High G2M Pathway Score Pancreatic Cancer is Associated with Worse Survival, Particularly after Margin-Positive (R1 or R2) Resection.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33036243", "kind": "science-record", "revision": 8, "content_hash": "sha256:e2e98e5db995ed96a2dc4af47dc8f6237c97028c2ac5ec1d2853221f8d97a0cb", "created_at": "2026-11-01T15:41:12Z", "updated_at": "2026-11-01T22:02:19Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "High G2M Pathway Score Pancreatic Cancer is Associated with Worse Survival, Particularly after Margin-Positive (R1 or R2) Resection.", "doi": "10.3390/cancers12102871", "pmid": "33036243", "authors": ["Masanori Oshi", "Stephanie Newman", "Yoshihisa Tokumaru", "Li Yan", "Ryusei Matsuyama", "Itaru Endo", "Matthew H G Katz", "Kazuaki Takabe"], "journal": "Cancers", "year": 2020, "abstract": "Pancreatic cancer is highly mortal due to uncontrolled cell proliferation. The G2M checkpoint pathway is an essential part of the cell cycle. We hypothesized that a high G2M pathway score is associated with cell proliferation and worse survival in pancreatic cancer patients. Gene set variation analysis using the Hallmark G2M checkpoint gene set was used as a score to analyze a total of 390 human pancreatic cancer patients from 3 cohorts (TCGA, GSE62452, GSE57495). High G2M score tumors enriched other cell proliferation genes sets as well as MKI67 expression, pathological grade, and proliferation score. Independent of other prognostic factors, G2M score was predictive of disease-specific survival in pancreatic cancer. High G2M tumor was associated with high mutation rate of KRAS and TP53 and significantly enriched these pathway gene sets, as well as high infiltration of Th2 cells. High G2M score consistently associated with worse overall survival in 3 cohorts, particularly in R1/2 resection, but not in R0. High G2M tumor in R1/2 highly enriched metabolic and cellular components' gene sets compared to R0. To our knowledge, this is the first study to use gene set variation analysis as a score to examine the clinical relevancy of the G2M pathway in pancreatic cancer.", "claims": [{"id": "claim-method", "statement": "For uni- and multi-variate analysis, Cox proportional hazard analyses were used to estimate HR, 95% CI, and p-value.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33036243", "locator": "sections[16] \"4.5. Statistical Analysis\" paragraph 2", "quote": "For uni- and multi-variate analysis, Cox proportional hazard analyses were used to estimate HR, 95% CI, and p-value."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Transcriptomic profiling and clinical information of the TCGA pancreatic cancer (TCGA_PAAD) was downloaded from the Genomic Data Commons Data Portal (GDC).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33036243", "locator": "sections[12] \"4.1. Pancreatic Cancer Cohorts and Their Data\" paragraph 2", "quote": "Transcriptomic profiling and clinical information of the TCGA pancreatic cancer (TCGA_PAAD) was downloaded from the Genomic Data Commons Data Portal (GDC)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:33036243"], "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:GSE28746"], "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:GSE28746"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33036243", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/cancers12102871", "sha256": "sha256:6d7c517469f6bad44ebd43f8b0c5481f2b21ba40891d2165bb8a4946096a01ea", "bytes": 54092, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/cancers12102871", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7599494", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE28746", "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=GSE28746", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE28746", "version": null, "note": "Transcriptomic profiling and clinical information of the TCGA pancreatic cancer (TCGA_PAAD) was downloaded from the Genomic Data Commons Data Portal (GDC).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Transcriptomic profiling and clinical information of the TCGA pancreatic cancer (TCGA_PAAD) was downloaded from the Genomic Data Commons Data Portal (GDC).