{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:30568862", "kind": "science-record", "revision": 7, "content_hash": "sha256:34364cc16039c8d7a456306430684de0b89075d6f47521d24a815bf785cb1a17", "created_at": "2026-11-01T15:40:39Z", "updated_at": "2026-11-01T22:00:12Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "In silico analyses for potential key genes associated with gastric cancer.", "doi": "10.7717/peerj.6092", "pmid": "30568862", "authors": ["Ping Yan", "Yingchun He", "Kexin Xie", "Shan Kong", "Weidong Zhao"], "journal": "PeerJ", "year": 2018, "abstract": "BACKGROUND: Understanding hub genes involved in gastric cancer (GC) metastasis could lead to effective approaches to diagnose and treat cancer. In this study, we aim to identify the hub genes and investigate the underlying molecular mechanisms of GC.\nMETHODS: To explore potential therapeutic targets for GC,three expression profiles (GSE54129, GSE33651, GSE81948) of the genes were extracted from the Gene Expression Omnibus (GEO) database. The GEO2R online tool was applied to screen out differentially expressed genes (DEGs) between GC and normal gastric samples. Database for Annotation, Visualization and Integrated Discovery was applied to perform Gene Ontology (GO) and KEGG pathway enrichment analysis. The protein-protein interaction (PPI) network of these DEGs was constructed using a STRING online software. The hub genes were identified by the CytoHubba plugin of Cytoscape software. Then, the prognostic value of these identified genes was verified by gastric cancer database derived from Kaplan-Meier plotter platform.\nRESULTS: A total of 85 overlapped upregulated genes and 44 downregulated genes were identified. The majority of the DEGs were enriched in extracellular matrix organization, endodermal cell differentiation, and endoderm formation. Moreover, five KEGG pathways were significantly enriched, including ECM-receptor interaction, amoebiasis, AGE-RAGE signaling pathway in diabetic complications, focal adhesion, protein digestion and absorption. By combining the results of PPI network and CytoHubba, a total of nine hub genes including COL1A1, THBS1, MMP2, CXCL8, FN1, TIMP1, SPARC, COL4A1, and ITGA5 were selected. The Kaplan-Meier plotter database confirmed that overexpression levels of these genes were associated with reduced overall survival, except for THBS1 and CXCL8.\nCONCLUSIONS: Our study suggests that COL1A1, MMP2, FN1, TIMP1, SPARC, COL4A1, and ITGA5 may be potential biomarkers and therapeutic targets for GC. Further study is needed to assess the effect of THBS1 and CXCL8 on GC.", "claims": [{"id": "claim-method", "statement": "The hazard ratio (HR) was given with 95% confidence intervals, and log rank P value was calculated and displayed on the webpage.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30568862", "locator": "sections[7] \"Survival analysis of hub genes\" paragraph 2", "quote": "The hazard ratio (HR) was given with 95% confidence intervals, and log rank P value was calculated and displayed on the webpage."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The following information was supplied regarding data availability:\nGene Expression Omnibus: GSE54129, GSE33651, GSE81948.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:30568862", "locator": "sections[25] \"Data Availability Statement\" paragraphs 1-3", "quote": "The following information was supplied regarding data availability:\nGene Expression Omnibus: GSE54129, GSE33651, GSE81948."}], "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:30568862"], "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:GSE33651"], "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:GSE33651"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:30568862", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.6092", "sha256": "sha256:ae6a144788e5878eb1d740ee05b138d023276316ad288c7598335c0eb23c5986", "bytes": 35143, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.6092", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6287586", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE33651", "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=GSE33651", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33651", "version": null, "note": "The following information was supplied regarding data availability:\nGene Expression Omnibus: GSE54129, GSE33651, GSE81948.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nGene Expression Omnibus: GSE54129, GSE33651, GSE81948.