{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31294056", "kind": "science-record", "revision": 8, "content_hash": "sha256:9ae0000db431048bee786bb64baa4a9d5df169b3c1aeeed343531b772c8d1bc5", "created_at": "2026-11-01T15:40:47Z", "updated_at": "2026-11-01T22:44:04Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Transcriptomics data of a human in vitro model of non-alcoholic steatohepatitis exposed to elafibranor.", "doi": "10.1016/j.dib.2019.104093", "pmid": "31294056", "authors": ["Joost Boeckmans", "Karolien Buyl", "Alessandra Natale", "Valerie Vandenbempt", "Steven Branson", "Veerle De Boe", "Vera Rogiers", "Joery De Kock", "Robim M Rodrigues", "Tamara Vanhaecke"], "journal": "Data in brief", "year": 2019, "abstract": "The present dataset contains the transcriptomic characterization of a novel in vitro model of non-alcoholic steatohepatitis (NASH) as well as its transcriptomics read-outs for the evaluation of elafibranor, a potential anti-NASH compound. We report whole genome microarray data (Affymetrix HG U133 plus 2.0) of human multipotent stem cell-derived hepatic cells (hSKP-HPC) exposed to mediators of NASH. These cells were exposed to lipogenic inducers (insulin, glucose, fatty acids) and pro-inflammatory factors (IL-1β, TNF-α, TGF-β) to trigger hepatocellular responses characteristic of NASH. In addition, to evaluate the anti-NASH features of elafibranor, a dual peroxisome proliferator-activated receptor (PPAR) agonist that currently is under investigation as a potential anti-NASH therapeutic, was tested this in vitro set-up. This paper provides a detailed description of the microarray data as well as an indication of their value for evaluating cell signaling pathways (e.g. NFκB network) during the in vitro evaluation of anti-NASH compounds. Raw microarray data of different testing conditions were deposited as.CEL files in the Gene Expression Omnibus of NCBI with GEO Series accession number GSE126484. Further interpretation and discussion of these data can be found in the corresponding research article (DOI: 10.1016/j.phrs.2019.04.016) Boeckmans et al., 2019.", "claims": [{"id": "claim-method", "statement": "[Analysis cut-off: fold change [-2; +2], p < 0.05 (eBayes ANOVA)]", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31294056", "locator": "sections[2] \"Data\" paragraph 2", "quote": "[Analysis cut-off: fold change [-2; +2], p < 0.05 (eBayes ANOVA)]"}], "state": "complete"}, {"id": "claim-data-access", "statement": "Raw data is available at the Gene Expression Omnibus (GEO) from NCBI (GSE126484, www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE126484).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31294056", "locator": "sections[1] \"p\" paragraph 1", "quote": "Raw data is available at the Gene Expression Omnibus (GEO) from NCBI (GSE126484, www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE126484)."}], "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:31294056"], "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:GSE126484"], "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:GSE126484"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31294056", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2019.104093", "sha256": "sha256:7db4d852f7d1389293eaa8206542779a58b38975959489ac4a44ca27fbb4235e", "bytes": 9808, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2019.104093", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6595416", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE126484", "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=GSE126484", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE126484", "version": null, "note": "Raw data is available at the Gene Expression Omnibus (GEO) from NCBI (GSE126484, www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE126484).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Raw data is available at the Gene Expression Omnibus (GEO) from NCBI (GSE126484, www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE126484).