{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38596054", "kind": "science-record", "revision": 3, "content_hash": "sha256:0330f802f5e4cab3da0e5d0819872718d2978c1c41b7b30c5289663d971a44b2", "created_at": "2026-11-01T19:20:33Z", "updated_at": "2026-11-01T22:11:38Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Molecular subtype construction and prognosis model for stomach adenocarcinoma characterized by metabolism-related genes.", "doi": "10.1016/j.heliyon.2024.e28413", "pmid": "38596054", "authors": ["Jie Sun", "Yuanyuan Wang", "Kai Zhang", "Sijia Shi", "Xinxin Gao", "Xianghao Jia", "Bicong Cong", "Chunning Zheng"], "journal": "Heliyon", "year": 2024, "abstract": "Background: Metabolic reprogramming is implicated in cancer progression. However, the impact of metabolism-associated genes in stomach adenocarcinomas (STAD) has not been thoroughly reviewed. Herein, we characterized metabolic transcription-correlated STAD subtypes and evaluated a metabolic RiskScore for evaluation survival.\nMethod: Genes related to metabolism were gathered from previous study and metabolic subtypes were screened using ConsensusClusterPlus in TCGA-STAD and GSE66229 dataset. The ssGSEA, MCP-Count, ESTIMATE and CIBERSORT determined the immune infiltration. A RiskScore model was established using the WGCNA and LASSO Cox regression in the TCGA-STAD queue and verified in the GSE66229 datasets. RT-qPCR was employed to measure the mRNA expressions of genes in the model.\nResult: Two metabolism-related subtypes (C1 and C2) of STAD were constructed on account of the expression profiles of 113 prognostic metabolism genes with different immune outcomes and apparently distinct metabolic characteristic. The overall survival (OS) of C2 subtype was shorter than that of C1 subtype. Four metabolism-associated genes in turquoise model, which closely associated with C2 subtype, were employed to build the RiskScore (MATN3, OSBPL1A, SERPINE1, CPNE8) in TCGA-train dataset. Patients developed a poorer prognosis if they had a high RiskScore than having a low RiskScore. The promising effect of RiskScore was verified in the TCGA-test, TCGA-STAD and GSE66229 datasets. The prediction reliability of the RiskScore was validated by time-dependent receiver operating characteristic curve (ROC) and nomogram. Moreover, samples with high RiskScore had an enhanced immune status and TIDE score. Moreover, MATN3, OSBPL1A, SERPINE1 and CPNE8 mRNA levels were all elevated in SGC7901 cells. Inhibition of OSBPL1A decreased SGC7901 cells invasion numbers.\nConclusion: This work provided a new perspective into heterogeneity in metabolism and its association with immune escape in STAD. RiskScore was considered to be a strong prognostic label that could help individualize the treatment of STAD patients.", "claims": [{"id": "claim-method", "statement": "A RiskScore model was established using the WGCNA and LASSO Cox regression in the TCGA-STAD queue and verified in the GSE66229 datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38596054", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "A RiskScore model was established using the WGCNA and LASSO Cox regression in the TCGA-STAD queue and verified in the GSE66229 datasets."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The dataset used in this study was available in GSE66229 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE66229).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38596054", "locator": "sections[25] \"Data availability statement\" paragraph 2", "quote": "The dataset used in this study was available in GSE66229 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE66229)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "", "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:38596054"], "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:GSE66229"], "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:GSE66229"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38596054", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.heliyon.2024.e28413", "sha256": "sha256:4fe11b53b00ad9ec354e924296603a8be6de3c61cf7dbcf13fb60c9c942d2810", "bytes": 34141, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.heliyon.2024.e28413", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11002599", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE66229", "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=GSE66229", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE66229", "version": null, "note": "The dataset used in this study was available in GSE66229 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE66229).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The dataset used in this study was available in GSE66229 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE66229).