{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32596346", "kind": "science-record", "revision": 7, "content_hash": "sha256:e28c09afc49db8bfe9b63912e7d71d46dfb2358fc7e7fccedb026458983e4802", "created_at": "2026-11-01T15:41:04Z", "updated_at": "2026-11-01T22:01:49Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Integrated Analysis of a Gene Correlation Network Identifies Critical Regulation of Fibrosis by lncRNAs and TFs in Idiopathic Pulmonary Fibrosis.", "doi": "10.1155/2020/6537462", "pmid": "32596346", "authors": ["Fan Wang", "Pei Li", "Feng-Sen Li"], "journal": "BioMed research international", "year": 2020, "abstract": "Idiopathic pulmonary fibrosis (IPF), the most frequent form of irreversible interstitial pneumonia with unknown etiology, is characterized by massive remodeling of lung architecture and followed by progressive loss of lung function. However, the key regulatory genes and the specific signaling pathways involved in the onset and progression of IPF still remain unclear. The present study is aimed at investigating the key role of long noncoding RNAs (lncRNAs) and transcription factors (TFs) involved in the pathogenesis of IPF through the integrated analysis of three gene expression profiles from the GEO dataset (GSE2052, GSE44723, and GSE24206). A total of 8483 differentially expressed genes (DEGs) including 988 upregulated and 7495 downregulated genes were filtered. Subsequently, following the intersection of these DEGs, 29 overlapping genes were identified and further analyzed using a bioinformatics approach. Furthermore, the protein-protein interaction (PPI) network was used to obtain 18 modules of related genes. The hub genes were identified through hypergeometric testing, which were closely associated with ubiquitin-mediated proteolysis, the spliceosome, and the cell cycle. The significant difference was observed in the expression of these key genes, such as lncRNA MALAT1, E2F1, and YBX1, in the peripheral blood of IPF patients when compared with those normal control subjects by real-time polymerase chain reaction (RT-PCR) analysis. This study indicated that lncRNA MALAT1, E2F1, and YBX1 may be key regulators for the pathogenesis of IPF.", "claims": [{"id": "claim-method", "statement": "After pretreatment of the genes that came from more than one probe set, the DEGs identified with cutoff criteria of |logFC| > 1 and P < 0.05 by the classic t-test were considered statistically significant.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32596346", "locator": "sections[4] \"2.2. Identification of Differential Gene Expression in IPF\" paragraph 2", "quote": "After pretreatment of the genes that came from more than one probe set, the DEGs identified with cutoff criteria of |logFC| > 1 and P < 0.05 by the classic t-test were considered statistically significant."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32596346", "locator": "sections[19] \"Data Availability\" paragraph 2", "quote": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "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:32596346"], "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:GSE2052"], "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:GSE2052"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32596346", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2020/6537462", "sha256": "sha256:755fbab3960d354675a620b471d767a9b12093d5e9ddd4e2fcab7cd402178561", "bytes": 