{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30945310", "kind": "science-record", "revision": 8, "content_hash": "sha256:2d85b12c1f36afb4b3e692c2e16f356946ef98490eeb0d0cd91651c5fb9439ab", "created_at": "2026-11-01T15:40:44Z", "updated_at": "2026-11-01T22:00:28Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "G Protein γ subunit 7 loss contributes to progression of clear cell renal cell carcinoma.", "doi": "10.1002/jcp.28597", "pmid": "30945310", "authors": ["Shan Xu", "Haibao Zhang", "Tianjie Liu", "Yule Chen", "Dalin He", "Lei Li"], "journal": "Journal of cellular physiology", "year": 2019, "abstract": "Clear cell renal cell carcinoma (ccRCC) is a common urinary neoplasm, looking for useful candidates to establish scientific foundation for the therapy of ccRCC is urgent. We downloaded genomic profiles of GSE781, GSE6244, GSE53757, and GSE66271 from the Gene Expression Omnibus (GEO) database. GEO2R was used to analyze the derivative genes, while hub genes were screened by protein-protein interactions and cytoscape. Further, overall survival, gene methylation, gene mutation, and gene expression were all analyzed using bioinformatics tools. Colony formation and cell-cycle assay were used to detect the biological function of GNG7 in vitro. We found that GNG7 was downregulated in ccRCC tissues and negatively associated with overall survival in ccRCC patients. We also found that promoter methylation and frequent gene mutation were responsible for GNG7 gene suppression. GNG7 low expression was related to upregulation of enhancer of zeste homolog 2 and downregulation of disabled homolog 2-interacting protein. Further, Gene Set Enrichment Analysis results showed that mTOR1, E2F, G2M, and MYC pathways were all significantly altered in response to GNG7 low expression. In vitro, A498 and 786-O cells in which GNG7 expression was silenced, exhibited a lower G1 phase when compared to the negative control cells. Taken together, our findings suggest that GNG7 is a tumor suppressor gene in ccRCC progression and represents a novel candidate for ccRCC treatment.", "claims": [{"id": "claim-method", "statement": "The differences between two groups (Student's t test) were analyzed by GraphPad Prism version 6.0 software (GraphPad), p < 0.05 was considered significant.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30945310", "locator": "sections[15] \"Statistical analysis\" paragraph 2", "quote": "The differences between two groups (Student's t test) were analyzed by GraphPad Prism version 6.0 software (GraphPad), p < 0.05 was considered significant."}], "state": "complete"}, {"id": "claim-data-access", "statement": "GSE781, GSE6244, GSE53757, and GSE66271 were applied from the Gene Expression Omnibus (GEO), nine ccRCC patients‐tumor tissue and matched normal tissue were obtained after surgery in GSE781 data set on a GLP96/97 platform (Lenburg et al., 2003);", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30945310", "locator": "sections[3] \"Microarray data\" paragraph 2", "quote": "GSE781, GSE6244, GSE53757, and GSE66271 were applied from the Gene Expression Omnibus (GEO), nine ccRCC patients‐tumor tissue and matched normal tissue were obtained after surgery in GSE781 data set on a GLP96/97 platform (Lenburg et al., 2003);"}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:30945310"], "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": "blocked", "blocked_on": "method:student_t", "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": ["step:run_analysis blocked on method:student_t"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30945310", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1002/jcp.28597", "sha256": "sha256:f97ca5c5ad2a00a5c81c42053f9facabf29d37ef8988504241680b4341acf542", "bytes": 37581, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1002/jcp.28597", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6767067", "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": "GSE781, GSE6244, GSE53757, and GSE66271 were applied from the Gene Expression Omnibus (GEO), nine ccRCC patients‐tumor tissue and matched normal tissue were obtained after surgery in GSE781 data set on a GLP96/97 platform (Lenburg et al., 2003);", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE781, GSE6244, GSE53757, and GSE66271 were applied from the Gene Expression Omnibus (GEO), nine ccRCC