{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33613617", "kind": "science-record", "revision": 8, "content_hash": "sha256:b8408894f0669321383638bfc6ce159ab2f8e0c9f90a32c00d30648aa46fddba", "created_at": "2026-11-01T15:41:25Z", "updated_at": "2026-11-01T22:46:09Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of a Metastasis-Associated Gene Signature of Clear Cell Renal Cell Carcinoma.", "doi": "10.3389/fgene.2020.603455", "pmid": "33613617", "authors": ["Suhua Gao", "Lei Yan", "Hongtao Zhang", "Xiaoguang Fan", "Xiaojing Jiao", "Fengmin Shao"], "journal": "Frontiers in genetics", "year": 2020, "abstract": "Clear cell renal cell carcinoma (ccRCC) is one of the most frequent pathological subtypes of kidney cancer, accounting for ~70-75%, and the major cause of mortality is metastatic disease. The difference in gene expression profiles between primary ccRCC tumors and metastatic tumors has not been determined. Thus, we report integrated genomic and transcriptomic analysis for identifying differentially expressed genes (DEGs) between primary and metastatic ccRCC tumors to understand the molecular mechanisms underlying the development of metastases. The microarray datasets GSE105261 and GSE85258 were obtained from the Gene Expression Omnibus (GEO) database, and the R package limma was used for DEG analyses. In summary, the results described herein provide important molecular evidence that metastatic ccRCC tumors are different from primary tumors. Enrichment analysis indicated that the DEGs were mainly enriched in ECM-receptor interaction, platelet activation, protein digestion, absorption, focal adhesion, and the PI3K-Akt signaling pathway. Moreover, we found that DEGs associated with a higher level of tumor immune infiltrates and tumor mutation burden were more susceptible to poor prognosis of ccRCC. Specifically, our study indicates that seven core genes, namely the collagen family (COL1A2, COL1A1, COL6A3, and COL5A1), DCN, FBLN1, and POSTN, were significantly upregulated in metastatic tumors compared with those in primary tumors and, thus, potentially offer insight into novel therapeutic and early diagnostic biomarkers of ccRCC.", "claims": [{"id": "claim-method", "statement": "The microarray datasets GSE105261 and GSE85258 were obtained from the Gene Expression Omnibus (GEO) database, and the R package limma was used for DEG analyses.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33613617", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The microarray datasets GSE105261 and GSE85258 were obtained from the Gene Expression Omnibus (GEO) database, and the R package limma was used for DEG analyses."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33613617", "locator": "sections[19] \"Data Availability Statement\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material."}], "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:33613617"], "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:GSE105261"], "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:GSE105261"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33613617", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2020.603455", "sha256": "sha256:1fcaf1544e7caf845640a57a3c5d30f6260eb3321cadee0fdcc916c92c8ee487", "bytes": 31548, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2020.603455", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7889952", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE105261", "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=GSE105261", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE105261", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2825239", "GSM2825240", "GSM2825241", "GSM2825242", "GSM2825243", "GSM2825244", "GSM2825245", "GSM2825246", "GSM2825247", "GSM2825248", "GSM2825249", "GSM2825250", "GSM2825251", "GSM2825252", "GSM2825253", "GSM2825254", "GSM2825255", "GSM2825256", "GSM2825257", "GSM2825258", "GSM2825259", "GSM2825260", "GSM2825261", "GSM2825262", "GSM2825263", "GSM2825264", "GSM2825265", "GSM2825266", "GSM2825267", "GSM2825268", "GSM2825269", "GSM2825270", "GSM2825271", "GSM2825272", "GSM2825273", "GSM2825274", "GSM2825275", "GSM2825276", "GSM2825277", "GSM2825278", "GSM2825279", "GSM2825280", "GSM2825281", "GSM2825282"], "sample_count": 44, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Transcriptome analysis of normal kidney, primary and metastasis