36477, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2020/6537462", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7290873", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE2052", "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=GSE2052", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE2052", "version": null, "note": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM37404", "GSM37405", "GSM37406", "GSM37407", "GSM37408", "GSM37409", "GSM37410", "GSM37411", "GSM37412", "GSM37413", "GSM37414", "GSM37415", "GSM37416", "GSM37417", "GSM37418", "GSM37419", "GSM37420", "GSM37421", "GSM37422", "GSM37423", "GSM37424", "GSM37425", "GSM37426", "GSM37427", "GSM37428", "GSM37429"], "sample_count": 26, "group_sizes": null, "group_sizes_basis": null, "platform": "1739", "taxon": "Homo sapiens", "title": "IPF versus Control", "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:GSE24206", "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=GSE24206", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE24206", "version": null, "note": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM595407", "GSM595411", "GSM595414", "GSM595416", "GSM595417", "GSM595419", "GSM595421", "GSM595422", "GSM595423", "GSM595424", "GSM595425", "GSM595426", "GSM595427", "GSM595428", "GSM595429", "GSM595432", "GSM595434", "GSM595435", "GSM595437", "GSM595439", "GSM595441", "GSM595443", "GSM595445"], "sample_count": 23, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Validated Gene Expression Signatures of Idiopathic Pulmonary Fibrosis", "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:GSE44723", "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=GSE44723", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE44723", "version": null, "note": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1089614", "GSM1089615", "GSM1089616", "GSM1089617", "GSM1089618", "GSM1089619", "GSM1089620", "GSM1089621", "GSM1089622", "GSM1089623", "GSM1089624", "GSM1089625", "GSM1089626", "GSM1089627"], "sample_count": 14, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Bleomycin induces molecular changes directly relevant to idiopathic pulmonary fibrosis:  A model for “active” disease", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32596346:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:593c7a350faaad5e91d61a83596edbe0cf96a16896235af80a786da084bbf37b", "bytes": 3415, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#tab1", "version": null, "note": "DEGs were identified from three datasets, including 262 upregulated and 191 downregulated genes in IPF compared with normal lung tissues (upregulated genes were defined with fold change (FC) > 0 as the cutoff criterion. The opposite was defined as downregulated genes).", "structure": {"pmcid": "PMC7290873", "section_index": 11, "section_title": "3.1. Identification of Differentially Expressed Genes in IPF", "row_count": 4, "column_count": 2}, "table": {"label": "Table 1", "caption": "DEGs were identified from three datasets, including 262 upregulated and 191 downregulated genes in IPF compared with normal lung tissues (upregulated genes were defined with fold change (FC) > 0 as the cutoff criterion. The opposite was defined as downregulated genes).", "rows": [["DEGs", "Gene