{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:26203686", "kind": "science-record", "revision": 3, "content_hash": "sha256:2e764ef0d2004836903aab5b1a45c132db664f3fdfbd17dbf317d4b5604aaf8d", "created_at": "2026-11-01T15:01:41Z", "updated_at": "2026-11-01T16:36:33Z", "generator": {"name": "corpus-assay-engine", "run_id": "pdf-sci-2026-11-01"}, "paper": {"state": "partial", "title": "MicroRNA-125b and chemokine CCL4 expression are associated with calcific aortic valve disease.", "doi": "10.3109/07853890.2015.1059955", "pmid": "26203686", "authors": null, "journal": "Annals of medicine", "year": 2015, "abstract": "Calcific aortic valve disease (CAVD) is a progressive pathological condition with no effective pharmacological therapy. To identify novel molecular pathways as potential targets for pharmacotherapy, we studied microRNA (miRNA) profiles of heavily stenotic aortic valves (AS). One of the most upregulated miRNAs in AS valves compared to control valves was miR-125b (1.4-fold; P < 0.05). To identify CAVD-related changes in gene expression, DNA microarray analysis was performed, including an intermediate fibro(sclero)tic stage of the disease. This revealed changes especially in genes related to inflammation and immune response, including chemokine (C-C motif) ligand 3 (CCL3) and 4 (CCL4). CCL3 mRNA level was increased 3.9-fold (P < 0.05) when AS valves were compared to control valves, and a 2.5-fold increase (P < 0.05) in CCL4 gene expression was observed when fibro(sclero)tic valves were compared to control valves. Both CCL3 and CCL4 localized to macrophages by immunofluorescence. To identify chemokine-miRNA target pairs, data from miRNA target prediction databases were combined with valvular miRNA and mRNA expression profiles. MiR-125b was computationally predicted to target CCL4, as confirmed experimentally in cultured human THP-1 macrophages. Collectively, miR-125b and CCL4 appear to be involved in the progression of CAVD and may offer novel therapeutic and diagnostic strategies related to this disease.", "claims": [{"id": "claim-method", "statement": "Genes were defined as differentially expressed if the change was at least 2.0-fold and statistically significant (P<0.05, One-way ANOVA and Benjamini and Hochberg false discovery rate).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26203686", "locator": "sections[5] \"DNA microarray analysis\" paragraph 2", "quote": "Genes were defined as differentially expressed if the change was at least 2.0-fold and statistically significant (P<0.05, One-way ANOVA and Benjamini and Hochberg false discovery rate)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "CCL3 mRNA level was increased 3.9-fold (P < 0.05) when AS valves were compared to control valves, and a 2.5-fold increase (P < 0.05) in CCL4 gene expression was observed when fibro(sclero)tic valves were compared to control valves.", "kind": "quantitative", "target": {"value": null, "unit": null, "tolerance": null, "source": "CCL3 mRNA level was increased 3.9-fold (P < 0.05) when AS valves were compared to control valves, and a 2.5-fold increase (P < 0.05) in CCL4 gene expression was observed when fibro(sclero)tic valves were compared to control valves."}, "evidence": [{"asset": "source:pmid:26203686", "locator": "abstract paragraph 1", "quote": "CCL3 mRNA level was increased 3.9-fold (P < 0.05) when AS valves were compared to control valves, and a 2.5-fold increase (P < 0.05) in CCL4 gene expression was observed when fibro(sclero)tic valves were compared to control valves."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The complete data sets are available from the NCBI’s Gene Expression Omnibus (GEO) database and gene expression profiling data comply with the Minimum Information About a Microarray Experiment (MIAME) standard. The data can be obtained from the GEO database with the accession numbers GSE51472.