ccRCC", "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:GSE85258", "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=GSE85258", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE85258", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2263272", "GSM2263273", "GSM2263274", "GSM2263275", "GSM2263276", "GSM2263277", "GSM2263278", "GSM2263279", "GSM2263280", "GSM2263281", "GSM2263282", "GSM2263283", "GSM2263284", "GSM2263285", "GSM2263286", "GSM2263287", "GSM2263288", "GSM2263289", "GSM2263290", "GSM2263291", "GSM2263292", "GSM2263293", "GSM2263294", "GSM2263295", "GSM2263296", "GSM2263297", "GSM2263298", "GSM2263299", "GSM2263300", "GSM2263301", "GSM2263302"], "sample_count": 31, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Differential gene expression profiling of matched primary renal cell carcinoma and metastases reveals upregulation of extracellular matrix genes", "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:33613617:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:143ad6b140f93657445a43bd8e0a9fb49da27de96660c81a80eed8f7eae8911f", "bytes": 577, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T1", "version": null, "note": "Characteristics of the GSE105261 and GSE85258 datasets.", "structure": {"pmcid": "PMC7889952", "section_index": 11, "section_title": "Identification of DEGs", "row_count": 3, "column_count": 7}, "table": {"label": "Table 1", "caption": "Characteristics of the GSE105261 and GSE85258 datasets.", "rows": [["Series code", "Series geo accession", "Series type", "Number of samples", "Group", "Organism", "Series platform id"], ["G1", "GSE105261", "Expression profiling by array", "35", "Primary ccRCC (n = 9) Metastatic ccRCC (n = 26)", "Homo sapiens", "GPL10558"], ["G2", "GSE85258", "Expression profiling by array", "31", "Primary ccRCC (n = 15) Metastatic ccRCC (n = 16)", "Homo sapiens", "GPL570"]], "row_count": 3, "column_count": 7, "numeric_cells": 8, "header_rows": 1, "locator": "section[11]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:33613617:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8cadfc50e65a2c3e156889f095e8c7dd030eda941140bc64fd3cda4ef2ca3c9f", "bytes": 1238, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#T2", "version": null, "note": "The shared DEGs of the GSE105261 and GSE85258 datasets.", "structure": {"pmcid": "PMC7889952", "section_index": 11, "section_title": "Identification of DEGs", "row_count": 21, "column_count": 4}, "table": {"label": "Table 2", "caption": "The shared DEGs of the GSE105261 and GSE85258 datasets.", "rows": [["", "Gene", "Regulation", "Gene title"], ["1", "REN", "Up", "Renin"], ["2", "OGDHL", "Up", "Oxoglutarate dehydrogenase-like"], ["3", "HSD11B2", "Up", "Hydroxysteroid 11-beta dehydrogenase 2"], ["4", "COL3A1", "Down", "Collagen type III alpha 1 chain"], ["5", "COL1A1", "Down", "Collagen type I alpha 1 chain"], ["6", "COL1A2", "Down", "Collagen type I alpha 2 chain"], ["7", "COL6A3", "Down", "Collagen type VI alpha 3 chain"], ["8", "PRRX1", "Down", "Paired related homeobox 1"], ["9", "POSTN", "Down", "Periostin"], ["10", "COL5A1", "Down", "Collagen type V alpha 1 chain"], ["11", "FBLN1", "Down", "Fibulin 1"], ["12", "SPINK13", "Down", "Serine peptidase inhibitor, Kazal type 13 (putative)"], ["13", "GJB2", "Down", "Gap junction protein beta 2"], ["14", "PDGFRL", "Down", "Platelet-derived growth factor receptor-like"], ["15", "CTHRC1", "Down", "Collagen triple helix repeat containing 1"], ["16", "FGG", "Down", "Fibrinogen gamma chain"], ["17", "SCG5", "Down", "Secretogranin V"], ["18", "DCN", "Down", "Decorin"], ["19", "LUM", "Down", "Lumican"], ["20", "MXRA5", "Down", "Matrix remodeling associated 5"]], "row_count": 21, "column_count": 4, "numeric_cells": 34, "header_rows": 1, "locator": "section[11]/table-wrap[2]#T2"}}, {"id": "asset:table:pmid:33613617:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:efa52df7efdae1ff5727681848fea39cd6aa356ab1de77f45744c54af765a556", "bytes": 690, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[3]#T3", "version": null, "note": "The top 10 hub genes in the shared DEG PPI network.", "structure": {"pmcid": "PMC7889952", "section_index": 11, "section_title": "Identification of DEGs", "row_count": 11, "column_count": 5}, "table": {"label": "Table 3", "caption": "The top 10 hub genes in the shared DEG PPI network.", "rows": [["Rank", "Average shortest path length", "Betweenness