{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32486122", "kind": "science-record", "revision": 7, "content_hash": "sha256:d608ed0c9f9e8b9edfa35480a50efcb8629c59c7e93b2d54c06dffb8b9c1dda3", "created_at": "2026-11-01T15:41:02Z", "updated_at": "2026-11-01T22:01:43Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Pan-Proteomic Analysis and Elucidation of Protein Abundance among the Closely Related Brucella Species, Brucella abortus and Brucella melitensis.", "doi": "10.3390/biom10060836", "pmid": "32486122", "authors": ["Jayaseelan Murugaiyan", "Murat Eravci", "Christoph Weise", "Uwe Roesler", "Lisa D Sprague", "Heinrich Neubauer", "Gamal Wareth"], "journal": "Biomolecules", "year": 2020, "abstract": "Brucellosis is a zoonotic infection caused by bacteria of the genus Brucella. The species, B. abortus and B. melitensis, major causative agents of human brucellosis, share remarkably similar genomes, but they differ in their natural hosts, phenotype, antigenic, immunogenic, proteomic and metabolomic properties. In the present study, label-free quantitative proteomic analysis was applied to investigate protein expression level differences. Type strains and field strains were each cultured six times, cells were harvested at a midlogarithmic growth phase and proteins were extracted. Following trypsin digestion, the peptides were desalted, separated by reverse-phase nanoLC, ionized using electrospray ionization and transferred into an linear trap quadrapole (LTQ) Orbitrap Velos mass spectrometer to record full scan MS spectra (m/z 300-1700) and tandem mass spectrometry (MS/MS) spectra of the 20 most intense ions. Database matching with the reference proteomes resulted in the identification of 826 proteins. The Cluster of Gene Ontologies of the identified proteins revealed differences in bimolecular transport and protein synthesis mechanisms between these two strains. Among several other proteins, antifreeze proteins, Omp10, superoxide dismutase and 30S ribosomal protein S14 were predicted as potential virulence factors among the proteins differentially expressed. All mass spectrometry data are available via ProteomeXchange with identifier PXD006348.", "claims": [{"id": "claim-method", "statement": "Statistical analysis was carried out using a two-way Student t-test, error correction (p < 0.05) and FDR correction of the alpha error was carried out by the method of Benjamini–Hochberg [43].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32486122", "locator": "sections[8] \"2.6. Data Analysis\" paragraph 2", "quote": "Statistical analysis was carried out using a two-way Student t-test, error correction (p < 0.05) and FDR correction of the alpha error was carried out by the method of Benjamini–Hochberg [43]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All mass spectrometry data are available via ProteomeXchange with identifier PXD006348.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32486122", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "All mass spectrometry data are available via ProteomeXchange with identifier PXD006348."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:32486122"], "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:PXD006348"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:student_t", "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:PXD006348"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:student_t"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32486122", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/biom10060836", "sha256": "sha256:6a1346fefbab35aa099c0c3477397ed565b290d1db34e5345a84bc91f4932980", "bytes": 53881, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/biom10060836", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7355635", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD006348", "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=PXD006348", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD006348", "version": null, "note": "All mass spectrometry data are available via ProteomeXchange with identifier PXD006348.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All mass spectrometry data are available via ProteomeXchange with identifier PXD006348.