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:26203686", "locator": "sections[5] \"DNA microarray analysis\" paragraph 2", "quote": "The complete data sets are available from the NCBI’s Gene Expression Omnibus (GEO) database and gene expression profiling data comply with the Minimum Information About a Microarray Experiment (MIAME) standard. The data can be obtained from the GEO database with the accession numbers GSE51472."}], "state": "complete"}, {"id": "claim-target-ccl3-as-vs-control", "statement": "CCL3 (205114_s_at) was 7.32-fold in aortic stenosis vs control in the DNA microarray analysis.", "kind": "quantitative", "target": {"value": 7.32, "unit": "fold change (aortic stenosis vs control)", "tolerance": null, "source": "205114_s_at Chemokine (C-C motif) ligand 3 NM_002983 7.32"}, "evidence": [{"asset": "source:pmid:26203686", "locator": "sections[18] \"Supplementary Table 5. Differentially expressed genes between aortic stenosis group and\" paragraph 7", "quote": "205114_s_at Chemokine (C-C motif) ligand 3 NM_002983 7.32"}], "state": "complete"}, {"id": "claim-target-ccl4-as-vs-control", "statement": "CCL4 (204103_at) was 3.81-fold in aortic stenosis vs control in the DNA microarray analysis.", "kind": "quantitative", "target": {"value": 3.81, "unit": "fold change (aortic stenosis vs control)", "tolerance": null, "source": "204103_at Chemokine (C-C motif) ligand 4 NM_002984 3.81"}, "evidence": [{"asset": "source:pmid:26203686", "locator": "sections[18] \"Supplementary Table 5. Differentially expressed genes between aortic stenosis group and\" paragraph 7", "quote": "204103_at Chemokine (C-C motif) ligand 4 NM_002984 3.81"}], "state": "complete"}, {"id": "claim-target-ccl3-as-vs-fibro", "statement": "CCL3 (205114_s_at) was 5.66-fold in aortic stenosis vs fibro(sclerosis) in the DNA microarray analysis.", "kind": "quantitative", "target": {"value": 5.66, "unit": "fold change (aortic stenosis vs fibro(sclerosis))", "tolerance": null, "source": "205114_s_at Chemokine (C-C motif) ligand 3 NM_002983 5.66"}, "evidence": [{"asset": "source:pmid:26203686", "locator": "sections[19] \"Supplementary Table 6. Differentially expressed genes between aortic stenosis group and fibro(sclerotic)\" paragraph 5", "quote": "205114_s_at Chemokine (C-C motif) ligand 3 NM_002983 5.66"}], "state": "complete"}, {"id": "claim-target-ccl4-as-vs-fibro", "statement": "CCL4 (204103_at) was 3.03-fold in aortic stenosis vs fibro(sclerosis) in the DNA microarray analysis.", "kind": "quantitative", "target": {"value": 3.03, "unit": "fold change (aortic stenosis vs fibro(sclerosis))", "tolerance": null, "source": "204103_at Chemokine (C-C motif) ligand 4 NM_002984 3.03"}, "evidence": [{"asset": "source:pmid:26203686", "locator": "sections[19] \"Supplementary Table 6. Differentially expressed genes between aortic stenosis group and fibro(sclerotic)\" paragraph 7", "quote": "204103_at Chemokine (C-C motif) ligand 4 NM_002984 3.03"}], "state": "complete"}], "gaps": ["authors"]}, "experiment": {"state": "complete", "objective": "DNA microarray analysis of human aortic valve tissue identified differentially expressed genes in calcific aortic valve disease, using a ≥2-fold change with one-way ANOVA and Benjamini–Hochberg false discovery rate (P<0.05); the data are available in the NCBI GEO database under accession GSE51472, and CCL3 and CCL4 showed reported expression increases of 3.9-fold in aortic stenosis versus control valves and 2.5-fold in fibro(sclero)tic versus control valves, respectively.", "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:26203686"], "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:GSE51472"], "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": {"alpha": 0.05, "fold_change_threshold": 2.0, "false_discovery_rate": "Benjamini-Hochberg", "platform": "Affymetrix GeneChip Human Genome U133 Plus 2.0"}, "inputs": ["data:geo:GSE51472"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:26203686", "role": "manuscript", "format": "pdf", "media_type": "application/pdf", "uri": "https://ndownloader.figshare.com/files/2350161", "sha256": "sha256:6dbd53d906348f21636323a018356b51e1f8cf2bb58982eb3f0f6aff74315f2c", "bytes": 