{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31909123", "kind": "science-record", "revision": 8, "content_hash": "sha256:3f14cb4eeef9cb908a993c31d3d846e551092be6e9e703e7470256bda2d5ac9c", "created_at": "2026-11-01T15:40:54Z", "updated_at": "2026-11-01T22:44:28Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "RNA sequencing data of mouse 2-cell embryos treated with DMSO.", "doi": "10.1016/j.dib.2019.105025", "pmid": "31909123", "authors": ["Min-Hee Kang", "Seong-Yeob You", "Kwonho Hong", "Jin-Hoi Kim"], "journal": "Data in brief", "year": 2020, "abstract": "To understand the effect of DMSO in preimplantation embryos, we have treated mouse 1 cell zygotes with DMSO and found that DMSO treatment caused 2 or 4 cell embryonic arrest and altered the acetylation levels of mouse preimplantation embryos To illustrate the mechanism of DMSO in mouse preimplantation embryos, fertilized zygotes have been treated with 2% of DMSO and then performed RNA-seq analyses. Differentially expressed genes were identified using DESeq2 after adjustment for false discovery rate (FDR q value < 0.05). Gene Set Enrichment Analysis (GSEA) was also performed to identify biological pathways significantly modulated by DMSO. Raw and processed RNA-seq data were deposited and made publicly available on the Gene Expression Omnibus (GEO; GSE124598). The data presented in this article are related to the research paper entitled \"DMSO impairs the transcriptional program for maternal-to-embryonic transition by altering histone acetylation\", available in Biomaterials [1].", "claims": [{"id": "claim-method", "statement": "Differentially expressed gene (DEG) were analyzed by DESeq2 [4] in R/Bioconductor with the parameters (baseMean counts >14; false discovery rate (FDR) < 0.05).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31909123", "locator": "sections[7] \"RNA-seq data analysis\" paragraph 2", "quote": "Differentially expressed gene (DEG) were analyzed by DESeq2 [4] in R/Bioconductor with the parameters (baseMean counts >14; false discovery rate (FDR) < 0.05)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The raw data generated from Illumina sequencing were deposited on the Gene Expression Omnibus (GEO) with the reference number GSE124598 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124598).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31909123", "locator": "sections[3] \"Data\" paragraph 2", "quote": "The raw data generated from Illumina sequencing were deposited on the Gene Expression Omnibus (GEO) with the reference number GSE124598 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124598)."}], "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:31909123"], "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:GSE124598"], "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:GSE124598"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31909123", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2019.105025", "sha256": "sha256:809057bc41c8a8a0c5c2e9f6f9cd0f5a6e4dc523bfbcd79c7dfa93035ab714ae", "bytes": 12727, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2019.105025", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6940686", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE124598", "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=GSE124598", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE124598", "version": null, "note": "The raw data generated from Illumina sequencing were deposited on the Gene Expression Omnibus (GEO) with the reference number GSE124598 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124598).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The raw data generated from Illumina sequencing were deposited on the Gene Expression Omnibus (GEO) with the reference number GSE124598 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124598).