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3602413", "GSM3602414", "GSM3602415", "GSM3602416", "GSM3602417", "GSM3602418", "GSM3602419", "GSM3602420", "GSM3602421", "GSM3602422", "GSM3602423", "GSM3602424"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Elafibranor restricts lipogenic and inflammatory responses in a human skin stem cell-derived model of NASH", "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:31294056:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:be3a5e89ea0704e3d3975d10d9c529e52be748eb7e13ec7100e8a659d05fc807", "bytes": 2127, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#undtbl1", "version": null, "note": "Specifications table", "structure": {"pmcid": "PMC6595416", "section_index": 1, "section_title": "p", "row_count": 10, "column_count": 2}, "table": {"label": null, "caption": "Specifications table", "rows": [["Subject area", "Pharmacology"], ["More specific subject area", "Preclinical drug development"], ["Type of data", "Figures and tables"], ["How data was acquired", "Affymetrix Human Genome U133 plus 2.0 array"], ["Data format", "Raw (.CEL) and normalized"], ["Experimental factors", "Human skin-derived precursors (hSKP) were differentiated towards hepatic cells (hSKP-HPC) as previously documented [2]. These cells were exposed for 24h to a cocktail of insulin (100 nM), glucose (4,5 mg/mL), sodium oleate (65 μM), palmitic acid (45 μM), tumor necrosis factor alpha (TNF-α) (50 ng/mL), interleukin-1 beta (IL-1β) (25 ng/mL) and transforming growth factor beta 1 (TGF-β1) (8 ng/mL). The obtained in vitro model was termed ‘hSKP-HPC NASH’ and was evaluated in the presence or absence of elafibranor (10 μM or 30 μM). Bovine serum albumin (BSA) and dimethyl sulfoxide (DMSO)-treated samples served as controls."], ["Experimental features", "Total RNA was extracted from ‘hSKP-HPC’ control samples (n = 3), ‘hSKP-HPC NASH’ (n = 3), ‘hSKP-HPC NASH’ + elafibranor 10 μM (n = 3) and ‘hSKP-HPC NASH’ + elafibranor 30 μM (n = 3). Analyses were conducted using Robust Multichip Average (RMA) Express, Transcriptome Analysis Console (TAC) (version 4.0.025, Applied Biosystems) and Ingenuity Pathway Analysis (IPA) (version 43605602, Qiagen)."], ["Data source location", "Department of In Vitro Toxicology and Dermato-Cosmetology (IVTD), Vrije Universiteit Brussel (VUB), Brussels, Belgium."], ["Data accessibility", "Raw data is available at the Gene Expression Omnibus (GEO) from NCBI (GSE126484, www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE126484)."], ["Related research article", "J. Boeckmans, K. Buyl, A. Natale, V. Vandenbempt, S. Branson, V. De Boe, V. Rogiers, J. De Kock, R.M. Rodrigues, T. Vanhaecke, Elafibranor restricts lipogenic and inflammatory responses in a human skin stem cell-derived model of NASH, Pharmacol. Res., 2019, In Press [1]."]], "row_count": 10, "column_count": 2, "numeric_cells": 5, "header_rows": 0, "locator": "section[1]/table-wrap[1]#undtbl1"}}, {"id": "asset:table:pmid:31294056:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f6eadab7f88b1a03ec8729a0b0dc92c97e88afb2cc7d9bb1dd1b8bd65dd58588", "bytes": 683, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[2]#undtbl2", "version": null, "note": null, "structure": {"pmcid": "PMC6595416", "section_index": 1, "section_title": "p", "row_count": 1, "column_count": 1}, "table": {"label": null, "caption": null, "rows": [["Value of the data•Human-based in vitro models can contribute to the pharmacological investigation of NASH and the development of potential anti-NASH drugs [3].•These transcriptomics data of a human skin stem cell-derived in vitro model for NASH, can be used for data mining when investigating NASH in vitro. They can also be utilized in comparative transcriptomics studies using other human-based datasets.•This is the first publicly available microarray dataset evaluating elafibranor using stem cell-derived hepatic cells."]], "row_count": 1, "column_count": 1, "numeric_cells": 1, "header_rows": 0, "locator": "section[1]/table-wrap[2]#undtbl2"}}, {"id": "asset:table:pmid:31294056:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f79bdd3b1c87022a42a4cb65d9fb9eafe6482d8ea3fcce616b889a630d6cbf2f", "bytes": 1787, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[1]#tbl1", "version": null, "note": "Top-10 highest up- and down-regulated genes between ‘hSKP-HPC NASH’ vs control samples, ‘hSKP-HPC NASH’ + elafibranor 10 μM vs ‘hSKP-HPC NASH’ and ‘hSKP-HPC NASH’ + elafibranor 30 μM vs ‘hSKP-HPC NASH’. [Analysis cut-off: fold change [-2; +2], p ≤ 0.05 (Fischer's exact test)].", "structure": {"pmcid": "PMC6595416", "section_index": 2, "section_title": "Data", "row_count": 22, "column_count": 7}, "table": {"label": "Table 1", "caption": "Top-10 highest up- and down-regulated genes between ‘hSKP-HPC NASH’ vs control samples, ‘hSKP-HPC NASH’ + elafibranor 10 μM vs ‘hSKP-HPC NASH’ and ‘hSKP-HPC NASH’ + elafibranor 30 μM vs ‘hSKP-HPC NASH’. [Analysis cut-off: fold change [-2; +2], p ≤ 0.05 (Fischer's