{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31297409", "kind": "science-record", "revision": 8, "content_hash": "sha256:9711d622721d0bfa6d733bce57022027965f81dd566f332ac36ff73d2f920288", "created_at": "2026-11-01T15:40:47Z", "updated_at": "2026-11-01T22:44:05Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Data from differentially expressed proteins in platelet components associated with adverse transfusion reactions.", "doi": "10.1016/j.dib.2019.104013", "pmid": "31297409", "authors": ["Chaker Aloui", "Céline Barlier", "Danielle Awounou", "Stéphane Claverol", "Jocelyne Fagan", "Fabrice Cognasse", "Olivier Garraud", "Sandrine Laradi"], "journal": "Data in brief", "year": 2019, "abstract": "The presented dataset was used for the study focused on the search for differentially expressed proteins in blood platelet components (PCs) associated with adverse transfusion reactions (ATRs). Pellets of ATR platelet components and their controls were subjected to high-throughput proteomics analysis using a Q Exactive high-resolution tandem mass spectrometer. The data reported here constitutes an extension of \"Differential protein expression of blood platelet components associated with adverse transfusion reactions\" article Aloui et al., 2018. The reported data herein have been deposited into the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD003510 for the pooled platelet components (PPCs) and PXD008886 for the apheresis platelet components (SDA-PCs) associated with ATRs.", "claims": [{"id": "claim-method", "statement": "The obtained raw proteomic data were statistically analysed (ANOVA test and absolute fold change).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31297409", "locator": "sections[2] \"Data\" paragraph 2", "quote": "The obtained raw proteomic data were statistically analysed (ANOVA test and absolute fold change)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The reported data herein have been deposited into the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD003510 for the pooled platelet components (PPCs) and PXD008886 for the apheresis platelet components (SDA-PCs) associated with ATRs.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31297409", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "The reported data herein have been deposited into the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD003510 for the pooled platelet components (PPCs) and PXD008886 for the apheresis platelet components (SDA-PCs) associated with ATRs."}], "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:31297409"], "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:PXD003510"], "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:PXD003510"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31297409", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2019.104013", "sha256": "sha256:f99ca4273808d71c4a83d6028229eed2de7056f86793c56e454fb2ac144381c1", "bytes": 13749, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2019.104013", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6598860", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD003510", "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=PXD003510", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD003510", "version": null, "note": "The reported data herein have been deposited into the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD003510 for the pooled platelet components (PPCs) and PXD008886 for the apheresis platelet components (SDA-PCs) associated with ATRs.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The reported data herein have been deposited into the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD003510 for the pooled platelet components (PPCs) and PXD008886 for the apheresis platelet components (SDA-PCs) associated with ATRs.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Platelet proteomics profiling in transfusion adverse events, part 2", "resolution_checked_at": "2026-10-31T18:35:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD008886", "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=PXD008886", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD008886", "version": null, "note": "The reported data herein have been deposited into the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD003510 for the pooled platelet components (PPCs) and PXD008886 for the apheresis platelet components (SDA-PCs) associated with ATRs.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The reported data herein have been deposited into the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD003510 for the pooled platelet components (PPCs) and PXD008886 for the apheresis platelet components (SDA-PCs) associated with ATRs.