{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33686088", "kind": "science-record", "revision": 7, "content_hash": "sha256:5ab35b2a3a3e1337535fd083408734ee349924a4366b3111484bd021baffda9f", "created_at": "2026-11-01T15:41:27Z", "updated_at": "2026-11-01T22:03:16Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Bioinformatis analysis reveals possible molecular mechanism of PXR on regulating ulcerative colitis.", "doi": "10.1038/s41598-021-83742-8", "pmid": "33686088", "authors": ["Hanze Guo", "Yan Chi", "Naiyu Chi"], "journal": "Scientific reports", "year": 2021, "abstract": "Inflammatory bowel disease (IBD) is a chronic, recurrent inflammatory disease of the gastrointestinal (GI) tract. Ulcerative colitis (UC) is a type of IBD. Pregnane X Receptor (PXR) is a member of the nuclear receptor superfamily. In order to deepen understanding and exploration of the molecular mechanism of regulation roles of PXR on UC, biological informatics analysis was performed. First, 878 overlapping differentially expressed genes (DEGs) between UC and normal samples were obtained from the Gene Expression Omnibus (GEO) database (GSE59071 and GSE38713) by using the \"limma\" R language package. Then WGCNA analysis was performed by 878 DEGs to obtain co-expression modules that were positively and negatively correlated with clinical traits. GSEA analysis of PXR results obtained the signal pathways enriched in the PXR high and low expression group and the active genes of each signal pathway. Then the association of PXR with genes that are both active in high expression group and negatively related to diseases (gene set 1), or both active in low expression group and negatively related to diseases (gene set 2) was analyzed by String database. Finally, carboxylesterase 2 (CES2), ATP binding cassette subfamily G member 2 (ABCG2), phosphoenolpyruvate carboxykinase (PCK1), PPARG coactivator 1 alpha (PPARGC1A), cytochrome P450 family 2 subfamily B member 6 (CYP2B6) from gene set 1 and C-X-C motif chemokine ligand 8 (CXCL8) from gene set 2 were screened out. After the above analysis and reverse transcriptase quantitative polymerase chain reaction (RT-qPCR) verification, we speculated that PXR may exert a protective role on UC by promoting CES2, ABCG2, PCK1, PPARGC1A, CYP2B6 expression and inhibiting CXCL8 expression in their corresponding signal pathway in intestinal tissue.", "claims": [{"id": "claim-method", "statement": "Student’s t test was performed to determine statistical differences between groups.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33686088", "locator": "sections[11] \"Statistical analysis\" paragraph 2", "quote": "Student’s t test was performed to determine statistical differences between groups."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All authors make sure that all data and materials support published claims and comply with field standards.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33686088", "locator": "sections[28] \"notes\" paragraph 1", "quote": "All authors make sure that all data and materials support published claims and comply with field standards."