{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40307356", "kind": "science-record", "revision": 3, "content_hash": "sha256:a654f46555b0e493640cdcdb9ec29829b59af1adcab4adf5e3b6b5676913ba59", "created_at": "2026-11-01T20:30:27Z", "updated_at": "2026-11-01T22:13:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Integrated bioinformatics analysis of biomarkers and pathways to explore the mechanisms and molecular targets related to allergic rhinitis and pyroptosis.", "doi": "10.1038/s41598-025-99955-0", "pmid": "40307356", "authors": ["Mingai You", "Fangrui Liu", "Youshijie Cai", "Guodong Yu"], "journal": "Scientific reports", "year": 2025, "abstract": "Allergic rhinitis (AR) is a condition with a rising global prevalence, though its specific pathogenic mechanisms remain elusive. Several studies have indicated that pyroptosis is one of the key mechanisms in the pathogenesis of AR. However, no research has investigated the molecular targets of pyroptosis in the context of AR. Our study endeavored to identify common biomarkers and mechanisms that could offer insights into the prevention of AR progression and novel therapeutic targets. Data from the Gene Expression Omnibus (GEO) database, including GSE51392, GSE43523, and GSE44037, were downloaded and analyzed through weighted gene co-expression network analysis (WGCNA), Least Absolute Shrinkage and Selection Operator (LASSO), and random forest (RF) analysis to identify key intersecting genes associated with both AR and pyroptosis. The gene GZMA was identified as a significant candidate and was validated in another sample dataset (GSE101720). Western blot (WB) analysis confirmed the expression of GZMA in an AR mouse model. Gene Ontology (GO) analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis were conducted to explore the functional roles of the shared genes. An immune infiltration matrix was established using CIBERSORT analysis to estimate the degree of immune cell infiltration in AR. Single-sample Gene Set Enrichment Analysis (ssGSEA) was performed to analyze the biological functions of hub genes. In the immune infiltration matrix of AR, a reduced expression of Tregs was observed in the AR group. WB analysis further indicated elevated expression of GZMA in the AR group. As a gene related to both AR and pyroptosis, GZMA expression was positively correlated with the gene expression levels of CD8 + T cells. The reduction in Tregs and the increase in CD8 + T cells in AR, along with enhanced pyroptosis, contribute to the development of allergic inflammation. Therefore, it was hypothesized that GZMA could serve as a novel target for the prevention and treatment of AR.", "claims": [{"id": "claim-method", "statement": "The ROC curve was generated via the pROC package 1.18.5.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40307356", "locator": "sections[7] \"Analysis of PRG expression and ROC validation\" paragraph 2", "quote": "The ROC curve was generated via the pROC package 1.18.5."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data sets supporting the results of this article are included within the article and its additional files.The datasets analyzed during the current study are available in the GEO repository at www.ncbi.nlm.nih.gov/geo/ (accession number: GSE43523, GSE44037, GSE51392, and GSE101720) (accessed on 2024.09.12).The GeneCards database was searched for pyroptosis at https://www.genecards.org (accessed on 2024.08.09).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40307356", "locator": "sections[32] \"Data availability\" paragraph 2", "quote": "The data sets supporting the results of this article are included within the article and its additional files.The datasets analyzed during the current study are available in the GEO repository at www.ncbi.nlm.nih.gov/geo/ (accession number: GSE43523, GSE44037, GSE51392, and GSE101720) (accessed on 2024.09.12).The GeneCards database was searched for pyroptosis at https://www.genecards.org (accessed on 2024.08.09)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "GZMA was identified as a potential biomarker and novel therapeutic target for allergic rhinitis.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40307356", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The gene GZMA was identified as a significant candidate and was validated in another sample dataset (GSE101720)."}, {"asset": "source:pmid:40307356", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "As a gene related to both AR and pyroptosis, GZMA expression was positively correlated with the gene expression levels of CD8 + T cells."