{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32904176", "kind": "science-record", "revision": 6, "content_hash": "sha256:1b24ef73c89add69d96bedecd02b96e9d7ba1912d82ae4bb6d07427b6477242c", "created_at": "2026-11-01T15:41:10Z", "updated_at": "2026-11-01T21:23:46Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Spleen proteomics data from high fat diet fed mice.", "doi": "10.1016/j.dib.2020.106110", "pmid": "32904176", "authors": ["Sara L Svahn", "Bagmi Pattanaik", "Louise Grahnemo", "Saray Gutierrez", "Intawat Nookaew", "John-Olov Jansson", "Maria E Johansson"], "journal": "Data in brief", "year": 2020, "abstract": "The composition of the diet affects many processes in the body, including body weight and endocrine system. We have previously shown that dietary fat also affects the immune system. Mice fed high fat diet rich in polyunsaturated fatty acids survive S. aureus infection to a much greater extent than mice fed high fat diet rich in saturated fatty acids. Here we present data regarding the dietary effects on protein expression in spleen from mice fed three different diets, I) low fat/chow diet (LFD, n = 4), II) high fat diet rich in saturated fatty acids (HFD-S, n = 4) and III) high fat diet rich in polyunsaturated fatty acids (HFD-P, n = 4). We performed mass spectrophotometry based quantitative proteomics analysis of isolated spleen by implementing the isobaric tags for relative and absolute quantification (iTRAQ) approach. Mass spectrometry data were analyzed using Proteome Discoverer 2.4 software using the search engine mascot against Mus musculus in SwissProt. 924 proteins are identified in all sets (n = 4) for different dietary effects taken for statistical analysis using Qlucore Omics Explorer software. Only 20 proteins were found to be differentially expressed with a cut-off value of false discovery rate < 0.1 (q-value) when comparing HFD-S and HFD-P but no differentially expressed proteins were found when LFD was compared with HFD-P or HFD-S. The identified proteins and statistical analysis comparing HFD-S and HFD-P diets are available as a supplementary file S1. We identified a subset of proteins that showed an inverse expression pattern between two high fat diets. These differentially expressed proteins were further classified by gene ontology for their role in biological processes and molecular functions. Mass spectrometry raw data are also available via ProteomeXchange with identifier PXD020365.", "claims": [{"id": "claim-method", "statement": "Qlucore Omics Explorer 3.6 (Lund, Sweden https://qlucore.com) was used for statistical analysis using t-test two-groups comparison (HFD-S vs LFD; HFD-P vs LFD; HFD-P vs HFD-S).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32904176", "locator": "sections[8] \"Data analysis\" paragraph 3", "quote": "Qlucore Omics Explorer 3.6 (Lund, Sweden https://qlucore.com) was used for statistical analysis using t-test two-groups comparison (HFD-S vs LFD; HFD-P vs LFD; HFD-P vs HFD-S)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Analyzed data are available within the article and raw mass spectrometric proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE [1] partner repository with the dataset identifier PXD020365.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32904176", "locator": "sections[1] \"p\" paragraph 1", "quote": "Analyzed data are available within the article and raw mass spectrometric proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE [1] partner repository with the dataset identifier PXD020365."}], "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:32904176"], "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:PXD020365"], "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:PXD020365"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32904176", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2020.106110", "sha256": "sha256:f39e1c62ce1de7ce7a88c1d460feec9e7f39e3930212ad8121c1661f476b2723", "bytes": 17326, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2020.106110", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7451803", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD020365", "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=PXD020365", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD020365", "version": null, "note": "Analyzed data are available within the article and raw mass spectrometric proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE [1] partner repository with the dataset identifier PXD020365.