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Platelet proteomics profiling in transfusion adverse events", "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:31297409:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0410daaaee710f62919352cfb5c6ceab1f03a4a702b5b7351d6d7f4d3ed8e06b", "bytes": 2752, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#undtbl1", "version": null, "note": "Specifications table", "structure": {"pmcid": "PMC6598860", "section_index": 1, "section_title": "p", "row_count": 10, "column_count": 2}, "table": {"label": null, "caption": "Specifications table", "rows": [["Subject area", "Biology"], ["More specific subject area", "Platelet proteomics profiling associated with adverse transfusion reactions (ATRs)"], ["Type of data", "Mass spectrometry raw files, tables and figure"], ["How data was acquired", "Peptides were analysed on an Ultimate 3000 nanoLC system (Dionex, Amsterdam, The Netherlands) coupled to an Electrospray Q Exactive quadrupole Orbitrap benchtop mass spectrometer (Thermo Fisher Scientific, San Jose, CA, USA). Data were searched with SEQUEST through Proteome Discoverer 1.4 (Thermo Fisher Scientific) against the Homo sapiens reference proteome set (UniProt version 2015–07). Raw LC-MS/MS data were then imported into Progenesis QI 2.0 (Nonlinear Dynamics Ltd., Newcastle, UK) to analyse the label-free quantitative data."], ["Data format", "Raw and processed data"], ["Experimental factors", "Platelet pellets from leukodepleted platelet components (PCs) were sampled from 6 PCs implicated in ATRs and in matched controls. The collected samples were centrifuged at 1500 rpm for 10 min. The PC pellet was washed with sterile 1X PBS. The pellet was then resuspended in 80 μL of PBS and 20 μL of 5X Laemmli buffer (with 0.5 M DTT). After denaturation at 100°C for 3 min, the samples were stored at -80°C until analysis."], ["Experimental features", "For nanoLC-MS/MS analysis, 10 mg of each protein sample were solubilised in Laemmli buffer and deposited into a 10% acrylamide SDS-PAGE gel. Proteins were denatured, reduced, alkylated and digested with trypsin. The supernatant was collected, and an H2O/ACN/HCOOH (47.5:47.5:5) extraction solution was added onto the gel pieces for 15 min. Supernatants were dried in a vacuum centrifuge and resuspended in 100 μL of water acidified with 0.1% HCOOH. The peptide mixture generated was injected into the nano-liquid chromatography-mass spectrometry system."], ["Data source location", "Proteome Platform, CGFB, University of Bordeaux Segalen, 33 076 Bordeaux, France"], ["Data accessibility", "Data within this article were deposited to the ProteomeXchange via the PRIDE repository with the following PRIDE identifiers: PXD003510https://www.ebi.ac.uk/pride/archive/projects/PXD003510(for PPCs) and PXD008886https://www.ebi.ac.uk/pride/archive/projects/PXD008886(for SDA-PCs)."], ["Related research article", "C. Aloui, C. Barlier, S. Claverol, J. Fagan, D. Awounou, E. Tavernier, D. Guyotat, H. Hamzeh-Cognasse, F. Cognasse, O. Garraud, S. Laradi, Differential protein expression of blood platelet components associated with adverse transfusion reactions, J Proteomics 194 (2018) 25–36[1]."]], "row_count": 10, "column_count": 2, "numeric_cells": 6, "header_rows": 0, "locator": "section[1]/table-wrap[1]#undtbl1"}}, {"id": "asset:table:pmid:31297409:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ff86b9936b69e856c878656912c72789951323659709dacfe54f23f7a8093f00", "bytes": 992, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[2]#undtbl2", "version": null, "note": null, "structure": {"pmcid": "PMC6598860", "section_index": 1, "section_title": "p", "row_count": 1, "column_count": 1}, "table": {"label": null, "caption": null, "rows": [["Value of the data•This dataset presents the first exploration of the platelet proteomic signature associated with adverse transfusion reaction (ATRs) in two types of PCs•These data constitute an interesting resource, essential to direct subsequent/future studies, especially in the context of inflammation•These data provide a basis for subsequent comparisons of differential protein expression of blood platelet component associated with ATRs, including the investigation of the biological processes such as i) between platelet pellets and supernatants ii) between different preparation processes•This proteomics analysis paves the way to a better understanding of the pathophysiological mechanisms involved in ATRs•The provided dataset can be useful for transfusion medicine in order to improve transfusion safety and efficacy."]], "row_count": 1, "column_count": 1, "numeric_cells": 0, "header_rows": 