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM712302", "GSM712303", "GSM712304", "GSM712305", "GSM712306", "GSM712307", "GSM712308", "GSM712309", "GSM712310", "GSM712311", "GSM712312", "GSM712313", "GSM712314", "GSM712315", "GSM712316", "GSM712317", "GSM712318", "GSM712319", "GSM712320", "GSM712321", "GSM712322", "GSM712323", "GSM712324", "GSM712325", "GSM712326", "GSM712327", "GSM712328", "GSM712329", "GSM712330", "GSM712331", "GSM712332", "GSM712333", "GSM712334", "GSM712335", "GSM712336", "GSM712337", "GSM712338", "GSM712339", "GSM712340", "GSM712341", "GSM712342", "GSM712343", "GSM712344", "GSM712345", "GSM712346", "GSM712347", "GSM712348", "GSM712349", "GSM712350", "GSM712351", "GSM712352", "GSM712353", "GSM712354", "GSM712355", "GSM712356", "GSM712357", "GSM712358", "GSM712359", "GSM712360", "GSM712361", "GSM712362", "GSM712363", "GSM712364", "GSM712365", "GSM712366", "GSM712367", "GSM712368", "GSM712369", "GSM712370", "GSM712371", "GSM712372", "GSM712373", "GSM712374", "GSM712375", "GSM712376", "GSM712377", "GSM712378", "GSM712379", "GSM712380", "GSM712381", "GSM712382", "GSM712383", "GSM712384", "GSM712385"], "sample_count": 84, "group_sizes": null, "group_sizes_basis": null, "platform": "8490", "taxon": "Homo sapiens", "title": "Epigenome analysis of male identical twin pairs discordant for sexual orientation, age 21 to 55.", "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": "Transcriptomic profiling and clinical information of the TCGA pancreatic cancer (TCGA_PAAD) was downloaded from the Genomic Data Commons Data Portal (GDC).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Transcriptomic profiling and clinical information of the TCGA pancreatic cancer (TCGA_PAAD) was downloaded from the Genomic Data Commons Data Portal (GDC).", "access_statement_kind": "repository_route_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": "Transcriptomic profiling and clinical information of the TCGA pancreatic cancer (TCGA_PAAD) was downloaded from the Genomic Data Commons Data Portal (GDC).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Transcriptomic profiling and clinical information of the TCGA pancreatic cancer (TCGA_PAAD) was downloaded from the Genomic Data Commons Data Portal (GDC).", "access_statement_kind": "repository_route_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": "asset:table:pmid:33036243:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:cfd9f69ba7fbcd4f79627a05e0d216f8115899bd5d5988dacbc909e4be84cafd", "bytes": 1963, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#cancers-12-02871-t001", "version": null, "note": "Clinical characteristics of the low and high G2M score pancreatic cancer patients in The Cancer Genome Atlas (TCGA) cohort.", "structure": {"pmcid": "PMC7599494", "section_index": 5, "section_title": "2.3. Clinical Characteristics of the High G2M Pathway Score Pancreatic Cancer Patients", "row_count": 49, "column_count": 4}, "table": {"label": "Table 1", "caption": "Clinical characteristics of the low and high G2M score pancreatic cancer patients in The Cancer Genome Atlas (TCGA) cohort.", "rows": [["Clinical Variables", "G2M-Low(n = 88)", "G2M-High(n = 88)", "p-Value"], ["Age at diagnosis", "", "", "0.950"], ["Median", "65.0", "65.0", ""], ["IQR", "57–74", "58–71", ""], ["Gender", "", "", "0.650"], ["Male", "50 (56.8%)", "46 (52.3%)", ""], ["Female", "38 (43.2%)", "42 (47.7%)", ""], ["Race", "", "", "1.00"], ["White", "78 (88.6%)", "77 (87.5%)", ""], ["Other", "10 (11.4%)", "11 (12.5%)", ""], ["Primary site", "", "", "0.680"], ["Head", "66 (75.0%)", "71 (80.7%)", ""], ["Body/Tail", "15 (17.0%)", "13 (14.8%)", ""], ["Unknown", "7 (8.0%)", "4 (4.5%)", ""], ["Histology", "", "", "0.429"], ["PDAC", "70", "75", ""], ["Others", "18", "13", ""], ["Grade", "", "", "0.047"], ["G1", "21 (23.9%)", "10 (11.4%)", ""], ["G2", "47 (53.4%)", "46 (52.3%)", ""], ["G3", "18 (20.5%)", "30 (34.1%)", ""], ["G4", "1 (1.1%)", "1 (1.1%)", ""], ["Unknown", "1 (1.1%)", "1 (1.1%)", ""], ["", "", "", ""], ["AJCC T-category", "", "", ""], ["T1", "4 (4.5%)", "3 (3.4%)", "0.524"], ["T2", "14 (15.9%)", "9 (10.2%)", ""], ["T3", "66 (75.0%)", "75 (85.3%)", ""], ["T4", "2 (2.3%)", "1 (1.1%)", ""], ["Unknown", "2 (2.3%)", "0 (0.0%)", ""], ["AJCC N-category", "", "", ""], ["N−", "26 (29.5%)", "23 (26.1%)", "0.612"], ["N+", "58 (65.9%)", "64 (72.7%)", ""], ["Unknown", "4 (4.6%)", "1 (1.1%)", ""], ["AJCC M-category", "", "", ""], ["M−", "37 (42.0%)", "41 (46.6%)", "1.00"], ["M+", "2 (2.3%)", "2 (2.3%)", ""], ["Unknown", "49 (55.7%)", "45 (51.1%)", ""], ["AJCC Stage at diagnosis", "", "", "0.540"], ["I", "13 (14.8%)", "8 (9.1%)", ""], ["II", "69 (78.4%)", "76 (86.4%)", ""], ["III", "2 (2.3%)", "1 (1.1%)", ""], ["IV", "2 (2.3%)", "2 (2.3%)", ""], ["Unknown", "2 (2.3%)", "1 (1.1%)", ""], ["", "", "", ""], ["Resection status", "", "", "0.102"], ["R0", "57 (64.8%)", "48 (54.6%)", ""], ["R1/2", "23 (26.1%)", "34 (38.6%)", ""], ["Unknown", "8 (9.1%)", "6 (6.8%)", ""]], "row_count": 49, "column_count": 4, "numeric_cells": 84, "header_rows": 1, "locator": "section[5]/table-wrap[1]#cancers-12-02871-t001"}}, {"id": "asset:table:pmid:33036243:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:dba4673740d4b329f8bd34296068a99825bc54335feab3a796b06d9afe1f0e77", "bytes": 1100, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#cancers-12-02871-t002", "version": null, "note": "Survival analyses of the G2M pathway score and other factors in the TCGA cohort.", "structure": {"pmcid": "PMC7599494", "section_index": 9, "section_title": "2.7. High G2M Pathway Score Pancreatic Tumors were Significantly Associated with Worse Survival in Pathologically Margin-Positive Resection (R1 or R2), but not in Margin-Negative Resection (R0)", "row_count": 12, "column_count": 5}, "table": {"label": "Table 2", "caption": "Survival analyses of the G2M pathway score and other factors in the TCGA cohort.", "rows": [["TCGA (DSS)", "Univariate", "Multivariate"], ["HR (95% CI)", "p-Value", "HR (95% CI)", "p-Value"], ["Age", "1.02 (1.00–1.04)", "0.109", "", ""], ["Gender (Male vs. Female)", "0.77 (0.48–1.22)", "0.267", "", ""], ["Race (Caucasian vs. other)", "1.35 (0.45–2.83)", "0.420", "", ""], ["Primary tumor site (Head vs. Body/Tail)", "1.69 (0.86–3.31)", "0.126", "", ""], ["Grade (G3/4 vs. G1/2)", "3.28 (1.19–9.07)", "0.022 *", "0.71 (0.12–4.27)", "0.706"], ["AJCC-T category (pT3/4 vs. pT1/2)", "3.08 (1.33–7.14)", "0.009 *", "2.46 (0.59–10.19)", "0.215"], ["AJCC-N category (N+ vs. N-)", "2.58 (1.39–4.81)", "0.003 *", "1.93 (0.96–3.86)", "0.064"], ["AJCC-M category (M+ vs. M-)", "1.21 (0.29–5.09)", "0.799", "", ""], ["Resection (R1/2 vs. R0)", "1.82 (1.11–2.98)", "0.017 *", "1.58 (0.96–2.61)", "0.072"], ["G2M score", "2.65 (1.36–5.16)", "0.004 *", "2.08 (1.02–4.24)", "0.045 *"]], "row_count": 12, "column_count": 5, "numeric_cells": 35, "header_rows": 2, "locator": "section[9]/table-wrap[1]#cancers-12-02871-t002"}}], "gaps": ["asset:data:geo:GSE28746 not downloaded", "asset:data:geo:GSE28746 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"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "analysis of variance"}}, {"id": "method-2", "family": null, "specific": null, "label": "Cox proportional hazard analyses", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "For uni- and multi-variate analysis, Cox proportional hazard analyses were used to estimate HR, 95% CI, and p-value."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE62452", "GSE57495", "GSE28746"], "resolved_accessions": ["GSE62452", "GSE57495", "GSE28746"], "statements": ["Transcriptomic profiling and clinical information of the TCGA pancreatic cancer (TCGA_PAAD) was downloaded from the Genomic Data Commons Data Portal (GDC)."], "basis": "The paper names GSE62452, GSE57495, GSE28746 in Gene Expression Omnibus (GEO) repository of the US National Institutes of Health and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:33036243", "data:geo:GSE28746", "asset:table:pmid:33036243:1", "asset:table:pmid:33036243:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE28746"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:23:10Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 45187, "completion_tokens": 2126, "cached_tokens": 520}}, "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:33036243", "type": "paper", "label": "pmid:33036243"}, {"id": "source:pmid:33036243", "type": "manuscript", "label": "PMID 33036243 full text"}, {"id": "data:geo:GSE28746", "type": "dataset", "label": "GEO GSE28746"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33036243", "type": "paper", "label": "pmid:33036243"}, {"id": "source:pmid:33036243", "type": "manuscript", "label": "PMID 33036243 full text"}, {"id": "data:geo:GSE28746", "type": "dataset", "label": "GEO GSE28746"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33036243", "type": "extraction", "used": ["source:pmid:33036243"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE28746", "type": "accession_resolution", "used": ["data:geo:GSE28746"], "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:33036243", "parent_hash": "sha256:e60100db84e1aee71076b57aaba6f7d77192ba2a1dd84992fab5dcd63d25a2d9", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE28746 licence not read", "asset:data:geo:GSE28746 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", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["analysis of variance"], "order_basis": "analysis_only", "id": "assay:1"}]}