patients‐tumor tissue and matched normal tissue were obtained after surgery in GSE781 data set on a GLP96/97 platform (Lenburg et al., 2003);", "access_statement_kind": "repository_route_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": "data:geo:GSE6244", "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=GSE6244", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE6244", "version": null, "note": "GSE781, GSE6244, GSE53757, and GSE66271 were applied from the Gene Expression Omnibus (GEO), nine ccRCC patients‐tumor tissue and matched normal tissue were obtained after surgery in GSE781 data set on a GLP96/97 platform (Lenburg et al., 2003);", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE781, GSE6244, GSE53757, and GSE66271 were applied from the Gene Expression Omnibus (GEO), nine ccRCC patients‐tumor tissue and matched normal tissue were obtained after surgery in GSE781 data set on a GLP96/97 platform (Lenburg et al., 2003);", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM143851", "GSM143853", "GSM143855", "GSM143858", "GSM143860", "GSM143861"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "892", "taxon": "Oryza sativa Japonica Group; Oryza sativa Indica Group", "title": "Transcriptional profiling of indica rice cultivar IET8585 (Ajaya) infected with bacterial leaf blight pathogen (Xoo)", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE66271", "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=GSE66271", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE66271", "version": null, "note": "GSE781, GSE6244, GSE53757, and GSE66271 were applied from the Gene Expression Omnibus (GEO), nine ccRCC patients‐tumor tissue and matched normal tissue were obtained after surgery in GSE781 data set on a GLP96/97 platform (Lenburg et al., 2003);", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE781, GSE6244, GSE53757, and GSE66271 were applied from the Gene Expression Omnibus (GEO), nine ccRCC patients‐tumor tissue and matched normal tissue were obtained after surgery in GSE781 data set on a GLP96/97 platform (Lenburg et al., 2003);", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1618415", "GSM1618416", "GSM1618417", "GSM1618418", "GSM1618419", "GSM1618420", "GSM1618421", "GSM1618422", "GSM1618423", "GSM1618424", "GSM1618425", "GSM1618426", "GSM1618427", "GSM1618428", "GSM1618429", "GSM1618430", "GSM1618431", "GSM1618432", "GSM1618433", "GSM1618434", "GSM1618435", "GSM1618436", "GSM1618437", "GSM1618438", "GSM1618439", "GSM1618440"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Genome-wide analysis of gene expression patterns in human kidney cancer [patients with metastasis]", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE781", "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=GSE781", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE781", "version": null, "note": "GSE781, GSE6244, GSE53757, and GSE66271 were applied from the Gene Expression Omnibus (GEO), nine ccRCC patients‐tumor tissue and matched normal tissue were obtained after surgery in GSE781 data set on a GLP96/97 platform (Lenburg et al., 2003);", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "GSE781, GSE6244, GSE53757, and GSE66271 were applied from the Gene Expression Omnibus (GEO), nine ccRCC patients‐tumor tissue and matched normal tissue were obtained after surgery in GSE781 data set on a GLP96/97 platform (Lenburg et al., 2003);", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM11805", "GSM11810", "GSM11814", "GSM11815", "GSM11823", "GSM11827", "GSM11830", "GSM11832", "GSM12067", "GSM12069", "GSM12075", "GSM12078", "GSM12079", "GSM12083", "GSM12098", "GSM12099", "GSM12100", "GSM12101", "GSM12105", "GSM12106", "GSM12268", "GSM12269", "GSM12270", "GSM12274", "GSM12283", "GSM12287", "GSM12298", "GSM12299", "GSM12300", "GSM12301", "GSM12399", "GSM12412", "GSM12444", "GSM12448"], "sample_count": 34, "group_sizes": null, "group_sizes_basis": null, "platform": "96;97", "taxon": "Homo sapiens", "title": "Normal and Renal Cell Carcinoma Kidney Tissue, Human", "resolution_checked_at": "2026-11-01T15:14:33Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:30945310:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:034be885ed06e079d26ef212f5278b3317261d4a547540e67a6d0ae6564a5e27", "bytes": 739, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#jcp28597-tbl-0001", "version": null, "note": "Four