{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:36561844", "kind": "science-record", "revision": 3, "content_hash": "sha256:f74d0b6d35c1b088e28befb98e6f90b1772520d31547db1aad880f34feabbb39", "created_at": "2026-11-01T19:01:06Z", "updated_at": "2026-11-01T22:08:26Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Integrated bioinformatics analysis shows integrin alpha 3 is a prognostic biomarker for pancreatic cancer.", "doi": "10.1515/med-2022-0606", "pmid": "36561844", "authors": ["Fangfang Hu", "Liangtao Zhao", "Yang Wang", "Hao Ye", "Haodong Tang", "Jiahua Zhou"], "journal": "Open medicine (Warsaw, Poland)", "year": 2022, "abstract": "Integrin subunit alpha 3 (ITGA3) expression correlates with the development and prognosis of human cancers. This study aimed to investigate the association of ITGA3 expression with pancreatic cancer (PCa) prognosis. The ITGA3 gene expression data were extracted from The Cancer Genome Atlas (TCGA) pancreatic adenocarcinoma (PAAD) cohort and 14 Gene Expression Omnibus microarray datasets. The differences in ITGA3 expression levels between tumor and non-tumor tissues were compared using the Mann-Whitney U test. Cox regression analysis and meta-analysis were performed to detect the association of ITGA3 expression with PCa prognosis. ITGA3 expression was higher in tumors than in controls. Tumors with advanced grades (3/4) had higher ITGA3 levels compared with early-grade tumors (1/2). The meta-analysis of the TCGA PAAD cohort and seven microarray datasets (GSE28735, GSE62452, GSE79668, GSE71729, GSE57495, GSE78229, and GSE21501) showed that ITGA3 was a prognostic biomarker in PCa (hazard ratio (HR) = 1.38, 95% confidence interval (CI) 1.26-1.51, p < 0.00001). Five ITGA3-related genes, including ITGB1 (HR = 1.6), ITGB5 (HR = 1.6), ITGB6 (HR = 1.6), LAMA3 (HR = 2.1), and CD9 (HR = 2.3), correlated with PCa prognosis significantly (p < 0.05). Functional enrichment analysis showed that ITGA3 was related to \"hsa04151: PI3K-Akt signaling pathway\" and \"hsa04510: Focal adhesion.\" We concluded that high ITGA3 expression was a potential prognostic biomarker in PCa.", "claims": [{"id": "claim-method", "statement": "Cox regression analysis and meta-analysis were performed to detect the association of ITGA3 expression with PCa prognosis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36561844", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Cox regression analysis and meta-analysis were performed to detect the association of ITGA3 expression with PCa prognosis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:36561844", "locator": "sections[15] \"Footnotes\" paragraph 2", "quote": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "High ITGA3 expression was associated with poor prognosis in pancreatic cancer.", "kind": "quantitative", "target": {"value": 95.0, "unit": "per cent", "tolerance": null, "source": "A meta-analysis of the TCGA PAAD cohort and seven microarray datasets (GSE28735, GSE62452, GSE79668, GSE71729, GSE57495, GSE78229, and GSE21501) showed that high ITGA3 expression level was a prognostic biomarker of PCa (HR = 1.38, 95% CI 1.26–1.51, p < 0.00001; Figure 4)."}, "evidence": [{"asset": "source:pmid:36561844", "locator": "sections[9] \"Prognostic value of ITGA3 level in PAAD\" paragraph 4", "quote": "A meta-analysis of the TCGA PAAD cohort and seven microarray datasets (GSE28735, GSE62452, GSE79668, GSE71729, GSE57495, GSE78229, and GSE21501) showed that high ITGA3 expression level was a prognostic biomarker of PCa (HR = 1.38, 95% CI 1.26–1.51, p < 0.00001; Figure 4)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "High ITGA3 expression was associated with poor prognosis in pancreatic cancer.", "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:36561844"], "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": "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:GSE15471"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:36561844", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1515/med-2022-0606", "sha256": "sha256:a42af8113e718315898c40f033ced8761a23a82760bd45d6831e3fa55d7b57e8", "bytes": 25220, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1515/med-2022-0606", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9743194", "source": "europe_pmc_fulltext", "coverage": "whole_body", "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": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.