{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32832748", "kind": "science-record", "revision": 6, "content_hash": "sha256:e8d3624b8da02c04115bc68c2ab21d245171a4bd5f1118c6d837903fd324a28a", "created_at": "2026-11-01T15:41:08Z", "updated_at": "2026-11-01T21:23:40Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Pseudomonas aeruginosa Presents Multiple Vital Changes in Its Proteome in the Presence of 3-Hydroxyphenylacetic Acid, a Promising Antimicrobial Agent.", "doi": "10.1021/acsomega.0c00703", "pmid": "32832748", "authors": ["Ozgun O Ozdemir", "Ferda Soyer"], "journal": "ACS omega", "year": 2020, "abstract": "Pseudomonas aeruginosa, a widely distributed opportunistic pathogen, is an important threat to human health for causing serious infections worldwide. Due to its antibiotic resistance and virulence factors, it is so difficult to combat this bacterium; thus, new antimicrobial agents are in search. 3-Hydroxyphenylacetic acid (3-HPAA), which is a phenolic acid mostly found in olive oil wastewater, can be a promising candidate with its dose-dependent antimicrobial properties. Elucidating the molecular mechanism of action is crucial for future examinations and the presentation of 3-HPAA as a new agent. In this study, the antimicrobial activity of 3-HPAA on P. aeruginosa and its action mechanism was investigated via shot-gun proteomics. The data, which are available via ProteomeXchange with identifier PXD016243, were examined by STRING analysis to determine the interaction networks of proteins. KEGG Pathway enrichment analysis via the DAVID bioinformatics tool was also performed to investigate the metabolic pathways that undetected and newly detected groups of the proteins. The results displayed remarkable changes after 3-HPAA exposure in the protein profile of P. aeruginosa related to DNA replication and repair, RNA modifications, ribosomes and proteins, cell envelope, oxidative stress, as well as nutrient availability. 3-HPAA showed its antimicrobial action on P. aeruginosa by affecting multiple bacterial processes; hence, it could be categorized as a multitarget antimicrobial agent.", "claims": [{"id": "claim-method", "statement": "The significant metabolic pathways of the genes of these proteins were elucidated by the KEGG pathway enrichment analysis using the DAVID bioinformatics database (version 6.8).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32832748", "locator": "sections[19] \"Data Analysis\" paragraph 2", "quote": "The significant metabolic pathways of the genes of these proteins were elucidated by the KEGG pathway enrichment analysis using the DAVID bioinformatics database (version 6.8)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD016243.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32832748", "locator": "sections[24] \"notes\" paragraph 1", "quote": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD016243."}], "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:32832748"], "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:PXD016243"], "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:PXD016243"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32832748", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1021/acsomega.0c00703", "sha256": "sha256:8077b4cf175c5408bc699634462c2eac1b50cd58aa72741dd98333636c45f9a1", "bytes": 44661, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1021/acsomega.0c00703", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7439270", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD016243", "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=PXD016243", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD016243", "version": null, "note": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD016243.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD016243.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "The examination of Pseudomonas aeruginosa proteome in the presence of phenolic acids", "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:32832748:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b10cc8a77089cfa9c650faefbe3e8b4480800e67df4d4d9f41e34bfe61f561a3", "bytes": 441, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#tbl1", "version": null, "note": "Percent Inhibition in Bacterial Growth and Cell Viability of P. aeruginosa in the Presence of 3-HPAA", "structure": {"pmcid": "PMC7439270", "section_index": 1, "section_title": "Introduction", "row_count": 5, "column_count": 3}, "table": {"label": "Table 1", "caption": "Percent Inhibition in Bacterial Growth and Cell Viability of P. aeruginosa in the Presence of 3-HPAA", "rows": [["3-HPAA concentrations (mg/mL)", "percent inhibitions (%)", "cell viability (cfu/mL)"], ["1.7", "31", "5 × 106"], ["1.9", "58", "3.4 × 106"], ["2.1a", "98", "1.9 × 105"], ["2.3b", "99", "no survivors"]], "row_count": 5, "column_count": 3, "numeric_cells": 12, "header_rows": 1, "locator": "section[1]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:32832748:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:fe3996c056d8958fd50fb5916f7ca005e900eceb45c2397c7b540a8f07b0f618", "bytes": 