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM832257", "GSM832258", "GSM832259", "GSM832260", "GSM832261", "GSM832262", "GSM832263", "GSM832264", "GSM832265", "GSM832266", "GSM832267", "GSM832268", "GSM832269", "GSM832270", "GSM832271", "GSM832272", "GSM832273", "GSM832274", "GSM832275", "GSM832276", "GSM832277", "GSM832278", "GSM832279", "GSM832280", "GSM832281", "GSM832282", "GSM832283", "GSM832284", "GSM832285", "GSM832286", "GSM832287", "GSM832288", "GSM832289", "GSM832290", "GSM832291", "GSM832292", "GSM832293", "GSM832294", "GSM832295", "GSM832296", "GSM832297", "GSM832298", "GSM832299", "GSM832300", "GSM832301", "GSM832302", "GSM832303", "GSM832304", "GSM832305", "GSM832306", "GSM832307", "GSM832308"], "sample_count": 52, "group_sizes": null, "group_sizes_basis": null, "platform": "2895", "taxon": "Homo sapiens", "title": "Genome-wide gene expression profile of human gastric cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE54129", "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=GSE54129", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE54129", "version": null, "note": "The following information was supplied regarding data availability:\nGene Expression Omnibus: GSE54129, GSE33651, GSE81948.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nGene Expression Omnibus: GSE54129, GSE33651, GSE81948.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1308392", "GSM1308393", "GSM1308394", "GSM1308395", "GSM1308396", "GSM1308397", "GSM1308398", "GSM1308399", "GSM1308400", "GSM1308401", "GSM1308402", "GSM1308403", "GSM1308404", "GSM1308405", "GSM1308406", "GSM1308407", "GSM1308408", "GSM1308409", "GSM1308410", "GSM1308411", "GSM1308412", "GSM1308413", "GSM1308414", "GSM1308415", "GSM1308416", "GSM1308417", "GSM1308418", "GSM1308419", "GSM1308420", "GSM1308421", "GSM1308422", "GSM1308423", "GSM1308424", "GSM1308425", "GSM1308426", "GSM1308427", "GSM1308428", "GSM1308429", "GSM1308430", "GSM1308431", "GSM1308432", "GSM1308433", "GSM1308434", "GSM1308435", "GSM1308436", "GSM1308437", "GSM1308438", "GSM1308439", "GSM1308440", "GSM1308441", "GSM1308442", "GSM1308443", "GSM1308444", "GSM1308445", "GSM1308446", "GSM1308447", "GSM1308448", "GSM1308449", "GSM1308450", "GSM1308451", "GSM1308452", "GSM1308453", "GSM1308454", "GSM1308455", "GSM1308456", "GSM1308457", "GSM1308458", "GSM1308459", "GSM1308460", "GSM1308461", "GSM1308462", "GSM1308463", "GSM1308464", "GSM1308465", "GSM1308466", "GSM1308467", "GSM1308468", "GSM1308469", "GSM1308470", "GSM1308471", "GSM1308472", "GSM1308473", "GSM1308474", "GSM1308475", "GSM1308476", "GSM1308477", "GSM1308478", "GSM1308479", "GSM1308480", "GSM1308481", "GSM1308482", "GSM1308483", "GSM1308484", "GSM1308485", "GSM1308486", "GSM1308487", "GSM1308488", "GSM1308489", "GSM1308490", "GSM1308491", "GSM1308492", "GSM1308493", "GSM1308494", "GSM1308495", "GSM1308496", "GSM1308497", "GSM1308498", "GSM1308499", "GSM1308500", "GSM1308501", "GSM1308502", "GSM1308503", "GSM1308504", "GSM1308505", "GSM1308506", "GSM1308507", "GSM1308508", "GSM1308509", "GSM1308510", "GSM1308511", "GSM1308512", "GSM1308513", "GSM1308514", "GSM1308515", "GSM1308516", "GSM1308517", "GSM1308518", "GSM1308519", "GSM1308520", "GSM1308521", "GSM1308522", "GSM1308523"], "sample_count": 132, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Global gene expression analysis of gastric cancer by oligonucleotide microarrays", "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:GSE81948", "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=GSE81948", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE81948", "version": null, "note": "The following information was supplied regarding data availability:\nGene Expression Omnibus: GSE54129, GSE33651, GSE81948.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nGene Expression Omnibus: GSE54129, GSE33651, GSE81948.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2178316", "GSM2178317", "GSM2178318", "GSM2178319", "GSM2178320", "GSM2178321", "GSM2178322", "GSM2178323", "GSM2178324", "GSM2178325", "GSM2178326", "GSM2178327", "GSM2178328", "GSM2178329", "GSM2178330", "GSM2178331", "GSM2178332", "GSM2178333", "GSM2178334", "GSM2178335"], "sample_count": 20, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "miR-204 down-regulation elicited perturbation of a gene target signature common to human cholangiocarcinoma and gastric cancer.", "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:30568862:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1e2ece728dc47fbb1f70c5bc41089825b745b319d5bc4f19b73b441a1a12496c", "bytes": 462, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#table-1", "version": null, "note": "Details for GEO gastric cancer data.", "structure": {"pmcid": "PMC6287586", "section_index": 9, "section_title": "Identification of DEGs", "row_count": 4, "column_count": 6}, "table": {"label": "Table 1", "caption": "Details for GEO gastric cancer data.", "rows": [["Reference", "Sample", "GEO", "Platform", "Normal", "Tumor"], ["B Liu (2011, unpublished data)", "Stomach", "GSE54129", "GLP570", "21", "111"], ["DY Park (2011, unpublished data)", "Stomach", "GSE33651", "GLP2895", "12", "40"], ["Canu et al. (2017)", "Stomach", "GSE81948", "GLP6244", "5", "15"]], "row_count": 4, "column_count": 6, "numeric_cells": 15, "header_rows": 1, "locator": "section[9]/table-wrap[1]#table-1"}}, {"id": "asset:table:pmid:30568862:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f0f3159925b82e926262cbf16efa21d2b57dfc7d3124c4ed46729abf731313d2", "bytes": 