{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40949741", "kind": "science-record", "revision": 4, "content_hash": "sha256:5bb4efd57f2e7dfb97a6cefed4ab8a8221006099b4ade594a25cb4ee9963ffe0", "created_at": "2026-11-01T20:31:02Z", "updated_at": "2026-11-01T22:57:10Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Exploring differential gene expression and biomarker potential in systemic lupus erythematosus: a retrospective study.", "doi": "10.7717/peerj.19891", "pmid": "40949741", "authors": ["Jie Xiao", "Yuhong Luo", "Lina Duan", "Xinru Mao", "Lingyue Jin", "Haifang Wang", "Hongxia Wang", "Jie Pan", "Ying Gong", "Haixia Li"], "journal": "PeerJ", "year": 2025, "abstract": "Background: Systemic lupus erythematosus (SLE) is a chronic autoimmune disease characterized by inflammation and immune-mediated multi-organ system damage, accompanied by clinical manifestations such as fever, hair loss, skin rash, oral ulcers, and joint pain and swelling. SLE has been reported to affect more than 3.4 million people worldwide, of which approximately 90% are women.\nPurpose: This study aims to identify and characterize key hub genes implicated in SLE through comprehensive bioinformatics analyses, providing a theoretical foundation for the development of more effective therapeutic strategies.\nMethods: Two datasets were procured from the Gene Expression Omnibus (GEO) database: GSE13887 and GSE10325. Differentially expressed genes (DEGs) were identified and subjected to functional enrichment analysis, protein-protein interaction (PPI) network construction, and receiver operating characteristic (ROC) curve analysis to evaluate potential hub genes. The top 20 significantly upregulated and downregulated DEGs, alongside the top 15 enriched Gene Ontology (GO) terms and five Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways, were screened from both datasets. Quantitative real-time PCR (RT-q PCR) was utilized to validate hub gene expression in CD3 + T cells from peripheral blood samples of SLE patients. Concurrently, flow cytometry was employed to quantify inflammatory cytokines in peripheral blood samples.\nResults: Bioinformatics analyses identified 1,912 DEGs in GSE13887 and 52 DEGs in GSE10325, with eight DEGs common to both datasets. Functional enrichment analysis underscored critical biological processes, notably cell-mediated cytotoxicity and cell killing. PPI network and enrichment analyses highlighted seven hub genes, among which FCER1A and RGS1 demonstrated consistent expression trends across datasets and clinical samples-FCER1A was significantly downregulated, while RGS1 was upregulated in SLE patients. ROC curve analysis confirmed their strong diagnostic potential (AUC > 0.7). Principal component analysis (PCA) further highlighted distinct gene expression profiles differentiating SLE patients from healthy controls. Clinical validation via RT-q PCR and flow cytometry corroborated these findings, demonstrating decreased FCER1A expression and increased RGS1 expression in CD3 + T cells from SLE patients. Moreover, elevated plasma levels of IL-6 and TNF-α, coupled with diminished IL-10 levels, were observed in SLE patients. These findings suggest that FCER1A and RGS1 are promising biomarkers for SLE diagnosis.\nConclusions: FCER1A and RGS1 are significantly associated with SLE and serve as potential biomarkers for distinguishing SLE patients from healthy individuals. Their involvement in SLE pathogenesis underscores their potential as targets for future diagnostic and therapeutic interventions.", "claims": [{"id": "claim-method", "statement": "Differentially expressed genes (DEGs) between SLE and HCs were identified using the limma package (version 3.64.1) in R (version 4.2.1).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40949741", "locator": "sections[5] \"Identification of differentially expressed genes\" paragraph 2", "quote": "Differentially expressed genes (DEGs) between SLE and HCs were identified using the limma package (version 3.64.1) in R (version 4.2.1)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Raw data is available in the Supplemental Files.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40949741", "locator": "sections[30] \"Data Availability\" paragraph 2", "quote": "Raw data is available in the Supplemental Files."}], "state": "complete"}, {"id": "claim-target-result", "statement": "FCER1A was significantly downregulated and RGS1 was upregulated in SLE patients, and both showed strong diagnostic potential with AUC values exceeding 0.7.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40949741", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "PPI network and enrichment analyses highlighted seven hub genes, among which FCER1A and RGS1 demonstrated consistent expression trends across datasets and clinical samples—FCER1A was significantly downregulated, while RGS1 was upregulated in SLE patients."