{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:27926518", "kind": "science-record", "revision": 7, "content_hash": "sha256:9255429f24ea5e323ddd448107e2f1efaf0357ba0c38e41d062c2df8241b6c81", "created_at": "2026-11-01T15:40:21Z", "updated_at": "2026-11-01T22:42:50Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Higher programmed cell death 1 ligand 1 (PD-L1) mRNA level in clear cell renal cell carcinomas is associated with a favorable outcome due to the active immune responses in tumor tissues.", "doi": "10.18632/oncotarget.13765", "pmid": "27926518", "authors": ["Xiang-Hui Ning", "Yan-Qing Gong", "Shi-Ming He", "Teng Li", "Jiang-Yi Wang", "Shuang-He Peng", "Jin-Chao Chen", "Jia-Yuan Liu", "Nie-Nie Qi", "Ying-Lu Guo", "Kan Gong"], "journal": "Oncotarget", "year": 2017, "abstract": "Renal cell carcinoma is one of the most common urological tumors. The role of programmed cell death 1 ligand 1 (PD-L1) in renal cell carcinomas in predicting outcome of the patients is yet unclear. We analyzed the clinical and RNA-seq data of 522 kidney clear cell cancer, 259 kidney papillary cell carcinoma and 66 kidney chromophobe patients from The Cancer Genome Atlas (TCGA) database. In kidney clear cell cancer patients with high PD-L1 mRNA level and low PD-L1 mRNA level in tumors, the median overall survival periods were 45.0 and 37.1 months respectively (p=0.002). Multivariate Cox regression tests found that PD-L1 mRNA level in tumor was an independent predictor for overall survival status in kidney clear cell cancer patients (HR=0.7, 95% CI 0.5-0.9, p=0.007). However, no significant difference in overall survival status was found between high and low PD-L1 groups in kidney papillary cell carcinoma and kidney chromophobe cohorts. Gene-set enrichment analysis on the data from databases of TCGA and GSE53757 dataset in Gene Expression Omnibus databases showed that several pathways relating to immunological functions were activated in kidney clear cell cancers with high PD-L1 mRNA expression, and glycolysis and epithelial-mesenchymal transition pathways relating to tumor progression and metastasis were increased in kidney clear cell cancers with low PD-L1 mRNA level. In conclusion, higher PD-L1 mRNA level in kidney clear cell cancer tissues was associated with a favorable outcome due to the higher immunological responses in tumor tissues.", "claims": [{"id": "claim-method", "statement": "Overall survival was assessed using Kaplan-Meier method and log-rank test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27926518", "locator": "sections[11] \"Statistical methods\" paragraph 2", "quote": "Overall survival was assessed using Kaplan-Meier method and log-rank test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data used in this study are opened to public for access without limitation and restriction.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27926518", "locator": "sections[9] \"Patients and data collection\" paragraph 2", "quote": "The data used in this study are opened to public for access without limitation and restriction."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using TCGA clinical and RNA-seq data analyzed with multivariate Cox regression, higher tumor PD-L1 mRNA was an independent predictor of longer overall survival in kidney clear cell cancer (HR=0.7, 95% CI 0.5–0.9, p=0.007).", "kind": "quantitative", "target": {"value": 95.0, "unit": "per cent", "tolerance": null, "source": "Multivariate Cox regression tests found that PD-L1 mRNA level in tumor was an independent predictor for overall survival status in kidney clear cell cancer patients (HR=0.7, 95% CI 0.5-0.9, p=0.007)."}, "evidence": [{"asset": "source:pmid:27926518", "locator": "sections[1] \"INTRODUCTION\" paragraph 5", "quote": "we aimed to investigate the role of PD-L1 mRNA expression in tumors in predicting the outcome of RCC based on the analyses of the clinical and RNA-seq data presented in The Cancer Genome Atlas (TCGA) database."