM1019217", "GSM1019218", "GSM1019219", "GSM1019220", "GSM1019221", "GSM1019222", "GSM1019223", "GSM1019224", "GSM1019225", "GSM1019226", "GSM1019227", "GSM1019228", "GSM1019229", "GSM1019230", "GSM1019231", "GSM1019232", "GSM1019233", "GSM1019234", "GSM1019235", "GSM1019236", "GSM1019237", "GSM1019238", "GSM1019239", "GSM1019240", "GSM1019241", "GSM1019242", "GSM1019243", "GSM1019244", "GSM1019245", "GSM1019246", "GSM1019247", "GSM1019248", "GSM1019249", "GSM1019250", "GSM1019251", "GSM1019252", "GSM1019253", "GSM1019254", "GSM1019255", "GSM1019256", "GSM1019257", "GSM1019258", "GSM1019259", "GSM1019260", "GSM1019261", "GSM1019262", "GSM1019263", "GSM1019264", "GSM1019265", "GSM1019266", "GSM1019267", "GSM1019268", "GSM1019269", "GSM1019270", "GSM1019271", "GSM1019272", "GSM1019273", "GSM1019274", "GSM1019275", "GSM1019276", "GSM1019277", "GSM1019278", "GSM1019279", "GSM1019280", "GSM1019281", "GSM1019282", "GSM1019283", "GSM1019284", "GSM1019285", "GSM1019286", "GSM1019287", "GSM1019288", "GSM1019289", "GSM1019290", "GSM1019291", "GSM1019292", "GSM1019293", "GSM1019294", "GSM1019295", "GSM1019296", "GSM1019297", "GSM1019298", "GSM1019299", "GSM1019300", "GSM1019301", "GSM1019302", "GSM1019303", "GSM1019304", "GSM1019305", "GSM1019306", "GSM1019307", "GSM1019308", "GSM1019309", "GSM1019310", "GSM1019311", "GSM1019312", "GSM1019313", "GSM1019314", "GSM1019315", "GSM1019316", "GSM1019317", "GSM1019318", "GSM1019319", "GSM1019320", "GSM1019321", "GSM1019322", "GSM1019323", "GSM1019324", "GSM1019325", "GSM1019326", "GSM1019327", "GSM1019328", "GSM1019329", "GSM1019330", "GSM1019331", "GSM1019332", "GSM1019333"], "sample_count": 196, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Biomarker discovery in non-small cell lung cancer: integrating gene expression profiling, meta-analysis and tissue microarray validation", "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:GSE50081", "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=GSE50081", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE50081", "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": ["GSM1213669", "GSM1213670", "GSM1213671", "GSM1213672", "GSM1213673", "GSM1213674", "GSM1213675", "GSM1213676", "GSM1213677", "GSM1213678", "GSM1213679", "GSM1213680", "GSM1213681", "GSM1213682", "GSM1213683", "GSM1213684", "GSM1213685", "GSM1213686", "GSM1213687", "GSM1213688", "GSM1213689", "GSM1213690", "GSM1213691", "GSM1213692", "GSM1213693", "GSM1213694", "GSM1213695", "GSM1213696", "GSM1213697", "GSM1213698", "GSM1213699", "GSM1213700", "GSM1213701", "GSM1213702", "GSM1213703", "GSM1213704", "GSM1213705", "GSM1213706", "GSM1213707", "GSM1213708", "GSM1213709", "GSM1213710", "GSM1213711", "GSM1213712", "GSM1213713", "GSM1213714", "GSM1213715", "GSM1213716", "GSM1213717", "GSM1213718", "GSM1213719", "GSM1213720", "GSM1213721", "GSM1213722", "GSM1213723", "GSM1213724", "GSM1213725", "GSM1213726", "GSM1213727", "GSM1213728", "GSM1213729", "GSM1213730", "GSM1213731", "GSM1213732", "GSM1213733", "GSM1213734", "GSM1213735", "GSM1213736", "GSM1213737", "GSM1213738", "GSM1213739", "GSM1213740", "GSM1213741", "GSM1213742", "GSM1213743", "GSM1213744", "GSM1213745", "GSM1213746", "GSM1213747", "GSM1213748", "GSM1213749", "GSM1213750", "GSM1213751", "GSM1213752", "GSM1213753", "GSM1213754", "GSM1213755", "GSM1213756", "GSM1213757", "GSM1213758", "GSM1213759", "GSM1213760", "GSM1213761", "GSM1213762", "GSM1213763", "GSM1213764", "GSM1213765", "GSM1213766", "GSM