{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31612115", "kind": "science-record", "revision": 7, "content_hash": "sha256:108497bdbe81303afef99e2ceaf1e4d811ca1f669efdb6972a88b7a682fe7143", "created_at": "2026-11-01T15:40:50Z", "updated_at": "2026-11-01T22:00:54Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of a Nine-Gene Signature and Establishment of a Prognostic Nomogram Predicting Overall Survival of Pancreatic Cancer.", "doi": "10.3389/fonc.2019.00996", "pmid": "31612115", "authors": ["Mengwei Wu", "Xiaobin Li", "Taiping Zhang", "Ziwen Liu", "Yupei Zhao"], "journal": "Frontiers in oncology", "year": 2019, "abstract": "Background: Pancreatic cancer is highly lethal and aggressive with increasing trend of mortality in both genders. An effective prediction model is needed to assess prognosis of patients for optimization of treatment. Materials and Methods: Seven datasets of mRNA expression and clinical data were obtained from gene expression omnibus (GEO) database. Level 3 mRNA expression and clinicopathological data were obtained from The Cancer Genome Atlas pancreatic ductal adenocarcinoma (TCGA-PAAD) dataset. Differentially expressed genes (DEGs) between pancreatic tumor and normal tissue were identified by integrated analysis of multiple GEO datasets. Univariate and Lasso Cox regression analyses were applied to identify overall survival-related DEGs and establish a prognostic gene signature whose performance was evaluated by Kaplan-Meier curve, receiver operating characteristic (ROC), Harrell's concordance index (C-index) and calibration curve. GSE62452 and GSE57495 were used for external validation. Gene set enrichment analysis (GSEA) and tumor immunity analysis were applied to elucidate the molecular mechanisms and immune relevance. Multivariate Cox regression analysis was used to identify independent prognostic factors in pancreatic cancer. Finally, a prognostic nomogram was established based on the TCGA PAAD dataset. Results: A nine-gene signature comprising MET, KLK10, COL17A1, CEP55, ANKRD22, ITGB6, ARNTL2, MCOLN3, and SLC25A45 was established to predict overall survival of pancreatic cancer. The ROC curve and C-index indicated good performance of the nine-gene signature at predicting overall survival in the TCGA dataset and external validation datasets relative to classic AJCC staging. The nine-gene signature could classify patients into high- and low-risk groups with distinct overall survival and differentiate tumor from normal tissue. Univariate Cox regression revealed that the nine-gene signature was an independent prognostic factor in pancreatic cancer. The nomogram incorporating the gene signature and clinical prognostic factors was superior to AJCC staging in predicting overall survival. The high-risk group was enriched with multiple oncological signatures and aggressiveness-related pathways and associated with significantly lower levels of CD4+ T cell infiltration. Conclusion: Our study identified a nine-gene signature and established a prognostic nomogram that reliably predict overall survival in pancreatic cancer. The findings may be beneficial to therapeutic customization and medical decision-making.", "claims": [{"id": "claim-method", "statement": "A total of 234 DEGs including 160 upregulated and 74 downregulated genes were identified after integrated analysis by robust rank aggregation (RRA) method (Supplementary Table 1).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31612115", "locator": "sections[12] \"Identification of DEGs\" paragraph 2", "quote": "A total of 234 DEGs including 160 upregulated and 74 downregulated genes were identified after integrated analysis by robust rank aggregation (RRA) method (Supplementary Table 1)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31612115", "locator": "sections[23] \"Data Availability Statement\" paragraph 2", "quote": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:31612115"], "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:GSE15471"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:student_t", "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:GSE15471"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:student_t"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31612115", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fonc.2019.00996", "sha256": "sha256:6963258f947c0dd6e3747f1aa924cb1f0f872894c09e96bfbda9fba553da5ded", "bytes": 59829, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fonc.2019.00996", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6776930", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE15471", "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=GSE15471", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15471", "version": null, "note": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM388076", "GSM388077", "GSM388078", "GSM388079", "GSM388080", "GSM388081", "GSM388082", "GSM388083", "GSM388084", "GSM388085", "GSM388086", "GSM388087", "GSM388088", "GSM388089", "GSM388090", "GSM388091", "GSM388092", "GSM388093", "GSM388094", "GSM388095", "GSM388096", "GSM388097", "GSM388098", "GSM388099", "GSM388100", "GSM388101", "GSM388102", "GSM388103", "GSM388104", "GSM388105", "GSM388106", "GSM388107", "GSM388108", "GSM388109", "GSM388110", "GSM388111", "GSM388112", "GSM388113", "GSM388114", "GSM388115", "GSM388116", "GSM388117", "GSM388118", "GSM388119", "GSM388120", "GSM388121", "GSM388122", "GSM388123", "GSM388124", "GSM388125", "GSM388126", "GSM388127", "GSM388128", "GSM388129", "GSM388130", "GSM388131", "GSM388132", "GSM388133", "GSM388134", "GSM388135", "GSM388136", "GSM388137", "GSM388138", "GSM388139", "GSM388140", "GSM388141", "GSM388142", "GSM388143", "GSM388144", "GSM388145", "GSM388146", "GSM388147", "GSM388148", "GSM388149", "GSM388150", "GSM388151", "GSM388152", "GSM388153"], "sample_count": 78, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Whole-Tissue Gene Expression Study of Pancreatic Ductal Adenocarcinoma", "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:GSE16515", "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=GSE16515", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE16515", "version": null, "note": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM414924", "GSM414925", "GSM414926", "GSM414927", "GSM414928", "GSM414929", "GSM414930", "GSM414931", "GSM414932", "GSM414933", "GSM414934", "GSM414935", "GSM414936", "GSM414937", "GSM414938", "GSM414939", "GSM414940", "GSM414941", "GSM414942", "GSM414943", "GSM414944", "GSM414945", "GSM414946", "GSM414947", "GSM414948", "GSM414949", "GSM414950", "GSM414951", "GSM414952", "GSM414953", "GSM414954", "GSM414955", "GSM414956", "GSM414957", "GSM414958", "GSM414959", "GSM414960", "GSM414961", "GSM414962", "GSM414963", "GSM414964", "GSM414965", "GSM414966", "GSM414967", "GSM414968", "GSM414969", "GSM414970", "GSM414971", "GSM414972", "GSM414973", "GSM414974", "GSM414975"], "sample_count": 52, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from Mayo Clinic Pancreatic Tumor and Normal samples", "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:GSE28735", "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=GSE28735", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE28735", "version": null, "note": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM711904", "GSM711905", "GSM711906", "GSM711907", "GSM711908", "GSM711909", "GSM711910", "GSM711911", "GSM711912", "GSM711913", "GSM711914", "GSM711915", "GSM711916", "GSM711917", "GSM711918", "GSM711919", "GSM711920", "GSM711921", "GSM711922", "GSM711923", "GSM711924", "GSM711925", "GSM711926", "GSM711927", "GSM711928", "GSM711929", "GSM711930", "GSM711931", "GSM711932", "GSM711933", "GSM711934", "GSM711935", "GSM711936", "GSM711937", "GSM711938", "GSM711939", "GSM711940", "GSM711941", "GSM711942", "GSM711943", "GSM711944", "GSM711945", "GSM711946", "GSM711947", "GSM711948", "GSM711949", "GSM711950", "GSM711951", "GSM711952", "GSM711953", "GSM711954", "GSM711955", "GSM711956", "GSM711957", "GSM711958", "GSM711959", "GSM711960", "GSM711961", "GSM711962", "GSM711963", "GSM711964", "GSM711965", "GSM711966", "GSM711967", "GSM711968", "GSM711969", "GSM711970", "GSM711971", "GSM711972", "GSM711973", "GSM711974", "GSM711975", "GSM711976", "GSM711977", "GSM711978", "GSM711979", "GSM711980", "GSM711981", "GSM711982", "GSM711983", "GSM711984", "GSM711985", "GSM711986", "GSM711987", "GSM711988", "GSM711989", "GSM711990", "GSM711991", "GSM711992", "GSM711993"], "sample_count": 90, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Microarray gene-expression profiles of 45 matching pairs of pancreatic tumor and adjacent non-tumor tissues from 45 patients with pancreatic ductal adenocarcinoma", "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:GSE32676", "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=GSE32676", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32676", "version": null, "note": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM811004", "GSM811005", "GSM811006", "GSM811007", "GSM811008", "GSM811009", "GSM811010", "GSM811011", "GSM811012", "GSM811013", "GSM811014", "GSM811015", "GSM811016", "GSM811017", "GSM811018", "GSM811019", "GSM811020", "GSM811021", "GSM811022", "GSM811023", "GSM811024", "GSM811025", "GSM811026", "GSM811027", "GSM811028", "GSM811029", "GSM811030", "GSM811031", "GSM811032", "GSM811033", "GSM811034", "GSM811035"], "sample_count": 32, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Integrative Survival-Based Molecular Profiling of Human Pancreatic Cancer [mRNA]", "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:GSE57495", "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=GSE57495", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE57495", "version": null, "note": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1383778", "GSM1383779", "GSM1383780", "GSM1383781", "GSM1383782", "GSM1383783", "GSM1383784", "GSM1383785", "GSM1383786", "GSM1383787", "GSM1383788", "GSM1383789", "GSM1383790", "GSM1383791", "GSM1383792", "GSM1383793", "GSM1383794", "GSM1383795", "GSM1383796", "GSM1383797", "GSM1383798", "GSM1383799", "GSM1383800", "GSM1383801", "GSM1383802", "GSM1383803", "GSM1383804", "GSM1383805", "GSM1383806", "GSM1383807", "GSM1383808", "GSM1383809", "GSM1383810", "GSM1383811", "GSM1383812", "GSM1383813", "GSM1383814", "GSM1383815", "GSM1383816", "GSM1383817", "GSM1383818", "GSM1383819", "GSM1383820", "GSM1383821", "GSM1383822", "GSM1383823", "GSM1383824", "GSM1383825", "GSM1383826", "GSM1383827", "GSM1383828", "GSM1383829", "GSM1383830", "GSM1383831", "GSM1383832", "GSM1383833", "GSM1383834", "GSM1383835", "GSM1383836", "GSM1383837", "GSM1383838", "GSM1383839", "GSM1383840"], "sample_count": 63, "group_sizes": null, "group_sizes_basis": null, "platform": "15048", "taxon": "Homo sapiens", "title": "Development of a prognostic gene signature in pancreatic