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "GZMA was identified as a potential biomarker and novel therapeutic target for allergic rhinitis.", "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:40307356"], "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:GSE43523"], "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:GSE43523"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40307356", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-025-99955-0", "sha256": "sha256:656b8460d9c0dacce2ab1495bd4520e152a6ebad8c660b8d61259437e9f9abff", "bytes": 52654, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-025-99955-0", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12043997", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE43523", "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=GSE43523", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE43523", "version": null, "note": "The data sets supporting the results of this article are included within the article and its additional files.The datasets analyzed during the current study are available in the GEO repository at www.ncbi.nlm.nih.gov/geo/ (accession number: GSE43523, GSE44037, GSE51392, and GSE101720) (accessed on 2024.09.12).The GeneCards database was searched for pyroptosis at https://www.genecards.org (accessed on 2024.08.09).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data sets supporting the results of this article are included within the article and its additional files.The datasets analyzed during the current study are available in the GEO repository at www.ncbi.nlm.nih.gov/geo/ (accession number: GSE43523, GSE44037, GSE51392, and GSE101720) (accessed on 2024.09.12).The GeneCards database was searched for pyroptosis at https://www.genecards.org (accessed on 2024.08.09).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1064882", "GSM1064883", "GSM1064884", "GSM1064885", "GSM1064886", "GSM1064887", "GSM1064888", "GSM1064889", "GSM1064890", "GSM1064891", "GSM1064892", "GSM1064893"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "6883", "taxon": "Homo sapiens", "title": "Global gene expression of nasal epithelial cells in patients with seasonal allergic rhinitis", "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:GSE44037", "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=GSE44037", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE44037", "version": null, "note": "The data sets supporting the results of this article are included within the article and its additional files.The datasets analyzed during the current study are available in the GEO repository at www.ncbi.nlm.nih.gov/geo/ (accession number: GSE43523, GSE44037, GSE51392, and GSE101720) (accessed on 2024.09.12).The GeneCards database was searched for pyroptosis at https://www.genecards.org (accessed on 2024.08.09).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data sets supporting the results of this article are included within the article and its additional files.The datasets analyzed during the current study are available in the GEO repository at www.ncbi.nlm.nih.gov/geo/ (accession number: GSE43523, GSE44037, GSE51392, and GSE101720) (accessed on 2024.09.12).The GeneCards database was searched for pyroptosis at https://www.genecards.org (accessed on 2024.08.09).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1077128", "GSM1077129", "GSM1077130", "GSM1077131", "GSM1077132", "GSM1077133", "GSM1077134", "GSM1077135", "GSM1077136", "GSM1077137", "GSM1077138", "GSM1077139", "GSM1077140", "GSM1077141", "GSM1077142", "GSM1077143", "GSM1077144", "GSM1077145", "GSM1077146", "GSM1077147", "GSM1077148", "GSM1077149", "GSM1077150", "GSM1077151", "GSM1077152", "GSM1077153", "GSM1077154", "GSM1077155", "GSM1077156", "GSM1077157", "GSM1077158", "GSM1077159", "GSM1077160", "GSM1077161"], "sample_count": 34, "group_sizes": null, "group_sizes_basis": null, "platform": "13158", "taxon": "Homo sapiens", "title": "Expression data from airway epithelial cells from patients with asthma, rhinitis, and helathy controls", "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:GSE51392", "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=GSE51392", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE51392", "version": null, "note": "The data sets supporting the results of this article are included within the article and its additional files.The datasets analyzed during the current study are available in the GEO repository at www.ncbi.nlm.nih.gov/geo/ (accession number: GSE43523, GSE44037, GSE51392, and GSE101720) (accessed on 2024.09.12).The GeneCards database was searched for pyroptosis at https://www.genecards.org (accessed on 2024.08.09).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data sets supporting the results of this article are included within the article and its additional files.The datasets analyzed during the current study are available in the GEO repository at www.ncbi.nlm.nih.gov/geo/ (accession number: GSE43523, GSE44037, GSE51392, and GSE101720) (accessed on 2024.09.12).The GeneCards database was searched for pyroptosis at https://www.genecards.org (accessed on 2024.08.09).