names"], ["Upregulated", "SULF1, DEAF1, SCG5, DSG2, SLC1A4, CCND2, KCNN4, ST6GAL1, SLC38A1, SEC11C, XPOT, DPY30, PFKP, DDB1, HEPH, CXCL13, ATXN10, SEL1L3, CIAO1, CCL19, STARD5, SLFN12, ROR2, VAT1L, FPGT, GMPPA, COL18A1, COL7A1, PIGF, LMO4, FAM120A, SLC29A3, TCFL5, IGFBP2, UQCRQ, CCNA2, TWSG1, TCTN3, ASPN, PAM, BPIFB1, FAIM, FBLN2, SCARA3, COMP, ABCC5, DIO2, CHEK2, MCM4, TM9SF2, NAB1, DGKA, PTGFRN, FAT1, DOK5, CNIH1, ACTN1, PLA2G12A, MAGED1, ALG1, TWIST1, TRIM5, RCN2, CXCL14, ARMC1, STMN3, HMCN1, WDR5B, CROT, LEF1, TMEM14A, PLA2G4A, FKBP10, ABCC3, SPR, ROBO1, OXR1, CRLF1, TRIAP1, KDELR3, DIRAS3, BBS2, TGFB3, LGMN, CDK2AP1, CXCL12, RRM2, STRBP, TSPAN6, DAP, COL6A3, FZD6, TDO2, GMDS, PPP2R5E, SUPT7L, ZKSCAN7, CDKN3, CNTNAP1, IGF1, GSS, LRRC8D, TMEM98, TRIM2, LTBP1, BACE2, BRD8, COLEC11, FXN, PAFAH1B3, PGAM1, COL5A2, AOC1, ANTXR1, TMEM69, IMPACT, NET1, MXRA5, RCN1, MYO1E, DUSP23, CDH3, RHOD, CYP2S1, POSTN, ICMT, PDLIM4, C1QTNF6, ACVR1, SYTL2, PLA2G7, MFAP2, ZDHHC13, TMED10, ALDH1A3, SLN, CPOX, CDKN2C, PPIC, XRCC5, CLDN1, NSG1, ITGA7, R3HDM1, ERGIC2, TRIM36, EYA2, RPL39L, CCL13, RBP5, DONSON, SERPINB5, TXNDC15, HOMER3, ARL1, UBE2E3, CRYM, MEOX1, TMEM45A, COL15A1, ATP1B1, LDLRAD4, STEAP3, NABP2, BDKRB2, DCLK1, CFH, TRO, ECM1, PFN2, IL13RA2, MYOF, FHL2, CADPS, ITGAV, PCNA, PTK7, KIF2C, MEGF8, BMP4, PDCD2L, PRMT6, TP53BP1, OSBPL6, FMO1, PDE1A, PBX3, ELOVL4, ATF7IP, SYNDIG1, TMEM158, CFI, ALDH3A1, CKAP2, MRPL2, COL14A1, EGFL6, LHX6, THBS2, RRM1, YLPM1, TM7SF3, MLEC, CFB, BCL11A, GPR87, ZNF436, CLNS1A, ATIC, LGR4, CYP24A1, SEMA3C, PDGFC, TP63, ARMCX2, NUSAP1, ASB2, SLC39A6"], [""], ["Downregulated", "MKLN1, ECHDC3, RAB32, SLC25A51, HOPX, MATN3, MAP2, ARHGAP6, EPB41L5, NRGN, HEY1, PCTP, ACVRL1, TBX5, ERMP1, NAGA, MPP1, TXNIP, LRRN3, FLOT1AATK, RCL1, CSF3R, ANXA3, TEK, GRK5, HES1, HSPA1L, GATA6, EMP2, SLCO2A1, PMM1, STARD13, SEC14L1, SPTBN1, GHRL, TSPAN7, NEBL, ZNF655, TMEM11, UIMC1, NCOA3, ZFP36, CREBBP, LDLR, RAB20, SERTAD1, PPFIBP1, REPS2, ELF1, CALCOCO2, CSRNP1, GPM6A, DLL4, FPR1, CARHSP1, ADARB1, LMO7, RCOR1, LRRC32, CTNNBIP1, CA4, PADI4, OSGIN1, CXCL2, EGFR, CHI3L2, LPIN2, ANKHD1, ARHGEF4, ARHGAP29, VAMP5, RAI2, CYTIP, PRX, IER5, DNM2, IL17RA, BHLHE40, SLC39A8, RAPGEF5, PTPRM, CNOT8, DLC1, TLK2, EPAS1, PRELP, MAFF, ABTB1, HSD17B6, NDEL1, HYAL1, HECA, HSPB8, DNAJB1, CDH13, RGS16, PTPN12, CD55, TIPARP, CRYAB, CD36, NUP153, PTPRB, ITSN2, TNNC1, MAPT, THBD, CDKN2D, AOC3, P2RY1, ZBTB16, CSF3, EDNRB, FAM167A, SRGAP2, SLCO1A2, DAPK2, AGTR1, RIMKLB, ASRGL1, ANG, CCK, BCL2L13, OSGIN2, ACSM5, KIAA0040, KDR, FUT1, DOCK9, GADD45G, CLDN5, LIFR, STXBP6, GPR4, S1PR1, SLC1A1, PLAG1, EDA, DENND3, IDI1, KHDRBS3, CLEC1A, INMT, MPP3, PLLP, MTSS1, FSTL3, CRTAC1, GTF2IRD1, F3, KLF10, KLRD1, FBLN5IZUMO4, PIR, MAOA, C1QL1, THRB, RNF182, ALDH6A1, FAM49A, ST6GALNAC3, SSFA2, SLC25A24, AMPH, ADAMTS8, PLSCR1, BCKDHA, STXBP4, FLRT3, AOX1, SYAP1, RLF, SSH2, DERA, PIM1, STARD3NL, SUN2, SEPP1, IL1R2, EIF2A, FAH, METTL7A, EIF4E3, CHRM2, 1-Mar, PDK1, TJP2, RASL11A, NKX3-1"]], "row_count": 4, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[11]/table-wrap[1]#tab1"}}, {"id": "asset:table:pmid:32596346:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ae52efda3c297e90c40e8cedcb635b14d191a6e4d27e77d62c1e207fecd3f5f4", "bytes": 2111, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#tab2", "version": null, "note": "The significantly enriched analysis of differentially expressed genes in idiopathic pulmonary fibrosis.", "structure": {"pmcid": "PMC7290873", "section_index": 12, "section_title": "3.2. GO and KEGG Enrichment Analyses of Differentially Expressed Genes", "row_count": 25, "column_count": 5}, "table": {"label": "Table 2", "caption": "The significantly enriched analysis of differentially expressed genes in idiopathic pulmonary fibrosis.", "rows": [["Category", "Pathway