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1523727", "GSM1523728", "GSM1523729", "GSM1523730", "GSM1523731", "GSM1523732", "GSM1523733", "GSM1523734", "GSM1523735", "GSM1523736", "GSM1523737", "GSM1523738", "GSM1523739", "GSM1523740", "GSM1523741", "GSM1523742", "GSM1523743", "GSM1523744", "GSM1523745", "GSM1523746", "GSM1523747", "GSM1523748", "GSM1523749", "GSM1523750", "GSM1523751", "GSM1523752", "GSM1523753", "GSM1523754", "GSM1523755", "GSM1523756", "GSM1523757", "GSM1523758", "GSM1523759", "GSM1523760", "GSM1523761", "GSM1523762", "GSM1523763", "GSM1523764", "GSM1523765", "GSM1523766", "GSM1523767", "GSM1523768", "GSM1523769", "GSM1523770", "GSM1523771", "GSM1523772", "GSM1523773", "GSM1523774", "GSM1523775", "GSM1523776", "GSM1523777", "GSM1523778", "GSM1523779", "GSM1523780", "GSM1523781", "GSM1523782", "GSM1523783", "GSM1523784", "GSM1523785", "GSM1523786", "GSM1523787", "GSM1523788", "GSM1523789", "GSM1523790", "GSM1523791", "GSM1523792", "GSM1523793", "GSM1523794", "GSM1523795", "GSM1523796", "GSM1523797", "GSM1523798", "GSM1523799", "GSM1523800", "GSM1523801", "GSM1523802", "GSM1523803", "GSM1523804", "GSM1523805", "GSM1523806", "GSM1523807", "GSM1523808", "GSM1523809", "GSM1523810", "GSM1523811", "GSM1523812", "GSM1523813", "GSM1523814", "GSM1523815", "GSM1523816", "GSM1523817", "GSM1523818", "GSM1523819", "GSM1523820", "GSM1523821", "GSM1523822", "GSM1523823", "GSM1523824", "GSM1523825", "GSM1523826", "GSM1523827", "GSM1523828", "GSM1523829", "GSM1523830", "GSM1523831", "GSM1523832", "GSM1523833", "GSM1523834", "GSM1523835", "GSM1523836", "GSM1523837", "GSM1523838", "GSM1523839", "GSM1523840", "GSM1523841", "GSM1523842", "GSM1523843", "GSM1523844", "GSM1523845", "GSM1523846", "GSM1523847", "GSM1523848", "GSM1523849", "GSM1523850", "GSM1523851", "GSM1523852", "GSM1523853", "GSM1523854", "GSM1523855", "GSM1523856", "GSM1523857", "GSM1523858", "GSM1523859", "GSM1523860", "GSM1523861", "GSM1523862", "GSM1523863", "GSM1523864", "GSM1523865", "GSM1523866", "GSM1523867", "GSM1523868", "GSM1523869", "GSM1523870", "GSM1523871", "GSM1523872", "GSM1523873", "GSM1523874", "GSM1523875", "GSM1523876", "GSM1523877", "GSM1523878", "GSM1523879", "GSM1523880", "GSM1523881", "GSM1523882", "GSM1523883", "GSM1523884", "GSM1523885", "GSM1523886", "GSM1523887", "GSM1523888", "GSM1523889", "GSM1523890", "GSM1523891", "GSM1523892", "GSM1523893", "GSM1523894", "GSM1523895", "GSM1523896", "GSM1523897", "GSM1523898", "GSM1523899", "GSM1523900", "GSM1523901", "GSM1523902", "GSM1523903", "GSM1523904", "GSM1523905", "GSM1523906", "GSM1523907", "GSM1523908", "GSM1523909", "GSM1523910", "GSM1523911", "GSM1523912", "GSM1523913", "GSM1523914", "GSM1523915", "GSM1523916", "GSM1523917", "GSM1523918", "GSM1523919", "GSM1523920", "GSM1523921", "GSM1523922", "GSM1523923", "GSM1523924", "GSM1523925", "GSM1523926", "GSM1523927", "GSM1523928", "GSM1523929", "GSM1523930", "GSM1523931", "GSM1523932", "GSM1523933", "GSM1523934", "GSM1523935", "GSM1523936", "GSM1523937", "GSM1523938", "GSM1523939", "GSM1523940", "GSM1523941", "GSM1523942", "GSM1523943", "GSM1523944", "GSM1523945", "GSM1523946", "GSM1523947", "GSM1523948", "GSM1523949", "GSM1523950", "GSM1523951", "GSM1523952", "GSM1523953", "GSM1523954", "GSM1523955", "GSM1523956", "GSM1523957", "GSM1523958", "GSM1523959", "GSM1523960", "GSM1523961", "GSM1523962", "GSM1523963", "GSM1523964", "GSM1523965", "GSM1523966", "GSM1523967", "GSM1523968", "GSM1523969", "GSM1523970", "GSM1523971", "GSM1523972", "GSM1523973", "GSM1523974", "GSM1523975", "GSM1523976", "GSM1523977", "GSM1523978", "GSM1523979", "GSM1523980", "GSM1523981", "GSM1523982", "GSM1523983", "GSM1523984", "GSM1523985", "GSM1523986", "GSM1523987", "GSM1523988", "GSM1523989", "GSM1523990", "GSM1523991", "GSM1523992", "GSM1523993", "GSM1523994", "GSM1523995", "GSM1523996", "GSM1523997", "GSM1523998", "GSM1523999", "GSM1524000", "GSM1524001", "GSM1524002", "GSM1524003", "GSM1524004", "GSM1524005", "GSM1524006", "GSM1524007", "GSM1524008", "GSM1524009", "GSM1524010", "GSM1524011", "GSM1524012", "GSM1524013", "GSM1524014", "GSM1524015", "GSM1524016", "GSM1524017", "GSM1524018", "GSM1524019", "GSM1524020", "GSM1524021", "GSM1524022", "GSM1524023", "GSM1524024", "GSM1524025", "GSM1524026", "GSM1524027", "GSM1524028", "GSM1524029", "GSM1524030", "GSM1524031", "GSM1524032", "GSM1524033", "GSM1524034", "GSM1524035", "GSM1524036", "GSM1524037", "GSM1524038", "GSM1524039", "GSM1524040", "GSM1524041", "GSM1524042", "GSM1524043", "GSM1524044", "GSM1524045", "GSM1524046", "GSM1524047", "GSM1524048", "GSM1524049", "GSM1524050", "GSM1524051", "GSM1524052", "GSM1524053", "GSM1524054", "GSM1524055", "GSM1524