cancer", "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:GSE62165", "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=GSE62165", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62165", "version": null, "note": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1520738", "GSM1520739", "GSM1520740", "GSM1520741", "GSM1520742", "GSM1520743", "GSM1520744", "GSM1520745", "GSM1520746", "GSM1520747", "GSM1520748", "GSM1520749", "GSM1520750", "GSM1520751", "GSM1520752", "GSM1520753", "GSM1520754", "GSM1520755", "GSM1520756", "GSM1520757", "GSM1520758", "GSM1520759", "GSM1520760", "GSM1520761", "GSM1520762", "GSM1520763", "GSM1520764", "GSM1520765", "GSM1520766", "GSM1520767", "GSM1520768", "GSM1520769", "GSM1520770", "GSM1520771", "GSM1520772", "GSM1520773", "GSM1520774", "GSM1520775", "GSM1520776", "GSM1520777", "GSM1520778", "GSM1520779", "GSM1520780", "GSM1520781", "GSM1520782", "GSM1520783", "GSM1520784", "GSM1520785", "GSM1520786", "GSM1520787", "GSM1520788", "GSM1520789", "GSM1520790", "GSM1520791", "GSM1520792", "GSM1520793", "GSM1520794", "GSM1520795", "GSM1520796", "GSM1520797", "GSM1520798", "GSM1520799", "GSM1520800", "GSM1520801", "GSM1520802", "GSM1520803", "GSM1520804", "GSM1520805", "GSM1520806", "GSM1520807", "GSM1520808", "GSM1520809", "GSM1520810", "GSM1520811", "GSM1520812", "GSM1520813", "GSM1520814", "GSM1520815", "GSM1520816", "GSM1520817", "GSM1520818", "GSM1520819", "GSM1520820", "GSM1520821", "GSM1520822", "GSM1520823", "GSM1520824", "GSM1520825", "GSM1520826", "GSM1520827", "GSM1520828", "GSM1520829", "GSM1520830", "GSM1520831", "GSM1520832", "GSM1520833", "GSM1520834", "GSM1520835", "GSM1520836", "GSM1520837", "GSM1520838", "GSM1520839", "GSM1520840", "GSM1520841", "GSM1520842", "GSM1520843", "GSM1520844", "GSM1520845", "GSM1520846", "GSM1520847", "GSM1520848", "GSM1520849", "GSM1520850", "GSM1520851", "GSM1520852", "GSM1520853", "GSM1520854", "GSM1520855", "GSM1520856", "GSM1520857", "GSM1520858", "GSM1520859", "GSM1520860", "GSM1520861", "GSM1520862", "GSM1520863", "GSM1520864", "GSM1520865", "GSM1520866", "GSM1520867", "GSM1520868"], "sample_count": 131, "group_sizes": null, "group_sizes_basis": null, "platform": "13667", "taxon": "Homo sapiens", "title": "Prognostic relevance of molecular subtypes and master regulators in pancreatic ductal adenocarcinoma", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE62452", "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=GSE62452", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62452", "version": null, "note": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1527105", "GSM1527106", "GSM1527107", "GSM1527108", "GSM1527109", "GSM1527110", "GSM1527111", "GSM1527112", "GSM1527113", "GSM1527114", "GSM1527115", "GSM1527116", "GSM1527117", "GSM1527118", "GSM1527119", "GSM1527120", "GSM1527121", "GSM1527122", "GSM1527123", "GSM1527124", "GSM1527125", "GSM1527126", "GSM1527127", "GSM1527128", "GSM1527129", "GSM1527130", "GSM1527131", "GSM1527132", "GSM1527133", "GSM1527134", "GSM1527135", "GSM1527136", "GSM1527137", "GSM1527138", "GSM1527139", "GSM1527140", "GSM1527141", "GSM1527142", "GSM1527143", "GSM1527144", "GSM1527145", "GSM1527146", "GSM1527147", "GSM1527148", "GSM1527149", "GSM1527150", "GSM1527151", "GSM1527152", "GSM1527153", "GSM1527154", "GSM1527155", "GSM1527156", "GSM1527157", "GSM1527158", "GSM1527159", "GSM1527160", "GSM1527161", "GSM1527162", "GSM1527163", "GSM1527164", "GSM1527165", "GSM1527166", "GSM1527167", "GSM1527168", "GSM1527169", "GSM1527170", "GSM1527171", "GSM1527172", "GSM1527173", "GSM1527174", "GSM1527175", "GSM1527176", "GSM1527177", "GSM1527178", "GSM1527179", "GSM1527180", "GSM1527181", "GSM1527182", "GSM1527183", "GSM1527184", "GSM1527185", "GSM1527186", "GSM1527187", "GSM1527188", "GSM1527189", "GSM1527190", "GSM1527191", "GSM1527192", "GSM1527193", "GSM1527194", "GSM1527195", "GSM1527196", "GSM1527197", "GSM1527198", "GSM1527199", "GSM1527200", "GSM1527201", "GSM1527202", "GSM1527203", "GSM1527204", "GSM1527205", "GSM1527206", "GSM1527207", "GSM1527208", "GSM1527209", "GSM1527210", "GSM1527211", "GSM1527212", "GSM1527213", "GSM1527214", "GSM1527215", "GSM1527216", "GSM1527217", "GSM1527218", "GSM1527219", "GSM1527220", "GSM1527221", "GSM1527222", "GSM1527223", "GSM1527224", "GSM1527225", "GSM1527226", "GSM1527227", "GSM1527228", "GSM1527229", "GSM1527230", "GSM1527231", "GSM1527232", "GSM1527233", "GSM1527234"], "sample_count": 130, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Microarray gene-expression profiles of 69 pancreatic tumors and 61 adjacent non-tumor tissue from patients with pancreatic ductal adenocarcinoma", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE71729", "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=GSE71729", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE71729", "version": null, "note": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1843893", "GSM1843894", "GSM1843895", "GSM1843896", "GSM1843897", "GSM1843898", "GSM1843899", "GSM1843900", "GSM1843901", "GSM1843902", "GSM1843903", "GSM1843904", "GSM1843905", "GSM1843906", "GSM1843907", "GSM1843908", "GSM1843909", "GSM1843910", "GSM1843911", "GSM1843912", "GSM1843913", "GSM1843914", "GSM1843915", "GSM1843916", "GSM1843917", "GSM1843918", "GSM1843919", "GSM1843920", "GSM1843921", "GSM1843922", "GSM1843923", "GSM1843924", "GSM1843925", "GSM1843926", "GSM1843927", "GSM1843928", "GSM1843929", "GSM1843930", "GSM1843931", "GSM1843932", "GSM1843933", "GSM1843934", "GSM1843935", "GSM1843936", "GSM1843937", "GSM1843938", "GSM1843939", "GSM1843940", "GSM1843941", "GSM1843942", "GSM1843943", "GSM1843944", "GSM1843945", "GSM1843946", "GSM1843947", "GSM1843948", "GSM1843949", "GSM1843950", "GSM1843951", "GSM1843952", "GSM1843953", "GSM1843954", "GSM1843955", "GSM1843956", "GSM1843957", "GSM1843958