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:GSE15932", "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=GSE15932", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15932", "version": null, "note": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM399666", "GSM399667", "GSM399669", "GSM399676", "GSM399679", "GSM399682", "GSM399685", "GSM399689", "GSM399694", "GSM399697", "GSM399699", "GSM399704", "GSM399705", "GSM399706", "GSM399707", "GSM399708", "GSM399709", "GSM399710", "GSM399711", "GSM399712", "GSM399713", "GSM399714", "GSM399715", "GSM399716", "GSM399717", "GSM399718", "GSM399719", "GSM399761", "GSM399762", "GSM399763", "GSM399765", "GSM399766"], "sample_count": 32, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Blood biomarkers of pancreatic cancer associated diabetes identified by peripheral blood-based gene expression profiles", "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": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.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:GSE21501", "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=GSE21501", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE21501", "version": null, "note": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM535948", "GSM535949", "GSM535950", "GSM535951", "GSM536032", "GSM536033", "GSM536034", "GSM536035", "GSM536036", "GSM536037", "GSM536038", "GSM536039", "GSM536040", "GSM536041", "GSM536042", "GSM536043", "GSM536044", "GSM536045", "GSM536046", "GSM536443", "GSM536444", "GSM536445", "GSM536446", "GSM536447", "GSM536448", "GSM536449", "GSM536450", "GSM536451", "GSM536452", "GSM536453", "GSM536454", "GSM536455", "GSM536456", "GSM536457", "GSM536458", "GSM536459", "GSM536460", "GSM536461", "GSM536462", "GSM536463", "GSM536464", "GSM536465", "GSM536466", "GSM536467", "GSM536468", "GSM536469", "GSM536470", "GSM536471", "GSM536472", "GSM536473", "GSM536474", "GSM536475", "GSM536476", "GSM536477", "GSM536478", "GSM536479", "GSM536480", "GSM536481", "GSM536482", "GSM536483", "GSM536484", "GSM536485", "GSM536486", "GSM536487", "GSM536488", "GSM536489", "GSM536490", "GSM536491", "GSM536492", "GSM536882", "GSM536883", "GSM536884", "GSM536885", "GSM536886", "GSM536887", "GSM536888", "GSM536889", "GSM536890", "GSM536891", "GSM536892", "GSM536893", "GSM536894", "GSM536895", "GSM536896", "GSM536897", "GSM536898", "GSM536899", "GSM536900", "GSM536901", "GSM536902", "GSM536903", "GSM536904", "GSM536905", "GSM536906", "GSM536907", "GSM536908", "GSM536909", "GSM536910", "GSM536911", "GSM536917", "GSM536918", "GSM536919", "GSM536920", "GSM536921", "GSM536922", "GSM536923", "GSM536924", "GSM536925", "GSM536926", "GSM536927", "GSM536928", "GSM536929", "GSM536930", "GSM536931", "GSM536932", "GSM536933", "GSM536934", "GSM536935", "GSM536936", "GSM536937", "GSM536938", "GSM536939", "GSM536940", "GSM536941", "GSM536942", "GSM536943", "GSM536944", "GSM536945", "GSM536946", "GSM536947", "GSM536948", "GSM536949"], "sample_count": 132, "group_sizes": null, "group_sizes_basis": null, "platform": "4133", "taxon": "Homo sapiens", "title": "A six-gene signature predicts survival of patients with localized 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:GSE22780", "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=GSE22780", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE22780", "version": null, "note": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM563305", "GSM563306", "GSM563307", "GSM563308", "GSM563309", "GSM563310", "GSM563311", "GSM563312", "GSM563313", "GSM563314", "GSM563315", "GSM563316", "GSM563317", "GSM563318", "GSM563319", "GSM563320"], "sample_count": 16, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Affymetrix Arrays Interrogated with Tumor/Normal Pancreatic 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": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.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": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.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:GSE41372", "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=GSE41372", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE41372", "version": null, "note": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1015732", "GSM1015733", "GSM1015734", "GSM1015735", "GSM1015736", "GSM1015737", "GSM1015738", "GSM1015739", "GSM1015740", "GSM1015741", "GSM1015742", "GSM1015743", "GSM1015744", "GSM1015745", "GSM1015746", "GSM1015747", "GSM1015748", "GSM1015749", "GSM1015750", "GSM1015751", "GSM1015752", "GSM1015753", "GSM1015754", "GSM1015755", "GSM1015756", "GSM1015757", "GSM1015758", "GSM1015759", "GSM1015760", "GSM1015761"], "sample_count": 30, "group_sizes": null, "group_sizes_basis": null, "platform": "16142;6244", "taxon": "Homo sapiens", "title": "MicroRNAs Cooperatively Inhibit a Network of Tumor Suppressor Genes to Promote Pancreatic Tumor Growth and Progression", "resolution_checked_at": "2026-11-01T18:46:34Z", "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": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.