{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39660117", "kind": "science-record", "revision": 4, "content_hash": "sha256:2e5e88f562da0940ffbdf3b902773d928d47b643e0257d3d745688f19cd57c53", "created_at": "2026-11-01T20:29:57Z", "updated_at": "2026-11-01T22:55:47Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Multi-modal transcriptomics: integrating machine learning and convolutional neural networks to identify immune biomarkers in atherosclerosis.", "doi": "10.3389/fcvm.2024.1397407", "pmid": "39660117", "authors": ["Haiqing Chen", "Haotian Lai", "Hao Chi", "Wei Fan", "Jinbang Huang", "Shengke Zhang", "Chenglu Jiang", "Lai Jiang", "Qingwen Hu", "Xiuben Yan", "Yemeng Chen", "Jieying Zhang", "Guanhu Yang", "Bin Liao", "Juyi Wan"], "journal": "Frontiers in cardiovascular medicine", "year": 2024, "abstract": "Background: Atherosclerosis, a complex chronic vascular disorder with multifactorial etiology, stands as the primary culprit behind consequential cardiovascular events, imposing a substantial societal and economic burden. Nevertheless, our current understanding of its pathogenesis remains imprecise. In this investigation, our objective is to establish computational models elucidating molecular-level markers associated with atherosclerosis. This endeavor involves the integration of advanced machine learning techniques and comprehensive bioinformatics analyses.\nMaterials and methods: Our analysis incorporated data from three publicly available the Gene Expression Omnibus (GEO) datasets: GSE100927 (104 samples, 30,558 genes), which includes atherosclerotic lesions and control arteries from carotid, femoral, and infra-popliteal arteries of deceased organ donors; GSE43292 (64 samples, 23,307 genes), consisting of paired carotid endarterectomy samples from 32 hypertensive patients, comparing atheroma plaques and intact tissues; and GSE159677 (30,498 single cells, 33,538 genes), examining single-cell transcriptomes of calcified atherosclerotic core plaques and adjacent carotid artery tissues from patients undergoing carotid endarterectomy. Utilizing single-cell sequencing, highly variable atherosclerotic monocyte subpopulations were systematically identified. We analyzed cellular communication patterns with temporal dynamics. The bioinformatics approach Weighted Gene Co-expression Network Analysis (WGCNA) identified key modules, constructing a Protein-Protein Interaction (PPI) network from module-associated genes. Three machine-learning models derived marker genes, formulated through logistic regression and validated via convolutional neural network(CNN) modeling. Subtypes were clustered based on Gene Set Variation Analysis (GSVA) scores, validated through immunoassays.\nResults: Three pivotal atherosclerosis-associated genes-CD36, S100A10, CSNK1A1-were unveiled, offering valuable clinical insights. Profiling based on these genes delineated two distinct isoforms: C2 demonstrated potent microbicidal activity, while C1 engaged in inflammation regulation, tissue repair, and immune homeostasis. Molecular docking analyses explored therapeutic potential for Estradiol, Zidovudine, Indinavir, and Dronabinol for clinical applications.\nConclusion: This study introduces three signature genes for atherosclerosis, shaping a novel paradigm for investigating clinical immunological medications. It distinguishes the high biocidal C2 subtype from the inflammation-modulating C1 subtype, utilizing identified signature gene as crucial targets.", "claims": [{"id": "claim-method", "statement": "One-way analysis of variance (ANOVA) and t-tests were employed to explore potential significant differences in atherosclerosis model genes, functional enrichment results, immune cell infiltration, and immune function scores among the patient groups.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39660117", "locator": "sections[14] \"Statistical analysis\" paragraph 2", "quote": "One-way analysis of variance (ANOVA) and t-tests were employed to explore potential significant differences in atherosclerosis model genes, functional enrichment results, immune cell infiltration, and immune function scores among the patient groups."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39660117", "locator": "sections[31] \"Data availability statement\" paragraph 2", "quote": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Three pivotal atherosclerosis-associated genes—CD36, S100A10, CSNK1A1—were unveiled, offering valuable clinical insights.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39660117", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Three pivotal atherosclerosis-associated genes—CD36, S100A10, CSNK1A1—were unveiled, offering valuable clinical insights."