", "GSM1843959", "GSM1843960", "GSM1843961", "GSM1843962", "GSM1843963", "GSM1843964", "GSM1843965", "GSM1843966", "GSM1843967", "GSM1843968", "GSM1843969", "GSM1843970", "GSM1843971", "GSM1843972", "GSM1843973", "GSM1843974", "GSM1843975", "GSM1843976", "GSM1843977", "GSM1843978", "GSM1843979", "GSM1843980", "GSM1843981", "GSM1843982", "GSM1843983", "GSM1843984", "GSM1843985", "GSM1843986", "GSM1843987", "GSM1843988", "GSM1843989", "GSM1843990", "GSM1843991", "GSM1843992", "GSM1843993", "GSM1843994", "GSM1843995", "GSM1843996", "GSM1843997", "GSM1843998", "GSM1843999", "GSM1844000", "GSM1844001", "GSM1844002", "GSM1844003", "GSM1844004", "GSM1844005", "GSM1844006", "GSM1844007", "GSM1844008", "GSM1844009", "GSM1844010", "GSM1844011", "GSM1844012", "GSM1844013", "GSM1844014", "GSM1844015", "GSM1844016", "GSM1844017", "GSM1844018", "GSM1844019", "GSM1844020", "GSM1844021", "GSM1844022", "GSM1844023", "GSM1844024", "GSM1844025", "GSM1844026", "GSM1844027", "GSM1844028", "GSM1844029", "GSM1844030", "GSM1844031", "GSM1844032", "GSM1844033", "GSM1844034", "GSM1844035", "GSM1844036", "GSM1844037", "GSM1844038", "GSM1844039", "GSM1844040", "GSM1844041", "GSM1844042", "GSM1844043", "GSM1844044", "GSM1844045", "GSM1844046", "GSM1844047", "GSM1844049", "GSM1844050", "GSM1844051", "GSM1844052", "GSM1844053", "GSM1844054", "GSM1844055", "GSM1844056", "GSM1844057", "GSM1844058", "GSM1844059", "GSM1844060", "GSM1844061", "GSM1844062", "GSM1844063", "GSM1844064", "GSM1844065", "GSM1844066", "GSM1844067", "GSM1844068", "GSM1844069", "GSM1844070", "GSM1844071", "GSM1844072", "GSM1844073", "GSM1844074", "GSM1844075", "GSM1844076", "GSM1844077", "GSM1844078", "GSM1844079", "GSM1844080", "GSM1844081", "GSM1844082", "GSM1844083", "GSM1844084", "GSM1844085", "GSM1844086", "GSM1844088", "GSM1844089", "GSM1844090", "GSM1844091", "GSM1844092", "GSM1844093", "GSM1844094", "GSM1844095", "GSM1844096", "GSM1844097", "GSM1844098", "GSM1844099", "GSM1844100", "GSM1844101", "GSM1844102", "GSM1844103", "GSM1844104", "GSM1844105", "GSM1844106", "GSM1844107", "GSM1844108", "GSM1844109", "GSM1844110", "GSM1844111", "GSM1844112", "GSM1844113", "GSM1844114", "GSM1844115", "GSM1844116", "GSM1844117", "GSM1844118", "GSM1844119", "GSM1844120", "GSM1844121", "GSM1844122", "GSM1844123", "GSM1844124", "GSM1844125", "GSM1844126", "GSM1844127", "GSM1844128", "GSM1844129", "GSM1844130", "GSM1844131", "GSM1844132", "GSM1844133", "GSM1844134", "GSM1844135", "GSM1844136", "GSM1844137", "GSM1844138", "GSM1844139", "GSM1844140", "GSM1844141", "GSM1844142", "GSM1844143", "GSM1844144", "GSM1844145", "GSM1844146", "GSM1844147", "GSM1844148", "GSM1844149", "GSM1844150", "GSM1844151", "GSM1844152", "GSM1844153", "GSM1844154", "GSM1844155", "GSM1844156", "GSM1844157", "GSM1844158", "GSM1844159", "GSM1844160", "GSM1844161", "GSM1844162", "GSM1844163", "GSM1844164", "GSM1844165", "GSM1844166", "GSM1844167", "GSM1844168", "GSM1844169", "GSM1844170", "GSM1844171", "GSM1844172", "GSM1844173", "GSM1844174", "GSM1844175", "GSM1844176", "GSM1844177", "GSM1844178", "GSM1844179", "GSM1844180", "GSM1844181", "GSM1844182", "GSM1844183", "GSM1844184", "GSM1844185", "GSM1844186", "GSM1844187", "GSM1844188", "GSM1844189", "GSM1844190", "GSM1844191", "GSM1844192", "GSM1844193", "GSM1844194", "GSM1844195", "GSM1844196", "GSM1844197", "GSM1844198", "GSM1844199", "GSM1844200", "GSM1844201", "GSM1844202", "GSM1844203", "GSM1844204", "GSM1844205", "GSM1844206", "GSM1844207", "GSM1844208", "GSM1844209", "GSM1844210", "GSM1844211", "GSM1844212", "GSM1844213", "GSM1844214", "GSM1844215", "GSM1844216", "GSM1844217", "GSM1844218", "GSM1844219", "GSM1844220", "GSM1844221", "GSM1844222", "GSM1844223", "GSM1844224", "GSM1844225", "GSM1844226", "GSM1844227", "GSM1844228", "GSM1844229", "GSM1844230", "GSM1844231", "GSM1844232", "GSM1844233", "GSM1844234", "GSM1844235", "GSM1844236", "GSM1844237", "GSM1844238", "GSM1844239", "GSM1844240", "GSM1844241", "GSM1844242", "GSM1844243", "GSM1844244", "GSM1844245", "GSM1844246", "GSM1844247", "GSM1844248", "GSM1844249", "GSM1844250", "GSM1844251"], "sample_count": 357, "group_sizes": null, "group_sizes_basis": null, "platform": "20769", "taxon": "Homo sapiens", "title": "Virtual Microdissection of Pancreatic Ductal Adenocarcinoma Reveals Tumor and Stroma Subtypes.", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31612115:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:eb98ddbb23b3f1e6a649fd36f652a4521d11955843a7994c4085b5883068e74c", "bytes": 1412, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T1", "version": null, "note": "Details of the GEO datasets included in this study.", "structure": {"pmcid": "PMC6776930", "section_index": 12, "section_title": "Identification of DEGs", "row_count": 9, "column_count": 5}, "table": {"label": "Table 1", "caption": "Details of the GEO datasets included in this study.", "rows": [["Datasets", "References", "Platform", "Sample size (tumor/control)", "Application"], ["GSE71729", "Moffitt et al. (9)", "Agilent-014850 whole human genome microarray 4x44K G4112F (Gene Symbol Version; updated July, 2014)", "357 (145/46)", "Identification of DEGs"], ["GSE62165", "Janky et al. (10)", "[HG-U219] affymetrix human genome U219 array", "131 (118/13)", "Identification of DEGs"], ["GSE62452", "Yang et al. (11)", "[HuGene-1_0-st] affymetrix human gene 1.0 ST array [transcript (gene) version]", "130 (69/61)", "Identification of DEGs and validation"], ["GSE28735", "Zhang et al. (12)", "[HuGene-1_0-st] affymetrix human gene 1.0 ST array [transcript (gene) version]", "90 (45/45)", "Identification