}, {"asset": "source:pmid:27926518", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Multivariate Cox regression tests found that PD-L1 mRNA level in tumor was an independent predictor for overall survival status in kidney clear cell cancer patients (HR=0.7, 95% CI 0.5-0.9, p=0.007)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Using TCGA clinical and RNA-seq data analyzed with multivariate Cox regression, higher tumor PD-L1 mRNA was an independent predictor of longer overall survival in kidney clear cell cancer (HR=0.7, 95% CI 0.5–0.9, p=0.007).", "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:27926518"], "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:GSE53757"], "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:GSE53757"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:27926518", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/oncotarget.13765", "sha256": "sha256:e3b82ed7787f0d483f5649725d636719949be41d27b7334d4b0fd3029096b900", "bytes": 22638, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/oncotarget.13765", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5356887", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE53757", "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=GSE53757", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE53757", "version": null, "note": "The data used in this study are opened to public for access without limitation and restriction.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data used in this study are opened to public for access without limitation and restriction.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1300062", "GSM1300063", "GSM1300064", "GSM1300065", "GSM1300066", "GSM1300067", "GSM1300068", "GSM1300069", "GSM1300070", "GSM1300071", "GSM1300072", "GSM1300073", "GSM1300074", "GSM1300075", "GSM1300076", "GSM1300077", "GSM1300078", "GSM1300079", "GSM1300080", "GSM1300081", "GSM1300082", "GSM1300083", "GSM1300084", "GSM1300085", "GSM1300086", "GSM1300087", "GSM1300088", "GSM1300089", "GSM1300090", "GSM1300091", "GSM1300092", "GSM1300093", "GSM1300094", "GSM1300095", "GSM1300096", "GSM1300097", "GSM1300098", "GSM1300099", "GSM1300100", "GSM1300101", "GSM1300102", "GSM1300103", "GSM1300104", "GSM1300105", "GSM1300106", "GSM1300107", "GSM1300108", "GSM1300109", "GSM1300110", "GSM1300111", "GSM1300112", "GSM1300113", "GSM1300114", "GSM1300115", "GSM1300116", "GSM1300117", "GSM1300118", "GSM1300119", "GSM1300120", "GSM1300121", "GSM1300122", "GSM1300123", "GSM1300124", "GSM1300125", "GSM1300126", "GSM1300127", "GSM1300128", "GSM1300129", "GSM1300130", "GSM1300131", "GSM1300132", "GSM1300133", "GSM1300134", "GSM1300135", "GSM1300136", "GSM1300137", "GSM1300138", "GSM1300139", "GSM1300140", "GSM1300141", "GSM1300142", "GSM1300143", "GSM1300144", "GSM1300145", "GSM1300146", "GSM1300147", "GSM1300148", "GSM1300149", "GSM1300150", "GSM1300151", "GSM1300152", "GSM1300153", "GSM1300154", "GSM1300155", "GSM1300156", "GSM1300157", "GSM1300158", "GSM1300159", "GSM1300160", "GSM1300161", "GSM1300162", "GSM1300163", "GSM1300164", "GSM1300165", "GSM1300166", "GSM1300167", "GSM1300168", "GSM1300169", "GSM1300170", "GSM1300171", "GSM1300172", "GSM1300173", "GSM1300174", "GSM1300175", "GSM1300176", "GSM1300177", "GSM1300178", "GSM1300179", "GSM1300180", "GSM1300181", "GSM1300182", "GSM1300183", "GSM1300184", "GSM1300185", "GSM1300186", "GSM1300187", "GSM1300188", "GSM1300189", "GSM1300190", "GSM1300191", "GSM1300192", "GSM1300193", "GSM1300194", "GSM1300195", "GSM1300196", "GSM1300197", "GSM1300198", "GSM1300199", "GSM1300200", "GSM1300201", "GSM1300202", "GSM1300203", "GSM1300204", "GSM1300205"], "sample_count": 144, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene array analysis of clear cell renal cell carcinoma tissue versus matched normal kidney