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3537434", "GSM3537435", "GSM3537436", "GSM3537437"], "sample_count": 4, "group_sizes": null, "group_sizes_basis": null, "platform": "17021", "taxon": "Mus musculus", "title": "Differentially expressed genes by DMSO in mouse 2-cell embryos identified by RNA sequencing", "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:31909123:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d9225bb70129a83e11f7294793587d24a17217732775f3676ae37a187b1f7e2e", "bytes": 6731, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#tbl1", "version": null, "note": "KEGG and REACTOME pathway analysis in DMSO-treated 2-cell embryos.", "structure": {"pmcid": "PMC6940686", "section_index": 3, "section_title": "Data", "row_count": 73, "column_count": 6}, "table": {"label": "Table 1", "caption": "KEGG and REACTOME pathway analysis in DMSO-treated 2-cell embryos.", "rows": [["", "Pathway ID", "Pathway Term", "adj_pvalue", "No. of Genes", "% Genes"], ["1", "R-MMU:2262752", "Cellular responses to stress", "0.00107233", "92", "24.02"], ["2", "R-MMU:72702", "Ribosomal scanning and start codon recognition", "0.00109672", "23", "41.07"], ["3", "R-MMU:1234176", "Oxygen-dependent proline hydroxylation of Hyposia-inducible factor alpha", "0.00115378", "24", "40.00"], ["4", "R-MMU:72689", "Formation of a pool of free 40S subunits", "0.00117991", "20", "44.44"], ["5", "R-MMU:8948751", "Regulation of PTEN stability and activity", "0.00118317", "25", "39.06"], ["6", "R-MMU:373076", "Class A/1 (Rhodopsin-like receptors)", "0.00134226", "20", "6.25"], ["7", "R-MMU:4641258", "Degradation of DVL", "0.00147675", "22", "41.51"], ["8", "R-MMU:74158", "RNA Polymerase III Transcription", "0.00154192", "17", "48.57"], ["9", "R-MMU:76046", "RNA Polymerase III Transcription Initiation", "0.00154192", "17", "48.57"], ["10", "R-MMU:6807505", "RNA polymerase II transcribes snRNA genes", "0.00160451", "27", "36.99"], ["11", "R-MMU:69275", "G2/M Transition", "0.00170795", "50", "28.57"], ["12", "R-MMU:212436", "Generic Transcription Pathway", "0.00209786", "135", "21.63"], ["13", "R-MMU:453274", "Mitotic G2-G2/M phases", "0.00214072", "50", "28.25"], ["14", "R-MMU:4608870", "Asymmetric localization of PCP proteins", "0.00222022", "23", "39.66"], ["15", "R-MMU:5689603", "UCH proteinases", "0.00278995", "32", "33.33"], ["16", "R-MMU:174113", "SCF-beta-TrCP mediated degradation of Emi1", "0.00288664", "21", "41.18"], ["17", "R-MMU:8854050", "FBXL7 down-regulates AURKA during mitotic entry and in early mitosis", "0.00288664", "21", "41.18"], ["18", "R-MMU:5687128", "MAPK6/MAPK4 signaling", "0.00300873", "26", "36.62"], ["19", "R-MMU:174154", "APC/C:Cdc20 mediated degradation of Securin", "0.00312854", "24", "38.10"], ["20", "R-MMU:5621481", "C-type lectin receptors (CLRs)", "0.003421", "35", "31.82"], ["21", "R-MMU:73863", "RNA Polymerase I Transcription Termination", "0.00380234", "15", "50.00"], ["22", "R-MMU:1236978", "Cross-presentation of soluble exogenous antigens (endosomes)", "0.00388676", "20", "41.67"], ["23", "R-MMU:174178", "APC/C:Cdh1 mediated degradation of Cdc20 and other APC/C:Cdh1 targeted proteins in late mitosis/early G1", "0.00417739", "25", "36.76"], ["24", "R-MMU:174184", "Cdc20:Phospho-APC/C mediated degradation of Cyclin A", "0.00417739", "25", "36.76"], ["25", "R-MMU:351202", "Metabolism of polyamines", "0.0042154", "29", "34.52"], ["26", "R-MMU:68882", "Mitotic Anaphase", "0.00531307", "52", "27.08"], ["27", "KEGG:03008", "Ribosome biogenesis in eukaryotes", "0.00545287", "36", "31.03"], ["28", "R-MMU:179419", "APC:Cdc20 mediated degradation of cell cycle proteins prior to satisfaction of the cell cycle checkpoint", "0.00560289", "25", "36.23"], ["29", "R-MMU:1234174", "Regulation of Hypoxia-inducible Factor (HIF) by oxygen", "0.00579829", "24", "36.92"], ["30", "R-MMU:2262749", "Cellular response to hypoxia", "0.00579829", "24", "36.92"], ["31", "R-MMU:5610780", "Degradation