722529, "access": "open", "state": "verified", "reader": "read_pdf", "reader_status": "available", "identifier": "10.3109/07853890.2015.1059955", "version": null, "note": "The publisher's PDF, fetched as open material; the checksum covers the PDF bytes. The hash of the text read out of it is in structure.text_hash.", "structure": {"pmcid": null, "source": "publisher_pdf", "coverage": "whole_supplementary_document", "document_kind": "supplementary_material", "licence": "CC BY 4.0", "text_hash": "32ac39d27c986a97f0bc7ae713e81da79516c415ad4e0e3b334fb1014feb37ec", "text_hash_scope": "rendered_pdf_text", "cut": [{"what": "article-body", "reason": "The journal is not in PMC and the article body is not open. The publisher's supplementary material is open and is what was read.", "chars": null}]}}, {"id": "data:geo:GSE51472", "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=GSE51472", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE51472", "version": null, "note": "The complete data sets are available from the NCBI’s Gene Expression Omnibus (GEO) database and gene expression profiling data comply with the Minimum Information About a Microarray Experiment (MIAME) standard. The data can be obtained from the GEO database with the accession numbers GSE51472.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The complete data sets are available from the NCBI’s Gene Expression Omnibus (GEO) database and gene expression profiling data comply with the Minimum Information About a Microarray Experiment (MIAME) standard. The data can be obtained from the GEO database with the accession numbers GSE51472.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1246204", "GSM1246205", "GSM1246206", "GSM1246207", "GSM1246208", "GSM1246209", "GSM1246210", "GSM1246211", "GSM1246212", "GSM1246213", "GSM1246214", "GSM1246215", "GSM1246216", "GSM1246217", "GSM1246218"], "sample_count": 15, "group_sizes": {"control aortic valve": 5, "fibro(sclerotic) aortic valve": 5, "aortic stenosis aortic valve": 5}, "group_sizes_basis": "GEO sample metadata for GSE51472: fifteen samples in three groups of five, named here as the paper names them. Sample metadata only; no data was downloaded.", "platform": "570", "taxon": "Homo sapiens", "title": "Expression data of human aortic valve cusps", "resolution_checked_at": "2026-11-01T11:38:18Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:pdf:pmid:26203686:1", "role": "supplementary", "format": "pdf", "media_type": "application/pdf", "uri": "https://ndownloader.figshare.com/files/2350161", "sha256": "sha256:6dbd53d906348f21636323a018356b51e1f8cf2bb58982eb3f0f6aff74315f2c", "bytes": 722529, "access": "open", "state": "verified", "reader": "read_pdf", "reader_status": "available", "identifier": "https://ndownloader.figshare.com/files/2350161", "version": null, "note": "The publisher's PDF, carried with its checksum.", "structure": {"document_kind": "supplementary_material", "licence": "CC BY 4.0"}}], "gaps": ["asset:data:geo:GSE51472 not downloaded", "asset:data:geo:GSE51472 licence not read"], "group_sizes": {"aortic stenosis aortic valve": 5, "control aortic valve": 5, "fibro(sclerotic) aortic valve": 5}}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "One-way ANOVA with Benjamini and Hochberg false discovery rate", "label": "One-way analysis of variance", "dsl_operations": ["group_comparison_anova", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {"alpha": 0.05, "fold_change_threshold": 2.0, "false_discovery_rate": "Benjamini-Hochberg", "platform": "Affymetrix GeneChip Human Genome U133 Plus 2.0"}, "data_shapes": ["grouped numeric gene-expression measurements"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Genes were defined as differentially expressed if the change was at least 2.0-fold and statistically significant (P<0.05, One-way ANOVA and Benjamini and Hochberg false discovery rate)."}}], "targets": [{"id": "target-ccl3-as-vs-control", "claim_id": "claim-target-ccl3-as-vs-control", "operation": "group_comparison_anova", "expected_value": 7.32, "unit": "fold change (aortic stenosis vs control)", "tolerance": null, "state": "complete", "note": "CCL3, probe 205114_s_at, as printed in Supplementary Table 5 of the supplement. The abstract's 3.9-fold for CCL3 and 2.5-fold for CCL4 are the real-time qPCR values and are not what a re-analysis of the microarray series produces."