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": null, "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:33686088"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33686088", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-021-83742-8", "sha256": "sha256:c6a386b85f179c8cc7604c3555b9628231e4ede588a053b9af6e3990fe848e6a", "bytes": 32801, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-021-83742-8", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7940411", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:33686088:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6a161f7a0bd662ebc92b73c05992e7360be47ee3b895d30bdff7480182d68173", "bytes": 1781, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#Tab1", "version": null, "note": "Biological signal pathways and active genes in PXR high expression group by GSEA.", "structure": {"pmcid": "PMC7940411", "section_index": 10, "section_title": "RT-qPCR", "row_count": 21, "column_count": 4}, "table": {"label": "Table 1", "caption": "Biological signal pathways and active genes in PXR high expression group by GSEA.", "rows": [["Pathway regulated by PXR", "NES", "Size", "Active genes"], ["PEROXISOME", "1.32", "13", "EPHX2 XDH EHHADH PEX11A PHYH PEX26 PXMP2 ABCD3 ACOX1 NOS2"], ["NITROGEN_METABOLISM", "1.31", "5", "CA1 CA7 CA4 CA2"], ["HUNTINGTONS_DISEASE", "1.29", "5", "PPARG PPARGC1A"], ["DRUG_METABOLISM_OTHER_ENZYMES", "1.27", "5", "NAT2 UGT1A3 XDH CES2"], ["GLYCOLYSIS_GLUCONEOGENESIS", "1.25", "6", "ALDOB ACSS2 PCK1 ADH1C ADH6"], ["PROXIMAL_TUBULE_BICARBONATE_RECLAMATION", "1.24", "5", "CA4 SLC9A3 CA2 SLC4A4 PCK1"], ["ABC_TRANSPORTERS", "1.22", "7", "ABCG2 ABCB1"], ["GLYCEROPHOSPHOLIPID_METABOLISM", "1.21", "9", "GPD1L PLA2G12B LPGAT1 PLA2G2A CHKA AGPAT4 CHPT1"], ["ALDOSTERONE_REGULATED_SODIUM_REABSORPTION", "1.20", "5", "SCNN1B"], ["DRUG_METABOLISM_CYTOCHROME_P450", "1.18", "10", "FMO5 CYP2B6 UGT1A3 MAOA FMO4 ADH1C ADH6"], ["FATTY_ACID_METABOLISM", "1.16", "12", "EHHADH ADH1C ACADS ADH6 ACAA2 ACOX1 CPT1A CPT2"], ["INSULIN_SIGNALING_PATHWAY", "1.15", "5", "PPARGC1A PTPRF PCK1 PDE3A"], ["VALINE_LEUCINE_AND_ISOLEUCINE_DEGRADATION", "1.15", "7", "HMGCS2 EHHADH ACADS ACAA2"], ["TYROSINE_METABOLISM", "1.14", "5", "MAOA ADH1C DDC ADH6"], ["STEROID_HORMONE_BIOSYNTHESIS", "1.13", "7", "UGT1A3 HSD11B2 HSD17B2 HSD3B2 STS UGT2A3"], ["ARGININE_AND_PROLINE_METABOLISM", "1.13", "7", "MAOA CKB NOS2 OTC ASS1 ALDH18A1"], ["LONG_TERM_DEPRESSION", "1.13", "5", "GNA11 PLA2G12B PRKG2 PLA2G2A"], ["RETINOL_METABOLISM", "1.11", "7", "CYP2B6 UGT1A3 ADH1C RETSAT ADH6"], ["METABOLISM_OF_XENOBIOTICS_BY_CYTOCHROME_P450", "1.05", "8", "CYP2B6 UGT1A3 ADH1C ADH6 CYP2S1 UGT2A3"], ["KEGG_PROGESTERONE_MEDIATED_OOCYTE_MATURATION", "1.03", "5", "RPS6KA6 PDE3A"]], "row_count": 21, "column_count": 4, "numeric_cells": 47, "header_rows": 1, "locator": "section[10]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:33686088:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5ade8720745e1c215a74e61b13c53a932cc514b5beb60ce6cfe5a00f2f376d40", "bytes": 2651, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#Tab2", "version": null, "note": "Biological signal pathways and active genes in PXR low expression group by GSEA.", "structure": {"pmcid": "PMC7940411", "section_index": 16, "section_title": "GSEA associated with PXR", "row_count": 21, "column_count": 4}, "table": {"label": "Table 2", "caption": "Biological signal pathways and active genes in PXR low expression group by GSEA.", "rows": [["Pathway regulated by PXR", "NES", "Size", "Active genes"], ["PRIMARY_IMMUNODEFICIENCY", "− 1.43", "7", "BTK PTPRC IL7R CD79A"], ["LEUKOCYTE_TRANSENDOTHELIAL_MIGRATION", "− 1.39", "19", "RAC2 NCF4 MSN ICAM1 CDH5 JAM2 NCF2 RASSF5 ITGB2 PECAM1 RHOH MMP9 THY1 CXCR4 VCAM1"], ["VASCULAR_SMOOTH_MUSCLE_CONTRACTION", "− 1.29", "5", "EDNRA CALCRL"], ["CHEMOKINE_SIGNALING_PATHWAY", "− 1.21", "28", "CXCL5 ELMO1 CXCL10 CCL11 CXCR2 CCR1 CCL18 CCL4 CCR7 CXCR4 CXCL9 CXCL6 CCL2 CCL19 CXCL13"], ["SYSTEMIC_LUPUS_ERYTHEMATOSUS", "− 1.16", "16", "C2 