4256, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#tbl2", "version": null, "note": "Significant Undetected Proteins of P. aeruginosa after 3-HPAA Exposure", "structure": {"pmcid": "PMC7439270", "section_index": 4, "section_title": "Overall Protein Profile", "row_count": 31, "column_count": 5}, "table": {"label": "Table 2", "caption": "Significant Undetected Proteins of P. aeruginosa after 3-HPAA Exposure", "rows": [["protein IDaI", "protein name", "gene name", "function", "group of protein profileb"], ["Q9HWG0", "UvrABC system protein A", "uvrA PA4234", "nucleotide excision repair, SOS response", "DNA"], ["Q9HY08", "DNA mismatch repair protein", "mutS PA3620", "mismatch repair", "DNA"], ["Q9HUJ8", "DNA topoisomerase 4 subunit B", "parE PA4967", "DNA topological change", "DNA"], ["Q9HT76", "vitamin B12-dependent ribonucleotide reductase", "nrdJA PA5497", "DNA biosynthetic process, DNA replication", "DNA"], ["P49988", "RNA polymerase sigma-54 factor", "rpoN PA4462", "transcription initiation, sigma factor activity", "RNA"], ["Q9HU59", "transcriptional regulator NtrC", "ntrC PA5125", "nitrogen fixation, regulation of nitrogen utilization, regulation of transcription", "RNA"], ["Q03456", "ferric uptake regulation protein", "fur PA4764", "negative regulation of transcription", "RNA"], ["Q9HVY7", "stringent starvation protein A", "sspA PA4428", "RNA polymerase core enzyme binding", "RNA"], ["Q9I382", "tRNA 2-selenouridine/geranyl-2-thiouridine synthase", "selU PA1643", "tRNA seleno modification", "RNA"], ["Q9HY82", "ribonuclease T", "rnt PA3528", "tRNA 3′-end processing", "RNA"], ["Q9I2U8", "glutamine-tRNA ligase", "glnS PA1794", "glutamine-tRNA ligase activity", "ribosomes and protein"], ["Q9I2U7", "cysteine-tRNA ligase", "cysS PA1795", "cysteine-tRNA ligase activity", "ribosomes and protein"], ["Q9HV58", "30S ribosomal protein S15", "rpsO PA4741", "ribosome constituent, translation", "ribosomes and protein"], ["Q9HU56", "protein-export protein SecB", "secB PA5128", "protein tetramerization, protein transport", "ribosomes and protein"], ["Q9HZC5", "aminopeptidase N", "pepN PA3083", "peptide catabolic process, proteolysis", "ribosomes and protein"], ["O68822", "cytosol aminopeptidase", "pepA phpA, PA3831", "release of an N-terminal amino acid, processing and regular turnover of intracellular proteins.", "ribosomes and protein"], ["Q9HT06", "membrane protein insertase YidC", "yidC PA5568", "membrane insertase activity, insertion and/or proper folding and/or complex formation of integral membrane proteins into the membrane", "cell wall and membrane"], ["Q9I6C1", "signal recognition particle receptor FtsY", "ftsY PA0373", "cotranslational protein targeting to membrane", "cell wall and membrane"], ["Q9HV48", "ATP-dependent zinc metalloprotease FtsH", "ftsH PA4751", "cell division, response to antibiotic", "cell wall and membrane"], ["P50598", "Tol-Pal system protein TolQ", "tolQ PA0969", "cell cycle, cell division, bacteriocin transport", "cell wall and membrane"], ["P23189", "glutathione reductase", "gor PA2025", "cell redox homeostasis, response to oxygen radical", "redox and cell homeostasis"], ["Q9I6Z2", "alkyl hydroperoxide reductase", "ahpF PA0140", "response to reactive oxygen species", "redox and cell homeostasis"], ["P53652", "superoxide dismutase [Mn]", "sodA PA4468", "removal of superoxide radicals", "redox and cell homeostasis"], ["Q9I5R7", "S-adenosylmethionine decarboxylase proenzyme", "speD PA0654", "S-adenosylmethioninamine biosynthetic process, spermidine biosynthetic process", "redox and cell homeostasis"], ["Q9I5F9", "lon protease", "lon PA0779", "response to antibiotic, response to stress, nitric oxide metabolic process, peptidase activity", "redox and cell homeostasis"], ["Q9I2T9", "lon protease", "lon PA1803", "response to antibiotics, response to drug, response to stress, pathogenesis, protein quality control for misfolded or incompletely synthesized proteins, single-species biofilm formation, type IV pilus-dependent motility, flagellum-dependent swarming motility", "redox and cell homeostasis"], ["Q9HTW6", "aminopeptidase P", "pepP PA5224", "aminopeptidase activity", "metabolism"], ["Q9HWG9", "5-methylphenazine-1-carboxylate 1-monooxygenase", "phzS PA4217", "pyocyanine biosynthetic process", "metabolism"], ["O69753", "phenazine biosynthesis protein PhzB1", "phzB1 PA4211", "phenazine biosynthetic process", "metabolism"], ["Q7DC81", "phenazine biosynthesis protein PhzE", "phzE1 phzE2, PA1903, PA4214", "glutamine metabolic process, tryptophan biosynthetic process, phenazine biosynthetic process", "metabolism"]], "row_count": 31, "column_count": 5, "numeric_cells": 54, "header_rows": 1, "locator": "section[4]/table-wrap[1]#tbl2"}}, {"id": "asset:table:pmid:32832748:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:af7c7e1b4695a24e965e0f0c9d84dfb3c23acb5bfd3fa46a7aadfa1db8b3f85c", "bytes": 2109, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[2]#tbl3", "version": null, "note": "Significant Newly Detected Proteins of