}, {"id": "target-ccl4-as-vs-control", "claim_id": "claim-target-ccl4-as-vs-control", "operation": "group_comparison_anova", "expected_value": 3.81, "unit": "fold change (aortic stenosis vs control)", "tolerance": null, "state": "complete", "note": "CCL4, probe 204103_at, as printed in Supplementary Table 5 of the supplement. The abstract's 3.9-fold for CCL3 and 2.5-fold for CCL4 are the real-time qPCR values and are not what a re-analysis of the microarray series produces."}, {"id": "target-ccl3-as-vs-fibro", "claim_id": "claim-target-ccl3-as-vs-fibro", "operation": "group_comparison_anova", "expected_value": 5.66, "unit": "fold change (aortic stenosis vs fibro(sclerosis))", "tolerance": null, "state": "complete", "note": "CCL3, probe 205114_s_at, as printed in Supplementary Table 6 of the supplement. The abstract's 3.9-fold for CCL3 and 2.5-fold for CCL4 are the real-time qPCR values and are not what a re-analysis of the microarray series produces."}, {"id": "target-ccl4-as-vs-fibro", "claim_id": "claim-target-ccl4-as-vs-fibro", "operation": "group_comparison_anova", "expected_value": 3.03, "unit": "fold change (aortic stenosis vs fibro(sclerosis))", "tolerance": null, "state": "complete", "note": "CCL4, probe 204103_at, as printed in Supplementary Table 6 of the supplement. The abstract's 3.9-fold for CCL3 and 2.5-fold for CCL4 are the real-time qPCR values and are not what a re-analysis of the microarray series produces."}], "gaps": []}, "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:target_data_not_deposited", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["group_comparison_anova", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used on the microarray data: one-way ANOVA with the Benjamini and Hochberg false discovery rate at P<0.05 and a 2.0-fold threshold. The named operation is in the DSL catalogue. The physical methods of the paper are named as well, and they are not analysis operations."}, "capability": {"tier": "R4", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis of the microarray series is owned. The bench for the ELISA, the miRNA-125b transfection and the immunohistochemistry is not, so the paper's physical validation cannot be run here."}, "data": {"tier": "R4", "reachable": false, "accessions": ["GSE51472"], "statements": ["The complete data sets are available from the NCBI’s Gene Expression Omnibus (GEO) database and gene expression profiling data comply with the Minimum Information About a Microarray Experiment (MIAME) standard. The data can be obtained from the GEO database with the accession numbers GSE51472."], "basis": "GSE51472 resolves and covers the DNA microarray analysis, which is the part of this paper a re-analysis can check. The microRNA array, the real-time qPCR, the ELISA and the transfection experiment behind the paper's headline finding are not deposited anywhere, so that finding has no data route."}}, "can_run": {"dsl_operations": ["group_comparison_anova", "fdr_bh"], "assets": ["source:pmid:26203686", "data:geo:GSE51472", "asset:pdf:pmid:26203686:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE51472"]}, "gaps": ["data:target_data_not_deposited"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T14:26:04Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 16, "usage": {"prompt_tokens": 229985, "completion_tokens": 7501, "cached_tokens": 1204}}, "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:26203686", "type": "paper", "label": "pmid:26203686"}, {"id": "source:pmid:26203686", "type": "manuscript", "label": "PMID 26203686 full text"}, {"id": "data:geo:GSE51472", "type": "dataset", "label": "GEO GSE51472"}], "activities": [{"id": "activity-pdf-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:26203686", "type": "paper", "label": "pmid:26203686"}, {"id": "source:pmid:26203686", "type": "manuscript", "label": "PMID 