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Analyzed data are available within the article and raw mass spectrometric proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE [1] partner repository with the dataset identifier PXD020365.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Spleen proteomics data from high fat diet fed mice", "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:32904176:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:636975971786fa00e01d6732d1b254991a9fbab0180f6512011ef624ab23be03", "bytes": 2237, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#utbl0001", "version": null, "note": null, "structure": {"pmcid": "PMC7451803", "section_index": 1, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject", "Endocrinology, Diabetes, and Metabolism"], ["Specific subject area", "dietary proteomics"], ["Type of data", "Raw data, Excel files, Tables, Figures"], ["How data were acquired", "Samples were analyzed on an LTQ-Orbitrap Velos mass spectrometer interfaced with an Easy-nLC (Thermo Fisher Scientific).For relative quantification, the MS raw data files for each iTRAQ set were merged in the search using Proteome Discoverer version 2.4 (Thermo Fisher Scientific).The database search was performed with the Mascot search engine (Matrix Science) against Mus musculus in SwissProt version July 2019 (Swiss Institute of Bioinformatics, Switzerland)."], ["Data format", "AnalyzedRaw"], ["Parameters for data collection", "C57BL/6 mice were fed one of three different diets for 8 weeks, I) low fat/chow diet (LFD), II) high fat diet rich in saturated fatty acids (HFD-S), or III) high fat diet rich in polyunsaturated fatty acids (HFD-P). Proteins from spleen were extracted and analyzed using quantitative proteomics. n = 4 per group."], ["Description of data collection", "The experimental layout is presented in Fig. 1. Data presented in this manuscript are spleen proteins affected by three different diets, I) low fat/chow diet (LFD), II) high fat diet rich in saturated fatty acids (HFD-S), or III) high fat diet rich in polyunsaturated fatty acids (HFD-P) (Table 1). We identified 924 proteins present in all datasets of different dietary conditions (Supplementary file S1). With a cut-off value of false discovery rate < 0.1 (q-value), the number of differentially expressed proteins data is presented in a Venn diagram (Fig. 2), and Table 2 and the two high fat diets are visualized in a heat map (Fig. 3). 20 differentially expressed proteins were further classified by gene ontology (Fig 4)."], ["Data source location", "Gothenburg, Sweden"], ["Data accessibility", "Analyzed data are available within the article and raw mass spectrometric proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE [1] partner repository with the dataset identifier PXD020365."]], "row_count": 9, "column_count": 2, "numeric_cells": 4, "header_rows": 0, "locator": "section[1]/table-wrap[1]#utbl0001"}}, {"id": "asset:table:pmid:32904176:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b6d4db433cdfd77a2097ca8c948a53c2415a236ad756883282ed12fe5128b9b1", "bytes": 975, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#tbl0001", "version": null, "note": "Energy density and composition of experimental diets: low fat/chow diet (LFD), high fat diet rich in saturated fatty acids (HFD-S), or high fat diet rich in polyunsaturated fatty acids (HFD-P). From Svahn SL et al [2,3].", "structure": {"pmcid": "PMC7451803", "section_index": 3, "section_title": "Data description", "row_count": 17, "column_count": 4}, "table": {"label": "Table 1", "caption": "Energy density and composition of experimental diets: low fat/chow diet (LFD), high fat diet rich in saturated fatty acids (HFD-S), or high fat diet rich in polyunsaturated fatty acids (HFD-P). From Svahn SL et al [2,3].", "rows": [["", "LFD", "HFD-S", "HFD-P"], ["Energy density (kcal/g)", "3.9", "5.2", "5.2"], ["Macronutrients (% kcal)", "", "", ""], ["Protein", "20", "20", "20"], ["Carbohydrate", "70", "20", "20"], ["Fat", "10", "60", "60"], ["Fat source (% of total fat)", "", "", ""], ["Soybean oil", "55.6", "9.3", "9.3"], ["Lard", "44.4", "90.7", "27.8"], ["Menhaden oil", "-", "-", "63.0"], ["Fatty acids (% by wt of total fatty acids)", "", "", ""], ["∑ SFA", "22.7", "32.0", "28.7"], ["∑ MUFA", "29.8", "36.0", "27.5"], ["∑ PUFA", "47.5", "32.0", "43.9"], ["∑ n-3 total fat", "5.2", "2.1", "25.6"], ["∑ n-6 total fat", "42.4", "29.9", "16.2"], ["n-6/n-3", "8.2", "14.1", "0.6"]], "row_count": 17, "column_count": 4, "numeric_cells": 40, "header_rows": 1, "locator": "section[3]/table-wrap[1]#tbl0001"}}, {"id": "asset:table:pmid:32904176:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b8734feb30be2767042d87f417267bcbfc92d99513737fc3e8115c84f2798e25", "bytes": 