of DEGs"], ["GSE15471", "Badea et al. (13)", "[HG-U133_Plus_2] affymetrix human genome U133 Plus 2.0 array", "78 (39/39)", "Identification of DEGs"], ["GSE16515", "Pei et al. (14)", "[HG-U133_Plus_2] affymetrix human genome U133 Plus 2.0 array", "52 (36/16)", "Identification of DEGs"], ["GSE32676", "Donahue et al. (15)", "[HG-U133_Plus_2] affymetrix human genome U133 Plus 2.0 array", "32 (25/7)", "Identification of DEGs"], ["GSE57495", "Chen et al. (16)", "Rosetta/Merck human RSTA custom affymetrix 2.0 microarray", "63(63/0)", "Validation"]], "row_count": 9, "column_count": 5, "numeric_cells": 32, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:31612115:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c9ac17bac8a96e099b15faf1c65d23a189e1057698cedd34d1df0774b0df1f59", "bytes": 3306, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#T2", "version": null, "note": "Clinical features of pancreatic cancer patients in the TCGA Dataset.", "structure": {"pmcid": "PMC6776930", "section_index": 14, "section_title": "Identification of Survival-Related DEGs and Establishment of the Nine-Gene Prognostic Signature", "row_count": 106, "column_count": 2}, "table": {"label": "Table 2", "caption": "Clinical features of pancreatic cancer patients in the TCGA Dataset.", "rows": [["Clinical features", "Mean + SD"], ["Follow-up time (day)", "591.02 ± 479.02"], ["Age", "64.53 ± 10.84"], ["Size (cm)", "3.91 ± 1.70"], ["", "N (%)"], ["Survival status"], ["Alive", "76 (46.06%)"], ["Dead", "89 (53.94%)"], ["Sex"], ["Male", "90 (54.55%)"], ["Female", "75 (45.45%)"], ["Site"], ["Head of pancreas", "128 (77.58%)"], ["Body of pancreas", "14 (8.48%)"], ["Tail of pancreas", "12 (7.27%)"], ["Others", "11 (6.67%)"], ["Subtype"], ["Pancreas-adenocarcinoma ductal type", "140 (84.85%)"], ["Pancreas-adenocarcinoma-other subtype", "25 (15.15%)"], ["Grade"], ["G1", "27 (16.36%)"], ["G2", "89 (53.94%)"], ["G3", "47 (28.48%)"], ["G4", "1 (0.61%)"], ["Not available", "1 (0.61%)"], ["T"], ["T1", "6 (3.64%)"], ["T2", "20 (12.12%)"], ["T3", "134 (81.21%)"], ["T4", "3 (1.82%)"], ["Not available", "2 (1.21%)"], ["N"], ["N0", "45 (27.27%)"], ["N1", "116 (70.30%)"], ["Not available", "4 (2.42%)"], ["M"], ["M0", "74 (44.85%)"], ["M1", "4 (2.42%)"], ["Mx", "87 (52.73%)"], ["AJCC stage"], ["I", "1 (0.61%)"], ["IA", "4 (2.42%)"], ["IB", "13 (7.88%)"], ["IIA", "26 (15.76%)"], ["IIB", "112 (67.88%)"], ["III", "3 (1.82%)"], ["IV", "4 (2.42%)"], ["Not available", "2 (1.21%)"], ["Residual tumor"], ["R0", "96 (58.18%)"], ["R1", "51 (30.91%)"], ["R2", "5 (3.03%)"], ["Not available", "13 (7.88%)"], ["Initial pathologic diagnosis method"], ["Tumor resection", "99 (60.00%)"], ["Tissue biopsy", "35 (21.21%)"], ["Cytology (e.g., Peritoneal or pleural fluid)", "22 (13.33%)"], ["Fine needle aspiration biopsy", "4 (2.42%)"], ["Not available", "5 (3.03%)"], ["Surgical treatment"], ["Whipple", "130 (78.79%)"], ["Distal pancreatectomy", "22 (13.33%)"], ["Distal pancreatectomy and laporoscopy followed by Hand-assisted and splenectomy", "1 (0.61%)"], ["Subtotal pancreatectomy", "2 (1.21%)"], ["Subtotal pancreatectomy and splenectomy and cholecystectomy", "1 (0.61%)"], ["Near total pancreatomy with splenectomy, duodenum perserving", "1 (0.61%)"], ["Radical pancreaticoduodenectomy", "3 (1.82%)"], ["Total pancreatectomy", "2 (1.21%)"], ["Endoscopic retrograde cholangiopancreaticography", "1 (0.61%)"], ["Not available", "2 (1.21%)"], ["History of neoadjuvant treatment"], ["No", "164 (99.39%)"], ["Yes", "1 (0.61%)"], ["History of chemotherapy"], ["No", "51 (30.91%)"], ["Yes", "114 (69.09%)"], ["History of radiation therapy"], ["No", "94 (56.97%)"], ["Yes", "45 (27.27%)"], ["Not available", "26 (15.76%)"], ["History of targeted molecular therapy"], ["No", "41 (24.85%)"], ["Yes", "112 (67.88%)"], ["Not available", "12 (7.27%)"], ["Tobacco smoking history"], ["Lifelong non-smoker", "60 (36.36%)"], ["Current smoker", "18 (10.91%)"], ["Current reformed smoker for >15 years", "27 (16.36%)"], ["Current reformed smoker for ≤15 years", "22 (13.33%)"], ["Current reformed smoker, duration not specified", "7 (4.24%)"], ["Not available", "31 (18.79%)"], ["Alcohol drinking history"], ["No", "61 (36.97%)"], ["Yes", "92 (55.76%)"], ["Not available", "12 (7.27%)"], ["History of chronic pancreatitis"], ["No", "119 (72.12%)"], ["Yes", "13 (7.88%)"], ["Not available", "33 (20.00%)"], ["History of diabetes"], ["No", "102 (61.82%)"], ["Yes", "34 (20.61%)"], ["Not available", "29 (17.58%)"], ["History of prior malignancy"], ["No", "148 (89.70%)"], ["Yes", "17 (10.30)"]], "row_count": 106, "column_count": 2, "numeric_cells": 85, "header_rows": 1, "locator": "section[14]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:31612115:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7735b8982ca439240eced7ecffd99c48c230de6afcc2382e54ad161de6c6c2d0", "bytes": 2840, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#T3", "version": null, "note": "Baseline characteristics of patients included for univariate and multivariate Cox regression analysis.", "structure": {"pmcid": "PMC6776930", "section_index": 17, "section_title": "Evaluation of Prognostic Factors in PAAD", "row_count": 92, "column_count": 2}, "table": {"label": "Table 3", "caption": "Baseline characteristics of patients included for univariate and multivariate Cox regression analysis.", "rows": [["Clinical features", "Mean + SD"], ["Risk score", "2.06 ± 0.44"], ["Age", "63.59 ± 11.31"], ["Follow-up time (day)", "528.46 ± 371.92"], ["Size (cm)", "3.77 ± 1.44"], ["", "N (%)"], ["Survival