1084, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[2]#table-2", "version": null, "note": "Screening DEGs in gastric cancer by integrated microarray.", "structure": {"pmcid": "PMC6287586", "section_index": 9, "section_title": "Identification of DEGs", "row_count": 3, "column_count": 2}, "table": {"label": "Table 2", "caption": "Screening DEGs in gastric cancer by integrated microarray.", "rows": [["DEGs", "Gene terms"], ["Upregulated", "SLC39A8 S100A10 ANTXR1 DYSF SERPINE2 ADAMTS9 LCP2 NOTCH1 FAS LRP8 C3AR1 MMP3 ANOS1 CALU CXCL10 HAVCR2 MYO1B MMP12 LAMA4 ASAP1 FGD6 HTRA1 ATP1B3 SULF2 FAM83D ANGPT2 CD86 LGALS1 C2 KIRREL PLEK EPHB2 COL15A1 LOX ACTN1 CTSL COL5A1 BCL6 SERPINH1 PMEPA1 NID2 CD248 RAB31 ANGPTL2 ITGB2 MSR1 PCOLCE SPARC IGF2BP3 PLA2G7 PDPN PLXDC2 COL4A2 LAPTM5 FBXO32 CTSK BAG2 MMP2 TNC TNFAIP6 ADAMTS2 OLFML2B COL4A1 CAP2 FNDC1 ITGA5 COL12A1 THY1 SERPINE1 ASPN LY6E THBS1 FN1 GUCY1A3 EDNRA FAP FCGR3B CTHRC1 PDLIM7 SULF1 CXCL8 SFRP4 COL1A1 CHI3L1 COL8A1"], ["Downregulated", "SCGB2A1 SST KRT20 DPCR1 ACER2 SOSTDC1 VSIG1 CAPN9 AKR1B10 ATP4B ADGRG2 TFF2 CWH43 ANXA10 HPGD VSIG2 MAL PSAPL1 PSCA LYPD6B ERO1B ALDH3A1 RASSF6 RDH12 C16orf89 RNASE1 RAB27A AKR7A3 FBXL13 FMO5 ABCC5 PBLD B3GNT6 SELENBP1 TFCP2L1 PXMP2 PDIA2 CAPN13 ALDH6A1 MFSD4A AQP4 SUCLG2 CHGA NRG4"]], "row_count": 3, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[9]/table-wrap[2]#table-2"}}], "gaps": ["asset:data:geo:GSE33651 not downloaded", "asset:data:geo:GSE33651 licence not read", "asset:data:geo:GSE54129 not downloaded", "asset:data:geo:GSE54129 licence not read", "asset:data:geo:GSE81948 not downloaded", "asset:data:geo:GSE81948 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The hazard ratio (HR) was given with 95% confidence intervals, and log rank P value was calculated and displayed on the webpage."}}, {"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": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"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": "protein-protein interaction"}}, {"id": "method-4", "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": 0.7, "band": "medium", "quote": "pathway enrichment"}}], "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": ["logrank_test"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: log_rank_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": ["GSE54129", "GSE33651", "GSE81948"], "resolved_accessions": ["GSE54129", "GSE33651", "GSE81948"], "statements": ["The following information was supplied regarding data availability:\nGene Expression Omnibus: GSE54129, GSE33651, GSE81948."], "basis": "The paper names GSE54129, GSE33651, GSE81948 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": ["logrank_test"], "assets": ["source:pmid:30568862", "data:geo:GSE33651", "asset:table:pmid:30568862:1", "asset:table:pmid:30568862:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE33651"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:13:15Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 29427, "completion_tokens": 2058, "cached_tokens": 9992}}, "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:30568862", "type": "paper", "label": "pmid:30568862"}, {"id": "source:pmid:30568862", "type": "manuscript", "label": "PMID 30568862 full text"}, {"id": "data:geo:GSE33651", "type": "dataset", "label": "GEO GSE33651"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:30568862", "type": "paper", "label": "pmid:30568862"}, {"id": "source:pmid:30568862", "type": "manuscript", "label": "PMID 30568862 full text"}, {"id": "data:geo:GSE33651", "type": "dataset", "label": "GEO GSE33651"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-30568862", "type": "extraction", "used": ["source:pmid:30568862"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE33651", "type": "accession_resolution", "used": ["data:geo:GSE33651"], "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:30568862", "parent_hash": "sha256:8aaac7b2c46fc4c59740d156d62f106702aff561a1ed36ffddc59e65d4e3f808", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE33651 licence not read", "asset:data:geo:GSE33651 not downloaded", "asset:data:geo:GSE54129 licence not read", "asset:data:geo:GSE54129 not downloaded", "asset:data:geo:GSE81948 licence not read", "asset:data:geo:GSE81948 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": 0.93, "evidence": ["downregulated as determined from integrated microarray gastric cancer data, P<0.05 were considered"], "order_basis": "paper_text_order:2670", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["logrank_test"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The hazard ratio (HR) was given with 95% confidence intervals, and log rank P value was calculated and displayed on the webpage."], "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":"2026-11-04T01:49:52+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}}}