{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32311223", "kind": "science-record", "revision": 7, "content_hash": "sha256:00a0b5b0ae7fd38ee2c36d85488dccb5614357bd8222164cd4256a9b3a438899", "created_at": "2026-11-01T15:40:59Z", "updated_at": "2026-11-01T22:01:31Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Comprehensive insights on pivotal prognostic signature involved in clear cell renal cell carcinoma microenvironment using the ESTIMATE algorithm.", "doi": "10.1002/cam4.2983", "pmid": "32311223", "authors": ["Jun Luo", "Yi Xie", "Yuxiao Zheng", "Chenji Wang", "Feng Qi", "Jiateng Hu", "Yaoting Xu"], "journal": "Cancer medicine", "year": 2020, "abstract": "Emerging evidence has highlighted that the immune and stromal cells formed the majority of tumor microenvironment (TME) which are served as important roles in tumor progression. In our study, we aimed to screen vital prognostic signature associated with TME in clear cell renal cell carcinoma (ccRCC). We obtained total 611 samples from TCGA database consisting of transcriptome profiles and clinical data. ESTIMATE algorithm was applied to estimate the infiltrating fractions of immune/stromal cells. We found that the immune scores revealed more prognostic significance in overall survival and positive associations with risk clinical factors than stromal scores. We carried out differential expression analysis between Immunescore and stromalscore groups to obtain the 72 intersect genes. Protein to protein interaction (PPI) network and functional analysis was performed to indicate potential altered pathways. Additionally, we further conducted multivariate Cox analysis to identify 12 hub genes associated highly with TME of ccRCC using a stepwise regression procedure. Accordingly, risk score was constructed from the multivariate Cox results and Receiver Operating Characteristic (ROC) curve was used to assess the predictive value (AUC = 0.781). The ccRCC patients with high risk scores suffered poor survival outcomes than that with low risk scores. In the validation cohort from GSE53757, TNFSF13B, CASP5, and GJB6 correlated positively with tumor stages, while FREM1 negatively correlated with tumor stages. Importantly, we further observed that TNFSF13B, CASP5 and XCR1 showed the remarkable correlations with tumor-infiltrating immune cells. Taken together, our research identified specific signatures that related to the infiltration of stromal and immune cells in TME of ccRCC using the transciptome profiles, which reached a comprehensive understanding of tumor microenvironment in ccRCC.", "claims": [{"id": "claim-data-access", "statement": "The data that support the findings of this study are available from the corresponding author upon reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32311223", "locator": "sections[24] \"DATA AVAILABILITY STATEMENT\" paragraph 2", "quote": "The data that support the findings of this study are available from the corresponding author upon reasonable request."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:32311223"], "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:32311223", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1002/cam4.2983", "sha256": "sha256:b579de3aaeadfd4e1f1a8fad889aebd80b6345d4eee0a81746623a469fc6e0e5", "bytes": 44762, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1002/cam4.2983", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7300420", "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 that support the findings of this study are available from the corresponding author upon reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data that support the findings of this study are available from the corresponding author upon reasonable request.", "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:32311223:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:beb53c71bc0fd82d480ace1e561a5e91d3074f963955505c3bbd6590305ab0ce", "bytes": 1070, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#cam42983-tbl-0001", "version": null, "note": "Clinical baseline of 530 ccRCC patients included in study from TCGA cohort", "structure": {"pmcid": "PMC7300420", "section_index": 11, "section_title": "Immune scores revealed more prognostic value in ccRCC versus stromal scores", "row_count": 37, "column_count": 3}, "table": {"label": "TABLE 1", "caption": "Clinical baseline of 530 ccRCC patients included in study from TCGA cohort", "rows": [["Variables", "Number", "Percentage"], ["Vital status"], ["Alive", "166", "31.32"], ["Dead", "364", "68.68"], ["Age", "60.56 ± 12.14", ""], ["Gender"], ["Female", "186", "35.10"], ["Male", "344", "64.90"], ["AJCC‐T"], ["T0/Ta", "0", "0"], ["T1", "271", "51.13"], ["T2", "69", "13.02"], ["T3", "179", "33.77"], ["T4", "11", "2.08"], ["AJCC‐N"], ["N0", "239", "45.09"], ["N1", "16", "3.02"], ["NX", "275", "51.89"], ["AJCC‐M"], ["G1/G2", "241", "45.47"], ["G3/G4", "286", "53.96"], ["Unknown", "3", "0.57"], ["Stage"], ["Stage