ID", "Description", "Count", "P value"], ["GOTERM_BP", "GO:0007155", "Cell adhesion", "45", "1.46327E − 09"], ["GOTERM_BP", "GO:0022610", "Biological adhesion", "45", "1.50199E − 09"], ["GOTERM_BP", "GO:0042127", "Regulation of cell proliferation", "42", "9.51714E − 07"], ["GOTERM_BP", "GO:0035295", "Tube development", "18", "1.51015E − 05"], ["GOTERM_BP", "GO:0032103", "Positive regulation of response to external stimulus", "10", "1.56397E − 05"], ["GOTERM_BP", "GO:0001501", "Skeletal system development", "22", "1.77224E − 05"], ["GOTERM_MF", "GO:0005509", "Calcium ion binding", "38", "0.000949643"], ["GOTERM_MF", "GO:0019955", "Cytokine binding", "10", "0.001081524"], ["GOTERM_MF", "GO:0008009", "Chemokine activity", "6", "0.004374834"], ["GOTERM_MF", "GO:0042802", "Identical protein binding", "27", "0.00485805"], ["GOTERM_MF", "GO:0042379", "Chemokine receptor binding", "6", "0.005747644"], ["GOTERM_MF", "GO:0008017", "Microtubule binding", "7", "0.00692901"], ["GOTERM_CC", "GO:0044421", "Extracellular region part", "54", "3.94172E − 10"], ["GOTERM_CC", "GO:0005615", "Extracellular space", "38", "4.31806E − 07"], ["GOTERM_CC", "GO:0031012", "Extracellular matrix", "24", "2.55104E − 06"], ["GOTERM_CC", "GO:0005578", "Proteinaceous extracellular matrix", "22", "8.9433E − 06"], ["GOTERM_CC", "GO:0044459", "Plasma membrane part", "76", "5.14236E − 05"], ["GOTERM_CC", "GO:0031226", "Intrinsic to plasma membrane", "48", "0.000103242"], ["KEGG_PATHWAY", "hsa04512", "ECM-receptor interaction", "9", "0.00286045"], ["KEGG_PATHWAY", "hsa04060", "Cytokine-cytokine receptor interaction", "17", "0.003658523"], ["KEGG_PATHWAY", "hsa04510", "Focal adhesion", "13", "0.01357663"], ["KEGG_PATHWAY", "hsa04610", "Complement and coagulation cascades", "7", "0.014586106"], ["KEGG_PATHWAY", "hsa05414", "Dilated cardiomyopathy", "8", "0.017081193"], ["KEGG_PATHWAY", "hsa00360", "Phenylalanine metabolism", "4", "0.024804532"]], "row_count": 25, "column_count": 5, "numeric_cells": 72, "header_rows": 1, "locator": "section[12]/table-wrap[1]#tab2"}}, {"id": "asset:table:pmid:32596346:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a29d5634e9b50968498f8e3dcb602e64be9976ba988f13d1be0117a3a214da74", "bytes": 2609, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#tab3", "version": null, "note": "The significant GO enrichment analysis of module gene function in idiopathic pulmonary fibrosis.", "structure": {"pmcid": "PMC7290873", "section_index": 13, "section_title": "3.3. Construction and Enrichment Analysis of Modules", "row_count": 31, "column_count": 5}, "table": {"label": "Table 3", "caption": "The significant GO enrichment analysis of module gene function in idiopathic pulmonary fibrosis.", "rows": [["Category", "Pathway ID", "Pathway description", "Count", "P value"], ["GO_BP_m1", "GO:0000209", "Protein polyubiquitination", "47", "1.77E − 64"], ["GO_BP_m10", "GO:0097711", "Ciliary basal body-plasma membrane docking", "32", "6.55E − 71"], ["GO_BP_m11", "GO:0048193", "Golgi vesicle transport", "30", "9.70E − 41"], ["GO_BP_m12", "GO:0006898", "Receptor-mediated endocytosis", "19", "6.36E − 21"], ["GO_BP_m13", "GO:0060337", "Type I interferon signaling pathway", "20", "1.37E − 38"], ["GO_BP_m14", "GO:0007059", "Chromosome segregation", "29", "2.58E − 38"], ["GO_BP_m15", "GO:0009165", "Nucleotide biosynthetic process", "20", "2.61E − 27"], ["GO_BP_m16", "GO:0036297", "Interstrand cross-link repair", "16", "1.73E − 32"], ["GO_BP_m17", "GO:0006289", "Nucleotide-excision