hub genes with MCC value > 1,000 and degree ≥ 10", "structure": {"pmcid": "PMC6767067", "section_index": 17, "section_title": "The hub genes in clear cell renal cell carcinoma progression", "row_count": 5, "column_count": 4}, "table": {"label": "Table 1", "caption": "Four hub genes with MCC value > 1,000 and degree ≥ 10", "rows": [["Nos.", "Gene symbol", "Full name", "Function"], ["1", "GNG2", "G Protein subunit γ 2", "GNG2 inhibits proliferation of malignant melanoma cells in vitro and in vivo"], ["2", "GNG7", "G Protein subunit γ 7", "Low‐expression GNG7 is associated with tumor grade and stage"], ["3", "KNG1", "Kininogen 1", "Kininogen‐1 is a constituent of the blood coagulation system as well as the kinin‐kallikrein system"], ["4", "GNB4", "G protein subunit β 4", "GNB4 mutations as a cause of Dominant Intermediate Charcot‐Marie‐Tooth Disease"]], "row_count": 5, "column_count": 4, "numeric_cells": 9, "header_rows": 1, "locator": "section[17]/table-wrap[1]#jcp28597-tbl-0001"}}], "gaps": ["asset:data:geo:GSE53757 not downloaded", "asset:data:geo:GSE53757 licence not read", "asset:data:geo:GSE6244 not downloaded", "asset:data:geo:GSE6244 licence not read", "asset:data:geo:GSE66271 not downloaded", "asset:data:geo:GSE66271 licence not read", "asset:data:geo:GSE781 not downloaded", "asset:data:geo:GSE781 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The differences between two groups (Student's t test) were analyzed by GraphPad Prism version 6.0 software (GraphPad), p < 0.05 was considered significant."}}], "targets": [], "gaps": ["method.student_t"]}, "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": false, "required_operations": [], "missing_operations": ["student_t"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: student_t_test."}, "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": ["GSE781", "GSE6244", "GSE53757", "GSE66271"], "resolved_accessions": ["GSE781", "GSE6244", "GSE53757", "GSE66271"], "statements": ["GSE781, GSE6244, GSE53757, and GSE66271 were applied from the Gene Expression Omnibus (GEO), nine ccRCC patients‐tumor tissue and matched normal tissue were obtained after surgery in GSE781 data set on a GLP96/97 platform (Lenburg et al., 2003);"], "basis": "The paper names GSE781, GSE6244, GSE53757, GSE66271 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": [], "assets": ["source:pmid:30945310", "data:geo:GSE53757", "asset:table:pmid:30945310:1"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "student_t", "unlocks_papers": null, "priority": null}], "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": "2026-10-31T18:14:29Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 33997, "completion_tokens": 2484, "cached_tokens": 785}}, "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:30945310", "type": "paper", "label": "pmid:30945310"}, {"id": "source:pmid:30945310", "type": "manuscript", "label": "PMID 30945310 full text"}, {"id": "data:geo:GSE53757", "type": "dataset", "label": "GEO GSE53757"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30945310", "type": "paper", "label": "pmid:30945310"}, {"id": "source:pmid:30945310", "type": "manuscript", "label": "PMID 30945310 full text"}, {"id": "data:geo:GSE53757", "type": "dataset", "label": "GEO GSE53757"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30945310", "type": "extraction", "used": ["source:pmid:30945310"], "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:30945310", "parent_hash": "sha256:71264f389e3b1bc0cbfbe2d59a518599522453bd9a40e543f53f9571995f4ae3", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE53757 licence not read", "asset:data:geo:GSE53757 not downloaded", "asset:data:geo:GSE6244 licence not read", "asset:data:geo:GSE6244 not downloaded", "asset:data:geo:GSE66271 licence not read", "asset:data:geo:GSE66271 not downloaded", "asset:data:geo:GSE781 licence not read", "asset:data:geo:GSE781 not downloaded", "execution.not_run", "method.student_t", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:student_t"], "assays": [{"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The differences between two groups (Student's t test) were analyzed by GraphPad Prism version 6.0 software (GraphPad), p < 0.05 was considered significant."], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T00:32:52+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}}}