tissue", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:27926518:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7e857cdd0492add396ec5f0df35f63bf31e9e81b54003a87bfd13f6f3cdaf610", "bytes": 1228, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#T1", "version": null, "note": "Patient and tumor characteristics of the three RCC subtype cohorts in TCGA", "structure": {"pmcid": "PMC5356887", "section_index": 3, "section_title": "Description of the integrated RCC data in TCGA", "row_count": 24, "column_count": 4}, "table": {"label": "Table 1", "caption": "Patient and tumor characteristics of the three RCC subtype cohorts in TCGA", "rows": [["Variable", "KIRC", "KIRP", "KICH"], ["Sample (n)", "522", "259", "66"], ["Median age (year)", "61 (26-90)", "62 (28-88)", "50 (17-86)"], ["Median PD-L1", "40.8 (0-5361.1)", "23.6 (0-640.6)", "67.4 (0.5-2930.8)"], ["Gender"], ["Male", "337 (64.6%)", "191 (73.7%)", "39 (50.1%)"], ["Female", "185 (35.4%)", "68 (26.3%)", "27 (40.9%)"], ["Laterality"], ["Left", "248 (47.5%)", "144 (55.6%)", "30 (45.5%)"], ["Right", "273 (52.3%)", "113 (43.6%)", "36 (54.5%)"], ["Others", "1 (0.2%)", "2 (0.8%)", ""], ["Clinical stage"], ["Stage I", "260 (49.8%)", "172 (66.4%)", "21 (31.8%)"], ["Stage II", "56 (10.7%)", "21 (8.1%)", "25 (37.9%)"], ["Stage III", "123 (23.6%)", "51 (19.7%)", "14 (21.2%)"], ["Stage IV", "83 (15.9%)", "15 (5.8%)", "6 (9.1%)"], ["Tumor stage"], ["T1", "265 (50.8%)", "175 (67.6%)", "21 (31.8%)"], ["T2", "68 (13.0%)", "24 (9.3%)", "25 (37.9%)"], ["T3", "178 (34.1%)", "56 (21.6%)", "18 (27.3%)"], ["T4", "11 (2.1%)", "2 (0.8%)", "2 (3.0%)"], ["Survival status"], ["Alive", "348 (66.7%)", "218 (84.2%)", "50 (75.8%)"], ["Died", "174 (33.3%)", "41 (15.8%)", "16 (24.2%)"]], "row_count": 24, "column_count": 4, "numeric_cells": 53, "header_rows": 1, "locator": "section[3]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:27926518:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fcaa43d149a4ae59bb36f1e42595ec4f22e21597f0f6431dbfb4eb2ff322876e", "bytes": 938, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#T2", "version": null, "note": "Univariate and multivariate regression analyses for predicting overall survival in KIRC cohort", "structure": {"pmcid": "PMC5356887", "section_index": 4, "section_title": "PD-L1 mRNA level and survival status", "row_count": 11, "column_count": 5}, "table": {"label": "Table 2", "caption": "Univariate and multivariate regression analyses for predicting overall survival in KIRC cohort", "rows": [["Variable", "Univariate", "Multivariate"], ["HR (95% CI)", "p-value", "HR (95% CI)", "p-value"], ["Age", "1.8 (1.3-2.4)", "<0.001*", "1.6 (1.2-2.1)", "0.003*"], ["Gender", "1.1 (0.8-1.4)", "0.741", "1.2 (0.9-1.6)", "0.326"], ["Laterality", "0.7 (0.5-1.0)", "0.024*", "0.8 (0.6-1.0)", "0.070"], ["Tumor grade", "2.2 (1.8-2.7)", "<0.001*", "1.5 (1.2-1.9)", "<0.001*"], ["Clinical stage", "1.9 (1.6-2.1)", "<0.001*", "1.6 (1.4-1.9)", "<0.001*"], ["Tumor stage", "1.9 (1.6-2.2)", "<0.001*", "0.8 (0.6-1.1)", "0.109"], ["Lymph node metastasis", "0.9 (0.8-1.1)", "0.267", "0.9 (0.8-1.1)", "0.187"], ["Distant metastasis", "2.3 (1.8-2.9)", "<0.001*", "1.1 (0.7-1.8)", "0.643"], ["PD-L1 mRNA level", "0.6 (0.5-0.8)", "0.002*", "0.7 (0.5-0.9)", "0.007*"]], "row_count": 11, "column_count": 5, "numeric_cells": 38, "header_rows": 2, "locator": "section[4]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:27926518:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:83e75fb0bae1154de3dd7852c0d2e0d1572df5b9e4d513bba387a9976fc05361", "bytes": 1673, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#T3", "version": null, "note": "Comparison of clinical characteristics between low PD-L1 group and high PD-L1 group in KIRC cohort", "structure": {"pmcid": "PMC5356887", "section_index": 5, "section_title": "PD-L1 mRNA level and clinical features of KIRC cohort", "row_count": 40, "column_count": 4}, "table": {"label": "Table 3", "caption": "Comparison of clinical