{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26986014", "kind": "science-record", "revision": 8, "content_hash": "sha256:69eea4a003d4e3b1ed5354da4290c0bf5ab769ab6822666a71acda9d301b7451", "created_at": "2026-11-01T15:40:17Z", "updated_at": "2026-11-01T21:58:59Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Prediction of the molecular mechanisms and potential therapeutic targets for diabetic nephropathy by bioinformatics methods.", "doi": "10.3892/ijmm.2016.2527", "pmid": "26986014", "authors": ["Wan-Ning Wang", "Wen-Long Zhang", "Guang-Yu Zhou", "Fu-Zhe Ma", "Tao Sun", "Sen-Sen Su", "Zhong-Gao Xu"], "journal": "International journal of molecular medicine", "year": 2016, "abstract": "In this study, we aimed to explore the molecular mechanisms of and genetic factors influencing diabetic nephropathy (DN). Gene expression profiles associated with DN were obtained from the GEO database (Accession no. GSE20844). The differentially expressed genes (DEGs) between diabetic mice and non-diabetic mice were screened. Subsequently, the DEGs were subjected to functional and pathway analysis. The protein-protein interaction (PPI) network was constructed and the transcription factors (TFs) were screened among the DEGs. A total of 92 upregulated and 118 downregulated genes were screened. Pathway analysis revealed that the p53 signaling pathway, the transforming growth factor (TGF)-β signaling pathway and the mitogen-activated protein kinase (MAPK) signaling pathway were significantly enriched by upregulated genes. Serpine1 (also known as plasminogen activator inhibitor-1), early growth response 1 (Egr1) and Mdk were found to be significant nodes in the PPI network by three methods. A total of 12 TFs were found to be differentially expressed, of which nuclear receptor subfamily 4, group A, member 1 (Nr4a1) and peroxisome proliferator-activated receptor gamma (Pparg) were found to have multiple interactions with other DEGs. We demonstrated that the p53 signaling pathway, the TGF-β signaling pathway and the MAPK signaling pathway were dysregulated in the diabetic mice. The significant nodes (Serpine1, Egr1 and Mdk) and differentially expressed TFs (Nr4a1 and Pparg) may provide a novel avenue for the targeted therapy of DN.", "claims": [{"id": "claim-method", "statement": "The P-value for each gene was calculated using the Student's t-test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26986014", "locator": "sections[4] \"Analysis of DEGs\" paragraph 2", "quote": "The P-value for each gene was calculated using the Student's t-test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "In the present study, we downloaded the same microarray data from the Gene Expression Omnibus (GEO) database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26986014", "locator": "sections[1] \"Introduction\" paragraph 4", "quote": "In the present study, we downloaded the same microarray data from the Gene Expression Omnibus (GEO) database."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using Bioconductor limma with a Student's t-test on GEO dataset GSE20844, the study identified 210 differentially expressed genes in diabetic mice, comprising 92 upregulated and 118 downregulated genes.", "kind": "quantitative", "target": {"value": 0.05, "unit": "p-value", "tolerance": null, "source": "According to values of p<0.05 and |log2FC(fold change)|≥0.58, a total of 210 genes were found to be differentially expressed in the diabetic group, including 92 upregulated and 118 downregulated genes."}, "evidence": [{"asset": "source:pmid:26986014", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Gene expression profiles associated with DN were obtained from the GEO database (Accession no. GSE20844)."}, {"asset": "source:pmid:26986014", "locator": "sections[9] \"Identification of DEGs\" paragraph 2", "quote": "According to values of p<0.05 and |log2FC(fold change)|≥0.58, a total of 210 genes were found to be differentially expressed in the diabetic group, including 92 upregulated and 118 downregulated genes."