{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40951447", "kind": "science-record", "revision": 3, "content_hash": "sha256:25fa610cee47ef8de14bd985176b00cc945cc43d15369d1b0eaa48c3838a3e9c", "created_at": "2026-11-01T20:31:02Z", "updated_at": "2026-11-01T22:14:42Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Novel Biomarkers Associated with Corticosteroid Resistance in Asthma by Bioinformatics Analysis and Experimental Validation.", "doi": "10.2147/JIR.S527640", "pmid": "40951447", "authors": ["Lingling Xuan", "Lulu Ren", "Wen Zhang", "Zhuoling An"], "journal": "Journal of inflammation research", "year": 2025, "abstract": "Background: Corticosteroid resistance in asthma, marked by reduced glucocorticoid response, is significantly influenced by cigarette smoke (CS). We sought to explore potential novel biomarkers and therapeutic targets associated with CS-induced corticosteroid resistance in asthma.\nMethods: GSE230048 (related to corticosteroid resistance) and GSE13896 (from CS-exposed macrophages) were obtained from GEO. Initially, we performed differential gene expression analysis and weighted gene co-expression network analysis (WGCNA) to discover key genes involved in corticosteroid resistance in asthma. Gene Ontology (GO) term and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses were conducted. Receiver operating characteristic (ROC) analysis was used to assess the diagnostic accuracy of these markers. CIBERSORT was applied to clarify immune cell infiltration. Expression of the key biomarker was validated in asthma patients and asthma murine models.\nResults: Five overlapping genes upregulated in corticosteroid-resistant asthma patients and smokers' alveolar macrophages were identified. Subsequently, using WGCNA, the most relevant modules were identified and intersected with differentially expressed genes. Tensin 1 (TNS1), ATP-binding cassette subfamily C member 4 (ABCC4), and TNF receptor superfamily member 21 (TNFRSF21) were identified as critical biomarkers for corticosteroid resistance in asthma. ROC analysis showed an AUC of 0.718 for the three-marker combination. Single-cell RNA sequencing confirmed their expression in macrophages from asthmatic patients. Elevated levels of TNS1, ABCC4, TNFRSF21, and M2 macrophage markers (CD301 and CD206) were observed in CS-exposed murine lung tissues and CS condensate-treated Raw264.7 cells. TNS1 knockdown significantly reduced CD301 and CD206 expression, suggesting its role in promoting macrophage M2 polarization.\nConclusion: In conclusion, we identified three hub genes (TNS1, ABCC4, and TNFRSF21) associated with CS-induced corticosteroid resistance in asthma. Additionally, TNS1 may be involved in CS-induced corticosteroid resistance in asthma by promoting macrophage M2 polarization.", "claims": [{"id": "claim-method", "statement": "We used the online analysis tool GEO2R to screen the differential genes in dataset GSE230048 and dataset GSE13896.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40951447", "locator": "sections[5] \"Identification of Differentially Expressed Genes (DEGs)\" paragraph 2", "quote": "We used the online analysis tool GEO2R to screen the differential genes in dataset GSE230048 and dataset GSE13896."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data are available from the corresponding author on request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40951447", "locator": "sections[29] \"Data Sharing Statement\" paragraph 2", "quote": "Data are available from the corresponding author on request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Differential-expression and weighted gene co-expression analyses identified TNS1, ABCC4, and TNFRSF21 as critical biomarkers associated with cigarette-smoke-induced corticosteroid resistance in asthma.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40951447", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "Tensin 1 (TNS1), ATP-binding cassette subfamily C member 4 (ABCC4), and TNF receptor superfamily member 21 (TNFRSF21) were identified as critical biomarkers for corticosteroid resistance in asthma."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Differential-expression and weighted gene co-expression analyses identified TNS1, ABCC4, and TNFRSF21 as critical biomarkers associated with cigarette-smoke-induced corticosteroid resistance in asthma.", "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:40951447"], "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:GSE13896"], "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:GSE13896"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40951447", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/JIR.S527640", "sha256": "sha256:14a454ae6a3b05108942a123a9663240d29c56acb74e5af32aaca79c286325c1", "bytes": 60131, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/JIR.S527640", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12433222", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE13896", "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=GSE13896", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE13896", "version": null, "note": "Data are available from the corresponding author on request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available from the corresponding author on