characteristics between low PD-L1 group and high PD-L1 group in KIRC cohort", "rows": [["", "Group", "p-Value"], ["", "Low PD-L1", "High PD-L1", ""], ["Sample (n)", "261", "261", ""], ["Age (year)", "", "", "0.381"], ["≤61", "133 (51.0%)", "143 (54.8%)", ""], [">61", "128 (49.0%)", "118 (45.2%)", ""], ["Gender", "", "", "0.022*"], ["Male", "181 (69.3%)", "156 (59.8%)", ""], ["Female", "80 (30.7%)", "105 (40.2%)", ""], ["Laterality", "", "", "0.601"], ["Left", "123 (47.1%)", "125 (47.9%)", ""], ["Right", "137 (52.5%)", "136 (52.1%)", ""], ["Others", "1 (0.4%)", "0", ""], ["Clinical stage", "", "", "0.082"], ["Stage I", "133 (50.9%)", "127 (48.7%)", ""], ["Stage II", "19 (7.3%)", "37 (14.2%)", ""], ["Stage III", "66 (25.3%)", "57 (21.8%)", ""], ["Stage IV", "43 (16.5%)", "40 (15.3%)", ""], ["Tumor stage", "", "", "0.056"], ["T1", "135 (51.7%)", "130 (49.8%)", ""], ["T2", "26 (10.0%)", "42 (16.1%)", ""], ["T3", "97 (37.2%)", "81 (31.0%)", ""], ["T4", "3 (1.1%)", "8 (3.1%)", ""], ["Lymph node metastasis", "", "", "0.208"], ["N0", "109 (41.8%)", "129 (49.4%)", ""], ["N1", "9 (3.4%)", "7 (2.7%)", ""], ["NX", "143 (54.8%)", "125 (47.9%)", ""], ["Distant metastasis", "", "", "0.620"], ["M0", "207 (79.3%)", "214 (82.0%)", ""], ["M1", "41 (15.7%)", "38 (14.6%)", ""], ["MX", "13 (5.0%)", "9 (3.4%)", ""], ["Tumor grade", "", "", "0.609"], ["G1", "6 (2.3%)", "6 (2.3%)", ""], ["G2", "104 (39.8%)", "121 (46.4%)", ""], ["G3", "110 (42.1%)", "95 (36.4%)", ""], ["G4", "39 (15.0%)", "36 (13.8%)", ""], ["GX", "2 (0.8%)", "3 (1.1%)", ""], ["Survival status", "", "", "0.002*"], ["Alive", "157 (60.2%)", "191 (73.2%)", ""], ["Died", "104 (39.8%)", "70 (26.8%)", ""]], "row_count": 40, "column_count": 4, "numeric_cells": 69, "header_rows": 2, "locator": "section[5]/table-wrap[1]#T3"}}, {"id": "asset:table:pmid:27926518:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:9eb8bae9a278671cc1848cebb91c7ee01a76a7573ed4ceb0400df22df714ba91", "bytes": 2201, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#T4", "version": null, "note": "Pathway analyses for high PD-L1 group and low PD-L1 group in KIRC cohort from TCGA and GEO databases", "structure": {"pmcid": "PMC5356887", "section_index": 6, "section_title": "Gene expression signature in high PD-L1 group and low PD-L1 group of KIRC cohort", "row_count": 20, "column_count": 9}, "table": {"label": "Table 4", "caption": "Pathway analyses for high PD-L1 group and low PD-L1 group in KIRC cohort from TCGA and GEO databases", "rows": [["", "KIRC from TCGA (522 cases)", "KIRC from GSEA 53757 in GEO (72 cases)"], ["High PD-L1", "q-val.", "Low PD-L1", "q-val.", "High PD-L1", "q-val.", "Low PD-L1", "q-val."], ["1", "Interferon-γ response*", "<0.001", "DNA repair", "<0.001", "Allograft rejection*", "<0.001", "Epithelial mesenchymal transition*", "<0.001"], ["2", "Allograft rejection*", "<0.001", "MYC targets v2", "<0.001", "Interferon-γ response*", "<0.001", "Uv response down", "<0.001"], ["3", "Interferon-α response*", "<0.001", "Myogenesis*", "0.001", "Interferon-α response*", "<0.001", "Angiogenesis", "<0.001"], ["4", "Protein secretion", "<0.001", "MYC targets v1", "0.004", "IL6 JAK Stat3 signaling*", "<0.001", "Myogenesis*", "<0.001"], ["5", "Mitotic spindle", "<0.001", "Glycolysis", "0.003", "E2F targets", "<0.001", "TGF–β signaling", "<0.001"], ["6", "Inflammatory response*", "<0.001", "Epithelial mesenchymal transition*", "0.008", "Inflammatory response*", "<0.001", "Hypoxia", "<0.001"], ["7", "G2M checkpoint*", "0.001", "Coagulation*", "0.041", "G2M checkpoint*", "<0.001", "Notch signaling", "0.002"], ["8", "Androgen response", "0.002", "Oxidative phosphorylation", "0.043", "TNF-α signaling via NF-κB*", "<0.001", "Apical junction", "<0.001"], ["9", "IL6 JAK Stat3 signaling*", "0.006", "", "", "Complement*", "<0.001", "Wnt β-catenin signaling", "0.004"], ["10", "Kras signaling up", "0.005", "", "", "IL2 STAT5 signaling*", "<0.001", "Hedgehog