repair", "26", "7.46E − 53"], ["GO_BP_m18", "GO:0000280", "Nuclear division", "24", "7.63E − 35"], ["GO_CC_m1", "GO:0000151", "Ubiquitin ligase complex", "42", "1.34E − 54"], ["GO_CC_m10", "GO:0044450", "Microtubule organizing center part", "19", "1.93E − 29"], ["GO_CC_m11", "GO:0005875", "Microtubule-associated complex", "27", "1.16E − 46"], ["GO_CC_m12", "GO:0030136", "Clathrin-coated vesicle", "22", "8.55E − 33"], ["GO_CC_m13", "GO:0042611", "MHC protein complex", "5", "6.87E − 10"], ["GO_CC_m14", "GO:0000775", "Chromosome, centromeric region", "35", "4.74E − 59"], ["GO_CC_m15", "GO:0008074", "Guanylate cyclase complex, soluble", "2", "2.57E − 06"], ["GO_CC_m16", "GO:0043240", "Fanconi anemia nuclear complex", "7", "9.55E − 17"], ["GO_CC_m17", "GO:1990391", "DNA repair complex", "9", "3.70E − 17"], ["GO_CC_m18", "GO:0005819", "Spindle", "17", "5.08E − 23"], ["GO_MF_m1", "GO:0004842", "Ubiquitin-protein transferase activity", "69", "5.10E − 99"], ["GO_MF_m10", "GO:0005200", "Structural constituent of cytoskeleton", "6", "4.58E − 08"], ["GO_MF_m11", "GO:0003777", "Microtubule motor activity", "21", "3.95E − 38"], ["GO_MF_m12", "GO:0030276", "Clathrin binding", "9", "2.00E − 14"], ["GO_MF_m13", "GO:0042605", "Peptide antigen binding", "5", "2.31E − 09"], ["GO_MF_m14", "GO:0043515", "Kinetochore binding", "4", "9.27E − 10"], ["GO_MF_m15", "GO:0016776", "Phosphotransferase activity", "10", "4.97E − 20"], ["GO_MF_m16", "GO:0140097", "Catalytic activity, acting on DNA", "13", "5.26E − 17"], ["GO_MF_m17", "GO:0003684", "Damaged DNA binding", "16", "9.67E − 31"], ["GO_MF_m18", "GO:0004674", "Protein serine/threonine kinase activity", "8", "6.57E − 07"]], "row_count": 31, "column_count": 5, "numeric_cells": 117, "header_rows": 1, "locator": "section[13]/table-wrap[1]#tab3"}}, {"id": "asset:table:pmid:32596346:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2c8913d3a71f3fc3ec993c063b39b164196f7e079ec55e1b3e999923af9a0072", "bytes": 3491, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[2]#tab4", "version": null, "note": "The significant KEGG enrichment analysis of module gene function in idiopathic pulmonary fibrosis.", "structure": {"pmcid": "PMC7290873", "section_index": 13, "section_title": "3.3. Construction and Enrichment Analysis of Modules", "row_count": 19, "column_count": 5}, "table": {"label": "Table 4", "caption": "The significant KEGG enrichment analysis of module gene function in idiopathic pulmonary fibrosis.", "rows": [["Pathway", "Pathway description", "Count", "P value", "Genes"], ["KEGG_Pathway_m1", "Ubiquitin mediated proteolysis", "30", "1.21E − 46", "10273, 10477, 11065, 22954, 23327, 25898, 51433, 51434, 54926, 55070, 57154, 65264, 7318, 7320, 7321, 7323, 7326, 7328, 7332, 7428, 83737, 8454, 8697, 9021, 90293, 9246, 92912, 9820, 991, 6921"], ["KEGG_Pathway_m2", "Spliceosome", "30", "1.23E − 44", "10084, 10262, 10285, 10594, 10907, 10946, 10992, 1665, 22827, 51340, 51690, 57187, 57819, 6428, 6429, 6430, 6432, 6434, 6625, 6626, 6628, 6635, 7307, 8175, 84321, 8449, 84991, 9775, 988, 9984"], ["KEGG_Pathway_m15", "Purine metabolism", "26", "8.05E − 39", "10201, 11128, 124583, 171568, 205, 2987, 29922, 3704, 4831, 4832, 4833, 4881, 50484, 50808, 51251, 5138, 5315, 5422, 6240, 6241, 84284, 953, 955, 956, 2982, 2983"], ["KEGG_Pathway_m16", "Fanconi anemia pathway", "20", "2.23E − 37", "2067, 2072, 2176, 2178, 2188, 2189, 22909, 29089, 51426, 5429, 55120, 5889, 6118, 6119, 672, 80010, 80198, 84464, 80233, 