{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:27364158", "kind": "science-record", "revision": 8, "content_hash": "sha256:d2c944ce2fd4fb7a68045b5ca44221b4926eff4ac7d9ce399849773e1ff27f83", "created_at": "2026-11-01T15:40:18Z", "updated_at": "2026-11-01T22:42:42Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Coordination of Metabolism and Virulence Factors Expression of Extraintestinal Pathogenic Escherichia coli Purified from Blood Cultures of Patients with Sepsis.", "doi": "10.1074/mcp.M116.060582", "pmid": "27364158", "authors": ["Veronika Kuchařová Pettersen", "Knut Anders Mosevoll", "Paul Christoffer Lindemann", "Harald G Wiker"], "journal": "Molecular & cellular proteomics : MCP", "year": 2016, "abstract": "One of the trademarks of extraintestinal pathogenic Escherichia coli is adaptation of metabolism and basic physiology to diverse host sites. However, little is known how this common human pathogen adapts to permit survival and growth in blood. We used label-free quantitative proteomics to characterize five E. coli strains purified from clinical blood cultures associated with sepsis and urinary tract infections. Further comparison of proteome profiles of the clinical strains and a reference uropathogenic E. coli strain 536 cultivated in blood culture and on two different solid media distinguished cellular features altered in response to the pathogenically relevant condition. The analysis covered nearly 60% of the strains predicted proteomes, and included quantitative description based on label-free intensity scores for 90% of the detected proteins. Statistical comparison of anaerobic and aerobic blood cultures revealed 32 differentially expressed proteins (1.5% of the shared proteins), mostly associated with acquisition and utilization of metal ions critical for anaerobic or aerobic respiration. Analysis of variance identified significantly altered amounts of 47 proteins shared by the strains (2.7%), including proteins involved in vitamin B6 metabolism and virulence. Although the proteomes derived from blood cultures were fairly similar for the investigated strains, quantitative proteomic comparison to the growth on solid media identified 200 proteins with substantially changed levels (11% of the shared proteins). Blood culture was characterized by up-regulation of anaerobic fermentative metabolism and multiple virulence traits, including cell motility and iron acquisition. In a response to the growth on solid media there were increased levels of proteins functional in aerobic respiration, catabolism of medium-specific carbon sources and protection against oxidative and osmotic stresses. These results demonstrate on the expressed proteome level that expression of extraintestinal virulence factors and overall cellular metabolism closely reflects specific growth conditions. Data are available via ProteomeXchange with identifier PXD002912.", "claims": [{"id": "claim-method", "statement": "One-way analysis of variance (ANOVA) with permutation-based FDR correction for multiple hypotheses testing (cutoff FDR value of 1%) was used to compare LFQ intensities of 1757 proteins quantified in all studied strains.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27364158", "locator": "sections[24] \"Quantitative Analysis of Six ExPEC Proteomes Derived from Blood Cultures Reveals Minor Variations Between the Strains\" paragraph 2", "quote": "One-way analysis of variance (ANOVA) with permutation-based FDR correction for multiple hypotheses testing (cutoff FDR value of 1%) was used to compare LFQ intensities of 1757 proteins quantified in all studied strains."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data are available via ProteomeXchange with identifier PXD002912.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27364158", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange with identifier PXD002912."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Label-free quantitative proteomics of clinical ExPEC blood cultures revealed condition-dependent protein expression: 32 proteins differed between anaerobic and aerobic cultures, 47 varied among strains, and 200 changed across blood culture and solid-media conditions; the source data are available through ProteomeXchange under identifier PXD002912.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:27364158", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Statistical comparison of anaerobic and aerobic blood cultures revealed 32 differentially expressed proteins (1.5% of the shared proteins), mostly associated with acquisition and utilization of metal ions critical for anaerobic or aerobic respiration."}, {"asset": "source:pmid:27364158", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Analysis of variance identified significantly altered amounts of 47 proteins shared by the strains (2.7%), including proteins involved in vitamin B6 metabolism and virulence."