1213767", "GSM1213768", "GSM1213769", "GSM1213770", "GSM1213771", "GSM1213772", "GSM1213773", "GSM1213774", "GSM1213775", "GSM1213776", "GSM1213777", "GSM1213778", "GSM1213779", "GSM1213780", "GSM1213781", "GSM1213782", "GSM1213783", "GSM1213784", "GSM1213785", "GSM1213786", "GSM1213787", "GSM1213788", "GSM1213789", "GSM1213790", "GSM1213791", "GSM1213792", "GSM1213793", "GSM1213794", "GSM1213795", "GSM1213796", "GSM1213797", "GSM1213798", "GSM1213799", "GSM1213800", "GSM1213801", "GSM1213802", "GSM1213803", "GSM1213804", "GSM1213805", "GSM1213806", "GSM1213807", "GSM1213808", "GSM1213809", "GSM1213810", "GSM1213811", "GSM1213812", "GSM1213813", "GSM1213814", "GSM1213815", "GSM1213816", "GSM1213817", "GSM1213818", "GSM1213819", "GSM1213820", "GSM1213821", "GSM1213822", "GSM1213823", "GSM1213824", "GSM1213825", "GSM1213826", "GSM1213827", "GSM1213828", "GSM1213829", "GSM1213830", "GSM1213831", "GSM1213832", "GSM1213833", "GSM1213834", "GSM1213835", "GSM1213836", "GSM1213837", "GSM1213838", "GSM1213839", "GSM1213840", "GSM1213841", "GSM1213842", "GSM1213843", "GSM1213844", "GSM1213845", "GSM1213846", "GSM1213847", "GSM1213848", "GSM1213849"], "sample_count": 181, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Validation of a histology-independent prognostic gene signature for early stage, non-small cell lung cancer including stage IA 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": "asset:table:pmid:31088477:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:949d3cf30c69e2b8598f1a52620f03a94860da8d25965fd828a5f41461a3fce0", "bytes": 3706, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "Univariate and multivariate Cox regression analysis of the gene signature and disease-free survival of NSCLC patients", "structure": {"pmcid": "PMC6515678", "section_index": 3, "section_title": "Patient data", "row_count": 44, "column_count": 7}, "table": {"label": "Table 1", "caption": "Univariate and multivariate Cox regression analysis of the gene signature and disease-free survival of NSCLC patients", "rows": [["Variables", "Patients(N)", "Univariate analysis", "Multivariate analysis"], ["HR (95% CI)", "P", "HR (95% CI)", "P"], ["GSE31210"], ["Age", "≤ 65/> 65", "176/50", "1.89 (1.12–3.18)", "1.70E−02", "2.36 (1.37–4.04)", "1.83E−03"], ["Gender", "Female/male", "121/105", "1.27 (0.78–2.07)", "3.38E−01", "", ""], ["ALK fusion", "+/−", "215/11", "0.74 (0.18–3.02)", "6.73E−01", "", ""], ["EGFR mutation", "+/−", "99/127", "0.60 (0.37–0.98)", "4.29E−02", "1.98 (0.88–4.47)", "1.00E−01"], ["KRAS mutation", "+/−", "206/20", "0.98 (0.42–2.26)", "9.56E−01", "", ""], ["Triple negative", "No/yes", "158/68", "1.87 (1.14–3.08)", "1.39E−02", "2.91 (1.30–6.54)", "9.71E−03"], ["Myc copy", "Low/high", "207/17", "1.04 (0.42–2.59)", "9.33E−01", "", ""], ["Stage", "I/II", "168/58", "3.16 (1.92–5.21)", "6.09E−06", "2.77 (1.63–4.71)", "1.62E−04"], ["Smoking", "No/yes", "115/111", "1.33 (0.82–2.18)", "2.52E−01", "", ""], ["Risk score", "Low/high", "123/103", "3.26 (1.92–5.53)", "1.24E−05", "3.10 (1.77–5.41)", "7.17E−05"], ["GSE37745"], ["Age", "≤ 65/> 65", "45/51", "0.89 (0.50–1.55)", "6.70E−01", "", ""], ["Gender", "Female/male", "46/50", "1.01 (0.58–1.78)", "9.60E−01", "", ""], ["Stage", "I/II", "63/18", "1.13 (0.54–2.38)", "7.45E−01", "", ""], ["Stage", "I/III", "63/14", "1.78 (0.81–3.91)", "1.48E−01", "", ""], ["Stage", "I/IV", "63/1", "5.71 (0.75–43.63)", "9.32E−02", "", ""], ["Histological type", "Adeno/large", "53/13", "1.05 (0.46–2.42)", "9.08E−01", "", ""], ["Histological type", "Adeno/squamous", "53/30", "1.12 (0.60–2.10)", "7.17E−01", "", ""], ["WHO performance status", "0/1", "54/32", "2.21 (1.21–4.03)", "1.02E−02", "2.43 (1.32–4.47)", "4.31E−03"], ["WHO performance status", "0/2", "54/6", "1.04 (0.25–4.42)", "9.52E−01", "1.12 (0.26–4.75)", "8.77E−01"], ["WHO performance status", "0/3", "54/4", "1.66 (0.50–5.53)", "4.08E−01", "1.62 (0.49–5.38)", "4.34E−01"], ["Risk score", "Low/high", "46/50", "2.31 (1.27–4.21)", "6.08E−03", "2.49 (1.36–4.55)", "3.10E−03"], ["GSE50081"], ["Age", "≤ 65/> 65", "59/118", "1.24 (0.69–2.24)", "4.77E−01", "", ""], ["Gender", "Female/male", "81/96", "1.68 (0.95–2.99)", "7.59E−02", "", ""], ["Stage", "I/II", "124/53", "1.87 (1.06–3.28)", "3.03E−02", "1.71 (0.97–3.01)", "6.30E−02"], ["Histological type", "Adeno/large", "124/7", "1.04 (0.25–4.31)", "9.59E−01", "", ""], ["Histological type", "Adeno/squamous", "124/42", "0.73 (0.10–5.36)", "7.61E−01", "", ""], ["Histological type", "Adeno/other", "124/4", "0.74 (0.38–1.45)", "3.79E−01", "", ""], ["Smoking", "No/yes", "24/133", "0.70 (0.35–1.40)", "3.14E−01", "", ""], ["Risk score", "Low/high", "83/94", "2.42 (1.33–4.43)", "4.02E−03", "2.30 (1.26–4.22)", "6.97E−03"], ["All patients"], ["Age", "≤ 65/> 65", "280/219", "1.36 (1.00–1.84)", "5.04E−02", "", ""], ["Gender", "Female/male", "248/251", "1.31 (0.96–1.78)", "8.51E−02", "", ""], ["Stage", "I/II", "355/129", "2.05 (1.47–2.85)", "2.02E−05", "1.72 (1.23–2.40)", "1.50E−03"], ["Stage", "I/III", "355/14", "3.45 (1.68–7.11)", "7.74E−04", "2.62 (1.27–5.43)", "9.41E−03"], ["Stage", "I/IV", "355/1", "22.26 (3.01–164.44)", "2.36E−03", "14.79 (2.00–109.7)", "8.40E−03"], ["Histological type", "Adeno/large", "403/20", "1.48 (0.75–2.93)", "2.61E−01", "", ""], ["Histological type", "Adeno/squamous", "403/72", "0.76 (0.11–5.44)", "7.85E−01", "", ""], ["Histological type", "Adeno/other", "403/4", "1.17 (0.77–1.78)", "4.52E−01", "", ""], ["Risk score", "Low/high", "252/247", "2.7 (1.94–3.76)", "4.16E−09", "2.39 (1.70–3.35)", "4.47E−07"]], "row_count": 44, "column_count": 7, "numeric_cells": 156, "header_rows": 2, "locator": "section[3]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:31088477:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:67100b8d6c326771db5fed234e741cb8fd19441dafa8c660574e4dc420186160", "bytes": 3944, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#Tab2", "version": null, "note": "Univariate and multivariate Cox regression analysis of the gene signature and overall survival of NSCLC patients", "structure": {"pmcid": "PMC6515678", "section_index": 3, "section_title": "Patient data", "row_count": 44, "column_count": 7}, "table": {"label": "Table 2", "caption": "Univariate and multivariate Cox regression analysis of the gene signature and overall survival of NSCLC patients", "rows": [["Variables", "Patients(N)", "Univariate analysis", "Multivariate analysis"], ["HR (95% CI)", "P", "HR (95% CI)", "P"], ["GSE31210"], ["Age", "≤ 65/> 65", "176/50", "2.58 (1.31–5.08)", "5.99E−03", "3.51 (1.72–7.15)", "5.44E−04"], ["Gender", "Female/male", "121/105", "1.52 (0.78–2.96)", "2.19E−01", "", ""], ["ALK fusion", "+/−", "215/11", "1.49 (0.36–6.24)", "5.82E−01", "", ""], ["EGFR mutation", "+/−", "99/127", "0.47 (0.24–0.93)", "2.96E−02", "1.87 (0.65–5.37)", "2.47E−01"], ["KRAS mutation", "+/−", "206/20", "0.87 (0.27–2.85)", "8.17E−01", "", ""], ["Triple negative", "No/yes", "158/68", "2.19 (1.12–4.26)", "2.12E−02", "2.95 (1.06–8.19)", "3.76E−02"], ["Myc copy", "Low/high", "207/17", "0.7 (0.17–2.9)", "6.18E−01", "", ""], ["Stage", "I/II", "168/58", "4.23 (2.17–8.24)", "2.17E−05", "3.45 (1.72–6.93)", "5.06E−04"], ["Smoking", "No/yes", "115/111", "1.64 (0.84–3.2)", "1.50E−01", "", ""], ["Risk score", "Low/high", "129/97", "6.14 (2.68–14.07)", "1.84E−05", "5.47 (2.3–12.99)", "1.21E−04"], ["GSE37745"], ["Age", "≤ 65/> 65", "102/94", "1.35 (0.98–1.88)", "6.88E−02", "", ""], ["Gender", "Female/male", "89/107", "1.1 (0.79–1.52)", "5.85E−01", "", ""], ["Stage", "I/II", "130/35", "1.22 (0.79–1.87)", "3.66E−01", "1.14 (0.73–1.77)", "5.68E−01"], ["Stage", "I/III", "130/27", "1.86 (1.19–2.93)", "6.88E−03", "1.63 (1.02–2.63)", "4.27E−02"], ["Stage", "I/IV", "130/4", "1.31 (0.42–4.15)", "6.43E−01", "1.97 (0.61–6.35)", "2.57E−01"], ["Histological type", "Adeno/large", "106/24", "0.89 (0.52–1.53)", "6.75E−01", "", ""], ["Histological type", "Adeno/squamous", "106/66", "1.26 (0.88–1.79)", "2.05E−01", "", ""], ["WHO performance status", "0/1", "105/75", "1.91 (1.35–2.7)", "2.38E−04", "1.96 (1.39–2.79)", "1.53E−04"], ["WHO performance status", "0/2", "105/12", "1.95 (1.01–3.79)", "4.83E−02", "1.81 (0.92–3.57)", "8.66E−02"], ["WHO performance status", "0/3", "105/4", "1.13 (0.36–3.61)", "8.32E−01", "1.09 (0.34–3.54)", "8.80E−01"], ["Risk score", "Low/high", "97/99", "1.56 (1.12–2.16)", "8.31E−03", "1.44 (1.02–2.04)", "3.80E−02"], ["GSE50081"], ["Age", "≤ 65/> 65", "59/122", "1.56 (0.93–2.61)", "9.04E−02", "", ""], ["Gender", "Female/male", "83/98", "1.93 (1.19–3.14)", "7.80E−03", "2 (1.23–3.26)", "5.47E−03"], ["Stage", "I/II", "127/54", "1.69 (1.05–2.72)", "3.10E−02", "1.63 (1.01–2.63)", "4.71E−02"], ["Histological type", "Adeno/large", "127/7", "1.71 (0.62–4.74)", "3.01E−01", "", ""], ["Histological type", "Adeno/squamous", "127/43", "1.84 (0.57–5.92)", "3.03E−01", "", ""], ["Histological type", "Adeno/other", "127/4", "0.8 (0.46–1.39)", "4.35E−01", "", ""], ["Smoking", "No/yes", "24/136", "1.39 (0.66–2.92)", "3.89E−01", "", ""], ["Risk score", "Low/high", "79/102", "2.21 (1.34–3.64)", "1.81E−03", "2.09 (1.27–3.45)", "3.91E−03"], ["All patients"], ["Age", "≤ 65/> 65", "337/266", "1.92 (1.5–2.46)", "2.48E−07", "1.83 (1.42–2.35)", "2.94E−06"], ["Gender", "Female/male", "293/310", "1.45 (1.13–1.86)", "3.79E−03", "1.27 (0.98–1.64)", "7.14E−02"], ["Stage", "I/II", "425/147", "1.67 (1.26–2.21)", "3.43E−04", "1.5 (1.13–2)", "5.31E−03"], ["Stage", "I/III", "425/27", "3.6 (2.34–5.56)", "7.02E−09", "2.79 (1.79–4.36)", "6.58E−06"], ["Stage", "I/IV", "425/4", "2.53 (0.81–7.93)", "1.12E−01", "3.23 (1.02–10.23)", "4.58E−02"], ["Histological type", "Adeno/large", "459/31", "1.76 (1.1–2.81)", "1.83E−02", "1.51 (0.94–2.43)", "9.16E−02"], ["Histological type", "Adeno/squamous", "459/109", "2.29 (0.73–7.18)", "1.56E−01", "1.92 (0.6–6.1)", "2.70E−01"], ["Histological type", "Adeno/other", "459/4", "1.85 (1.39–2.45)", "2.09E−05", "1.27 (0.94–1.72)", "1.18E−01"], ["Risk score", "Low/high", "305/298", "2.11 (1.63–2.72)", "1.03E−08", "1.65 (1.26–2.18)", "3.32E−04"]], "row_count": 44, "column_count": 7, "numeric_cells": 174, "header_rows": 2, "locator": "section[3]/table-wrap[2]#Tab2"}}, {"id": "asset:table:pmid:31088477:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:99b08ec484bfbad06ec2db508752ac702f392106ed828497f6c9aefac7fe83c2", "bytes": 768, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#Tab3", "version": null, "note": "Overall information