056", "GSM1524057", "GSM1524058", "GSM1524059", "GSM1524060", "GSM1524061", "GSM1524062", "GSM1524063", "GSM1524064", "GSM1524065", "GSM1524066", "GSM1524067", "GSM1524068", "GSM1524069", "GSM1524070", "GSM1524071", "GSM1524072", "GSM1524073", "GSM1524074", "GSM1524075", "GSM1524076", "GSM1524077", "GSM1524078", "GSM1524079", "GSM1524080", "GSM1524081", "GSM1524082", "GSM1524083", "GSM1524084", "GSM1524085", "GSM1524086", "GSM1524087", "GSM1524088", "GSM1524089", "GSM1524090", "GSM1524091", "GSM1524092", "GSM1524093", "GSM1524094", "GSM1524095", "GSM1524096", "GSM1524097", "GSM1524098", "GSM1524099", "GSM1524100", "GSM1524101", "GSM1524102", "GSM1524103", "GSM1524104", "GSM1524105", "GSM1524106", "GSM1524107", "GSM1524108", "GSM1524109", "GSM1524110", "GSM1524111", "GSM1524112", "GSM1524113", "GSM1524114", "GSM1524115", "GSM1524116", "GSM1524117", "GSM1524118", "GSM1524119", "GSM1524120", "GSM1524121", "GSM1524122", "GSM1524123", "GSM1524124", "GSM1524125", "GSM1524126"], "sample_count": 400, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Molecular analysis of gastric cancer identifies discrete subtypes associated with distinct clinical characteristics and survival outcomes: the ACRG (Asian Cancer Research Group) study", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE66229 not downloaded", "asset:data:geo:GSE66229 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "A RiskScore model was established using the WGCNA and LASSO Cox regression in the TCGA-STAD queue and verified in the GSE66229 datasets."}}, {"id": "method-2", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"id": "method-3", "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": "Kaplan-Meier"}}], "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": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE66229"], "resolved_accessions": ["GSE66229"], "statements": ["The dataset used in this study was available in GSE66229 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE66229)."], "basis": "The paper names GSE66229 in Gene Expression Omnibus (GEO) database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:38596054", "data:geo:GSE66229"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE66229"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:14:58Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 10476, "completion_tokens": 1012, "cached_tokens": 264}}, "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:38596054", "type": "paper", "label": "pmid:38596054"}, {"id": "source:pmid:38596054", "type": "manuscript", "label": "PMID 38596054 full text"}, {"id": "data:geo:GSE66229", "type": "dataset", "label": "GEO GSE66229"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38596054", "type": "paper", "label": "pmid:38596054"}, {"id": "source:pmid:38596054", "type": "manuscript", "label": "PMID 38596054 full text"}, {"id": "data:geo:GSE66229", "type": "dataset", "label": "GEO GSE66229"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38596054", "type": "extraction", "used": ["source:pmid:38596054"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE66229", "type": "accession_resolution", "used": ["data:geo:GSE66229"], "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:38596054", "parent_hash": "sha256:5cd15ff9592a5000760a625d852ac06f2c8b84c32fd31ad83bf1612ec629f2fa", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE66229 licence not read", "asset:data:geo:GSE66229 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": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["queue and verified in the GSE66229 datasets. RT-qPCR was employed to measure the mRNA expressions", "ue and verified in the GSE66229 datasets. RT-qPCR was employed to measure the mRNA expressions", "for 48 h prior to conducting the experiment. RT-qPCR. Extraction of total RNA was realized using", "d using TRIzol reagent (Thermo Fisher, USA). RT-qPCR with the use of FastStart Universal SYBR Gre"], "order_basis": "paper_text_order:791", "id": "assay:1"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["the subtypes with p < 0.05. Cell culture and transfection DMEM containing 10% FBS (Gibco, Thermo Fishe", "ectamine 3000 (Invitrogen) was used for cell transfection following the protocol. The transfected cell", "ell transfection following the protocol. The transfected cells were then cultured for 48 h prior to c"], "order_basis": "paper_text_order:2646", "id": "assay:2"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["A RiskScore model was established using the WGCNA and LASSO Cox regression in the TCGA-STAD queue and verified in the GSE66229 datasets."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:37:17+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}}}