0, "locator": "section[1]/table-wrap[2]#undtbl2"}}, {"id": "asset:table:pmid:31297409:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7a1a0d4a2e87254c0df01c40b00a83876ef1e888f8f931c456f2e01b734a707a", "bytes": 1048, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[2]/table-wrap[1]#tbl1", "version": null, "note": "The DE proteins in ATRs, present a significant role in degranulation/platelet activation and/or cytoskeleton remodelling and are involved in the signalling integrin pathway in ATR-PPCs and in ATR-SDA-PCs.", "structure": {"pmcid": "PMC6598860", "section_index": 2, "section_title": "Data", "row_count": 6, "column_count": 8}, "table": {"label": "Table 1", "caption": "The DE proteins in ATRs, present a significant role in degranulation/platelet activation and/or cytoskeleton remodelling and are involved in the signalling integrin pathway in ATR-PPCs and in ATR-SDA-PCs.", "rows": [["", "DE proteins (Gene Name [ID Uniprot])", "Peptide count", "Abundances (Grouped): ATR-PCs", "Abundances (Grouped): no.ATR-PCs", "Confidence score", "P-value", "Ratio"], ["In ATR-PPCs", "Platelet basic protein (PPBP [P02775])", "6", "244 050 285", "109 065 780", "29.57", "0.0012", "2.24"], ["Rho-related GTP-binding protein RhoG (RHOG [P84095])", "5", "6 404 276", "1801 718", "10.89", "0.0048", "3.55"], ["Alpha-1-antichymotrypsin (SERPINA3 [P01011])", "3", "0", "735 679", "7.98", "0.0000002", "∼0"], ["In ATR-SDA-PCs", "Alpha-actinin-1 (ACTN1 [P12814])", "685", "3 894 757 912", "2 081 306 441", "2425.56", "0.0165", "1.87"], ["Multimerin-1 (MMRN1 [Q13201])", "299", "13 616 389 948", "8 630 563 950", "1023.55", "0.0173", "1.58"]], "row_count": 6, "column_count": 8, "numeric_cells": 35, "header_rows": 1, "locator": "section[2]/table-wrap[1]#tbl1"}}], "gaps": ["asset:data:geo:PXD003510 not downloaded", "asset:data:geo:PXD003510 licence not read", "asset:data:geo:PXD008886 not downloaded", "asset:data:geo:PXD008886 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": "The obtained raw proteomic data were statistically analysed (ANOVA test and absolute fold change)."}}], "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": ["PXD003510", "PXD008886"], "resolved_accessions": ["PXD003510", "PXD008886"], "statements": ["The reported data herein have been deposited into the ProteomeXchange Consortium via the PRIDE partner repository with the dataset identifiers PXD003510 for the pooled platelet components (PPCs) and PXD008886 for the apheresis platelet components (SDA-PCs) associated with ATRs."], "basis": "The paper names PXD003510, PXD008886 in PRIDE 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:31297409", "data:geo:PXD003510", "asset:table:pmid:31297409:1", "asset:table:pmid:31297409:2", "asset:table:pmid:31297409:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD003510"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:15:20Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 11735, "completion_tokens": 1692, "cached_tokens": 4104}}, "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:31297409", "type": "paper", "label": "pmid:31297409"}, {"id": "source:pmid:31297409", "type": "manuscript", "label": "PMID 31297409 full text"}, {"id": "data:geo:PXD003510", "type": "dataset", "label": "GEO PXD003510"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31297409", "type": "paper", "label": "pmid:31297409"}, {"id": "source:pmid:31297409", "type": "manuscript", "label": "PMID 31297409 full text"}, {"id": "data:geo:PXD003510", "type": "dataset", "label": "GEO PXD003510"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31297409", "type": "extraction", "used": ["source:pmid:31297409"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD003510", "type": "accession_resolution", "used": ["data:geo:PXD003510"], "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:31297409", "parent_hash": "sha256:5881b8f66e437ecb6f8ac1a85b40d44586d495ce3023dcbf3fefbe2188f20675", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:PXD003510 licence not read", "asset:data:geo:PXD003510 not downloaded", "asset:data:geo:PXD008886 licence not read", "asset:data:geo:PXD008886 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": ["r controls were subjected to high-throughput proteomics analysis using a Q Exactive high-resolution", "d methods Sample collection and preparation, mass spectrometry and data analysis are summarised in Fig. 1."], "order_basis": "paper_text_order:351", "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": ["The obtained raw proteomic data were statistically analysed (ANOVA test and absolute fold change)."], "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":"2026-11-04T02:12:19+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}}}