}, {"asset": "source:pmid:27364158", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange with identifier PXD002912."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Label-free quantitative proteomics of clinical ExPEC blood cultures revealed condition-dependent protein expression: 32 proteins differed between anaerobic and aerobic cultures, 47 varied among strains, and 200 changed across blood culture and solid-media conditions; the source data are available through ProteomeXchange under identifier PXD002912.", "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:27364158"], "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:PXD002912"], "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:PXD002912"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:27364158", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1074/mcp.M116.060582", "sha256": "sha256:0c9bb3fdd92f40f0deb1039b7b9242dfbd74f2775ab8fe32234dcb92fb9c0169", "bytes": 92843, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1074/mcp.M116.060582", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5013306", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD002912", "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=PXD002912", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD002912", "version": null, "note": "Data are available via ProteomeXchange with identifier PXD002912.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange with identifier PXD002912.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Expressed Proteome of Extraintestinal Escherichia coli Associated with Urinary Tract Infections", "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:27364158:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b6b6ae6f3bfcffa91f85916281710ad50584f4813c4f1e465b7a605a25468294", "bytes": 1077, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#TI", "version": null, "note": "E. coli strains used in this study. Abbreviations: UTI–Urinary Tract Infection; Trim/Sulfa - Trimethoprim/Sulfamethoxazole; N - Anaerobic; O - Aerobic, M - Male, F - Female", "structure": {"pmcid": "PMC5013306", "section_index": 20, "section_title": "ExPEC solates from Clinical Blood Cultures Associated with Sepsis", "row_count": 8, "column_count": 7}, "table": {"label": "Table I", "caption": "E. coli strains used in this study. Abbreviations: UTI–Urinary Tract Infection; Trim/Sulfa - Trimethoprim/Sulfamethoxazole; N - Anaerobic; O - Aerobic, M - Male, F - Female", "rows": [["E. coli strain", "Clinical characteristics (patient sex and age)", "MALDI-TOF identification", "Resistance to antibiotics", "Sequence type (ST), Phylogenetic group", "Nr. of blood cultures"], ["Blood culture", "Urine"], ["C4n", "UTI with sepsis (M76)", "E. coli", "E. coli", "Ciprofloxacin, Trim/Sulfa", "ST131, B2", "1 N, 1 O"], ["D4n", "UTI with sepsis (F84)", "E. coli", "Mixed samplea", "-", "ST73, B2", "2 N"], ["E4n", "UTI with sepsis (M78)", "E. coli", "E. coli", "Ciprofloxacin, Trim/Sulfa", "ST131, B2", "2 O"], ["F4d", "UTI with sepsis (F90)", "E. coli", "Mixed samplea", "-", "ST73, B2", "2 N, 2 O"], ["G5m", "Immunosuppression with sepsis (M65)", "E. coli", "E. coli", "-", "ST372, B2", "2 N, 2 O"], ["UPEC 536", "Blood from healthy volunteer (M55)", "-", "-", "-", "ST92, B2", "1 N, 1 O"]], "row_count": 8, "column_count": 7, "numeric_cells": 19, "header_rows": 2, "locator": "section[20]/table-wrap[1]#TI"}}, {"id": "asset:table:pmid:27364158:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:869253cdbbbf797a07bfbbeda193e91c6283fd32177468b77ddfedb04aeb3b12", "bytes": 2622, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[25]/table-wrap[1]#TII", "version": null, "note": "Differentially expressed UPEC 536 protein complexes in response to three growth conditions", "structure": {"pmcid": "PMC5013306", "section_index": 25, "section_title": "Adaptation of UPEC 536 Physiology to Three Distinct In Vitro Conditions", "row_count": 25, "column_count": 6}, "table": {"label": "Table II", "caption": "Differentially expressed UPEC 536 protein complexes in response to three growth conditions", "rows": [["Biological function", "All detected proteins within an operon", "Proteins detected under specific condition (log2LFQ intensitya)"], ["Aerobic blood culture", "Anaerobic blood culture", "Blood agar", "Lactose agar"], ["K+ transport", "KdpABCDE", "BDE (22.7)", "BDE (22.7)", "DE (24.0)", "ABCDE (26.7)"], ["Lactose utilization", "LacZYAI", "I (NQ)", "I (NQ)", "I (21.5)", "ZYAI (28.7)"], ["Thiamine biosynthesis", "ThiBCDEFGHILMPQS", "BCEFGHILMPQ (29.4)", "BILQ (26.8)", "BILMPQ (26.3)", "BCDEFGHILMPQS (31.0)"], ["Ethanolamine utilization", "EutABCKLMQT", "CL (NQ)", "BCLMQ (NQ)", "ABCKLMQT (27.3)", "BCL (NQ)"], ["Glycolate utilization", "GlcABCEG", "BC (26.5)", "BG (26.6)", "ABCEG (29.4)", "BCG (27.4)"], ["Xylose utilization", "XylABF", "- (NQ)", "B (NQ)", "ABF (24.4)", "B (21.2)"], ["N-acetylneuraminate degradation", "NanAA2EKMR", "AA2ER (25.3)", "AA2EKMR (25.6)", "AA2EKMR (27.4)", "EKMR (25.7)"], ["Fatty acid metabolism", "FadABDEHIJLMR", "DILMR (26.9)", "DLR (26.7)", "ABDEHIJLMR (30.6)", "BDEHLMR (26.9)"], ["Glycerol-3-phosphate transport", "UgpABCEQ", "BQ (23.7)", "Q (23.12)", "ABCEQ (28.8)", "BCQ (25.5)"], ["Heme and peptide transport", "DppABCDF", "AD (23.9)", "AD (19.9)", "ABCDF (30.2)", "A (21.4)"], ["Galactose transport", "MglABC", "AB (23.9)", "AB (NQ)", "ABC (30.3)", "ABC (27.0)"], ["l-arginine degradation", "AstABCDE", "ABD (22.3)", "BD (NQ)", "ABCDE (31.3)", "BCD (21.3)"], ["Hydrogen metabolism", "HyaABCDEF", "ABCDEF (29.4)", "ABCDEF (29.3)", "B (22.8)", "B (NQ)"], ["HybABCDEFGO", "ABCDEFGO (28.1)", "ABCDEFGO (28.8)", "BCD (23.2)", "BCD (22.4)"], ["HycABCDEFGHI", "ABCDEFGHI (29.5)", "ABCDEFGHI (30.2)", "EI (24.2)", "BEI (23.9)"], ["HypABCDEF", "ABDEF (28.2)", "ABCDEF (27.9)", "BDEF (24.9)", "BDEF (23.7)"], ["Mixed acid fermentation", "FrdABCD", "ABCD (30.7)", "ABCD (30.7)", "ABCD (28.6)", "ABCD (26.6)"], ["Nickel transport", "NikABCDER", "ABCDER (28.5)", "ABCDER (30.6)", "AER (25.8)", "ABER (26.3)"], ["Glycerol degradation", "GlpABC", "ABC (27.8)", "ABC (28.5)", "AB (21.2)", "- (NQ)"], ["Chemotaxis", "CheABRWYZ, MotAB", "(Che) ABRWYZ, (Mot) AB (29.2, 23.8)", "(Che) ABRWYZ, (Mot) AB (30.8, 26.5)", "(Che) ABRWY, - (23.7, NQ)", "(Che) ABRWYZ, (Mot) AB (28.9, NQ)"], ["Heme uptake", "ChuASTUWXY", "ASTWXY (29.7)", "ASX (22.5)", "ASTX (25.9)", "ASTXY (28.2)"], ["Polysialic acid synthesis", "KpsCDEFMSTU", "CDEFSTU (28.4)", "CDEFSTU (28.6)", "CDEFTU (27.9)", "CDETU (27.1)"], ["Transcription antitermination", "CspACDEG", "ACDEG (30.8)", "ACEG (30.9)", "CE (26.9)", "ACEG (27.5)"]], "row_count": 25, "column_count": 6, "numeric_cells": 82, "header_rows": 2, "locator": "section[25]/table-wrap[1]#TII"}}], "gaps": ["asset:data:geo:PXD002912 not downloaded", "asset:data:geo:PXD002912 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": "One-way analysis of variance (ANOVA) with permutation-based FDR correction for multiple hypotheses testing (cutoff FDR value of 1%) was used to compare LFQ intensities of 1757 proteins quantified in all studied strains."}}, {"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": "Principal component analysis"}}], "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": ["PXD002912"], "resolved_accessions": ["PXD002912"], "statements": ["Data are available via ProteomeXchange with identifier PXD002912."], "basis": "The paper names PXD002912 in ProteomeXchange 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:27364158", "data:geo:PXD002912", "asset:table:pmid:27364158:1", "asset:table:pmid:27364158:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD002912"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:28:51Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 179105, "completion_tokens": 2583, "cached_tokens": 1832}}, "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:27364158", "type": "paper", "label": "pmid:27364158"}, {"id": "source:pmid:27364158", "type": "manuscript", "label": "PMID 27364158 full text"}, {"id": "data:geo:PXD002912", "type": "dataset", "label": "GEO PXD002912"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:27364158", "type": "paper", "label": "pmid:27364158"}, {"id": "source:pmid:27364158", "type": "manuscript", "label": "PMID 27364158 full text"}, {"id": "data:geo:PXD002912", "type": "dataset", "label": "GEO PXD002912"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-27364158", "type": "extraction", "used": ["source:pmid:27364158"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD002912", "type": "accession_resolution", "used": ["data:geo:PXD002912"], "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:27364158", "parent_hash": "sha256:efebba45c4321977c7c685c13233d3993610c9a76fb81ecd8a41ac74c4698990", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:PXD002912 licence not read", "asset:data:geo:PXD002912 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "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": ["th in blood. We used label-free quantitative proteomics to characterize five E. coli strains purifie", "Design and Statistical Rationale Samples for LC-MS/MS analysis included two or four blood cultures", "r for the investigated strains, quantitative proteomic comparison to the growth on solid media iden"], "order_basis": "paper_text_order:392", "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": ["One-way analysis of variance (ANOVA) with permutation-based FDR correction for multiple hypotheses testing (cutoff FDR value of 1%) was used to compare LFQ intensities of 1757 proteins quantified in all studied strains."], "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":"2026-11-04T00:46:23+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}}}