1084, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#tbl0002", "version": null, "note": "Protein ID and respective protein names presented in the heat map.", "structure": {"pmcid": "PMC7451803", "section_index": 3, "section_title": "Data description", "row_count": 21, "column_count": 2}, "table": {"label": "Table 2", "caption": "Protein ID and respective protein names presented in the heat map.", "rows": [["Protein ID", "Protein name"], ["Q9CY02", "Alpha-hemoglobin-stabilizing protein"], ["P84228", "Histone H3,2"], ["P43276", "Histone H1,5"], ["P09405", "Nucleolin"], ["P42932", "T-complex protein 1 subunit theta"], ["P54071", "Isocitrate dehydrogenase [NADP], mitochondrial"], ["Q8VIJ6", "Splicing factor, proline- and glutamine-rich"], ["Q3TEA8", "Heterochromatin protein 1-binding protein 3"], ["O89100", "GRB2-related adaptor protein 2"], ["Q3UTJ2", "Sorbin and SH3 domain-containing protein 2"], ["Q8R409", "Protein HEXIM1"], ["P42209", "Septin-1"], ["Q8BYZ1", "ABI gene family member 3"], ["Q6PIU9", "Uncharacterized protein FLJ45252 homolog"], ["Q8CI51", "PDZ and LIM domain protein 5"], ["Q62507", "Cochlin"], ["Q3TJD7", "PDZ and LIM domain protein 7"], ["Q9D154", "Leukocyte elastase inhibitor A"], ["Q8C3W1", "Uncharacterized protein C1orf198 homolog"], ["O54724", "Caveolae-associated protein 1"]], "row_count": 21, "column_count": 2, "numeric_cells": 26, "header_rows": 1, "locator": "section[3]/table-wrap[2]#tbl0002"}}], "gaps": ["asset:data:geo:PXD020365 not downloaded", "asset:data:geo:PXD020365 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "t-test two-groups comparison", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Qlucore Omics Explorer 3.6 (Lund, Sweden https://qlucore.com) was used for statistical analysis using t-test two-groups comparison (HFD-S vs LFD; HFD-P vs LFD; HFD-P vs HFD-S)."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (t-test two-groups comparison), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["PXD020365"], "resolved_accessions": ["PXD020365"], "statements": ["Analyzed data are available within the article and raw mass spectrometric proteomics data have been deposited to the ProteomeXchange Consortium via the PRIDE [1] partner repository with the dataset identifier PXD020365."], "basis": "The paper names PXD020365 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:32904176", "data:geo:PXD020365", "asset:table:pmid:32904176:1", "asset:table:pmid:32904176:2", "asset:table:pmid:32904176:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD020365"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:22:21Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 14282, "completion_tokens": 852, "cached_tokens": 776}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:32904176", "type": "paper", "label": "pmid:32904176"}, {"id": "source:pmid:32904176", "type": "manuscript", "label": "PMID 32904176 full text"}, {"id": "data:geo:PXD020365", "type": "dataset", "label": "GEO PXD020365"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32904176", "type": "paper", "label": "pmid:32904176"}, {"id": "source:pmid:32904176", "type": "manuscript", "label": "PMID 32904176 full text"}, {"id": "data:geo:PXD020365", "type": "dataset", "label": "GEO PXD020365"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32904176", "type": "extraction", "used": ["source:pmid:32904176"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD020365", "type": "accession_resolution", "used": ["data:geo:PXD020365"], "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:32904176", "parent_hash": "sha256:e75afe78e0920e10b97b2e393b1545edbd49e833162a1462e2efa66a31bed761", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD020365 licence not read", "asset:data:geo:PXD020365 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": ["Spleen proteomics data from high fat diet fed mice.", "nd absolute quantification (iTRAQ) approach. Mass spectrometry data were analyzed using Proteome Discoverer", "iological processes and molecular functions. Mass spectrometry raw data are also available via ProteomeXcha", "ed mass spectrophotometry based quantitative proteomics analysis of isolated spleen by implementing"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["erials and methods Six-week-old male C57BL/6 mice were obtained from Harlan Netherlands B.V. (Horst", "therlands B.V. (Horst, The Netherlands). The mice were housed under standard conditions of light an"], "order_basis": "paper_text_order:1911", "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":"2026-11-04T03:34:27+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}}}