request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM219241", "GSM219242", "GSM219243", "GSM219244", "GSM219245", "GSM219246", "GSM219247", "GSM219248", "GSM219249", "GSM219250", "GSM219251", "GSM219252", "GSM219253", "GSM219254", "GSM219256", "GSM219257", "GSM219258", "GSM219259", "GSM219260", "GSM219261", "GSM219262", "GSM219263", "GSM219264", "GSM349912", "GSM349913", "GSM349914", "GSM349915", "GSM349916", "GSM349917", "GSM349918", "GSM349919", "GSM349920", "GSM349921", "GSM349922", "GSM349923", "GSM349924", "GSM349925", "GSM349926", "GSM349927", "GSM349928", "GSM349929", "GSM349930", "GSM349931", "GSM349932", "GSM349933", "GSM349934", "GSM349935", "GSM349936", "GSM349937", "GSM349938", "GSM349939", "GSM349940", "GSM349941", "GSM349942", "GSM349943", "GSM349944", "GSM349945", "GSM349946", "GSM349947", "GSM349948", "GSM349949", "GSM349950", "GSM349951", "GSM349952", "GSM349953", "GSM349954", "GSM349955", "GSM349956", "GSM349957", "GSM349958"], "sample_count": 70, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Smoking-dependent Reprogramming of Alveolar Macrophage Polarization: Implication for Pathogenesis of COPD", "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:GSE230048", "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=GSE230048", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE230048", "version": null, "note": "Data are available from the corresponding author on request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available from the corresponding author on request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM7184431", "GSM7184432", "GSM7184433", "GSM7184434", "GSM7184435", "GSM7184436", "GSM7184437", "GSM7184438", "GSM7184439", "GSM7184440", "GSM7184441", "GSM7184442", "GSM7184443", "GSM7184444", "GSM7184445", "GSM7184446", "GSM7184447", "GSM7184448", "GSM7184449", "GSM7184450", "GSM7184451", "GSM7184452", "GSM7184453", "GSM7184454", "GSM7184455", "GSM7184456", "GSM7184457", "GSM7184458", "GSM7184459", "GSM7184460", "GSM7184461", "GSM7184462", "GSM7184463", "GSM7184464", "GSM7184465", "GSM7184466", "GSM7184467", "GSM7184468", "GSM7184469", "GSM7184470", "GSM7184471", "GSM7184472", "GSM7184473", "GSM7184474", "GSM7184475", "GSM7184476", "GSM7184477", "GSM7184478", "GSM7184479", "GSM7184480", "GSM7184481", "GSM7184482", "GSM7184483", "GSM7184484", "GSM7184485", "GSM7184486", "GSM7184487", "GSM7184488", "GSM7184489", "GSM7184490", "GSM7184491", "GSM7184492", "GSM7184493", "GSM7184494", "GSM7184495", "GSM7184496", "GSM7184497", "GSM7184498", "GSM7184499", "GSM7184500", "GSM7184501", "GSM7184502", "GSM7184503", "GSM7184504", "GSM7184505", "GSM7184506", "GSM7184507", "GSM7184508", "GSM7184509", "GSM7184510", "GSM7184511", "GSM7184512", "GSM7184513", "GSM7184514", "GSM7184515", "GSM7184516", "GSM7184517", "GSM7184518"], "sample_count": 88, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "Gene expression profiling of whole blood and peripheral neutrophils from asthma.", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE27002", "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=GSE27002", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE27002", "version": null, "note": "Data are available from the corresponding author on request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available from the corresponding author on request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM665104", "GSM665105", "GSM665106", "GSM665107", "GSM665108", "GSM665109", "GSM665110", "GSM665111", "GSM665112", "GSM665113", "GSM665114", "GSM665115", "GSM665116", "GSM665117", "GSM665118", "GSM665119", "GSM665120", "GSM665121", "GSM665122", "GSM665123", "GSM665124", "GSM665125", "GSM665126"], "sample_count": 23, "group_sizes": null, "group_sizes_basis": null, "platform": "5175", "taxon": "Homo sapiens", "title": "Chronic Cigarette Smoke Exposure Results in Coordinated Methylation and Gene Expression Changes in Human Alveolar Macrophages", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE74986", "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=GSE74986", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE74986", "version": null, "note": "Data are available from the corresponding author on request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available from the corresponding author on request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1939699", "GSM1939700", "GSM1939701", "GSM1939702", "GSM1939703", "GSM1939704", "GSM1939705", "GSM1939706", "GSM1939707", "GSM1939708", "GSM1939709", "GSM1939710", "GSM1939711", "GSM1939712", "GSM1939713", "GSM1939714", "GSM1939715", "GSM1939716", "GSM1939717", "GSM1939718", "GSM1939719", "GSM1939720", "GSM1939721", "GSM1939722", "GSM1939723", "GSM1939724", "GSM1939725", "GSM1939726", "GSM1939727", "GSM1939728", "GSM1939729", "GSM1939730", "GSM1939731", "GSM1939732", "GSM1939733", "GSM1939734", "GSM1939735", "GSM1939736", "GSM1939737", "GSM1939738", "GSM1939739", "GSM1939740", "GSM1939741", "GSM1939742", "GSM1939743", "GSM1939744", "GSM1939745", "GSM1939746", "GSM1939747", "GSM1939748", "GSM1939749", "GSM1939750", "GSM1939751", "GSM1939752", "GSM1939753", "GSM1939754", "GSM1939755", "GSM1939756", "GSM1939757", "GSM1939758", "GSM1939759", "GSM1939760", "GSM1939761", "GSM1939762", "GSM1939763", "GSM1939764", "GSM1939765", "GSM1939766", "GSM1939767", "GSM1939768", "GSM1939769", "GSM1939770", "GSM1939771", "GSM1939772", "GSM1939773", "GSM1939774", "GSM1939775", "GSM1939776", "GSM1939777", "GSM1939778", "GSM1939779", "GSM1939780", "GSM1939781", "GSM1939782", "GSM1939783", "GSM1939784"], "sample_count": 86, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Analysis of gene expression in human Bronchial Alveolar Lavage Cell (BAL) cell pellets", "resolution_checked_at": "2026-11-01T18:06:44Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE13896 not downloaded", "asset:data:geo:GSE13896 licence not read", "asset:data:geo:GSE230048 not downloaded", "asset:data:geo:GSE230048 licence not read", "asset:data:geo:GSE27002 not downloaded", "asset:data:geo:GSE27002 licence not read", "asset:data:geo:GSE74986 not downloaded", "asset:data:geo:GSE74986 licence not read"]}, "analysis": {"state": "partial", "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": 0.8, "band": "high", "quote": "ANOVA"}}, {"id": "method-2", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "pathway enrichment"}}, {"id": "method-3", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.7, "band": "medium", "quote": "ROC analysis"}}, {"id": "method-4", "family": null, "specific": null, "label": "GEO2R differential gene expression analysis and weighted gene co-expression network analysis (WGCNA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We used the online analysis tool GEO2R to screen the differential genes in dataset GSE230048 and dataset GSE13896."}}], "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": ["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": ["GSE230048", "GSE13896", "GSE27002", "GSE74986"], "resolved_accessions": ["GSE230048", "GSE13896", "GSE27002", "GSE74986"], "statements": ["Data are available from the corresponding author on request."], "basis": "The paper names GSE230048, GSE13896, GSE27002, GSE74986 in 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:40951447", "data:geo:GSE13896"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE13896"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:01:30Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 15374, "completion_tokens": 1570, "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:40951447", "type": "paper", "label": "pmid:40951447"}, {"id": "source:pmid:40951447", "type": "manuscript", "label": "PMID 40951447 full text"}, {"id": "data:geo:GSE13896", "type": "dataset", "label": "GEO GSE13896"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40951447", "type": "paper", "label": "pmid:40951447"}, {"id": "source:pmid:40951447", "type": "manuscript", "label": "PMID 40951447 full text"}, {"id": "data:geo:GSE13896", "type": "dataset", "label": "GEO GSE13896"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40951447", "type": "extraction", "used": ["source:pmid:40951447"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE13896", "type": "accession_resolution", "used": ["data:geo:GSE13896"], "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:40951447", "parent_hash": "sha256:c2feec038852fbf4ec1f22d2565f53f017acbcebd1ac72266d0ba6d2ad79f4c7", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE13896 licence not read", "asset:data:geo:GSE13896 not downloaded", "asset:data:geo:GSE230048 licence not read", "asset:data:geo:GSE230048 not downloaded", "asset:data:geo:GSE27002 licence not read", "asset:data:geo:GSE27002 not downloaded", "asset:data:geo:GSE74986 licence not read", "asset:data:geo:GSE74986 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["was validated in asthma patients and asthma murine models. Results: Five overlapping genes upre", "CD301 and CD206) were observed in CS-exposed murine lung tissues and CS condensate-treated Raw26", "ients and in Corticosteroid-Resistant Asthma Murine Models Data from the Human Protein Atlas sho", "oid resistance in asthma, OVA-induced asthma mice were exposed to CS as detailed in methods. sRaw w"], "order_basis": "paper_text_order:1059", "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": ["C of 0.718 for the three-marker combination. Single-cell RNA sequencing confirmed their expression in macrophages fr", "the UMAP plot. Major cell types captured by single-cell RNA sequencing included monocytes, natural killer (NK) cell"], "order_basis": "paper_text_order:1602", "id": "assay:2"}, {"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": ["or the three-marker combination. Single-cell RNA sequencing confirmed their expression in macrophages fr", "ot. Major cell types captured by single-cell RNA sequencing included monocytes, natural killer (NK) cell"], "order_basis": "paper_text_order:1614", "id": "assay:3"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.85, "evidence": ["d CS condensate-treated Raw264.7 cells. TNS1 knockdown significantly reduced CD301 and CD206 expres"], "order_basis": "paper_text_order:1877", "id": "assay:4"}, {"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": ["ed corticosteroid-resistant murine models by RT-qPCR. CS exposure increased TNS1, ABCC4 and TNFRS", "corticosteroid-resistant murine models by RT-qPCR. CS exposure increased TNS1, ABCC4 and TNFRS"], "order_basis": "paper_text_order:8932", "id": "assay:5"}, {"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": 0.8, "evidence": ["ANOVA"], "order_basis": "consumes_earlier_output", "id": "assay:6"}]},"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":"2026-11-04T01:34:43+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}}}