status"], ["Alive", "35 (38.46%)"], ["Dead", "56 (61.54%)"], ["Sex"], ["Male", "52 (57.14%)"], ["Female", "39 (42.86%)"], ["Site"], ["Head of pancreas", "74 (81.32%)"], ["Body of pancreas", "5 (5.49%)"], ["Tail of Pancreas", "9 (9.89%)"], ["Others", "3 (3.30%)"], ["Subtype"], ["Pancreas-adenocarcinoma ductal type", "79 (86.81%)"], ["Pancreas-adenocarcinoma-other subtype", "12 (13.19%)"], ["Grade"], ["G1", "9 (9.89%)"], ["G2", "51 (56.04%)"], ["G3", "30 (32.97%)"], ["G4", "1 (1.10%)"], ["T"], ["T1", "4 (4.40%)"], ["T2", "11 (12.09%)"], ["T3", "75 (82.42%)"], ["T4", "1 (1.10%)"], ["N"], ["N0", "26 (28.57%)"], ["N1", "65 (71.43%)"], ["M"], ["M0", "54 (59.34%)"], ["M1", "1 (1.10%)"], ["Mx", "36 (39.56%)"], ["AJCC stage"], ["IA", "3 (3.30%)"], ["IB", "8 (8.79%)"], ["IIA", "14 (15.38%)"], ["IIB", "64 (70.33%)"], ["III", "1 (1.10%)"], ["IV", "1 (1.10%)"], ["Residual tumor"], ["R0", "55 (60.44%)"], ["R1", "34 (37.36%)"], ["R2", "2 (2.20%)"], ["Initial pathologic diagnosis method"], ["Tumor resection", "53 (58.24%)"], ["Tissue biopsy", "23 (25.27%)"], ["Cytology (e.g., Peritoneal or pleural fluid)", "13 (14.29%)"], ["Fine needle aspiration biopsy", "1 (1.10%)"], ["Not available", "1 (1.10%)"], ["Surgical treatment"], ["Whipple", "74 (81.32%)"], ["Distal pancreatectomy", "12 (13.19%)"], ["Distal pancreatectomy and laporoscopy followed by Hand-assisted and splenectomy", "1 (1.10%)"], ["Subtotal pancreatectomy", "1 (1.10%)"], ["Subtotal pancreatectomy and splenectomy and cholecystectomy", "1 (1.10%)"], ["Total pancreatectomy", "1 (1.10%)"], ["Endoscopic retrograde cholangiopancreaticography", "1 (1.10%)"], ["History of neoadjuvant treatment"], ["No", "90 (98.90%)"], ["Yes", "1 (1.10%)"], ["History of chemotherapy", ""], ["No", "25 (27.47%)"], ["Yes", "66 (72.53%)"], ["History of radiation therapy"], ["No", "67 (73.63%)"], ["Yes", "24 (26.37%)"], ["History of targeted molecular therapy"], ["No", "29 (31.87%)"], ["Yes", "62 (68.13%)"], ["Tobacco smoking history"], ["Lifelong non-smoker", "34 (37.36%)"], ["Current smoker", "16 (17.58%)"], ["Current reformed smoker for >15 years", "21 (23.08%)"], ["Current reformed smoker for ≤15 years", "15 (16.48%)"], ["Current reformed smoker, duration not specified", "5 (5.49%)"], ["Alcohol drinking history"], ["No", "25 (27.47%)"], ["Yes", "66 (72.53%)"], ["History of chronic pancreatitis"], ["No", "80 (87.91%)"], ["Yes", "11 (12.09%)"], ["History of diabetes"], ["No", "67 (73.63%)"], ["Yes", "24 (26.37%)"], ["History of prior malignancy"], ["No", "82 (90.11%)"], ["Yes", "9 (9.89%)"]], "row_count": 92, "column_count": 2, "numeric_cells": 71, "header_rows": 1, "locator": "section[17]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:31612115:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2e5ca9e14fdd576be9ee1cd5213472b52e3c946ce79736855f659020bdb3d7f1", "bytes": 3174, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[2]#T4", "version": null, "note": "Unadjusted univariate analysis.", "structure": {"pmcid": "PMC6776930", "section_index": 17, "section_title": "Evaluation of Prognostic Factors in PAAD", "row_count": 76, "column_count": 3}, "table": {"label": "Table 4", "caption": "Unadjusted univariate analysis.", "rows": [["Exposure", "Statistics", "Overall survival"], ["Risk score", "2.06 ± 0.44", "5.45 (2.09, 14.17) 0.0005"], ["Risk score tertile", "", ""], ["Low", "30 (32.97%)", "1"], ["Middle", "30 (32.97%)", "1.56 (0.79, 3.08) 0.1991"], ["High", "31 (34.07%)", "2.17 (1.12, 4.19) 0.0218"], ["Age", "63.59 ± 11.31", "1.02 (1.00, 1.05) 0.0663"], ["Age tertile", "", ""], ["Low", "30 (32.97%)", "1"], ["Middle", "29 (31.87%)", "1.07 (0.53, 2.16) 0.8510"], ["High", "32 (35.16%)", "1.68 (0.88, 3.22) 0.1155"], ["Sex", "", ""], ["Male", "52 (57.14%)", "1"], ["Female", "39 (42.86%)", "1.06 (0.62, 1.79) 0.8367"], ["Size(cm)", "3.77 ± 1.44", "1.24 (1.03, 1.49) 0.0235"], ["Size(cm) tertile", "", ""], ["Low", "26 (28.57%)", "1"], ["Middle", "25 (27.47%)", "0.91 (0.43, 1.92) 0.7992"], ["High", "40 (43.96%)", "1.33 (0.72, 2.46) 0.3660"], ["Site", "", ""], ["Head of pancreas", "74 (81.32%)", "1"], ["Body and tail of pancreas and others", "17 (18.68%)", "0.37 (0.16, 0.87) 0.0225"], ["Subtype", "", ""], ["Pancreas-adenocarcinoma ductal type", "79 (86.81%)", "1"], ["Pancreas-adenocarcinoma- other subtype", "12 (13.19%)", "0.30 (0.11, 0.84) 0.0215"], ["Grade", "", ""], ["G1 and G2", "60 (65.93%)", "1"], ["G3 and G4", "31 (34.07%)", "1.57 (0.92, 2.68) 0.0975"], ["T", "", ""], ["T1 and T2", "15 (16.48%)", "1"], ["T3 and T4", "76 (83.52%)", "3.24 (1.28, 8.20) 0.0129"], ["N", "", ""], ["N0", "26 (28.57%)", "1"], ["N1", "65 (71.43%)", "2.69 (1.35, 5.36) 0.0049"], ["M", "", ""], ["M0", "54 (59.34%)", "1"], ["M1", "1 (1.10%)", "2.10 (0.28, 15.54) 0.4681"], ["Mx", "36 (39.56%)", "0.79 (0.46, 1.36) 0.4016"], ["AJCC stage", "", ""], ["I", "11 (12.09%)", "1"], ["IIA", "14 (15.38%)", "1.33 (0.35, 4.99) 0.6770"], ["IIB", "63 (69.23%)", "3.34 (1.19, 9.41) 0.0224"], ["III and IV", "3 (3.30%)", "7.42 (1.59, 34.63) 0.0108"], ["Residual tumor", "", ""], ["R0", "55 (60.44%)", "1"], ["R1", "34 (37.36%)", "1.82 (1.05, 3.14) 0.0320"], ["R2", "2 (2.20%)", "1.72 (0.23, 12.82) 0.5976"], ["Surgical treatment", "", ""], ["Whipple", "74 (81.32%)", "1"], ["Distal pancreatectomy", "13 (14.29%)", "0.51 (0.22, 1.20) 0.1237"], ["Subtotal pancreatectomy", "2 (2.20%)", "0.00 (0.00, Inf) 0.9973"], ["Others", "2 (2.20%)", "0.00 (0.00, Inf) 0.9978"], ["History of chemotherapy", "", ""], ["No", "25 (27.47%)", "1"], ["Yes", "66 (72.53%)", "0.52 (0.30, 0.90) 0.0202"], ["History of radiation therapy", "", ""], ["No", "67 (73.63%)", "1"], ["Yes", "24 (26.37%)", "0.45 (0.23, 0.89) 0.0228"], ["History of targeted molecular therapy", "", ""], ["No", "29 (31.87%)", "1"], ["Yes", "62 (68.13%)", "0.30 (0.17, 0.51) <0.0001"], ["Tobacco smoking history", "", ""], ["Lifelong non-smoker", "34 (37.36%)", "1"], ["Current or former smoker", "57 (62.64%)", "0.77 (0.45, 1.32) 0.3397"], ["Alcohol drinking history", "", ""], ["No", "25 (27.47%)", "1"], ["Yes", "66 (72.53%)", "1.27 (0.70, 2.30) 0.4252"], ["History of chronic pancreatitis", "", ""], ["No", "80 (87.91%)", "1"], ["Yes", "11 (12.09%)", "0.81 (0.37, 1.79) 0.6029"], ["History of diabetes", "", ""], ["No", "67 (73.63%)", "1"], ["Yes", "24 (26.37%)", "0.94 (0.50, 1.75) 0.8422"], ["History of prior malignancy", "", ""], ["No", "82 (90.11%)", "1"], ["Yes", "9 (9.89%)", "1.18 (0.50, 2.77) 0.7006"]], "row_count": 76, "column_count": 3, "numeric_cells": 108, "header_rows": 1, "locator": "section[17]/table-wrap[2]#T4"}}, {"id": "asset:table:pmid:31612115:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b8fa5ede2414f11c67f0bbb18061b2aa1413f8c5295983c8154d148fad4fde4e", "bytes": 4143, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[3]#T5", "version": null, "note": "Multivariate Cox regression analysis.", "structure": {"pmcid": "PMC6776930", "section_index": 17, "section_title": "Evaluation of Prognostic Factors in PAAD", "row_count": 64, "column_count": 5}, "table": {"label": "Table 5", "caption": "Multivariate Cox regression analysis.", "rows": [["Exposure", "Non-adjusted", "Adjust I", "Adjust II", "Adjust III"], ["Risk score", "5.45 (2.09, 14.17) 0.0005", "4.74 (1.73, 12.96) 0.0025", "4.74 (1.73, 12.96) 0.0025", "3.58 (1.50, 8.51) 0.0040"], ["Age", "1.02 (1.00, 1.05) 0.0663", "1.02 (1.00, 1.05) 0.0872", "1.03 (1.00, 1.05) 0.0536", "NA"], ["Sex"], ["Male", "1", "1", "1", "NA"], ["Female", "1.06 (0.62, 1.79) 0.8367", "0.88 (0.51, 1.52) 0.6477", "0.86 (0.50, 1.48) 0.5961", "NA"], ["Size(cm)", "1.24 (1.03, 1.49) 0.0235", "1.19 (0.96, 1.47) 0.1219", "1.19 (0.96, 1.47) 0.1167", "1.30 (1.00, 1.68) 0.0463"], ["Site"], ["Head of pancreas", "1", "1", "1", "1"], ["Body and tail of pancreas and others", "0.37 (0.16, 0.87) 0.0225", "0.51 (0.21, 1.23) 0.1351", "0.49 (0.20, 1.19) 0.1143", "0.44 (0.16, 1.15) 0.0944"], ["Subtype"], ["Pancreas-adenocarcinoma ductal type", "1", "1", "1", "1"], ["Pancreas-adenocarcinoma-other subtype", "0.30 (0.11, 0.84) 0.0215", "0.53 (0.18, 1.58) 0.2524", "0.78 (0.26, 2.29) 0.6462", "0.49 (0.16, 1.47) 0.2005"], ["Grade"], ["G1 and G2", "1", "1", "1", "NA"], ["G3 and G4", "1.57 (0.92, 2.68) 0.0975", "1.39 (0.80, 2.42) 0.2490", "1.22 (0.70, 2.14) 0.4853", "NA"], ["T"], ["T1 and T2", "1", "1", "1", "1"], ["T3 and T4", "3.24 (1.28, 8.20) 0.0129", "4.00 (0.53, 29.92) 0.1770", "4.33 (0.58, 32.56) 0.1543", "4.50 (0.60, 33.92) 0.1439"], ["N"], ["N0", "1", "1", "1", "1"], ["N1", "2.69 (1.35, 5.36) 0.0049", "0.89 (0.08, 10.23) 0.9268", "0.48 (0.04, 5.72) 0.5603", "0.21 (0.01,3.20) 0.2603"], ["M"], ["M0", "1", "1", "1", "NA"], ["M1", "2.10 (0.28, 15.54) 0.4681", "0.44 (0.04, 5.46) 0.5261", "0.53 (0.04, 6.58) 0.6213", "NA"], ["Mx", "0.79 (0.46, 1.36) 0.4016", "0.74 (0.42, 1.30) 0.2906", "0.81 (0.46, 1.43) 0.4621", "NA"], ["AJCC stage"], ["I", "1", "1", "1", "1"], ["IIA", "1.33 (0.35, 4.99) 0.6770", "1.25 (0.33, 4.77) 0.7401", "0.96 (0.26, 3.64) 0.9571", "0.22 (0.02, 2.63) 0.2340"], ["IIB", "3.34 (1.19, 9.41) 0.0224", "3.13 (1.11, 8.83) 0.0315", "2.11 (0.75, 5.92) 0.1553", "2.00 (0.06, 64.49) 0.6957"], ["III and IV", "7.42 (1.59, 34.63) 0.0108", "8.61 (1.81, 40.88) 0.0068", "4.07 (0.85, 19.52) 0.0796", "1.60 (0.07, 36.94) 0.7701"], ["Residual tumor"], ["R0", "1", "1", "1", "1"], ["R1", "1.82 (1.05, 3.14) 0.0320", "1.63 (0.93, 2.87) 0.0895", "1.66 (0.95, 2.90) 0.0754", "1.25 (0.68, 2.29) 0.4658"], ["R2", "1.72 (0.23, 12.82) 0.5976", "1.94 (0.24, 15.36) 0.5312", "2.26 (0.28, 18.34) 0.4447", "3.55 (0.43, 29.18) 0.2377"], ["Surgical treatment"], ["Whipple", "1", "1", "1", "NA"], ["Distal pancreatectomy", "0.51 (0.22, 1.20) 0.1237", "0.72 (0.29, 1.76) 0.4649", "0.65 (0.27, 1.58) 0.3419", "NA"], ["Subtotal pancreatectomy", "0.00 (0.00, Inf) 0.9973", "0.00 (0.00, Inf) 0.9975", "0.00 (0.00, Inf) 0.9973", "NA"], ["Others", "0.00 (0.00, Inf) 0.9978", "0.00 (0.00, Inf) 0.9979", "0.00 (0.00, Inf) 0.9980", "NA"], ["History of chemotherapy"], ["No", "1", "1", "1", "1"], ["Yes", "0.52 (0.30, 0.90) 0.0202", "0.21 (0.11, 0.40) <0.0001", "0.20 (0.10, 0.39) <0.0001", "0.85 (0.31, 2.33) 0.7553"], ["History of radiation therapy"], ["No", "1", "1", "1", "1"], ["Yes", "0.45 (0.23, 0.89) 0.0228", "0.53 (0.26, 1.06) 0.0729", "0.54 (0.27, 1.09) 0.0866", "0.83 (0.38, 1.83) 0.6512"], ["History of targeted molecular therapy"], ["No", "1", "1", "1", "1"], ["Yes", "0.30 (0.17, 0.51) <0.0001", "0.17 (0.09, 0.31) <0.0001", "0.16 (0.08, 0.31) <0.0001", "0.17 (0.06, 0.48) 0.0009"], ["Tobacco smoking history"], ["Lifelong non-smoker", "1", "1", "1", "NA"], ["Current or former smoker", "0.77 (0.45, 1.32) 0.3397", "0.76 (0.44, 1.31) 0.3207", "0.78 (0.45, 1.34) 0.3657", "NA"], ["Alcohol drinking history"], ["No", "1", "1", "1", "NA"], ["Yes", "1.27 (0.70, 2.30) 0.4252", "1.34 (0.70, 2.57) 0.3778", "1.10 (0.58, 2.08) 0.7676", "NA"], ["History of chronic pancreatitis"], ["No", "1", "1", "1", "NA"], ["Yes", "0.81 (0.37, 1.79) 0.6029", "1.09 (0.47, 2.52) 0.8359", "0.84 (0.36, 1.97) 0.6950", "NA"], ["History of diabetes"], ["No", "1", "1", "1", "NA"], ["Yes", "0.94 (0.50, 1.75) 0.8422", "0.92 (0.49, 1.75) 0.8053", "0.85 (0.45, 1.59) 0.6058", "NA"], ["History of Prior