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Label-free quantitative proteomic analysis of Brucella abortus and Brucella melitensis", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:32486122:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:368b21a1d73611ba011ed16f002474bcd184caf4b5ea58f8a3729eb0957cd871", "bytes": 491, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#biomolecules-10-00836-t001", "version": null, "note": "Brucella strains used in this study.", "structure": {"pmcid": "PMC7355635", "section_index": 3, "section_title": "2.1. Brucella Culture", "row_count": 6, "column_count": 6}, "table": {"label": "Table 1", "caption": "Brucella strains used in this study.", "rows": [["Strain", "Designation/ID/Number", "Host", "Geographical Region"], ["FAO", "ATCC", "NCTC"], ["B. melitensis T", "16M", "23456", "10094", "Goat", "USA"], ["B. abortus T", "544", "23448", "10093", "Cattle", "UK"], ["B. melitensis", "C *", "", "", "Sheep", "China"], ["B. abortus", "T *", "", "", "Cattle", "Turkey"]], "row_count": 6, "column_count": 6, "numeric_cells": 6, "header_rows": 2, "locator": "section[3]/table-wrap[1]#biomolecules-10-00836-t001"}}, {"id": "asset:table:pmid:32486122:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:00b1d05c1e5fe2b537ac313c21b6af6ed33e74b4acd41e3408c8a2fef20069e5", "bytes": 422, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#biomolecules-10-00836-t002", "version": null, "note": "Number of regulated proteins among type and field strains.", "structure": {"pmcid": "PMC7355635", "section_index": 16, "section_title": "3.4. Comparative Proteomics of B. abortus and B. melitensis", "row_count": 4, "column_count": 7}, "table": {"label": "Table 2", "caption": "Number of regulated proteins among type and field strains.", "rows": [["Regulation", "Category"], ["IM vs. A", "IIM2 vs. A2", "IIIM2 vs. A", "IVM vs. A2", "VA2 vs. A", "VIM2 vs. M"], ["Down-", "173", "142", "166", "223", "83", "96"], ["Up-", "216", "199", "221", "248", "97", "129"]], "row_count": 4, "column_count": 7, "numeric_cells": 12, "header_rows": 2, "locator": "section[16]/table-wrap[1]#biomolecules-10-00836-t002"}}, {"id": "asset:table:pmid:32486122:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d9dc0269e2ec01d0c96b3b72baa36301f163ab4831960c01b44c9bbccfc932c2", "bytes": 1293, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#biomolecules-10-00836-t003", "version": null, "note": "KEGG pathways and the distribution of differentially expressed proteins.", "structure": {"pmcid": "PMC7355635", "section_index": 18, "section_title": "3.6. Bioinformatics Annotation of Differentially Expressed Proteins", "row_count": 19, "column_count": 7}, "table": {"label": "Table 3", "caption": "KEGG pathways and the distribution of differentially expressed proteins.", "rows": [["KEGG Pathways", "Category"], ["I", "II", "III", "IV", "V", "VI"], ["Metabolic pathways", "", "34 ↑", "", "", "", ""], ["Carbon metabolism", "", "", "6 ↑", "", "", ""], ["Glycolysis/gluconeogenesis", "", "", "", "7 ↓", "", ""], ["Pentose and glucuronate interconversions", "", "", "", "", "3 ↓", ""], ["Pyruvate metabolism", "", "", "4 ↑", "", "", ""], ["2-Oxocarboxylic acid metabolism", "4 ↓", "", "", "", "", ""], ["Microbial metabolism in diverse environments", "", "14 ↑", "10 ↑", "", "", ""], ["Biosynthesis of amino acids", "11 ↓", "", "", "14 ↓", "", ""], ["Histidine metabolism", "5 ↓", "5 ↓", "5 ↓", "6 ↓", "", ""], ["Valine, leucine and isoleucine biosynthesis", "", "", "", "4 ↓", "", ""], ["Purine metabolism", "", "7 ↑", "", "", "", ""], ["Pyrimidine metabolism", "5 ↑", "6 ↑", "", "7 ↑", "", ""], ["Biosynthesis of secondary metabolites", "19 ↓", "", "", "25 ↓", "", ""], ["RNA polymerase", "", "", "", "3 ↑", "", ""], ["Ribosome", "17 ↑", "18 ↓", "14 ↓", "19 ↑", "", "22 ↓"], ["Bacterial secretion system", "", "5 ↑", "5 ↑", "", "4 ↑", "5 ↑"], ["ABC transporters", "", "", "14 ↑", "", "", ""]], "row_count": 19, "column_count": 7, "numeric_cells": 33, "header_rows": 2, "locator": "section[18]/table-wrap[1]#biomolecules-10-00836-t003"}}, {"id": "asset:table:pmid:32486122:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3732a225385743c37f1a989fc205af924d22584c8a3432bdc417bb89439f3178", "bytes": 