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1244586", "GSM1244587", "GSM1244588", "GSM1244589", "GSM1244590", "GSM1244591", "GSM1244592", "GSM1244593", "GSM1244594", "GSM1244595", "GSM1244596", "GSM1244597", "GSM1244598", "GSM1244599", "GSM1244600", "GSM1244601", "GSM1244602", "GSM1244603", "GSM1244604", "GSM1244605", "GSM1244606", "GSM1244607", "GSM1244608", "GSM1244609", "GSM1244610", "GSM1244611", "GSM1244612", "GSM1244613", "GSM1244614", "GSM1244615", "GSM1244616", "GSM1244617", "GSM1244618", "GSM1244619", "GSM1244620", "GSM1244621", "GSM1244622", "GSM1244623", "GSM1244624", "GSM1244625", "GSM1244626", "GSM1244627", "GSM1244628", "GSM1244629", "GSM1244630", "GSM1244631", "GSM1244632", "GSM1244633", "GSM1244634", "GSM1244635", "GSM1244636", "GSM1244637", "GSM1244638", "GSM1244639", "GSM1244640", "GSM1244641", "GSM1244642", "GSM1244643", "GSM1244644", "GSM1244645", "GSM1244646", "GSM1244647", "GSM1244648", "GSM1244649", "GSM1244650", "GSM1244651", "GSM1244652", "GSM1244653"], "sample_count": 68, "group_sizes": null, "group_sizes_basis": null, "platform": "13158", "taxon": "Homo sapiens", "title": "Expression data from airway epithelial cells stimulated with Poly(I:C) from patients with asthma, rhinitis, and healthy controls", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE43523 not downloaded", "asset:data:geo:GSE43523 licence not read", "asset:data:geo:GSE44037 not downloaded", "asset:data:geo:GSE44037 licence not read", "asset:data:geo:GSE51392 not downloaded", "asset:data:geo:GSE51392 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": "PCA"}}, {"id": "method-2", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "random forest"}}, {"id": "method-3", "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-4", "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": 0.8, "band": "high", "quote": "ROC curve"}}, {"id": "method-5", "family": null, "specific": null, "label": "Receiver operating characteristic curve analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The ROC curve was generated via the pROC package 1.18.5."}}], "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": ["pca_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pca."}, "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": ["GSE43523", "GSE44037", "GSE51392", "and GSE101720"], "resolved_accessions": ["GSE43523", "GSE44037", "GSE51392"], "statements": ["The data sets supporting the results of this article are included within the article and its additional files.The datasets analyzed during the current study are available in the GEO repository at www.ncbi.nlm.nih.gov/geo/ (accession number: GSE43523, GSE44037, GSE51392, and GSE101720) (accessed on 2024.09.12).The GeneCards database was searched for pyroptosis at https://www.genecards.org (accessed on 2024.08.09)."], "basis": "The paper names GSE43523, GSE44037, GSE51392 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": ["pca_fit"], "assets": ["source:pmid:40307356", "data:geo:GSE43523"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE43523"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:51:22Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14854, "completion_tokens": 1473, "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:40307356", "type": "paper", "label": "pmid:40307356"}, {"id": "source:pmid:40307356", "type": "manuscript", "label": "PMID 40307356 full text"}, {"id": "data:geo:GSE43523", "type": "dataset", "label": "GEO GSE43523"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40307356", "type": "paper", "label": "pmid:40307356"}, {"id": "source:pmid:40307356", "type": "manuscript", "label": "PMID 40307356 full text"}, {"id": "data:geo:GSE43523", "type": "dataset", "label": "GEO GSE43523"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40307356", "type": "extraction", "used": ["source:pmid:40307356"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE43523", "type": "accession_resolution", "used": ["data:geo:GSE43523"], "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:40307356", "parent_hash": "sha256:dc00ee4ab2dbb84ee0fd7323960b41bfc8c041cfd9ba0a00c8c6d830103884c2", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE43523 licence not read", "asset:data:geo:GSE43523 not downloaded", "asset:data:geo:GSE44037 licence not read", "asset:data:geo:GSE44037 not downloaded", "asset:data:geo:GSE51392 licence not read", "asset:data:geo:GSE51392 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["dated in another sample dataset (GSE101720). Western blot (WB) analysis confirmed the expression of GZ"], "order_basis": "paper_text_order:1065", "id": "assay:1"}, {"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": ["is confirmed the expression of GZMA in an AR mouse model. Gene Ontology (GO) analysis and Kyoto Encyc", "is confirmed the expression of GZMA in an AR mouse model. Gene Ontology (GO) analysis and Kyoto"], "order_basis": "paper_text_order:1134", "id": "assay:2"}, {"role": "analysis", "definition_id": "principal_component_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pca_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["PCA"], "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":"2026-11-04T00:30:55+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}}}