{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37214088", "kind": "science-record", "revision": 3, "content_hash": "sha256:f6adcdd8d627827cc43a2dfd5ae8451975a20114bf3df438de290d230785c16f", "created_at": "2026-11-01T19:01:54Z", "updated_at": "2026-11-01T22:09:31Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of immune-related genes in acute myocardial infarction based on integrated bioinformatical methods and experimental verification.", "doi": "10.7717/peerj.15058", "pmid": "37214088", "authors": ["Jian Liu", "Lu Chen", "Xiang Zheng", "Caixia Guo"], "journal": "PeerJ", "year": 2023, "abstract": "Background: Acute myocardial infarction (AMI) is one of the leading causes of death worldwide. The etiology of AMI is complex and has not been fully defined. In recent years, the role of immune response in the development, progression and prognosis of AMI has received increasing attention. The aim of this study was to identify key genes associated with the immune response in AMI and to analyze their immune infiltration.\nMethods: The study included a total of two GEO databases, containing 83 patients with AMI and 54 healthy individuals. We used the linear model of microarray data (limma) package to find the differentially expressed genes associated with AMI, performing weighted gene co-expression analysis (WGCNA) to further identify the genes associated with inflammatory response to AMI. We found the final hub genes through the protein-protein interaction (PPI) network and least absolute shrinkage and selection operator (LASSO) regression model. To verify the above conclusions, we constructed mice AMI model, extracting myocardial tissue to perform qRT-PCR. Furthermore, the CIBERSORT tool for immune cells infiltration analysis was also carried out.\nResults: A total of 5,425 significant up-regulated and 2,126 down-regulated genes were found in GSE66360 and GSE24519. A total of 116 immune-related genes in close association with AMI were screened by WGCNA analysis. These genes were mostly clustered in the immune response on the basis of GO and KEGG enrichment. With construction of PPI network and LASSO regression analysis, this research found three hub genes (SOCS2, FFAR2, MYO10) among these differentially expressed genes. The immune cell infiltration results revealed that significant differences could be found on T cells CD4 memory activated, Tregs (regulatory T cells), macrophages M2, neutrophils, T cells CD8, T cells CD4 naive, eosinophils between controls and AMI patients.", "claims": [{"id": "claim-method", "statement": "We built a least absolute shrinkage and selection operator (LASSO) prediction model of disease occurrence by constructing a penalty function to obtain a more refined model.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37214088", "locator": "sections[18] \"Establishment of the diagnostic model based on LASSO\" paragraph 2", "quote": "We built a least absolute shrinkage and selection operator (LASSO) prediction model of disease occurrence by constructing a penalty function to obtain a more refined model."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The following information was supplied regarding data availability:\nThe raw measurements are available in the Supplemental Files.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37214088", "locator": "sections[34] \"Data Availability Statement\" paragraphs 1-3", "quote": "The following information was supplied regarding data availability:\nThe raw measurements are available in the Supplemental Files."}], "state": "complete"}, {"id": "claim-target-result", "statement": "With construction of PPI network and LASSO regression analysis, this research found three hub genes (SOCS2, FFAR2, MYO10) among these differentially expressed genes.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37214088", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "With construction of PPI network and LASSO regression analysis, this research found three hub genes (SOCS2, FFAR2, MYO10) among these differentially expressed genes."}, {"asset": "source:pmid:37214088", "locator": "sections[18] \"Establishment of the diagnostic model based on LASSO\" paragraph 2", "quote": "The results show that the optimum λ value is 0.13."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "With construction of PPI network and LASSO regression analysis, this research found three hub genes (SOCS2, FFAR2, MYO10) among these differentially expressed genes.", "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:37214088"], "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:GSE24519"], "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:GSE24519"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37214088", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.15058", "sha256": "sha256:1773e7f989aa25dad6390217f8560f6525ee7d0bd0ec34b44642721704bdf3c0", "bytes": 54536, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.15058", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10198157", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE24519", "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=GSE24519", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE24519", "version": null, "note": "The following information was supplied regarding data availability:\nThe raw measurements are available in the Supplemental Files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nThe raw measurements are available in the Supplemental Files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM604559", "GSM604560", "GSM604561", "GSM604562", "GSM604563", "GSM604564", "GSM604565", "GSM604566", "GSM604567", "GSM604568", "GSM604569", "GSM604570", "GSM604571", "GSM604572", "GSM604573", "GSM604574", "GSM604575", "GSM604576", "GSM604577", "GSM604578", "GSM604579", "GSM604580", "GSM604581", "GSM604582", "GSM604583", "GSM604584", "GSM604585", "GSM604586", "GSM604587", "GSM604588", "GSM604589", "GSM604590", "GSM604591", "GSM604592", "GSM604672", "GSM604673", "GSM604674", "GSM604675"], "sample_count": 38, "group_sizes": null, "group_sizes_basis": null, "platform": "2895", "taxon": "Homo sapiens", "title": "Gene expression profiling of patients affected by first acute myocardial infarction (FAMI)", "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:GSE48060", "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=GSE48060", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE48060", "version": null, "note": "The