P. aeruginosa after 3-HPAA Exposure", "structure": {"pmcid": "PMC7439270", "section_index": 4, "section_title": "Overall Protein Profile", "row_count": 12, "column_count": 5}, "table": {"label": "Table 3", "caption": "Significant Newly Detected Proteins of P. aeruginosa after 3-HPAA Exposure", "rows": [["protein IDaI", "protein name", "gene name", "function (UniProt)", "protein profile groupb"], ["Q9HXZ1", "DNA polymerase III subunit α", "dnaE PA3640", "DNA replication", "DNA"], ["Q9I7C4", "β sliding clamp", "dnaN PA0002", "DNA strand elongation involved in DNA replication, 3′–5′ exonuclease activity, DNA-directed DNA polymerase activity", "DNA"], ["P23620", "phosphate regulon transcriptional regulatory protein PhoB", "phoB PA5360", "flagellum-dependent swarming motility, phosphate-ion transport, positive regulation of cellular response to phosphate starvation, transcription", "RNA"], ["Q9HTL4", "OxyR", "oxyR PA5344", "RNA polymerase transcription activator, transcription regulatory region DNA binding source, negative regulation of secondary metabolite biosynthetic process, cell motility, lipid biosynthesis, response to reactive oxygen species", "RNA"], ["Q9HUN0", "30S ribosomal protein S18", "rpsR PA4934", "structural constituent of ribosome, translation", "ribosomes and protein"], ["P33641", "outer membrane protein assembly factor BamD", "bamD PA4545", "cell envelope organization, protein insertion into membrane", "cell wall and membrane"], ["G3XDB2", "cell division coordinator CpoB", "cpoB PA0974", "FtsZ-dependent cytokinesis", "cell wall and membrane"], ["Q9HUF1", "peptide methionine sulfoxide reductase MsrA", "msrA PA5018", "response to oxidative stress, response to hypochlorite", "redox and cell homeostasis"], ["Q9I6I9", "spermidine/putrescine import ATP-binding protein PotA", "spuF potA, PA0302", "spermidine transport, putrescine transport", "redox and cell homeostasis"], ["Q9HUX1", "biosynthetic arginine decarboxylase", "speA PA4839", "arginine catabolic process, putrescine biosynthetic process, spermidine biosynthetic process", "redox and cell homeostasis"], ["Q9X6R0", "polyamine aminopropyltransferase 1", "speE1 speE, PA1687", "spermidine biosynthetic process", "redox and cell homeostasis"]], "row_count": 12, "column_count": 5, "numeric_cells": 16, "header_rows": 1, "locator": "section[4]/table-wrap[2]#tbl3"}}], "gaps": ["asset:data:geo:PXD016243 not downloaded", "asset:data:geo:PXD016243 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The significant metabolic pathways of the genes of these proteins were elucidated by the KEGG pathway enrichment analysis using the DAVID bioinformatics database (version 6.8)."}}], "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": ["pathway_enrich"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pathway_enrichment."}, "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": ["PXD016243"], "resolved_accessions": ["PXD016243"], "statements": ["The mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifier PXD016243."], "basis": "The paper names PXD016243 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": ["pathway_enrich"], "assets": ["source:pmid:32832748", "data:geo:PXD016243", "asset:table:pmid:32832748:1", "asset:table:pmid:32832748:2", "asset:table:pmid:32832748:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD016243"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:21:59Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 31486, "completion_tokens": 825, "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:32832748", "type": "paper", "label": "pmid:32832748"}, {"id": "source:pmid:32832748", "type": "manuscript", "label": "PMID 32832748 full text"}, {"id": "data:geo:PXD016243", "type": "dataset", "label": "GEO PXD016243"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32832748", "type": "paper", "label": "pmid:32832748"}, {"id": "source:pmid:32832748", "type": "manuscript", "label": "PMID 32832748 full text"}, {"id": "data:geo:PXD016243", "type": "dataset", "label": "GEO PXD016243"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32832748", "type": "extraction", "used": ["source:pmid:32832748"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD016243", "type": "accession_resolution", "used": ["data:geo:PXD016243"], "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:32832748", "parent_hash": "sha256:26a79d0f5f93709753f38ece5bae40b97a578010e616ffd5cd6def50697071c9", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD016243 licence not read", "asset:data:geo:PXD016243 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "network_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pathway_enrich"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The significant metabolic pathways of the genes of these proteins were elucidated by the KEGG pathway enrichment analysis using the DAVID bioinformatics database (version 6.8)."], "order_basis": "analysis_only", "id": "assay:1"}]},"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":"2026-11-04T01:33:56+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}}}