exact test)].", "rows": [["", "‘hSKP-HPC NASH’ vs control samples", "‘hSKP-HPC NASH’ + elafibranor 10 μM vs ‘hSKP-HPC NASH’", "‘hSKP-HPC NASH’ + elafibranor 30 μM vs ‘hSKP-HPC NASH’"], ["Gene", "Fold change", "Gene", "Fold change", "Gene", "Fold change"], ["Image 1Top upregulate", "CCL20", "649.2", "F2RL2", "7.8", "F2RL2", "49.1"], ["CXCL5", "505.4", "SLC7A11", "4.7", "LINC00304", "38.5"], ["CCL8", "388.5", "NMRAL2P", "4.2", "STYK1", "38.0"], ["PTGS2", "178.5", "OSGIN2", "3.8", "HMOX1", "24.2"], ["MMP3", "138.9", "CES1", "3.5", "MAP2", "19.0"], ["CXCL8", "126.2", "SEL1L3", "3.0", "KCNE4", "18.1"], ["C15orf48", "121.9", "NQO1", "3.0", "mir-146", "17.7"], ["SERPINB4", "102.1", "PIR", "2.9", "NMRAL2P", "17.6"], ["CSF3", "91.8", "TMEFF2", "2.9", "SLCO2B1", "17.2"], ["HCK", "87.8", "MRPS15", "2.8", "HIST1H4F", "16.8"], ["Top down-regulatedImage 2", "SELENOP", "−77.3", "PI15", "−3.1", "CCL5", "−76.6"], ["SLC40A1", "−70.9", "SLC38A1", "−3.0", "CCL19", "−37.6"], ["AQP3", "−66.4", "CCL5", "−3.0", "DIRAS3", "−27.8"], ["ST8SIA4", "−57.6", "VCAM1", "−2.9", "DTL", "−23.2"], ["ADH1B", "−39.3", "TSPAN11", "−2.8", "GAP43", "−19.1"], ["PPL", "−34.4", "PSAT1", "−2.7", "IL24", "−18.8"], ["AHNAK2", "−31.1", "MEG8", "−2.7", "IL1RN", "−18.2"], ["DEPP1", "−28.0", "KLHL24", "−2.6", "WISP1", "−17.3"], ["STMN2", "−27.0", "MXRA5", "−2.6", "METTL7A", "−17.3"], ["SYNE2", "−25.8", "RAB27B", "−2.5", "MXRA5", "−16.8"]], "row_count": 22, "column_count": 7, "numeric_cells": 79, "header_rows": 2, "locator": "section[2]/table-wrap[1]#tbl1"}}], "gaps": ["asset:data:geo:GSE126484 not downloaded", "asset:data:geo:GSE126484 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "[Analysis cut-off: fold change [-2; +2], p < 0.05 (eBayes ANOVA)]"}}, {"id": "method-2", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "PCA"}}, {"id": "method-3", "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"}}], "targets": [], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["GSE126484"], "resolved_accessions": ["GSE126484"], "statements": ["Raw data is available at the Gene Expression Omnibus (GEO) from NCBI (GSE126484, www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE126484)."], "basis": "The paper names GSE126484 in Gene Expression Omnibus (GEO) from NCBI and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:31294056", "data:geo:GSE126484", "asset:table:pmid:31294056:1", "asset:table:pmid:31294056:2", "asset:table:pmid:31294056:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE126484"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:15:28Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 10548, "completion_tokens": 1192, "cached_tokens": 776}}, "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:31294056", "type": "paper", "label": "pmid:31294056"}, {"id": "source:pmid:31294056", "type": "manuscript", "label": "PMID 31294056 full text"}, {"id": "data:geo:GSE126484", "type": "dataset", "label": "GEO GSE126484"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31294056", "type": "paper", "label": "pmid:31294056"}, {"id": "source:pmid:31294056", "type": "manuscript", "label": "PMID 31294056 full text"}, {"id": "data:geo:GSE126484", "type": "dataset", "label": "GEO GSE126484"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31294056", "type": "extraction", "used": ["source:pmid:31294056"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE126484", "type": "accession_resolution", "used": ["data:geo:GSE126484"], "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:31294056", "parent_hash": "sha256:3f9a1acf85533d752e8e53a5021db7ec35816d05f5acd3767583e10dcdbf7bcc", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE126484 licence not read", "asset:data:geo:GSE126484 not downloaded", "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": ["l anti-NASH compound. We report whole genome microarray data (Affymetrix HG U133 plus 2.0) of human", "paper provides a detailed description of the microarray data as well as an indication of their value", "vitro evaluation of anti-NASH compounds. Raw microarray data of different testing conditions were de", "und. We report whole genome microarray data (Affymetrix HG U133 plus 2.0) of human multipotent stem"], "order_basis": "paper_text_order:321", "id": "assay:1"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["[Analysis cut-off: fold change [-2; +2], p < 0.05 (eBayes ANOVA)]"], "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":"2026-11-04T04:12:30+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}}}