following information was supplied regarding data availability:\nThe raw measurements are available in the Supplemental Files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nThe raw measurements are available in the Supplemental Files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1167072", "GSM1167073", "GSM1167074", "GSM1167075", "GSM1167076", "GSM1167077", "GSM1167078", "GSM1167079", "GSM1167080", "GSM1167081", "GSM1167082", "GSM1167083", "GSM1167084", "GSM1167085", "GSM1167086", "GSM1167087", "GSM1167088", "GSM1167089", "GSM1167090", "GSM1167091", "GSM1167092", "GSM1167093", "GSM1167094", "GSM1167095", "GSM1167096", "GSM1167097", "GSM1167098", "GSM1167099", "GSM1167100", "GSM1167101", "GSM1167102", "GSM1167103", "GSM1167104", "GSM1167105", "GSM1167106", "GSM1167107", "GSM1167108", "GSM1167109", "GSM1167110", "GSM1167111", "GSM1167112", "GSM1167113", "GSM1167114", "GSM1167115", "GSM1167116", "GSM1167117", "GSM1167118", "GSM1167119", "GSM1167120", "GSM1167121", "GSM1167122", "GSM1167123"], "sample_count": 52, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Transcriptome from circulating cells suggests dysregulated pathways associated with long-term recurrent events following first-time myocardial infarction.", "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:GSE66360", "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=GSE66360", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE66360", "version": null, "note": "The following information was supplied regarding data availability:\nThe raw measurements are available in the Supplemental Files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:\nThe raw measurements are available in the Supplemental Files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1620819", "GSM1620820", "GSM1620821", "GSM1620822", "GSM1620823", "GSM1620824", "GSM1620825", "GSM1620826", "GSM1620827", "GSM1620828", "GSM1620829", "GSM1620830", "GSM1620831", "GSM1620832", "GSM1620833", "GSM1620834", "GSM1620835", "GSM1620836", "GSM1620837", "GSM1620838", "GSM1620839", "GSM1620840", "GSM1620841", "GSM1620842", "GSM1620843", "GSM1620844", "GSM1620845", "GSM1620846", "GSM1620847", "GSM1620848", "GSM1620849", "GSM1620850", "GSM1620851", "GSM1620852", "GSM1620853", "GSM1620854", "GSM1620855", "GSM1620856", "GSM1620857", "GSM1620858", "GSM1620859", "GSM1620860", "GSM1620861", "GSM1620862", "GSM1620863", "GSM1620864", "GSM1620865", "GSM1620866", "GSM1620867", "GSM1620868", "GSM1620869", "GSM1620870", "GSM1620871", "GSM1620872", "GSM1620873", "GSM1620874", "GSM1620875", "GSM1620876", "GSM1620877", "GSM1620878", "GSM1620879", "GSM1620880", "GSM1620881", "GSM1620882", "GSM1620883", "GSM1620884", "GSM1620885", "GSM1620886", "GSM1620887", "GSM1620888", "GSM1620889", "GSM1620890", "GSM1620891", "GSM1620892", "GSM1620893", "GSM1620894", "GSM1620895", "GSM1620896", "GSM1620897", "GSM1620898", "GSM1620899", "GSM1620900", "GSM1620901", "GSM1620902", "GSM1620903", "GSM1620904", "GSM1620905", "GSM1620906", "GSM1620907", "GSM1620908", "GSM1620909", "GSM1620910", "GSM1620911", "GSM1620912", "GSM1620913", "GSM1620914", "GSM1620915", "GSM1620916", "GSM1620917"], "sample_count": 99, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "A Whole Blood Molecular Signature for the Identification of Acute Myocardial Infarction Without Relying Upon Myonecrosis (microarray)", "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:GSE24519 not downloaded", "asset:data:geo:GSE24519 licence not read", "asset:data:geo:GSE48060 not downloaded", "asset:data:geo:GSE48060 licence not read", "asset:data:geo:GSE66360 not downloaded", "asset:data:geo:GSE66360 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.7, "band": "medium", "quote": "limma"}}, {"id": "method-2", "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-3", "family": null, "specific": null, "label": "least absolute shrinkage and selection operator (LASSO) regression", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We built a least absolute shrinkage and selection operator (LASSO) prediction model of disease occurrence by constructing a penalty function to obtain a more refined model."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE24519", "GSE66360", "GSE48060"], "resolved_accessions": ["GSE24519", "GSE66360", "GSE48060"], "statements": ["The following information was supplied regarding data availability:\nThe raw measurements are available in the Supplemental Files."], "basis": "The paper names GSE24519, GSE66360, GSE48060 in Gene Expression Omnibus and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:37214088", "data:geo:GSE24519"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE24519"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:41:00Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 15892, "completion_tokens": 1924, "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:37214088", "type": "paper", "label": "pmid:37214088"}, {"id": "source:pmid:37214088", "type": "manuscript", "label": "PMID 37214088 full text"}, {"id": "data:geo:GSE24519", "type": "dataset", "label": "GEO GSE24519"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37214088", "type": "paper", "label": "pmid:37214088"}, {"id": "source:pmid:37214088", "type": "manuscript", "label": "PMID 37214088 full text"}, {"id": "data:geo:GSE24519", "type": "dataset", "label": "GEO GSE24519"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37214088", "type": "extraction", "used": ["source:pmid:37214088"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE24519", "type": "accession_resolution", "used": ["data:geo:GSE24519"], "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:37214088", "parent_hash": "sha256:b5411b7a8d09ab31b6454dcd7577e1b43927c9ae541044ccb2bec09ec65cba90", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE24519 licence not read", "asset:data:geo:GSE24519 not downloaded", "asset:data:geo:GSE48060 licence not read", "asset:data:geo:GSE48060 not downloaded", "asset:data:geo:GSE66360 licence not read", "asset:data:geo:GSE66360 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": ["thy individuals. We used the linear model of microarray data (limma) package to find the differentia"], "order_basis": "paper_text_order:670", "id": "assay:1"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["limma"], "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":"2026-11-04T01:44:14+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}}}