Ⅰ & Ⅱ", "322", "60.75"], ["Stage Ⅲ & Ⅳ", "208", "39.25"], ["Immune score"], ["Low level", "265", "50.00"], ["High level", "265", "50.00"], ["Stromal score"], ["Low level", "265", "50.00"], ["High level", "265", "50.00"], ["ESTIMATE score"], ["Low level", "265", "50.00"], ["High level", "265", "50.00"], ["Risk score"], ["Low level", "265", "50.38"], ["High level", "265", "49.62"]], "row_count": 37, "column_count": 3, "numeric_cells": 51, "header_rows": 1, "locator": "section[11]/table-wrap[1]#cam42983-tbl-0001"}}, {"id": "asset:table:pmid:32311223:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ea866142dfcf41b77c0557147d490589a52ca6b75c3a61ef1062cbe80bbfecc2", "bytes": 360, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#cam42983-tbl-0002", "version": null, "note": "Tumor stage of 72 ccRCC patients in GSE53737", "structure": {"pmcid": "PMC7300420", "section_index": 11, "section_title": "Immune scores revealed more prognostic value in ccRCC versus stromal scores", "row_count": 5, "column_count": 3}, "table": {"label": "TABLE 2", "caption": "Tumor stage of 72 ccRCC patients in GSE53737", "rows": [["Clinical stage", "Samples (n)", "Percentage"], ["Stage Ⅰ", "24", "33.34"], ["Stage Ⅱ", "19", "26.39"], ["Stage Ⅲ", "14", "19.44"], ["Stage Ⅳ", "15", "20.83"]], "row_count": 5, "column_count": 3, "numeric_cells": 8, "header_rows": 1, "locator": "section[11]/table-wrap[2]#cam42983-tbl-0002"}}, {"id": "asset:table:pmid:32311223:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:35d120a64ff1cef91461d546910c44fdcb857c7400b5f9263d8dd12ad4f72864", "bytes": 692, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#cam42983-tbl-0003", "version": null, "note": "Kyoto Encyclopedia of Genes and Genomes results from the functional pathway analysis of intersect genes", "structure": {"pmcid": "PMC7300420", "section_index": 13, "section_title": "Protein‐protein interactions among intersect genes and functional enrichment analysis", "row_count": 7, "column_count": 4}, "table": {"label": "TABLE 3", "caption": "Kyoto Encyclopedia of Genes and Genomes results from the functional pathway analysis of intersect genes", "rows": [["Description", "P value", "P adjust", "Count"], ["Cytokine‐cytokine receptor interaction", ".00000582", ".000587719", "10"], ["Hematopoietic cell lineage", ".000240228", ".012131514", "5"], ["Primary immunodeficiency", ".001278873", ".043055382", "3"], ["NF‐kappa B signaling pathway", ".002240071", ".048597712", "4"], ["Intestinal immune network for IgA production", ".002886993", ".048597712", "3"], ["Malaria", ".002886993", ".048597712", "3"]], "row_count": 7, "column_count": 4, "numeric_cells": 18, "header_rows": 1, "locator": "section[13]/table-wrap[1]#cam42983-tbl-0003"}}, {"id": "asset:table:pmid:32311223:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2201391a705300994c6902e281b0fa415d82dd62bd7512a2c6216f9be3e0fa95", "bytes": 3790, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#cam42983-tbl-0004", "version": null, "note": "43 prognostic genes from the batch survival analysis", "structure": {"pmcid": "PMC7300420", "section_index": 14, "section_title": "Batch survival analysis and construction of risk score based on hub genes", "row_count": 44, "column_count": 4}, "table": {"label": "TABLE 4", "caption": "43 prognostic genes from the batch survival analysis", "rows": [["Gene name", "Description", "Location", "Log‐rank test of P value"], ["PAEP", "Progestagen‐associated endometrial protein", "Chromosome 9, NC_000009.12", "<.001"], ["SLC22A6", "solute carrier family 22 member 6", "Chromosome 11, NC_000011.10", "<.001"], ["OGDHL", "oxoglutarate dehydrogenase like", "Chromosome 10, NC_000010.11", "<.001"], ["GJB6", "gap junction protein beta 6", "Chromosome 13, NC_000013.11", "<.001"], ["SLN", "sarcolipin", "Chromosome 11, NC_000011.10", "0 < .001"], ["OBP2A", "Odorant‐binding protein 2A", "Chromosome 9, NC_000009.12", "<.001"], ["LDHD", "lactate dehydrogenase D", "Chromosome 16, NC_000016.10", "<.001"], ["ADGRV1", "adhesion G protein‐coupled receptor V1", "Chromosome 5, NC_000005.10", "<.001"], ["APCDD1L", "APC down‐regulated 1 like", "Chromosome 20, NC_000020.11", "<.001"], ["SLC22A8", "solute carrier family 22 member 8", "Chromosome 11, NC_000011.10", "<.001"], ["CPA4", "carboxypeptidase A4", "Chromosome 7, NC_000007.14", "<.001"], ["CWH43", "Cwh43p", "Chromosome III, NC_001135.5", "<.001"], ["PPARGC1A", "PPARG coactivator 1 alpha", "Chromosome 4, NC_000004.12", "<.001"], ["HMGCS2", "3‐hydroxy‐3‐methylglutaryl‐CoA synthase 2", "Chromosome 2, NC_005101.4", "<.001"], ["SLC22A12", "solute carrier family 22 member 12", "Chromosome 11, NC_000011.10", "<.001"], ["AQP9", "aquaporin 9", "Chromosome 15, NC_000015.10", "<.001"], ["FDCSP", "follicular dendritic cell secreted protein", "Chromosome 4, NC_000004.12", "<.001"], ["GPAT3", "glycerol‐3‐phosphate