signaling", "0.018"], ["11", "Complement*", "0.010", "", "", "PI3K AKT mTOR signaling*", "0.004", "Androgen response", "0.008"], ["12", "TNF-α signaling via NF-κB*", "0.010", "", "", "", "", "Coagulation*", "0.002"], ["13", "Uv response down", "0.014", "", "", "", "", "Bile acid metabolism", "0.002"], ["14", "IL2 Stat5 signaling*", "0.018", "", "", "", "", "Fatty acid metabolism", "0.004"], ["15", "PI3K AKT mTOR signaling*", "0.019", "", "", "", "", "Adipogenesis", "0.004"], ["16", "", "", "", "", "", "", "Xenobiotic metabolism", "0.006"], ["17", "", "", "", "", "", "", "Kras signaling up", "0.008"], ["18", "", "", "", "", "", "", "Estrogen response early", "0.012"]], "row_count": 20, "column_count": 9, "numeric_cells": 72, "header_rows": 2, "locator": "section[6]/table-wrap[1]#T4"}}], "gaps": ["asset:data:geo:GSE53757 not downloaded", "asset:data:geo:GSE53757 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Overall survival was assessed using Kaplan-Meier method and log-rank test."}}, {"id": "method-2", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {"hazard_ratio": "r cell cancer patients (HR=0"}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Cox regression"}}, {"id": "method-3", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-4", "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": "chi-square"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "chi_square_test", "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": "chi_square_test", "expected_value": 0.7, "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": "chi_square_test", "expected_value": 0.007, "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": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE53757"], "resolved_accessions": ["GSE53757"], "statements": ["The data used in this study are opened to public for access without limitation and restriction."], "basis": "The paper names GSE53757 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:27926518", "data:geo:GSE53757", "asset:table:pmid:27926518:1", "asset:table:pmid:27926518:2", "asset:table:pmid:27926518:3", "asset:table:pmid:27926518:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE53757"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:30:07Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 52973, "completion_tokens": 2888, "cached_tokens": 2089}}, "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:27926518", "type": "paper", "label": "pmid:27926518"}, {"id": "source:pmid:27926518", "type": "manuscript", "label": "PMID 27926518 full text"}, {"id": "data:geo:GSE53757", "type": "dataset", "label": "GEO GSE53757"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:27926518", "type": "paper", "label": "pmid:27926518"}, {"id": "source:pmid:27926518", "type": "manuscript", "label": "PMID 27926518 full text"}, {"id": "data:geo:GSE53757", "type": "dataset", "label": "GEO GSE53757"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-27926518", "type": "extraction", "used": ["source:pmid:27926518"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE53757", "type": "accession_resolution", "used": ["data:geo:GSE53757"], "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:27926518", "parent_hash": "sha256:8f0b2f01099acbcc1f42ff2484c278186be07f286155b145a2ae20d947f4b23a", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE53757 licence not read", "asset:data:geo:GSE53757 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["is yet unclear. We analyzed the clinical and RNA-seq data of 522 kidney clear cell cancer, 259 ki", "and data collection Clinical, follow-up and RNA-seq data of the 536 KIRC, 291 KIRP and 66 KICH p"], "order_basis": "paper_text_order:369", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Overall survival was assessed using Kaplan-Meier method and log-rank test."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:39:02+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}}}