1001, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[19]/table-wrap[1]#biomolecules-10-00836-t004", "version": null, "note": "Differentially expressed proteins predicted as potentially virulence-associated.", "structure": {"pmcid": "PMC7355635", "section_index": 19, "section_title": "3.7. Predicted Virulence-Associated Proteins", "row_count": 9, "column_count": 5}, "table": {"label": "Table 4", "caption": "Differentially expressed proteins predicted as potentially virulence-associated.", "rows": [["Acc.", "Protein Description", "Reg", "Significance", "Reference"], ["D0B8I3*", "Antifreeze protein", "(+)", "Associated with MucR, a transcriptional regulator linked to Brucella virulence", "[63]"], ["Q8YIA9", "Antifreeze protein", "(-)"], ["Q2YM39", "Antifreeze protein type I", "(-)"], ["D0B248 *", "LipA family protein", "(-)", "", ""], ["Q2YIP8", "Lipoprotein Omp10", "(-)", "Reduced virulence in B. abortus with gene deletion and used in diagnostics", "[64,65,66]"], ["Q2YKV9", "Superoxide dismutase [Cu-Zn]", "(-)", "intracellular survival and used as antigens for subunit vaccines", "[19,67]"], ["Q2YRA8", "30S ribosomal protein S14", "(-)", "role in cellular adhesion and virulence in Candida albicans", "[68]"], ["ribosomal protein L7/L12 based subunit vaccines", "[69,70]"]], "row_count": 9, "column_count": 5, "numeric_cells": 10, "header_rows": 1, "locator": "section[19]/table-wrap[1]#biomolecules-10-00836-t004"}}, {"id": "asset:table:pmid:32486122:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:322bb30e21cdbf2551e23cd52ae80ca0390d56e5b939caed49e3fe573c380819", "bytes": 2600, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#biomolecules-10-00836-t005", "version": null, "note": "Differentially expressed proteins among the field isolates in comparison to that of the respective type strains.", "structure": {"pmcid": "PMC7355635", "section_index": 20, "section_title": "3.8. Field Strains and Host Adaptability", "row_count": 50, "column_count": 2}, "table": {"label": "Table 5", "caption": "Differentially expressed proteins among the field isolates in comparison to that of the respective type strains.", "rows": [["UniProt ID", "Protein"], ["Downregulated in Field Isolates"], ["Q8YBH7", "Bacterial extracellular solute-binding protein family 1"], ["Q8YIX9", "Glyceraldehyde-3-phosphate dehydrogenase"], ["Q2YMI0", "Phosphatidylserine decarboxylase proenzyme"], ["Q2YLU2", "Peptidylprolyl isomerase"], ["Q2YLF8", "Leu/Ile/Val-binding protein homolog 1"], ["Q2YLG0", "Leu/Ile/Val-binding protein homolog 2"], ["Q2YJA9", "Leu/Ile/Val-binding protein homolog 5"], ["Q2YQQ6", "Glutelin:Lipoprotein YaeC family:NLPA lipoprotein"], ["Q2YRP7", "Ribosome-recycling factor"], ["Q2YR20", "Uncharacterized protein"], ["Upregulated in Field Isolates"], ["Q2YJ78", "Type IV secretion system protein virB8"], ["Q2YJ79", "Type IV secretion system protein virB9"], ["Q2YJ81", "Type IV secretion system protein virB10"], ["Q2YJ83", "Type IV secretion system-outer membrane lipoprotein"], ["Q2YJ77", "Type IV secretion system putative lipoprotein virB7"], ["Q8YB25", "Alpha-methylacyl-CoA racemase"], ["Q2YIG7", "NADH:flavin oxidoreductase/NADH oxidase"], ["Q2YKS6", "Aminotransferase class IV"], ["Q8YCZ2", "N-acetylglucosamine-6-phosphate deacetylase"], ["Q8YI04", "ATP-dependent DNA ligase"], ["Q2YK32", "Catalase"], ["Q2YLX9", "Lipoprotein putative"], ["Q2YN45", "Probable cytosol aminopeptidase"], ["Q2YRJ0", "ATP/GTP-binding site motif A (P-loop)"], ["Q2YRN7", "Uncharacterized protein"], ["Q8YBU9", "Putative uroporphyrin-iii c-methyltransferase"], ["Q2YKY2", "Uncharacterized protein"], ["Q2YL40", "Uncharacterized protein"], ["Q2YLM7", "Uncharacterized protein"], ["Downregulated in B. abortus and Upregulated in B. melitensis"], ["Q2YME1", "Threonylcarbamoyl-AMP synthase"], ["Q2YNW9", "Dihydroxy-acid dehydratase"], ["Q8YHA5", "Glutaryl-CoA dehydrogenase"], ["Q2YP66", "Zinc-containing alcohol dehydrogenase"], ["Q2YQE3", "Periplasmic binding protein"], ["Q2YMW1", "Uncharacterized protein"], ["Q2YPK6", "Uncharacterized protein"], ["Upregulated in B. abortus and Downregulated in B. melitensis"], ["Q2YQV7", "50S ribosomal protein