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Three pivotal atherosclerosis-associated genes—CD36, S100A10, CSNK1A1—were unveiled, offering valuable clinical insights.", "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:39660117"], "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:GSE100927"], "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:GSE100927"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39660117", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fcvm.2024.1397407", "sha256": "sha256:78482dd0af7df78f9c476211e8994f6fb414f94910b3276aa65c4020ef0d0426", "bytes": 70772, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fcvm.2024.1397407", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11628520", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE100927", "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=GSE100927", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE100927", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2696609", "GSM2696610", "GSM2696611", "GSM2696612", "GSM2696613", "GSM2696614", "GSM2696615", "GSM2696616", "GSM2696617", "GSM2696618", "GSM2696619", "GSM2696620", "GSM2696621", "GSM2696622", "GSM2696623", "GSM2696624", "GSM2696625", "GSM2696626", "GSM2696627", "GSM2696628", "GSM2696629", "GSM2696630", "GSM2696631", "GSM2696632", "GSM2696633", "GSM2696634", "GSM2696635", "GSM2696636", "GSM2696637", "GSM2696638", "GSM2696639", "GSM2696640", "GSM2696641", "GSM2696642", "GSM2696643", "GSM2696644", "GSM2696645", "GSM2696646", "GSM2696647", "GSM2696648", "GSM2696649", "GSM2696650", "GSM2696651", "GSM2696652", "GSM2696653", "GSM2696654", "GSM2696655", "GSM2696656", "GSM2696657", "GSM2696658", "GSM2696659", "GSM2696660", "GSM2696661", "GSM2696662", "GSM2696663", "GSM2696664", "GSM2696665", "GSM2696666", "GSM2696667", "GSM2696668", "GSM2696669", "GSM2696670", "GSM2696671", "GSM2696672", "GSM2696673", "GSM2696674", "GSM2696675", "GSM2696676", "GSM2696677", "GSM2696678", "GSM2696679", "GSM2696680", "GSM2696681", "GSM2696682", "GSM2696683", "GSM2696684", "GSM2696685", "GSM2696686", "GSM2696687", "GSM2696688", "GSM2696689", "GSM2696690", "GSM2696691", "GSM2696692", "GSM2696693", "GSM2696694", "GSM2696695", "GSM2696696", "GSM2696697", "GSM2696698", "GSM2696699", "GSM2696700", "GSM2696701", "GSM2696702", "GSM2696703", "GSM2696704", "GSM2696705", "GSM2696706", "GSM2696707", "GSM2696708", "GSM2696709", "GSM2696710", "GSM2696711", "GSM2696712"], "sample_count": 104, "group_sizes": null, "group_sizes_basis": null, "platform": "17077", "taxon": "Homo sapiens", "title": "Atherosclerotic and control peripheral artery gene expression", "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:GSE159677", "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=GSE159677", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE159677", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4837523", "GSM4837524", "GSM4837525", "GSM4837526", "GSM4837527", "GSM4837528"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "18573", "taxon": "Homo sapiens", "title": "Decoding the transcriptome of calcified atherosclerotic plaque at single-cell resolution", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE43292", "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=GSE43292", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE43292", "version": null, "note": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1060117", "GSM1060118", "GSM1060119", "GSM1060120", "GSM1060121", "GSM1060122", "GSM1060123", "GSM1060124", "GSM1060125", "GSM1060126", "GSM1060127", "GSM1060128", "GSM1060129", "GSM1060130", "GSM1060131", "GSM1060132", "GSM1060133", "GSM1060134", "GSM1060135", "GSM1060136", "GSM1060137", "GSM1060138", "GSM1060139", "GSM1060140", "GSM1060141", "GSM1060142", "GSM1060143", "GSM1060144", "GSM1060145", "GSM1060146", "GSM1060147", "GSM1060148", "GSM1060149", "GSM1060150", "GSM1060151", "GSM1060152", "GSM1060153", "GSM1060154", "GSM1060155", "GSM1060156", "GSM1060157", "GSM1060158", "GSM1060159", "GSM1060160", "GSM1060161", "GSM1060162", "GSM1060163", "GSM1060164", "GSM1060165", "GSM1060166", "GSM1060167", "GSM1060168", "GSM1060169", "GSM1060170", "GSM1060171", "GSM1060172", "GSM1060173", "GSM1060174", "GSM1060175", "GSM1060176", "GSM1060177", "GSM1060178", "GSM1060179", "GSM1060180"], "sample_count": 64, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Genome-wide expression study of human carotid atheroma", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE100927 not downloaded", "asset:data:geo:GSE100927 licence not read", "asset:data:geo:GSE159677 not downloaded", "asset:data:geo:GSE159677 licence not read", "asset:data:geo:GSE43292 not downloaded", "asset:data:geo:GSE43292 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "One-way analysis of variance (ANOVA) and t-tests were employed to explore potential significant differences in atherosclerosis model genes, functional enrichment results, immune cell infiltration, and immune function scores among the patient groups."