of the 6 genes for constructing the prognostic signature", "structure": {"pmcid": "PMC6515678", "section_index": 9, "section_title": "Identification of a six-gene prognostic signature", "row_count": 7, "column_count": 6}, "table": {"label": "Table 3", "caption": "Overall information of the 6 genes for constructing the prognostic signature", "rows": [["Gene stable ID", "Gene name", "Gene type", "Chromosome", "Gene start (bp)", "Gene end (bp)"], ["ENSG00000152527", "PLEKHH2", "Protein coding", "2", "43,637,273", "43,767,987"], ["ENSG00000136003", "ISCU", "Protein coding", "12", "108,562,582", "108,569,384"], ["ENSG00000079101", "CLUL1", "Protein coding", "18", "596,988", "650,334"], ["ENSG00000101938", "CHRDL1", "Protein coding", "X", "110,673,856", "110,795,819"], ["ENSG00000124374", "PAIP2B", "Protein coding", "2", "71,182,739", "71,227,083"], ["ENSG00000163814", "CDCP1", "Protein coding", "3", "45,082,278", "45,146,422"]], "row_count": 7, "column_count": 6, "numeric_cells": 23, "header_rows": 1, "locator": "section[9]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:31088477:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c725c9d90dc4fd362c0ebf70307de2cafa406aa657d4507c3fafe76bd557f9fc", "bytes": 1823, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Tab4", "version": null, "note": "Univariate and multivariate Cox regression analysis of the gene signature and survival of NSCLC patients in TCGA cohort", "structure": {"pmcid": "PMC6515678", "section_index": 13, "section_title": "Further validation of the six-gene signature using another independent dataset", "row_count": 18, "column_count": 7}, "table": {"label": "Table 4", "caption": "Univariate and multivariate Cox regression analysis of the gene signature and survival of NSCLC patients in TCGA cohort", "rows": [["Variables", "Group", "Patients(N)", "Univariate analysis", "Multivariate analysis"], ["HR (95% CI)", "P", "HR (95% CI)", "P"], ["DFS"], ["Age", "≤ 67/> 67", "383/378", "0.97 (0.75–1.26)", "8.30E−01", "1.11 (0.85–1.45)", "4.30E−01"], ["Gender", "Female/male", "326/435", "0.96 (0.74–1.25)", "7.60E−01", "1.08 (0.81–1.43)", "6.00E−01"], ["Stage", "I/II", "410/220", "1.64 (1.21–2.22)", "1.30E−03", "1.74 (1.28–2.37)", "3.60E−04"], ["Stage", "I/III", "410/109", "2.16 (1.51–3.08)", "2.20E−05", "2.25 (1.57–3.22)", "9.30E−06"], ["Stage", "I/IV", "410/22", "1.76 (0.82–3.80)", "1.50E−01", "1.56 (0.71–3.40)", "2.70E−01"], ["Histological type", "Adeno/squamous", "395/366", "0.65 (0.50–0.85)", "1.60E−03", "0.58 (0.43–0.77)", "1.60E−04"], ["Risk score", "Low/high", "380/381", "1.33 (1.02–1.73)", "3.70E−02", "1.40 (1.08–1.83)", "1.30E−02"], ["OS"], ["Age", "≤ 67/> 67", "383/378", "1.25 (0.98–1.58)", "7.10E−02", "1.34 (1.05–1.70)", "1.90E−02"], ["Gender", "Female/male", "326/435", "1.22 (0.96–1.57)", "1.10E−01", "1.19 (0.92–1.53)", "2.00E−01"], ["Stage", "I/II", "410/220", "1.51 (1.14–2.00)", "4.30E−03", "1.45 (1.09–1.93)", "1.10E−02"], ["Stage", "I/III", "410/109", "2.07 (1.50–2.85)", "9.60E−06", "2.04 (1.47–2.83)", "1.80E−05"], ["Stage", "I/IV", "410/22", "2.77 (1.59–4.83)", "3.20E−04", "2.83 (1.60–5.00)", "3.40E−04"], ["Histological type", "Adeno/squamous", "395/366", "1.13 (0.89–1.44)", "3.20E−01", "0.93 (0.71–1.22)", "5.90E−01"], ["Risk score", "Low/high", "380/381", "1.54 (1.20–1.96)", "5.50E−04", "1.48 (1.14–1.91)", "3.30E−03"]], "row_count": 18, "column_count": 7, "numeric_cells": 74, "header_rows": 2, "locator": "section[13]/table-wrap[1]#Tab4"}}], "gaps": ["asset:data:geo:GSE31210 