26203686 full text"}, {"id": "data:geo:GSE51472", "type": "dataset", "label": "GEO GSE51472"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-26203686", "type": "extraction", "used": ["source:pmid:26203686"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE51472", "type": "accession_resolution", "used": ["data:geo:GSE51472"], "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": "pdf-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:26203686", "parent_hash": "sha256:49431df699b24b8923df550b06cee944b9f93e614dfe33d13749b68c88f97f65", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE51472 licence not read", "asset:data:geo:GSE51472 not downloaded", "authors", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["CAVD-related changes in gene expression, DNA microarray analysis was performed, including an interme", "ntary data Table 1). For miRNA-array and DNA microarray analyses, the samples were matched for all p"], "order_basis": "paper_text_order:493", "id": "assay:1"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["th CCL3 and CCL4 localized to macrophages by immunofluorescence. To identify chemokine-miRNA target pairs, d", "the area of the tissue sections. Factor VIII immunohistochemical staining was used to visualize density of bl", "in aortic valve cusps was also confirmed by immunohistochemical staining. Specific antibodies for CCL3/MIP-1"], "order_basis": "paper_text_order:1021", "id": "assay:2"}, {"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": ["nufacturer’s instructions and verified using qPCR (Supplementary Fig. 4). The cells and cell c", "cell culture supernatants were collected for qPCR and ELISA analyses. In qPCR, the average miR", "re collected for qPCR and ELISA analyses. In qPCR, the average miRNA- 125b expression of cells", "gen, Hilden, Germany). The quantification of real-time quantitative PCR results was done using the ѐѐCT method. Smal"], "order_basis": "paper_text_order:3945", "id": "assay:3"}, {"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": ["Collection (Manassas, VA; cat. TIB-202) and cultured in RPMI 1640 supplemented with 2 mM L- glutamin"], "order_basis": "paper_text_order:4838", "id": "assay:4"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["a- Aldrich, St. Louis, MO) for 24 hours. The transfection mixtures were prepared according to the manu", "UAACUUGUGA) mimics (by Ambion, Austin, USA). Transfection reagent was 1.4% Lipofectamin (Invitrogen) i", "were washed with PBS and incubated with the transfection reagents in THP-1 medium in the presence of", "the average miRNA- 125b expression of cells transfected with miRNA-125b was 170-fold (P<0.001) as co"], "order_basis": "paper_text_order:5182", "id": "assay:5"}, {"role": "data_generation", "definition_id": "elisa", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ure supernatants were collected for qPCR and ELISA analyses. In qPCR, the average miRNA- 125b e", "ed from cell culture media with a commercial ELISA kit (R&D Systems, Minneapolis, MN, USA) acco"], "order_basis": "paper_text_order:6022", "id": "assay:6"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["econdary antibody (Alexa Fluor 594 goat anti-mouse IgG3 (red), 1:100) was incubated for 1 hour", "dary antibodies (Alexa Fluor 488 donkey anti-mouse IgG1 (green) for CCL3 and Alexa Fluor 488 go", "s were carried out by substituting nonimmune mouse or rabbit serum for the primary antibodies.", "s were carried out by substituting nonimmune mouse or goat serum for the primary 9 antibodies."], "order_basis": "paper_text_order:8563", "id": "assay:7"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_comparison_anova", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Genes were defined as differentially expressed if the change was at least 2.0-fold and statistically significant (P<0.05, One-way ANOVA and Benjamini and Hochberg false discovery rate)."], "order_basis": "consumes_earlier_output", "id": "assay:8"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T00:41:10+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}}}