}}, {"id": "method-2", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "principal component analysis"}}, {"id": "method-3", "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": 0.8, "band": "high", "quote": "limma"}}, {"id": "method-4", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.7, "band": "medium", "quote": "logistic regression"}}, {"id": "method-5", "family": "clustering", "specific": "kmeans", "label": "Clustering", "dsl_operations": ["kmeans_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "k-means"}}, {"id": "method-6", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "Protein-Protein Interaction"}}], "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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["GSE100927", "GSE43292", "GSE159677"], "resolved_accessions": ["GSE100927", "GSE43292", "GSE159677"], "statements": ["The original contributions presented in the study are included in the article/Supplementary Material, further inquiries can be directed to the corresponding authors."], "basis": "The paper names GSE100927, GSE43292, GSE159677 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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:39660117", "data:geo:GSE100927"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE100927"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:41:34Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 15655, "completion_tokens": 2321, "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:39660117", "type": "paper", "label": "pmid:39660117"}, {"id": "source:pmid:39660117", "type": "manuscript", "label": "PMID 39660117 full text"}, {"id": "data:geo:GSE100927", "type": "dataset", "label": "GEO GSE100927"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39660117", "type": "paper", "label": "pmid:39660117"}, {"id": "source:pmid:39660117", "type": "manuscript", "label": "PMID 39660117 full text"}, {"id": "data:geo:GSE100927", "type": "dataset", "label": "GEO GSE100927"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39660117", "type": "extraction", "used": ["source:pmid:39660117"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE100927", "type": "accession_resolution", "used": ["data:geo:GSE100927"], "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:39660117", "parent_hash": "sha256:70984a7dab0cc78249a9988c64b3876abaddec2a11786a30bd6cd8e090a8f6e6", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE100927 licence not read", "asset:data:geo:GSE100927 not downloaded", "asset:data:geo:GSE159677 licence not read", "asset:data:geo:GSE159677 not downloaded", "asset:data:geo:GSE43292 licence not read", "asset:data:geo:GSE43292 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Multi-modal transcriptomics: integrating machine learning and convolutio", "g. Supplementary Figure S2Quality control of transcriptome data. (A) boxplot of intergroup batch effect", "cells, 33,538 genes), examining single-cell transcriptomes of calcified atherosclerotic core plaques an", "dataset. This dataset comprises single-cell RNA-seq data derived from three atherosclerotic core"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "data_generation", "definition_id": "scrna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "unsupported", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["he GSE159677 dataset. This dataset comprises single-cell RNA-seq data derived from three atherosclerotic core", "al Supplementary Figure S1Quality control of scRNA-seq data (A) Expression of scRNA-seq data before", "control of scRNA-seq data (A) Expression of scRNA-seq data before quality control. (A) Each point", "e total UMIs in each cell; (B) Expression of scRNA-seq data after quality control; (C) UMIs vs. sca"], "order_basis": "paper_text_order:3790", "id": "assay:2"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["One-way analysis of variance (ANOVA) and t-tests were employed to explore potential significant differences in atherosclerosis model genes, functional enrichment results, immune cell infiltration, and immune function scores among the patient groups."], "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":"2026-11-04T01:50:28+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}}}