of GLI1 by the proteasome", "0.00584049", "21", "39.62"], ["32", "R-MMU:72086", "mRNA Capping", "0.00770714", "14", "50.00"], ["33", "R-MMU:112382", "Formation of RNA Pol II elongation complex", "0.00820743", "21", "38.89"], ["34", "R-MMU:75955", "RNA Polymerase II Transcription Elongation", "0.00820743", "21", "38.89"], ["35", "R-MMU:2555396", "Mitotic Metaphase and Anaphase", "0.00834028", "52", "26.94"], ["36", "R-MMU:6807070", "PTEN Regulation", "0.00889033", "34", "31.48"], ["37", "R-MMU:3858494", "Beta-catenin independent WNT signaling", "0.01005271", "37", "30.08"], ["38", "R-MMU:2871837", "FCERI mediated NF-kB activation", "0.01119674", "26", "35.14"], ["39", "R-MMU:5358346", "Hedgehog ligand biogenesis", "0.01121237", "22", "37.29"], ["40", "R-MMU:5607761", "Dectin-1 mediated noncanonical NF-kB signaling", "0.01133035", "21", "38.18"], ["41", "R-MMU:5610785", "GLI3 is processed to GLI3R by the proteasome", "0.01133035", "21", "38.18"], ["42", "R-MMU:5676590", "NIK-->noncanonical NF-kB signaling", "0.01133035", "21", "38.18"], ["43", "R-MMU:68827", "CDT1 association with the CDC6:ORC:origin complex", "0.01133035", "21", "38.18"], ["44", "R-MMU:73772", "RNA Polymerase I Promoter Escape", "0.01271169", "14", "48.28"], ["45", "KEGG:03013", "RNA transport", "0.01396122", "46", "27.54"], ["46", "R-MMU:2454202", "Fc epsilon receptor (FCERI) signaling", "0.01424613", "36", "30.00"], ["47", "R-MMU:5658442", "Regulation of RAS by GAPs", "0.01448249", "23", "35.94"], ["48", "R-MMU:68867", "Assembly of the pre-replicative complex", "0.01448249", "23", "35.94"], ["49", "R-MMU:73762", "RNA Polymerase I Transcription Initiation", "0.01479977", "18", "40.91"], ["50", "R-MMU:5205647", "Mitophagy", "0.01554993", "13", "50.00"], ["51", "R-MMU:77075", "RNA Pol II CTD phosphorylation and interaction with CE", "0.01554993", "13", "50.00"], ["52", "R-MMU:176409", "APC/C:Cdc20 mediated degradation of mitotic proteins", "0.01645248", "25", "35.21"], ["53", "R-MMU:176814", "Activation of APC/C and APC/C:Cdc20 mediated degradation of mitotic proteins", "0.01850655", "25", "34.72"], ["54", "R-MMU:113418", "Formation of the Early Elongation Complex", "0.0203327", "14", "46.67"], ["55", "R-MMU:9006925", "Intracellular signaling by second messengers", "0.02051725", "62", "24.60"], ["56", "R-MMU:2467813", "Separation of Sister Chromatids", "0.02055007", "48", "26.52"], ["57", "R-MMU:176408", "Regulation of APC/C activators between G1/S and early anaphase", "0.02193502", "26", "33.33"], ["58", "KEGG:05206", "MicroRNAs in cancer", "0.02406351", "19", "6.76"], ["59", "R-MMU:76061", "RNA Polymerase III Transcription Initiation From Type 1 Promoter", "0.02559861", "13", "48.15"], ["60", "R-MMU:76066", "RNA Polymerase III Transcription Initiation From Type 2 Promoter", "0.02559861", "13", "48.15"], ["61", "R-MMU:202424", "Downstream TCR signaling", "0.02570574", "28", "32.56"], ["62", "R-MMU:72731", "Recycling of eIF2:GDP", "0.02607639", "7", "77.78"], ["63", "R-MMU:71291", "Metabolism of amino acids and derivatives", "0.0304537", "60", "24.69"], ["64", "R-MMU:76071", "RNA Polymerase III Transcription Initiation From Type 3 Promoter", "0.04105632", "13", "46.43"], ["65", "R-MMU:202403", "TCR signaling", "0.04107335", "31", "30.10"], ["66", "R-MMU:174143", "APC/C-mediated degradation of cell cycle proteins", "0.04146255", "27", "32.14"], ["67", "R-MMU:453276", "Regulation of mitotic cell cycle", "0.04146255", "27", "32.14"], ["68", "R-MMU:69304", "Regulation of DNA replication", "0.04440004", "24", "33.33"], ["69", "R-MMU:68949", "Orc1 removal from chromatin", "0.04507583", "23", "34.33"], ["70", "R-MMU:69052", "Switching of origins to a post-replicative state", "0.04507583", "23", "34.33"], ["71", "R-MMU:1236975", "Antigen processing-Cross presentation", "0.04695947", "27", "31.76"], ["72", "R-MMU:4086400", "PCP/CE pathway", "0.04695947", "27", "31.76"]], "row_count": 73, "column_count": 6, "numeric_cells": 372, "header_rows": 1, "locator": "section[3]/table-wrap[1]#tbl1"}}], "gaps": ["asset:data:geo:GSE124598 not downloaded", "asset:data:geo:GSE124598 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "deseq2", "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": 1.0, "band": "verbatim", "quote": "Differentially expressed gene (DEG) were analyzed by DESeq2 [4] in R/Bioconductor with the parameters (baseMean counts >14; false discovery rate (FDR) < 0.05)."