91442"], ["KEGG_Pathway_m4", "Protein digestion and absorption", "21", "1.16E − 36", "1277, 1278, 1281, 1285, 1287, 1288, 1289, 1290, 1292, 1293, 1294, 1299, 1300, 1303, 1306, 1308, 255631, 7373, 80781, 81578, 85301"], ["KEGG_Pathway_m5", "Glutathione metabolism", "20", "1.44E − 36", "124975, 2678, 2687, 27306, 2878, 2879, 2880, 2882, 2937, 2938, 2941, 2948, 2949, 2950, 2952, 373156, 4257, 4258, 493869, 51060"], ["KEGG_Pathway_m6", "Ribosome", "20", "4.77E − 35", "11222, 29088, 51069, 51073, 51116, 51263, 51264, 51318, 54460, 54948, 6183, 63875, 63931, 64928, 64963, 64965, 64983, 65003, 65008, 79590"], ["KEGG_Pathway_m17", "Nucleotide excision repair", "16", "4.27E − 30", "1022, 1069, 1642, 1643, 2067, 2072, 2968, 3978, 5111, 5425, 6118, 6119, 7507, 7508, 8451, 902"], ["KEGG_Pathway_m9", "Neuroactive ligand-receptor interaction", "25", "7.26E − 28", "10161, 10800, 1131, 1241, 148, 154, 185, 1902, 1910, 2149, 2151, 2925, 3061, 3357, 3358, 4829, 4923, 5021, 5028, 5031, 624, 680, 6915, 7201, 9002"], ["KEGG_Pathway_m3", "Neuroactive ligand-receptor interaction", "25", "3.41E − 21", "1129, 1268, 150, 152, 1813, 187, 1901, 1902, 1903, 2357, 2358, 2359, 2587, 2913, 2918, 4543, 4887, 59340, 624, 6752, 6755, 719, 728, 9294, 9568"], ["KEGG_Pathway_m8", "Ribosome biogenesis in eukaryotes", "12", "5.45E − 20", "10171, 10799, 134430, 23560, 27341, 3692, 51096, 51119, 51602, 55341, 55651, 84916"], ["KEGG_Pathway_m7", "Ribosome", "17", "7.99E − 19", "11224, 25873, 51065, 6128, 6141, 6156, 6157, 6160, 6168, 6169, 6181, 6201, 6205, 6229, 6231, 6232, 6234"], ["KEGG_Pathway_m12", "Endocytosis", "16", "3.91E − 16", "10109, 1173, 1759, 1785, 1956, 22905, 26119, 27131, 273, 3949, 408, 5868, 6456, 6643, 867, 8976"], ["KEGG_Pathway_m13", "Herpes simplex infection", "11", "8.93E − 13", "10379, 3105, 3113, 3115, 3122, 3134, 3434, 3661, 4938, 4940, 6041"], ["KEGG_Pathway_m18", "Cell cycle", "7", "9.18E − 11", "4085, 701, 7272, 8379, 890, 891, 9133"], ["KEGG_Pathway_m14", "Oocyte meiosis", "8", "8.35E − 10", "4085, 5516, 5525, 5528, 5529, 8379, 891, 9133"], ["KEGG_Pathway_m11", "Vasopressin-regulated water reabsorption", "6", "1.07E − 09", "10540, 1639, 51164, 79659, 84516, 8655"], ["KEGG_Pathway_m10", "Pathogenic Escherichia coli infection", "3", "5.99E − 05", "203068, 7277, 7846"]], "row_count": 19, "column_count": 5, "numeric_cells": 63, "header_rows": 1, "locator": "section[13]/table-wrap[2]#tab4"}}, {"id": "asset:table:pmid:32596346:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:66c2a3d19a6b05aafbef1700f48913f9842ff265a2a1ce4a1d6b63046a76f38d", "bytes": 2549, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#tab5", "version": null, "note": "Functional roles of the strongest correlations of lncRNAs and TFs in IPF.", "structure": {"pmcid": "PMC7290873", "section_index": 14, "section_title": "3.4. Selection and Analysis of Key Genes", "row_count": 13, "column_count": 4}, "table": {"label": "Table 5", "caption": "Functional roles of the strongest correlations of lncRNAs and TFs in IPF.", "rows": [["No.", "Gene symbol", "Full name", "Function"], ["1", "MALAT1", "Metastasis-associated lung adenocarcinoma transcript 1", "Form molecular scaffolds for ribonucleoprotein complexes, acting as a transcriptional regulator for numerous genes, and involved in cell cycle regulation"], ["2", "RNU1-1", "RNA, U1 small nuclear 1", "Its related pathways are spliceosomal splicing cycle"], ["3", "FENDRR", "FOXF1 adjacent noncoding developmental regulatory RNA", "Bind to polycomb repressive