acyltransferase 3", "Chromosome 4, NC_000004.12", "<.001"], ["TNFSF13B", "TNF superfamily member 13b", "Chromosome 13, NC_000013.11", "<.001"], ["FREM1", "FRAS1‐related extracellular matrix 1", "Chromosome 9, NC_000009.12", "<.001"], ["HSD11B2", "hydroxysteroid 11‐beta dehydrogenase 2", "Chromosome 16, NC_000016.10", "<.001"], ["MIXL1", "Mix1 homeobox‐like 1 (Xenopus laevis)", "Chromosome 1, NC_000067.6", ".001"], ["FCRL5", "Fc receptor like 5", "Chromosome 1, NC_000001.11", ".001"], ["GREM1", "gremlin 1, DAN family BMP antagonist", "Chromosome 15, NC_000015.10", ".003"], ["MZB1", "marginal zone B and B1 cell specific protein", "Chromosome 5, NC_000005.10", ".004"], ["XCR1", "X‐C motif chemokine receptor 1", "Chromosome 3, NC_000003.12", ".004"], ["ZPLD1", "zona pellucida‐like domain containing 1", "Chromosome 3, NC_000003.12", ".004"], ["CASP5", "caspase 5", "Chromosome 11, NC_000011.10", ".006"], ["TMEM38A", "transmembrane protein 38A", "Chromosome 8, NC_000074.6", ".006"], ["CHRDL2", "Chordin‐like 2", "Chromosome 11, NC_000011.10", ".007"], ["RORB", "RAR‐related orphan receptor beta", "Chromosome 19, NC_000085.6", ".008"], ["IGLL5", "immunoglobulin lambda‐like polypeptide 5", "Chromosome 22, NC_000022.11", ".009"], ["PAH", "phenylalanine hydroxylase", "Chromosome 12, NC_000012.12", ".010"], ["MUC20", "mucin 20, cell surface‐associated", "Chromosome 3, NC_000003.12", ".011"], ["SCARA5", "scavenger receptor class A member 5", "Chromosome 8, NC_000008.11", ".018"], ["KCNJ11", "potassium voltage‐gated channel subfamily J member 11", "Chromosome 11, NC_000011.10", ".019"], ["IL10", "interleukin 10", "Chromosome 1, NC_000001.11", ".027"], ["HSD11B1", "hydroxysteroid 11‐beta dehydrogenase 1", "Chromosome 1, NC_000001.11", ".028"], ["VSIG4", "V‐set and immunoglobulin domain containing 4", "Chromosome X, NC_000023.11", ".029"], ["F7", "coagulation factor VII", "Chromosome 13, NC_000013.11", ".037"], ["RAP1GAP", "RAP1 GTPase‐activating protein", "Chromosome 1, NC_000001.11", ".039"], ["POU2AF1", "POU class 2 homeobox‐associating factor 1", "Chromosome 11, NC_000011.10", ".043"], ["KLK3", "Kallikrein‐related peptidase 3", "Chromosome 19, NC_000019.10", ".044"]], "row_count": 44, "column_count": 4, "numeric_cells": 128, "header_rows": 1, "locator": "section[14]/table-wrap[1]#cam42983-tbl-0004"}}], "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": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Cox regression"}}, {"id": "method-2", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.8, "band": "high", "quote": "limma"}}, {"id": "method-3", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "PPI"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["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": ["GSE53757"], "resolved_accessions": ["GSE53757"], "statements": ["The data that support the findings of this study are available from the corresponding author upon reasonable request."], "basis": "The paper names GSE53757 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:32311223", "data:geo:GSE53757", "asset:table:pmid:32311223:1", "asset:table:pmid:32311223:2", "asset:table:pmid:32311223:3", "asset:table:pmid:32311223:4"], "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": "2026-10-31T19:00:32Z", "independence": "single_reader"}, "evidence_check": {"method": "absent", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 33625, "completion_tokens": 1721, "cached_tokens": 792}}, "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:32311223", "type": "paper", "label": "pmid:32311223"}, {"id": "source:pmid:32311223", "type": "manuscript", "label": "PMID 32311223 full text"}, {"id": "data:geo:GSE53757", "type": "dataset", "label": "GEO GSE53757"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32311223", "type": "paper", "label": "pmid:32311223"}, {"id": "source:pmid:32311223", "type": "manuscript", "label": "PMID 32311223 full text"}, {"id": "data:geo:GSE53757", "type": "dataset", "label": "GEO GSE53757"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32311223", "type": "extraction", "used": ["source:pmid:32311223"], "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:32311223", "parent_hash": "sha256:8c513de47daad179f98562bd8f53708a1123bd9c44294e4a43c071df5a699e4e", "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": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["kage was mainly used to deal with Affymetrix microarray data of 539 ccRCC patients. For samples with", "C Limma package was mainly used to deal with Affymetrix microarray data of 539 ccRCC patients. For s"], "order_basis": "paper_text_order:2749", "id": "assay:1"}, {"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": 0.8, "evidence": ["Cox regression"], "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":"2026-11-04T03:15:10+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}}}