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: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": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.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": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.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": "data:geo:GSE71989", "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=GSE71989", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE71989", "version": null, "note": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1849335", "GSM1849336", "GSM1849337", "GSM1849338", "GSM1849339", "GSM1849340", "GSM1849341", "GSM1849342", "GSM1849343", "GSM1849344", "GSM1849345", "GSM1849346", "GSM1849347", "GSM1849348", "GSM1849349", "GSM1849350", "GSM1849351", "GSM1849352", "GSM1849353", "GSM1849354", "GSM1849355", "GSM1849356"], "sample_count": 22, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "The gene expression of normal pancreatic and PDAC tisssues.", "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:GSE78229", "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=GSE78229", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE78229", "version": null, "note": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1527105", "GSM1527109", "GSM1527137", "GSM1527139", "GSM1527141", "GSM1527145", "GSM1527147", "GSM1527149", "GSM1527151", "GSM1527153", "GSM1527155", "GSM1527157", "GSM1527159", "GSM1527161", "GSM1527163", "GSM1527165", "GSM1527167", "GSM1527169", "GSM1527171", "GSM1527175", "GSM1527177", "GSM1527179", "GSM1527181", "GSM1527183", "GSM1527185", "GSM1527189", "GSM1527191", "GSM1527193", "GSM1527196", "GSM1527198", "GSM1527199", "GSM1527200", "GSM1527202", "GSM1527204", "GSM1527205", "GSM1527207", "GSM1527209", "GSM1527212", "GSM1527213", "GSM1527215", "GSM1527216", "GSM1527218", "GSM1527219", "GSM1527220", "GSM1527223", "GSM1527225", "GSM1527227", "GSM1527228", "GSM1527230", "GSM1527232"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Microarray gene-expression profiles of 50 pancreatic tumors tissue from patients with pancreatic ductal adenocarcinoma", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE79668", "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=GSE79668", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE79668", "version": null, "note": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2100851", "GSM2100852", "GSM2100853", "GSM2100854", "GSM2100855", "GSM2100856", "GSM2100857", "GSM2100858", "GSM2100859", "GSM2100860", "GSM2100861", "GSM2100862", "GSM2100863", "GSM2100864", "GSM2100865", "GSM2100866", "GSM2100867", "GSM2100868", "GSM2100869", "GSM2100870", "GSM2100871", "GSM2100872", "GSM2100873", "GSM2100874", "GSM2100875", "GSM2100876", "GSM2100877", "GSM2100878", "GSM2100879", "GSM2100880", "GSM2100881", "GSM2100882", "GSM2100883", "GSM2100884", "GSM2100885", "GSM2100886", "GSM2100887", "GSM2100888", "GSM2100889", "GSM2100890", "GSM2100891", "GSM2100892", "GSM2100893", "GSM2100894", "GSM2100895", "GSM2100896", "GSM2100897", "GSM2100898", "GSM2100899", "GSM2100900", "GSM2100901"], "sample_count": 51, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "RNA-sequencing of human pancreatic adenocarcinoma cancer tissues", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE15471 not downloaded", "asset:data:geo:GSE15471 licence not read", "asset:data:geo:GSE15932 not downloaded", "asset:data:geo:GSE15932 licence not read", "asset:data:geo:GSE16515 not downloaded", "asset:data:geo:GSE16515 licence not read", "asset:data:geo:GSE21501 not downloaded", "asset:data:geo:GSE21501 licence not read", "asset:data:geo:GSE22780 not downloaded", "asset:data:geo:GSE22780 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:GSE41372 not downloaded", "asset:data:geo:GSE41372 licence not read", "asset:data:geo:GSE57495 not downloaded", "asset:data:geo:GSE57495 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", "asset:data:geo:GSE71989 not downloaded", "asset:data:geo:GSE71989 licence not read", "asset:data:geo:GSE78229 not downloaded", "asset:data:geo:GSE78229 licence not read", "asset:data:geo:GSE79668 not downloaded", "asset:data:geo:GSE79668 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "Cox regression analysis and meta-analysis were performed to detect the association of ITGA3 expression with PCa prognosis."