not downloaded", "asset:data:geo:GSE31210 licence not read", "asset:data:geo:GSE37745 not downloaded", "asset:data:geo:GSE37745 licence not read", "asset:data:geo:GSE50081 not downloaded", "asset:data:geo:GSE50081 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "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-2", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {"hazard_ratio": "e analysisHR (95% CI) P HR (95% CI) P GSE31210 Age", "confidence_interval": "ultivariate analysisHR (95% CI) P HR (95% CI) P GSE312"}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Cox regression"}}, {"id": "method-3", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "log-rank"}}, {"id": "method-4", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC curve"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE31210", "GSE37745", "GSE50081"], "resolved_accessions": ["GSE31210", "GSE37745", "GSE50081"], "statements": ["The datasets used and/or analyzed during the current study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE31210, GSE37745, GSE50081 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": ["survival_km"], "assets": ["source:pmid:31088477", "data:geo:GSE31210", "asset:table:pmid:31088477:1", "asset:table:pmid:31088477:2", "asset:table:pmid:31088477:3", "asset:table:pmid:31088477:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE31210"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:44:36Z", "independence": "single_reader"}, "evidence_check": {"method": "absent", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 34235, "completion_tokens": 2049, "cached_tokens": 784}}, "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:31088477", "type": "paper", "label": "pmid:31088477"}, {"id": "source:pmid:31088477", "type": "manuscript", "label": "PMID 31088477 full text"}, {"id": "data:geo:GSE31210", "type": "dataset", "label": "GEO GSE31210"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31088477", "type": "paper", "label": "pmid:31088477"}, {"id": "source:pmid:31088477", "type": "manuscript", "label": "PMID 31088477 full text"}, {"id": "data:geo:GSE31210", "type": "dataset", "label": "GEO GSE31210"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31088477", "type": "extraction", "used": ["source:pmid:31088477"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE31210", "type": "accession_resolution", "used": ["data:geo:GSE31210"], "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:31088477", "parent_hash": "sha256:e95ff7ea2e69e8cd745d1a0dc68f1b91fbb59ba87398ad534275afcf5c706b2c", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE31210 licence not read", "asset:data:geo:GSE31210 not downloaded", "asset:data:geo:GSE37745 licence not read", "asset:data:geo:GSE37745 not downloaded", "asset:data:geo:GSE50081 licence not read", "asset:data:geo:GSE50081 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["dataset are described in Tables 1 and 2. All microarray data were normalized using robust multi-arra", "d using robust multi-array average (RMA) and microarray Suite 5 (MAS5) methods, and log2-scale trans", "were generated using the same chip platform Affymetrix HG-U133 Plus 2.0 platform. GSE31210 consiste"], "order_basis": "paper_text_order:2797", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Kaplan-Meier"], "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":"2026-11-04T04:15:42+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}}}