}, {"asset": "source:pmid:40949741", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "ROC curve analysis confirmed their strong diagnostic potential (AUC > 0.7)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "FCER1A was significantly downregulated and RGS1 was upregulated in SLE patients, and both showed strong diagnostic potential with AUC values exceeding 0.7.", "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:40949741"], "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:GSE10325"], "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": {"fdr_threshold": "ed by adjusted p-value (false discovery rate) < 0"}, "inputs": ["data:geo:GSE10325"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40949741", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.19891", "sha256": "sha256:ce68025b4a73620b53eb09acd2847271779947fd803847da6c2f50ade75a326b", "bytes": 66646, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.19891", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12424612", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE10325", "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=GSE10325", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE10325", "version": null, "note": "Raw data is available in the Supplemental Files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw data is available in the Supplemental Files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM260886", "GSM260887", "GSM260888", "GSM260889", "GSM260890", "GSM260891", "GSM260892", "GSM260893", "GSM260894", "GSM260895", "GSM260896", "GSM260897", "GSM260898", "GSM260899", "GSM260900", "GSM260901", "GSM260902", "GSM260903", "GSM260904", "GSM260905", "GSM260906", "GSM260907", "GSM260908", "GSM260909", "GSM260910", "GSM260911", "GSM260912", "GSM260913", "GSM260914", "GSM260915", "GSM260916", "GSM260917", "GSM260918", "GSM260919", "GSM260920", "GSM260921", "GSM260922", "GSM260923", "GSM260924", "GSM260925", "GSM260926", "GSM260927", "GSM260928", "GSM260929", "GSM260930", "GSM260931", "GSM260932", "GSM260933", "GSM260934", "GSM260935", "GSM260936", "GSM260937", "GSM260938", "GSM260939", "GSM260940", "GSM260941", "GSM260942", "GSM260943", "GSM260944", "GSM260945", "GSM260946", "GSM260947", "GSM260948", "GSM260949", "GSM260950", "GSM260951", "GSM260952"], "sample_count": 67, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Expression data from human peripheral blood subsets", "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:GSE13887", "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=GSE13887", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE13887", "version": null, "note": "Raw data is available in the Supplemental Files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw data is available in the Supplemental Files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM349725", "GSM349727", "GSM349729", "GSM349730", "GSM349731", "GSM349733", "GSM349734", "GSM349736", "GSM349737", "GSM349739", "GSM349740", "GSM349741", "GSM349742", "GSM349743", "GSM349744", "GSM349745", "GSM349746", "GSM349747", "GSM349748", "GSM349749", "GSM349764", "GSM349765", "GSM349766", "GSM349767", "GSM349768", "GSM349769", "GSM349770"], "sample_count": 27, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Activation of mTOR controls the loss of TCRζ in lupus T cells through HRES-1/Rab4-regulated lysosomal degradation", "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:GSE61635", "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=GSE61635", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE61635", "version": null, "note": "Raw data is available in the Supplemental Files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw data is available in the Supplemental Files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1509610", "GSM1509611", "GSM1509612", "GSM1509613", "GSM1509614", "GSM1509615", "GSM1509616", "GSM1509617", "GSM1509618", "GSM1509619", "GSM1509620", "GSM1509621", "GSM1509622", "GSM1509623", "GSM1509624", "GSM1509625", "GSM1509626", "GSM1509627", "GSM1509628", "GSM1509629", "GSM1509630", "GSM1509631", "GSM1509632", "GSM1509633", "GSM1509634", "GSM1509635", "GSM1509636", "GSM1509637", "GSM1509638", "GSM1509639", "GSM1509640", "GSM1509641", "GSM1509642", "GSM1509643", "GSM1509644", "GSM1509645", "GSM1509646", "GSM1509647", "GSM1509648", "GSM1509649", "GSM1509650", "GSM1509651", "GSM1509652", "GSM1509653", "GSM1509654", "GSM1509655", "GSM1509656", "GSM1509657", "GSM1509658", "GSM1509659", "GSM1509660", "GSM1509661", "GSM1509662", "GSM1509663", "GSM1509664", "GSM1509665", "GSM1509666", "GSM1509667", "GSM1509668", "GSM1509669", "GSM1509670", "GSM1509671", "GSM1509672", "GSM1509673", "GSM1509674", "GSM1509675", "GSM1509676", "GSM1509677", "GSM1509678", "GSM1509679", "GSM1509680", "GSM1509681", "GSM1509682", "GSM1509683", "GSM1509684", "GSM1509685", "GSM1509686", "GSM1509687", "GSM1509688", "GSM1509689", "GSM1509690", "GSM1509691", "GSM1509692", "GSM1509693", "GSM1509694", "GSM1509695", "GSM1509696", "GSM1509697", "GSM1509698", "GSM1509699", "GSM1509700", "GSM1509701", "GSM1509702", "GSM1509703", "GSM1509704", "GSM1509705", "GSM1509706", "GSM1509707", "GSM1509708", "GSM1509709", "GSM1509710", "GSM1509711", "GSM1509712", "GSM1509713", "GSM1509714", "GSM1509715", "GSM1509716", "GSM1509717", "GSM1509718", "GSM1509719", "GSM1509720", "GSM1509721", "GSM1509722", "GSM1509723", "GSM1509724", "GSM1509725", "GSM1509726", "GSM1509727", "GSM1509728", "GSM1509729", "GSM1509730", "GSM1509731", "GSM1509732", "GSM1509733", "GSM1509734", "GSM1509735", "GSM1509736", "GSM1509737", "GSM1509738"], "sample_count": 129, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression in RNP autoantibody+ systemic lupus erythematosus (SLE) patient blood", "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:GSE10325 not downloaded", "asset:data:geo:GSE10325 licence not read", "asset:data:geo:GSE13887 not downloaded", "asset:data:geo:GSE13887 licence not read", "asset:data:geo:GSE61635 not downloaded", "asset:data:geo:GSE61635 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {"fdr_threshold": "ed by adjusted p-value (false discovery rate) < 0"}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Differentially expressed genes (DEGs) between SLE and HCs were identified using the limma package (version 3.64.1) in R (version 4.2.1)."}}, {"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": 0.7, "band": "medium", "quote": "Principal component analysis"}}, {"id": "method-3", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"id": "method-4", "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": 0.8, "band": "high", "quote": "pathway enrichment"}}, {"id": "method-5", "family": "flow_cytometry_analysis", "specific": "gating", "label": "Flow cytometry analysis", "dsl_operations": ["gate_population", "quantify_mfi", "compensation_matrix"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["event_table"], "evidence": {"score": 0.8, "band": "high", "quote": "gating strategy"}}, {"id": "method-6", "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 curve"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: limma_voom."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE13887", "GSE10325", "GSE61635"], "resolved_accessions": ["GSE13887", "GSE10325", "GSE61635"], "statements": ["Raw data is available in the Supplemental Files."], "basis": "The paper names GSE13887, GSE10325, GSE61635 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:40949741", "data:geo:GSE10325"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE10325"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:01:27Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 18963, "completion_tokens": 1462, "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:40949741", "type": "paper", "label": "pmid:40949741"}, {"id": "source:pmid:40949741", "type": "manuscript", "label": "PMID 40949741 full text"}, {"id": "data:geo:GSE10325", "type": "dataset", "label": "GEO GSE10325"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40949741", "type": "paper", "label": "pmid:40949741"}, {"id": "source:pmid:40949741", "type": "manuscript", "label": "PMID 40949741 full text"}, {"id": "data:geo:GSE10325", "type": "dataset", "label": "GEO GSE10325"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40949741", "type": "extraction", "used": ["source:pmid:40949741"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE10325", "type": "accession_resolution", "used": ["data:geo:GSE10325"], "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:40949741", "parent_hash": "sha256:511e2463c97f579e7f6131341fd89d25aee02004530323885ab7f4f9773be711", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE10325 licence not read", "asset:data:geo:GSE10325 not downloaded", "asset:data:geo:GSE13887 licence not read", "asset:data:geo:GSE13887 not downloaded", "asset:data:geo:GSE61635 licence not read", "asset:data:geo:GSE61635 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["re screened from both datasets. Quantitative real-time PCR (RT-q PCR) was utilized to validate hub gene", "bead separation. RNA extraction followed by RT-qPCR revealed significant downregulation of FCER1", "ad separation. RNA extraction followed by RT-qPCR revealed significant downregulation of FCER1", "pp-1 Supplemental Information 2Raw data from qPCR experiments analyzing the expression levels"], "order_basis": "paper_text_order:1276", "id": "assay:1"}, {"role": "data_generation", "definition_id": "flow_cytometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["blood samples of SLE patients. Concurrently, flow cytometry was employed to quantify inflammatory cytoki", "ntrols. Clinical validation via RT-q PCR and flow cytometry corroborated these findings, demonstrating d", "many). The purity of T cell were analyzed by Flow cytometry (CantoII, BD Bioscience, Franklin Lakes, NJ,", "ig. 7A). These findings were corroborated by flow cytometry, which demonstrated a marked reduction in FC"], "order_basis": "paper_text_order:1424", "id": "assay:2"}, {"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["to transcriptional dysregulation in cancer, apoptosis, thyroid cancer, African trypanosomiasis, an"], "order_basis": "paper_text_order:6369", "id": "assay:3"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Differentially expressed genes (DEGs) between SLE and HCs were identified using the limma package (version 3.64.1) in R (version 4.2.1)."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"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":"2026-11-04T00:31:34+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}}}