}}, {"id": "method-2", "family": "group_comparison", "specific": "mann_whitney", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_mann_whitney"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.7, "band": "medium", "quote": "Mann-Whitney"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "cox_ph", "expected_value": 95.0, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}, {"id": "target-published-estimate-hazard-ratio", "claim_id": "claim-target-result", "operation": "cox_ph", "expected_value": 1.38, "unit": "hazard ratio", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}, {"id": "target-published-estimate-p-value", "claim_id": "claim-target-result", "operation": "cox_ph", "expected_value": 1e-05, "unit": "p-value", "tolerance": null, "state": "complete", "note": "The threshold the paper applied to its own result, as the paper states it. A run that reproduces the effect is judged against this threshold."}], "gaps": ["method.reader_differs_from_extractor"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE16515", "GSE22780", "GSE15471", "GSE71989", "GSE32676", "GSE15932", "GSE41372", "GSE28735", "GSE62452", "GSE79668", "GSE71729", "GSE57495", "GSE78229", "GSE21501"], "resolved_accessions": ["GSE16515", "GSE22780", "GSE15471", "GSE71989", "GSE32676", "GSE15932", "GSE41372", "GSE28735", "GSE62452", "GSE79668", "GSE71729", "GSE57495", "GSE78229", "GSE21501"], "statements": ["Data availability statement: The gene expression RNA-seq in the cohort of GDC TCGA PAAD was extracted from the UCSC Xena (https://xenabrowser.net/datapages/). The 14 microarray datasets GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE57495, GSE78229, GSE71729, and GSE21501 were downloaded from the GEO (https://www.ncbi.nlm.nih.gov/)."], "basis": "The paper names GSE16515, GSE22780, GSE15471, GSE71989, GSE32676, GSE15932, GSE41372, GSE28735, GSE62452, GSE79668, GSE71729, GSE57495, GSE78229, GSE21501 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:36561844", "data:geo:GSE15471"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "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": "2026-11-01T18:21:30Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 8934, "completion_tokens": 3014, "cached_tokens": 264}}, "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:36561844", "type": "paper", "label": "pmid:36561844"}, {"id": "source:pmid:36561844", "type": "manuscript", "label": "PMID 36561844 full text"}, {"id": "data:geo:GSE15471", "type": "dataset", "label": "GEO GSE15471"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:36561844", "type": "paper", "label": "pmid:36561844"}, {"id": "source:pmid:36561844", "type": "manuscript", "label": "PMID 36561844 full text"}, {"id": "data:geo:GSE15471", "type": "dataset", "label": "GEO GSE15471"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-36561844", "type": "extraction", "used": ["source:pmid:36561844"], "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:36561844", "parent_hash": "sha256:10e2b5755d318e17e9ae6676104acdb2b8347b09f2466df652efec4a1f45bd7d", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE15471 licence not read", "asset:data:geo:GSE15471 not downloaded", "asset:data:geo:GSE15932 licence not read", "asset:data:geo:GSE15932 not downloaded", "asset:data:geo:GSE16515 licence not read", "asset:data:geo:GSE16515 not downloaded", "asset:data:geo:GSE21501 licence not read", "asset:data:geo:GSE21501 not downloaded", "asset:data:geo:GSE22780 licence not read", "asset:data:geo:GSE22780 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:GSE41372 licence not read", "asset:data:geo:GSE41372 not downloaded", "asset:data:geo:GSE57495 licence not read", "asset:data:geo:GSE57495 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", "asset:data:geo:GSE71989 licence not read", "asset:data:geo:GSE71989 not downloaded", "asset:data:geo:GSE78229 licence not read", "asset:data:geo:GSE78229 not downloaded", "asset:data:geo:GSE79668 licence not read", "asset:data:geo:GSE79668 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Cox regression analysis and meta-analysis were performed to detect the association of ITGA3 expression with PCa prognosis."], "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":"2026-11-04T02:44:40+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}}}