complex 2 and/or TrxG/MLL complexes to promote the methylation of the promoters of target genes"], ["4", "TUG1", "Taurine upregulated 1", "Interacts with the polycomb repressor complex and functions in the epigenetic regulation of transcription, acting as a sponge for microRNAs"], ["5", "E2F1", "E2F transcription factor 1", "Bind preferentially to retinoblastoma protein pRB in a cell cycle-dependent manner and mediate both cell proliferation and p53-dependent/independent apoptosis"], ["6", "TP53", "Tumor protein P53", "Regulate expression of target genes, inducing cell cycle arrest, apoptosis, senescence, DNA repair, or changes in metabolism"], ["7", "SP1", "Sp1 transcription factor", "Be involved in many cellular processes, including cell differentiation, cell growth, apoptosis, immune responses, response to DNA damage, and chromatin remodeling"], ["8", "YBX1", "Y-box binding protein 1", "Be implicated in numerous cellular processes including regulation of transcription and translation, pre-mRNA splicing, DNA reparation, and mRNA packaging"], ["9", "BRCA1", "Breast cancer type 1 susceptibility protein", "Play a role in transcription, DNA repair of double-stranded breaks, and recombination which forms a large multisubunit protein complex known as the BRCA1-associated genome surveillance complex and interacts with histone deacetylase complexes"], ["10", "E2F4", "E2F transcription factor 4", "Act as proliferation-associated suppression genes and bind to all three of the tumor suppressor proteins pRB, p107, and p130"], ["11", "CREB1", "CAMP responsive element binding protein 1", "Its related pathways are development of HGF signaling pathway and circadian entrainment"], ["12", "CIITA", "Class II major histocompatibility complex transactivator", "Once it does not bind DNA but rather uses an intrinsic acetyltransferase activity to act in a coactivator-like fashion"]], "row_count": 13, "column_count": 4, "numeric_cells": 26, "header_rows": 1, "locator": "section[14]/table-wrap[1]#tab5"}}, {"id": "asset:table:pmid:32596346:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d2133cec8791b6d624d010e150c6b45f86778dfe404305a9c353701194a01a97", "bytes": 886, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#tab6", "version": null, "note": "Demographic and clinical characteristics of the subjects.", "structure": {"pmcid": "PMC7290873", "section_index": 15, "section_title": "3.5. Validation of the lncRNAs and TFs in IPF with qRT-PCR", "row_count": 15, "column_count": 4}, "table": {"label": "Table 6", "caption": "Demographic and clinical characteristics of the subjects.", "rows": [["", "Healthy controls", "IPF", "P value"], ["n = 20", "n = 20"], ["Age, mean (SD)", "68.4 (4.7)", "69.0 (6.6)", "0.74"], ["Gender, n (%)", "", "", "0.07"], ["Male", "11 (55)", "12 (60)", ""], ["Female", "9 (45)", "8 (40)", ""], ["Smoker, n (%)", "", "", "0.001"], ["Current", "4 (20)", "2 (10)", ""], ["Former", "7 (35)", "10 (50)", ""], ["Never", "9 (45)", "8 (40)", ""], ["Smoking dose (pack-year)", "37 (14.5-58)", "35.7 (12-56)", "0.14"], ["FVC (% predicted), mean (SD)", "96.2 (11.7)", "63.88 (17.0)", "<0.01"], ["DLCO (% predicted), mean (SD)", "80.8 (17.6)", "42.04 (16.5)", "<0.01"], ["FEV1 (% predicted), mean (SD)", "106.0 (18.6)", "71.7 (11.0)", "<0.001"], ["FEV1/FVC (%), mean (SD)", "79.9 (5.0)", "57.8 (8.3)", "<0.001"]], "row_count": 15, "column_count": 4, "numeric_cells": 32, "header_rows": 2, "locator": "section[15]/table-wrap[1]#tab6"}}], "gaps": ["asset:data:geo:GSE2052 not