Malignancy"], ["No", "1", "1", "1", "NA"], ["Yes", "1.18 (0.50, 2.77) 0.7006", "1.19 (0.49, 2.90) 0.7076", "1.05 (0.42, 2.59) 0.9197", "NA"]], "row_count": 64, "column_count": 5, "numeric_cells": 158, "header_rows": 1, "locator": "section[17]/table-wrap[3]#T5"}}], "gaps": ["asset:data:geo:GSE15471 not downloaded", "asset:data:geo:GSE15471 licence not read", "asset:data:geo:GSE16515 not downloaded", "asset:data:geo:GSE16515 licence not read", "asset:data:geo:GSE28735 not downloaded", "asset:data:geo:GSE28735 licence not read", "asset:data:geo:GSE32676 not downloaded", "asset:data:geo:GSE32676 licence not read", "asset:data:geo:GSE57495 not downloaded", "asset:data:geo:GSE57495 licence not read", "asset:data:geo:GSE62165 not downloaded", "asset:data:geo:GSE62165 licence not read", "asset:data:geo:GSE62452 not downloaded", "asset:data:geo:GSE62452 licence not read", "asset:data:geo:GSE71729 not downloaded", "asset:data:geo:GSE71729 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Student's t-test"}}, {"id": "method-2", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "ANOVA"}}, {"id": "method-3", "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-4", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Cox regression"}}, {"id": "method-5", "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": 0.8, "band": "high", "quote": "PPI"}}, {"id": "method-6", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}, {"id": "method-7", "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": 0.7, "band": "medium", "quote": "ROC curve"}}, {"id": "method-8", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "χ2"}}, {"id": "method-9", "family": "contingency_analysis", "specific": "fisher_exact", "label": "Categorical (contingency table) analysis", "dsl_operations": ["contingency_table", "chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "Fisher's exact"}}, {"id": "method-10", "family": null, "specific": null, "label": "Robust rank aggregation (RRA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "A total of 234 DEGs including 160 upregulated and 74 downregulated genes were identified after integrated analysis by robust rank aggregation (RRA) method (Supplementary Table 1)."}}], "targets": [], "gaps": ["method.reader_named_unmapped", "method.student_t"]}, "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": false, "required_operations": [], "missing_operations": ["student_t"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: student_t_test."}, "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": ["GSE71729", "GSE62165", "GSE62452", "GSE28735", "GSE15471", "GSE16515", "GSE32676", "GSE57495"], "resolved_accessions": ["GSE71729", "GSE62165", "GSE62452", "GSE28735", "GSE15471", "GSE16515", "GSE32676", "GSE57495"], "statements": ["The datasets analyzed for this study can be found in the Gene Expression Omnibus (https://www.ncbi.nlm.nih.gov/geo/) and TCGA (https://portal.gdc.cancer.gov/)."], "basis": "The paper names GSE71729, GSE62165, GSE62452, GSE28735, GSE15471, GSE16515, GSE32676, GSE57495 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": [], "assets": ["source:pmid:31612115", "data:geo:GSE15471", "asset:table:pmid:31612115:1", "asset:table:pmid:31612115:2", "asset:table:pmid:31612115:3", "asset:table:pmid:31612115:4", "asset:table:pmid:31612115:5"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "student_t", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE15471"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:16:24Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 40229, "completion_tokens": 2151, "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:31612115", "type": "paper", "label": "pmid:31612115"}, {"id": "source:pmid:31612115", "type": "manuscript", "label": "PMID 31612115 full text"}, {"id": "data:geo:GSE15471", "type": "dataset", "label": "GEO GSE15471"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31612115", "type": "paper", "label": "pmid:31612115"}, {"id": "source:pmid:31612115", "type": "manuscript", "label": "PMID 31612115 full text"}, {"id": "data:geo:GSE15471", "type": "dataset", "label": "GEO GSE15471"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31612115", "type": "extraction", "used": ["source:pmid:31612115"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE15471", "type": "accession_resolution", "used": ["data:geo:GSE15471"], "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:31612115", "parent_hash": "sha256:5cf310e2d671cc4fe2390a5b21726acac8e7465dcca373ced14ae95a48f6c3b6", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE15471 licence not read", "asset:data:geo:GSE15471 not downloaded", "asset:data:geo:GSE16515 licence not read", "asset:data:geo:GSE16515 not downloaded", "asset:data:geo:GSE28735 licence not read", "asset:data:geo:GSE28735 not downloaded", "asset:data:geo:GSE32676 licence not read", "asset:data:geo:GSE32676 not downloaded", "asset:data:geo:GSE57495 licence not read", "asset:data:geo:GSE57495 not downloaded", "asset:data:geo:GSE62165 licence not read", "asset:data:geo:GSE62165 not downloaded", "asset:data:geo:GSE62452 licence not read", "asset:data:geo:GSE62452 not downloaded", "asset:data:geo:GSE71729 licence not read", "asset:data:geo:GSE71729 not downloaded", "execution.not_run", "method.reader_named_unmapped", "method.student_t", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:student_t"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Student's t-test"], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:50:35+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}}}