centrality", "Degree", "Symbol"], ["1", "1.08333333", "0.05176768", "11", "COL1A2"], ["2", "1.08333333", "0.05176768", "11", "COL1A1"], ["3", "1.08333333", "0.05176768", "11", "COL3A1"], ["4", "1.08333333", "0.05176768", "11", "POSTN"], ["5", "1.25", "0.01515152", "9", "LUM"], ["6", "1.25", "0.01515152", "9", "COL6A3"], ["7", "1.25", "0.01010101", "9", "COL5A1"], ["8", "1.25", "0.16666667", "9", "DCN"], ["9", "1.25", "0.01010101", "9", "FBLN1"], ["10", "1.58333333", "0", "6", "MXRA5"]], "row_count": 11, "column_count": 5, "numeric_cells": 40, "header_rows": 1, "locator": "section[11]/table-wrap[3]#T3"}}], "gaps": ["asset:data:geo:GSE105261 not downloaded", "asset:data:geo:GSE105261 licence not read", "asset:data:geo:GSE85258 not downloaded", "asset:data:geo:GSE85258 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "The microarray datasets GSE105261 and GSE85258 were obtained from the Gene Expression Omnibus (GEO) database, and the R package limma was used for DEG analyses."}}, {"id": "method-2", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "KM"}}, {"id": "method-3", "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-4", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {"hazard_ratio": "In addition, the hazard ratio (HR) was calculated and", "p_value": "terval and the log-rank p-value, and the number-at-risk", "confidence_interval": "n on the chart with 95% confidence interval and the log-rank p-valu"}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-5", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "hierarchical clustering"}}, {"id": "method-6", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "PPI"}}, {"id": "method-7", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}, {"id": "method-8", "family": "network_analysis", "specific": "centrality", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "centrality"}}, {"id": "method-9", "family": "contingency_analysis", "specific": "fisher_exact", "label": "Categorical (contingency table) analysis", "dsl_operations": ["contingency_table", "chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "Fisher's exact"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "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": ["GSE105261", "GSE85258"], "resolved_accessions": ["GSE105261", "GSE85258"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material."], "basis": "The paper names GSE105261, GSE85258 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:33613617", "data:geo:GSE105261", "asset:table:pmid:33613617:1", "asset:table:pmid:33613617:2", "asset:table:pmid:33613617:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE105261"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:27:07Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 24309, "completion_tokens": 1509, "cached_tokens": 8200}}, "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:33613617", "type": "paper", "label": "pmid:33613617"}, {"id": "source:pmid:33613617", "type": "manuscript", "label": "PMID 33613617 full text"}, {"id": "data:geo:GSE105261", "type": "dataset", "label": "GEO GSE105261"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33613617", "type": "paper", "label": "pmid:33613617"}, {"id": "source:pmid:33613617", "type": "manuscript", "label": "PMID 33613617 full text"}, {"id": "data:geo:GSE105261", "type": "dataset", "label": "GEO GSE105261"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33613617", "type": "extraction", "used": ["source:pmid:33613617"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE105261", "type": "accession_resolution", "used": ["data:geo:GSE105261"], "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:33613617", "parent_hash": "sha256:3b2cd35afc07c5803affd26355decaca1c0e6c254bec0f2a9f6953c35d1a43d8", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE105261 licence not read", "asset:data:geo:GSE105261 not downloaded", "asset:data:geo:GSE85258 licence not read", "asset:data:geo:GSE85258 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "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": 0.93, "evidence": ["nderlying the development of metastases. The microarray datasets GSE105261 and GSE85258 were obtaine"], "order_basis": "paper_text_order:601", "id": "assay:1"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The microarray datasets GSE105261 and GSE85258 were obtained from the Gene Expression Omnibus (GEO) database, and the R package limma was used for DEG analyses."], "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":"2026-11-04T00:32:37+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}}}