HLA-DRA HLA-DMA HLA-DPA1 HLA-DMB CD40 FCGR3B FCGR2C C1R FCGR2A C1S CD86 C3 FCGR2B"], ["B_CELL_RECEPTOR_SIGNALING_PATHWAY", "− 1.14", "10", "PIK3R3 IFITM1 DAPP1 LYN CD81 RAC2 BTK CD79A FCGR2B"], ["CYTOKINE_CYTOKINE_RECEPTOR_INTERACTION", "− 1.14", "44", "CCL3L3 CXCL11 CXCL1 GHR IFNAR2 CD40 IL1B CXCL8 OSMR CSF3R CSF2RB TNFSF13B KDR TNFRSF11B TGFB1 CXCL5 IL10RA IL2RA CXCL10 CCL11 PDGFRB CD27 CXCR2 CCR1 CCL18 CCL4 INHBA CCR7 TNFRSF17 CXCR4 CXCL9 IL7R CXCL6 CCL2 IL24 CCL19 CXCL13"], ["CELL_ADHESION_MOLECULES_CAMS", "− 1.14", "28", "ICAM1 VCAN CDH5 JAM2 ITGB2 PECAM1 ICAM2 SELPLG CD86 PTPRC VCAM1 SELP SELL SELE"], ["FOCAL_ADHESION", "− 1.14", "22", "COL1A1 RAC2 COL3A1 COL4A2 COL1A2 VWF LAMC1 COL6A3 COL5A2 KDR COL4A1 SPP1 THBS2 ITGA5 CAV1 PDGFRB TNC"], ["JAK_STAT_SIGNALING_PATHWAY", "− 1.12", "12", "GHR IFNAR2 OSMR CSF3R CSF2RB IL10RA IL2RA IL7R IL13RA2 IL24"], ["NEUROACTIVE_LIGAND_RECEPTOR_INTERACTION", "− 1.06", "20", "FPR2 C3AR1 FPR1 S1PR1 P2RY13 P2RY8 EDNRA CALCRL"], ["ECM_RECEPTOR_INTERACTION", "− 1.05", "16", "CD44 COL1A1 COL3A1 COL4A2 COL1A2 VWF LAMC1 COL6A3 COL5A2 COL4A1 SPP1 THBS2 ITGA5 TNC"], ["TOLL_LIKE_RECEPTOR_SIGNALING_PATHWAY", "− 1.03", "15", "CXCL11 IFNAR2 CD40 IL1B CXCL8 TLR2 CXCL10 SPP1 CCL4 CD86 CTSK CXCL9 LY96"], ["LYSOSOME", "− 1.02", "5", "CTSH LAPTM5 LAMP3 CTSK"], ["ENDOCYTOSIS", "− 1.01", "13", "RAB31 ASAP1 SMAP2 KDR IL2RA CXCR2 CXCR4"], ["CYTOSOLIC_DNA_SENSING_PATHWAY", "− 1.01", "7", "IL1B AIM2 CXCL10 CCL4 IL33"], ["VIRAL_MYOCARDITIS", "− 1.01", "13", "HLA-DRA HLA-DMA HLA-DPA1 HLA-DMB CD40 RAC2 ICAM1 ITGB2 CAV1 CD86"], ["LEISHMANIA_INFECTION", "− 1.00", "19", "STAT1 HLA-DRA HLA-DMA HLA-DPA1 HLA-DMB IL1B NCF4 TLR2 NCF2 ITGB2 TGFB1 FCGR3B FCGR2C FCGR2A PTGS2 C3"], ["INTESTINAL_IMMUNE_NETWORK_FOR_IGA_PRODUCTION", "− 0.99", "12", "HLA-DRA HLA-DMA HLA-DPA1 HLA-DMB CD40 TNFSF13B TGFB1 CD86 TNFRSF17 CXCR4"], ["PRIMARY_IMMUNODEFICIENCY", "− 1.43", "7", "PIK3R3 LYN RAC2 FCER1G BTK"]], "row_count": 21, "column_count": 4, "numeric_cells": 54, "header_rows": 1, "locator": "section[16]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:33686088:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b3820816732b16e4e36f157fdb7a2ca2cb437f4f966cebc637b56148ebbab0a2", "bytes": 791, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#Tab3", "version": null, "note": "Active genes and their corresponding signal pathways they participate in after PPI analysis with PXR.", "structure": {"pmcid": "PMC7940411", "section_index": 17, "section_title": "Six genes were screened out that can interact and functionally associate with PXR", "row_count": 8, "column_count": 3}, "table": {"label": "Table 3", "caption": "Active genes and their corresponding signal pathways they participate in after PPI analysis with PXR.", "rows": [["Gene symbol", "Gene name", "Signal pathway"], ["PCK1", "phosphoenolpyruvate carboxykinase 1", "GLUCONEOGENESIS"], ["PPARGC1A", "PPARG Coactivator 1 Alpha", "INSULIN_PATHWAY"], ["CES2", "Carboxylesterase 2", "DRUG_METABOLISM_OTHER_ENZYMES"], ["ABCG2", "ATP Binding Cassette Subfamily G Member 2", "ABC_TRANSPORTERS"], ["CYP2B6", "Cytochrome P450 Family 2 Subfamily B Member 6", "METABOLISM_OF_XENOBIOTICS_BY_CYTOCHROME_P450"], ["CXCL8", "C-X-C Motif Chemokine Ligand 8", "TOLL-LIKE_RECEPTOR_SIGNALING_PATHWAY"], ["CYTOKINE-CYTOKINE_RECEPTOR_INTERACTION", "", ""]], "row_count": 8, "column_count": 3, "numeric_cells": 7, "header_rows": 1, "locator": "section[17]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:33686088:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f64dcaae38d5dd03947e7057429fb0dd58369fe0034c655fabea0d749e885bef", "bytes": 481, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#Tab4", "version": null, "note": "Predicted sequences that PXR bind on the gene promoters listed below with the highest scores.", "structure": {"pmcid": "PMC7940411", "section_index": 18, "section_title": "The six genes were regulated by PXR", "row_count": 6, "column_count": 3}, "table": {"label": "Table 4", "caption": "Predicted sequences that PXR bind on the gene promoters listed below with the highest scores.", "rows": [["Gene symbol", "Score", "Predicted sequence"], ["CES2", "8.662", "AGGGACTCTGCGCCCTT"], ["ABCG2", "7.78554", "TTAAAACAATTGAACTC"], ["PCK1", "8.51", "GTGCCCCGGCCAACCTT"], ["PPARGC1A", "7.97", "TTAAACCCAATATACTT"], ["CYP2B6", "10.3884", "GTGATCTCTGTGACCTA"]], "row_count": 6, "column_count": 3, "numeric_cells": 5, "header_rows": 1, "locator": "section[18]/table-wrap[1]#Tab4"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.7, "band": "medium", "quote": "limma"}}, {"id": "method-2", "family": null, "specific": null, "label": "Student’s t test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Student’s t test was performed to determine statistical differences between groups."}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "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": "R4", "reachable": false, "accessions": ["GSE59071 and GSE38713"], "resolved_accessions": [], "statements": ["All authors make sure that all data and materials support published claims and comply with field standards."], "basis": "The paper names GSE59071 and GSE38713, but the accession does not resolve in the repository (no reason recorded), so the data cannot be reached from here. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:33686088", "asset:table:pmid:33686088:1", "asset:table:pmid:33686088:2", "asset:table:pmid:33686088:3", "asset:table:pmid:33686088:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:27:40Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 27525, "completion_tokens": 970, "cached_tokens": 784}}, "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:33686088", "type": "paper", "label": "pmid:33686088"}, {"id": "source:pmid:33686088", "type": "manuscript", "label": "PMID 33686088 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33686088", "type": "paper", "label": "pmid:33686088"}, {"id": "source:pmid:33686088", "type": "manuscript", "label": "PMID 33686088 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33686088", "type": "extraction", "used": ["source:pmid:33686088"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:33686088", "parent_hash": "sha256:2f33aa8980fe0f205f70125c090d0add2522dbd311df651029ad082ab8b90c17", "fork_of": null, "generation": 6}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "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": ["tase quantitative polymerase chain reaction (RT-qPCR) verification, we speculated that PXR may ex", "e quantitative polymerase chain reaction (RT-qPCR) verification, we speculated that PXR may ex"], "order_basis": "paper_text_order:1623", "id": "assay:1"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["ike cell isolated from colon carcinoma, were cultured in DMEM containing 10% FBS with penicillin (100"], "order_basis": "paper_text_order:1966", "id": "assay:2"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["limma"], "order_basis": "consumes_earlier_output", "id": "assay: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":"2026-11-04T02:50:23+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}}}