downloaded", "asset:data:geo:GSE2052 licence not read", "asset:data:geo:GSE24206 not downloaded", "asset:data:geo:GSE24206 licence not read", "asset:data:geo:GSE44723 not downloaded", "asset:data:geo:GSE44723 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "hierarchical clustering"}}, {"id": "method-2", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {"n_modules": "work was used to obtain 18 modules of related genes"}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}, {"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": 0.8, "band": "high", "quote": "pathway enrichment"}}, {"id": "method-4", "family": null, "specific": null, "label": "Classic t-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "After pretreatment of the genes that came from more than one probe set, the DEGs identified with cutoff criteria of |logFC| > 1 and P < 0.05 by the classic t-test were considered statistically significant."}}], "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": ["hierarchical_cluster"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: hierarchical."}, "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": ["GSE2052", "GSE44723", "GSE24206"], "resolved_accessions": ["GSE2052", "GSE44723", "GSE24206"], "statements": ["The datasets used and/or analyzed during the present study are available from the corresponding author on reasonable request."], "basis": "The paper names GSE2052, GSE44723, GSE24206 in NCBI-GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["hierarchical_cluster"], "assets": ["source:pmid:32596346", "data:geo:GSE2052", "asset:table:pmid:32596346:1", "asset:table:pmid:32596346:2", "asset:table:pmid:32596346:3", "asset:table:pmid:32596346:4", "asset:table:pmid:32596346:5", "asset:table:pmid:32596346:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE2052"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:01Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 28611, "completion_tokens": 1233, "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:32596346", "type": "paper", "label": "pmid:32596346"}, {"id": "source:pmid:32596346", "type": "manuscript", "label": "PMID 32596346 full text"}, {"id": "data:geo:GSE2052", "type": "dataset", "label": "GEO GSE2052"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32596346", "type": "paper", "label": "pmid:32596346"}, {"id": "source:pmid:32596346", "type": "manuscript", "label": "PMID 32596346 full text"}, {"id": "data:geo:GSE2052", "type": "dataset", "label": "GEO GSE2052"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32596346", "type": "extraction", "used": ["source:pmid:32596346"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE2052", "type": "accession_resolution", "used": ["data:geo:GSE2052"], "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:32596346", "parent_hash": "sha256:40d37431f2eac5c9c5bd4d03811f6a9c3c6da0f8b9dea145c7ca12951aa88e09", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE2052 licence not read", "asset:data:geo:GSE2052 not downloaded", "asset:data:geo:GSE24206 licence not read", "asset:data:geo:GSE24206 not downloaded", "asset:data:geo:GSE44723 licence not read", "asset:data:geo:GSE44723 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "clustering", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["hierarchical_cluster"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["hierarchical clustering"], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:42:36+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}}}