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "Using Bioconductor limma with a Student's t-test on GEO dataset GSE20844, the study identified 210 differentially expressed genes in diabetic mice, comprising 92 upregulated and 118 downregulated genes.", "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:26986014"], "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:GSE20844"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:student_t", "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:GSE20844"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:student_t"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26986014", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3892/ijmm.2016.2527", "sha256": "sha256:2a51bf5f84f2d89b68f8fe8933f57f0c699ac27123a15b8f7bf8366bc58e8a36", "bytes": 24069, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3892/ijmm.2016.2527", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4829133", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE20844", "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=GSE20844", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE20844", "version": null, "note": "In the present study, we downloaded the same microarray data from the Gene Expression Omnibus (GEO) database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "In the present study, we downloaded the same microarray data from the Gene Expression Omnibus (GEO) database.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM519444", "GSM519445", "GSM519766", "GSM519813", "GSM519814", "GSM519815", "GSM519816"], "sample_count": 7, "group_sizes": null, "group_sizes_basis": null, "platform": "1261", "taxon": "Mus musculus", "title": "Differential Expression of Ove26(Diabetic) vs FVB(Nondiabetic) mice", "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:26986014:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3b16233a28a4da1751bdce631bcac1b2d6017195a39d3b6b007a34e7de3ace32", "bytes": 2079, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#tI-ijmm-37-05-1181", "version": null, "note": "The significant GO terms enriched by DEGs.", "structure": {"pmcid": "PMC4829133", "section_index": 10, "section_title": "GO and pathway analysis", "row_count": 39, "column_count": 3}, "table": {"label": "Table I", "caption": "The significant GO terms enriched by DEGs.", "rows": [["Term", "Count", "P-value"], ["Upregulated genes"], ["BP"], ["GO:0042127 - regulation of cell proliferation", "13", "2.30E-05"], ["GO:0045765 - regulation of angiogenesis", "5", "9.16E-05"], ["GO:0016525 - negative regulation of angiogenesis", "4", "2.04E-04"], ["GO:0008285 - negative regulation of cell proliferation", "7", "0.001184688"], ["GO:0009611 - response to wounding", "8", "0.002365745"], ["CC"], ["GO:0005576 - extracellular region", "20", "5.60E-05"], ["GO:0044421 - extracellular region part", "11", "0.001793488"], ["GO:0046658 - anchored to plasma membrane", "3", "0.002476471"], ["GO:0005615 - extracellular space", "8", "0.006777968"], ["GO:0044459 - plasma membrane part", "14", "0.022475418"], ["MF"], ["GO:0005172 - vascular endothelial growth factor receptor binding", "3", "2.41E-04"], ["GO:0005539 - glycosaminoglycan binding", "5", "0.002459879"], ["GO:0030247 - polysaccharide binding", "5", "0.00373434"], ["GO:0001871 - pattern binding", "5", "0.00373434"], ["GO:0030246 - carbohydrate binding", "7", "0.00480543"], ["Downregulated genes"], ["BP"], ["GO:0006873 - cellular ion homeostasis", "7", "0.002754032"], ["GO:0055082 - cellular chemical homeostasis", "7", "0.003139335"], ["GO:0048878 - chemical homeostasis", "8", "0.003390517"], ["GO:0050801 - ion homeostasis", "7", "0.004850765"], ["GO:0019725 - cellular homeostasis", "7", "0.010204447"], ["CC"], ["GO:0016324 - apical plasma membrane", "6", "3.76E-04"], ["GO:0005576 - extracellular region", "22", "0.001139987"], ["GO:0045177 - apical part of cell", "6", "0.001580783"], ["GO:0005615 - extracellular space", "9", "0.014078693"], ["GO:0005903 - brush border", "3", "0.020010741"], ["MF"], ["GO:0015293 - symporter activity", "5", "0.008223849"], ["GO:0019807 - aspartoacylase activity", "2", "0.012005144"], ["GO:0008201 - heparin binding", "4", "0.013672168"], ["GO:0004046 - aminoacylase activity", "2", "0.023867944"], ["GO:0031402 - sodium ion binding", "4", "0.024166754"]], "row_count": 39, "column_count": 3, "numeric_cells": 90, "header_rows": 1, "locator": "section[10]/table-wrap[1]#tI-ijmm-37-05-1181"}}, {"id": "asset:table:pmid:26986014:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d7fe5072f66c427f68a6497530f74f0c3d50fb708b11afd70b094d9335ce1284", "bytes": 693, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#tII-ijmm-37-05-1181", "version": null, "note": "Pathways significantly enriched by differentially expressed genes.", "structure": {"pmcid": "PMC4829133", "section_index": 10, "section_title": "GO and pathway analysis", "row_count": 10, "column_count": 3}, "table": {"label": "Table II", "caption": "Pathways significantly enriched by differentially expressed genes.", "rows": [["Term", "Count", "P-value"], ["Upregulation"], ["mmu04115: p53 signaling pathway", "5", "7.57E-04"], ["mmu04110: Cell cycle", "5", "0.007243672"], ["mmu04060: Cytokine-cytokine receptor interaction", "6", "0.015248477"], ["mmu04350: TGF-β signaling pathway", "4", "0.015533727"], ["mmu04010: MAPK signaling pathway", "6", "0.021089527"], ["mmu05219: Bladder cancer", "3", "0.026718766"], ["Downregulation"], ["mmu00040: Pentose and glucuronate interconversions", "3", "0.003652816"]], "row_count": 10, "column_count": 3, "numeric_cells": 21, "header_rows": 1, "locator": "section[10]/table-wrap[2]#tII-ijmm-37-05-1181"}}, {"id": "asset:table:pmid:26986014:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:53ea3ae386e53576dbb4f7cf611c0db29def21292e7812060fe763842b092369", "bytes": 1143, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#tIII-ijmm-37-05-1181", "version": null, "note": "Top 15 significant nodes in the protein-protein interaction network based on degree, betweenness and subgraph centralities.", "structure": {"pmcid": "PMC4829133", "section_index": 11, "section_title": "PPI network", "row_count": 16, "column_count": 6}, "table": {"label": "Table III", "caption": "Top 15 significant nodes in the protein-protein interaction network based on degree, betweenness and subgraph centralities.", "rows": [["Node", "Degree", "Node betweenness", "Betweenness", "Node subgragh", "Subgragh"], ["Serpine1", "16", "Serpine1", "2905.323", "Egr1", "337.665"], ["Egr1", "15", "Egr1", "2433.539", "Serpine1", "337.1419"], ["Mdk", "14", "Mdk", "2319.191", "Mdk", "285.9198"], ["Nr4a1", "12", "Pparg", "2105.681", "Icam1", "209.8053"], ["Icam1", "12", "Lrp2", "2064.846", "Cdkn1a", "187.7399"], ["Cdkn1a", "12", "Cdh16", "1583.724", "Nr4a1", "178.7159"], ["Tlr4", "11", "Umod", "1440.558", "Tlr4", "147.8937"], ["Cdk1", "10", "Ltf", "1421.087", "Dusp1", "119.8608"], ["Bmp2", "10", "Ggt1", "1384.699", "Bmp2", "117.067"], ["Dusp1", "9", "Tlr4", "1286.763", "Cyr61", "104.8729"], ["Pparg", "8", "Slc12a1", "1250.098", "Pparg", "85.67106"], ["Ltf", "7", "Nr4a1", "1248.253", "Cybb", "68.2394"], ["Egf", "7", "Icam1", "1223.037", "Smad6", "63.11027"], ["Cybb", "7", "Cdk1", "1119.84", "Cdk1", "56.22912"], ["Tgfb3", "7", "Wfdc15b", "1082.356", "Map3k8", "52.32016"]], "row_count": 16, "column_count": 6, "numeric_cells": 49, "header_rows": 1, "locator": "section[11]/table-wrap[1]#tIII-ijmm-37-05-1181"}}, {"id": "asset:table:pmid:26986014:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:02e9bf67ddd5b8d5d9f5c7bb584f45024971711a94033e046f6020203a4b711d", "bytes": 671, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#tIV-ijmm-37-05-1181", "version": null, "note": "The significant pathways enriched by 24 significant nodes in the protein-protein interaction network.", "structure": {"pmcid": "PMC4829133", "section_index": 11, "section_title": "PPI network", "row_count": 6, "column_count": 3}, "table": {"label": "Table IV", "caption": "The significant pathways enriched by 24 significant nodes in the protein-protein interaction network.", "rows": [["Term", "P-value", "Genes"], ["mmu04010: MAPK signaling pathway", "0.005210429", "Dusp1, Map3K8, Tgfb3, Nr4A1, Egf"], ["mmu05200: Pathways in cancer", "0.010457331", "Cdkn1A, Bmp2, Pparg, Tgfb3, Egf"], ["mmu04115: p53 signaling pathway", "0.015340116", "Cdk1, Cdkn1A, Serpine1"], ["mmu04350: TGF-β signaling pathway", "0.023759324", "Bmp2, Smad6, Tgfb3"], ["mmu04110: Cell cycle", "0.048314969", "Cdk1, Cdkn1A, Tgfb3"]], "row_count": 6, "column_count": 3, "numeric_cells": 10, "header_rows": 1, "locator": "section[11]/table-wrap[2]#tIV-ijmm-37-05-1181"}}, {"id": "asset:table:pmid:26986014:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f0a7f7756786626b10b76697b775e78f561ffd3b6470734d2efd3a20ec25f588", "bytes": 517, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#tV-ijmm-37-05-1181", "version": null, "note": "Differentially expressed transcription factors in diabetic samples.", "structure": {"pmcid": "PMC4829133", "section_index": 12, "section_title": "Analysis of TFs", "row_count": 13, "column_count": 2}, "table": {"label": "Table V", "caption": "Differentially expressed transcription factors in diabetic samples.", "rows": [["TF family", "TF gene symbol"], ["bHLH", "Atoh8"], ["bHLH", "Hey1"], ["HMG", "Tox2"], ["Homeobox", "Meox1"], ["Homeobox", "Six4"], ["IRF", "Irf6"], ["MH1", "Smad6"], ["Nuclear orphan receptor", "Nr4a1"], ["PPAR receptor", "Pparg"], ["Thyroid hormone receptor", "Vdr"], ["zf-C2H2", "Klf6"], ["zf-C2H2", "Egr1"]], "row_count": 13, "column_count": 2, "numeric_cells": 0, "header_rows": 1, "locator": "section[12]/table-wrap[1]#tV-ijmm-37-05-1181"}}], "gaps": ["asset:data:geo:GSE20844 not downloaded", "asset:data:geo:GSE20844 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The P-value for each gene was calculated using the Student's t-test."}}, {"id": "method-2", "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": 0.8, "band": "high", "quote": "limma"}}, {"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"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "build_graph", "expected_value": 0.05, "unit": "p-value", "tolerance": null, "state": "complete", "note": "The threshold the paper applied to its own result, as the paper states it. A run that reproduces the effect is judged against this threshold."}], "gaps": ["method.student_t"]}, "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": false, "required_operations": [], "missing_operations": ["student_t"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: student_t_test."}, "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": ["GSE20844"], "resolved_accessions": ["GSE20844"], "statements": ["In the present study, we downloaded the same microarray data from the Gene Expression Omnibus (GEO) database."], "basis": "The paper names GSE20844 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": [], "assets": ["source:pmid:26986014", "data:geo:GSE20844", "asset:table:pmid:26986014:1", "asset:table:pmid:26986014:2", "asset:table:pmid:26986014:3", "asset:table:pmid:26986014:4", "asset:table:pmid:26986014:5"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "student_t", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE20844"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:28:10Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 8, "usage": {"prompt_tokens": 52847, "completion_tokens": 2857, "cached_tokens": 2096}}, "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:26986014", "type": "paper", "label": "pmid:26986014"}, {"id": "source:pmid:26986014", "type": "manuscript", "label": "PMID 26986014 full text"}, {"id": "data:geo:GSE20844", "type": "dataset", "label": "GEO GSE20844"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26986014", "type": "paper", "label": "pmid:26986014"}, {"id": "source:pmid:26986014", "type": "manuscript", "label": "PMID 26986014 full text"}, {"id": "data:geo:GSE20844", "type": "dataset", "label": "GEO GSE20844"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26986014", "type": "extraction", "used": ["source:pmid:26986014"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE20844", "type": "accession_resolution", "used": ["data:geo:GSE20844"], "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:26986014", "parent_hash": "sha256:f2e82dfaab204bd82d5acf046ae1f2d01686e135343dee32fd000e03cf4c5e13", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE20844 licence not read", "asset:data:geo:GSE20844 not downloaded", "execution.not_run", "method.student_t", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:student_t"], "assays": [{"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["DEGs) between diabetic mice and non-diabetic mice were screened. Subsequently, the DEGs were subjec"], "order_basis": "paper_text_order:389", "id": "assay:1"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The P-value for each gene was calculated using the Student's t-test."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"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":"2026-11-04T02:48:40+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}}}