}}], "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: deseq2."}, "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": ["GSE124598"], "resolved_accessions": ["GSE124598"], "statements": ["The raw data generated from Illumina sequencing were deposited on the Gene Expression Omnibus (GEO) with the reference number GSE124598 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE124598)."], "basis": "The paper names GSE124598 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:31909123", "data:geo:GSE124598", "asset:table:pmid:31909123:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE124598"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:17:39Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 11137, "completion_tokens": 1266, "cached_tokens": 792}}, "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:31909123", "type": "paper", "label": "pmid:31909123"}, {"id": "source:pmid:31909123", "type": "manuscript", "label": "PMID 31909123 full text"}, {"id": "data:geo:GSE124598", "type": "dataset", "label": "GEO GSE124598"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31909123", "type": "paper", "label": "pmid:31909123"}, {"id": "source:pmid:31909123", "type": "manuscript", "label": "PMID 31909123 full text"}, {"id": "data:geo:GSE124598", "type": "dataset", "label": "GEO GSE124598"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31909123", "type": "extraction", "used": ["source:pmid:31909123"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE124598", "type": "accession_resolution", "used": ["data:geo:GSE124598"], "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:31909123", "parent_hash": "sha256:2d51356fa4e8c50cb49363036d165a87e2711554fa26b8c5b1f4e4b265ccffdc", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE124598 licence not read", "asset:data:geo:GSE124598 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "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": 0.99, "evidence": ["RNA sequencing data of mouse 2-cell embryos treated with DMSO.", "in preimplantation embryos, we have treated mouse 1 cell zygotes with DMSO and found that DMSO", "arrest and altered the acetylation levels of mouse preimplantation embryos To illustrate the me", "bryos To illustrate the mechanism of DMSO in mouse preimplantation embryos, fertilized zygotes"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["RNA sequencing data of mouse 2-cell embryos treated with DM", "n treated with 2% of DMSO and then performed RNA-seq analyses. Differentially expressed genes wer", "icantly modulated by DMSO. Raw and processed RNA-seq data were deposited and made publicly availa"], "order_basis": "paper_text_order:0", "id": "assay:2"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["f post hCG injection and each 10 zygotes was cultured in 20ul KSOM (95mM NaCl, 2.5mM KCl, 0.35mM KH2P", "os with second polar body were collected and cultured in KSOM with/without 2% DMSO for further analys"], "order_basis": "paper_text_order:1674", "id": "assay:3"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Differentially expressed gene (DEG) were analyzed by DESeq2 [4] in R/Bioconductor with the parameters (baseMean counts >14; false discovery rate (FDR) < 0.05)."], "order_basis": "consumes_earlier_output", "id": "assay:4"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:45:21+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}}}