L20"], ["Q2YR56", "50S ribosomal protein L28"], ["Q2YRY0", "ABC-type glycine betaine transport system"], ["Q8YBF5", "Maltose-binding periplasmic protein (Sugar ABC transporter)"], ["Q8YCD1", "Cystine-binding periplasmic protein"], ["Q8YGE8", "Cationic amino acid ABC transporter"], ["Q2YKN7", "Uncharacterized protein"], ["Q2YKN9", "Uncharacterized protein"], ["Q2YQM2", "Uncharacterized protein"]], "row_count": 50, "column_count": 2, "numeric_cells": 22, "header_rows": 1, "locator": "section[20]/table-wrap[1]#biomolecules-10-00836-t005"}}], "gaps": ["asset:data:geo:PXD006348 not downloaded", "asset:data:geo:PXD006348 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Statistical analysis was carried out using a two-way Student t-test, error correction (p < 0.05) and FDR correction of the alpha error was carried out by the method of Benjamini–Hochberg [43]."}}], "targets": [], "gaps": ["method.student_t"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": false, "required_operations": [], "missing_operations": ["student_t"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: student_t_test."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["PXD006348"], "resolved_accessions": ["PXD006348"], "statements": ["All mass spectrometry data are available via ProteomeXchange with identifier PXD006348."], "basis": "The paper names PXD006348 in ProteomeXchange Consortium via the PRIDE partner repository and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:32486122", "data:geo:PXD006348", "asset:table:pmid:32486122:1", "asset:table:pmid:32486122:2", "asset:table:pmid:32486122:3", "asset:table:pmid:32486122:4", "asset:table:pmid:32486122:5"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "student_t", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD006348"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:20:15Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 45673, "completion_tokens": 1362, "cached_tokens": 793}}, "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:32486122", "type": "paper", "label": "pmid:32486122"}, {"id": "source:pmid:32486122", "type": "manuscript", "label": "PMID 32486122 full text"}, {"id": "data:geo:PXD006348", "type": "dataset", "label": "GEO PXD006348"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32486122", "type": "paper", "label": "pmid:32486122"}, {"id": "source:pmid:32486122", "type": "manuscript", "label": "PMID 32486122 full text"}, {"id": "data:geo:PXD006348", "type": "dataset", "label": "GEO PXD006348"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32486122", "type": "extraction", "used": ["source:pmid:32486122"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD006348", "type": "accession_resolution", "used": ["data:geo:PXD006348"], "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:32486122", "parent_hash": "sha256:59b151c65e00a95b8bac02ed09da4aef7cc546c1addbe8cfa812048d50f0ff31", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:PXD006348 licence not read", "asset:data:geo:PXD006348 not downloaded", "execution.not_run", "method.student_t", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:student_t"], "assays": [{"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Pan-Proteomic Analysis and Elucidation of Protein Abundanc", "al hosts, phenotype, antigenic, immunogenic, proteomic and metabolomic properties. In the present s", "n the present study, label-free quantitative proteomic analysis was applied to investigate protein", "ll scan MS spectra (m/z 300-1700) and tandem mass spectrometry (MS/MS) spectra of the 20 most intense ions."], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"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": ["es. Type strains and field strains were each cultured six times, cells were harvested at a midloga"], "order_basis": "paper_text_order:585", "id": "assay:2"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Statistical analysis was carried out using a two-way Student t-test, error correction (p < 0.05) and FDR correction of the alpha error was carried out by the method of Benjamini–Hochberg [43]."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T00:37:30+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}}}