{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:25265318", "kind": "science-record", "revision": 6, "content_hash": "sha256:7cf4d43ea650f8d7ae3890f10790ab7d2546fab1a38b18ea87e9ccc9a5876af2", "created_at": "2026-11-01T15:40:06Z", "updated_at": "2026-11-01T21:19:52Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Label-free LC-MSe in tissue and serum reveals protein networks underlying differences between benign and malignant serous ovarian tumors.", "doi": "10.1371/journal.pone.0108046", "pmid": "25265318", "authors": ["Wouter Wegdam", "Carmen A Argmann", "Gertjan Kramer", "Johannes P Vissers", "Marrije R Buist", "Gemma G Kenter", "Johannes M F G Aerts", "Danielle Meijer", "Perry D Moerland"], "journal": "PloS one", "year": 2014, "abstract": "PURPOSE: To identify proteins and (molecular/biological) pathways associated with differences between benign and malignant epithelial ovarian tumors.\nEXPERIMENTAL PROCEDURES: Serum of six patients with a serous adenocarcinoma of the ovary was collected before treatment, with a control group consisting of six matched patients with a serous cystadenoma. In addition to the serum, homogeneous regions of cells exhibiting uniform histology were isolated from benign and cancerous tissue by laser microdissection. We subsequently employed label-free liquid chromatography tandem mass spectrometry (LC-MSe) to identify proteins in these serum and tissues samples. Analyses of differential expression between samples were performed using Bioconductor packages and in-house scripts in the statistical software package R. Hierarchical clustering and pathway enrichment analyses were performed, as well as network enrichment and interactome analysis using MetaCore.\nRESULTS: In total, we identified 20 and 71 proteins that were significantly differentially expressed between benign and malignant serum and tissue samples, respectively. The differentially expressed protein sets in serum and tissue largely differed with only 2 proteins in common. MetaCore network analysis, however inferred GCR-alpha and Sp1 as common transcriptional regulators. Interactome analysis highlighted 14-3-3 zeta/delta, 14-3-3 beta/alpha, Alpha-actinin 4, HSP60, and PCBP1 as critical proteins in the tumor proteome signature based on their relative overconnectivity. The data have been deposited to the ProteomeXchange with identifier PXD001084.\nDISCUSSION: Our analysis identified proteins with both novel and previously known associations to ovarian cancer biology. Despite the small overlap between differentially expressed protein sets in serum and tissue, APOA1 and Serotransferrin were significantly lower expressed in both serum and cancer tissue samples, suggesting a tissue-derived effect in serum. Pathway and subsequent interactome analysis also highlighted common regulators in serum and tissue samples, suggesting a yet unknown role for PCBP1 in ovarian cancer pathophysiology.", "claims": [{"id": "claim-method", "statement": "Differentially expressed proteins between benign and malignant tumors were detected using a moderated t-test. The mass spectrometry proteomics data have been deposited to the ProteomeXchange consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001084.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:25265318", "locator": "sections[8] \"Statistical analyses\" paragraph 3", "quote": "Differentially expressed proteins between benign and malignant tumors were detected using a moderated t-test."}, {"asset": "source:pmid:25265318", "locator": "sections[18] \"Data Availability\" paragraph 2", "quote": "The mass spectrometry proteomics data have been deposited to the ProteomeXchange consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001084."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The authors confirm that all data underlying the findings are fully available without restriction. The mass spectrometry proteomics data have been deposited to the ProteomeXchange consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001084.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:25265318", "locator": "sections[18] \"Data Availability\" paragraph 2", "quote": "The authors confirm that all data underlying the findings are fully available without restriction. The mass spectrometry proteomics data have been deposited to the ProteomeXchange consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001084."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study identified 20 significantly differentially expressed serum proteins and 71 significantly differentially expressed tissue proteins between benign and malignant ovarian tumors, with only two proteins shared between the two signatures.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:25265318", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "In total, we identified 20 and 71 proteins that were significantly differentially expressed between benign and malignant serum and tissue samples, respectively."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study identified 20 significantly differentially expressed serum proteins and 71 significantly differentially expressed tissue proteins between benign and malignant ovarian tumors, with only two proteins shared between the two signatures.", "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:25265318"], "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:GSE12172"], "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:GSE12172"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:25265318", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0108046", "sha256": "sha256:90d462f33c7dec2ece50a6f7cbf6136cc669587bc5f6e0a7351c1de79ba8ccb3", "bytes": 58108, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0108046", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4180266", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE12172", "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=GSE12172", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE12172", "version": null, "note": "The authors confirm that all data underlying the findings are fully available without restriction. The mass spectrometry proteomics data have been deposited to the ProteomeXchange consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001084.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The authors confirm that all data underlying the findings are fully available without restriction. The mass spectrometry proteomics data have been deposited to the ProteomeXchange consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001084.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM306158", "GSM306159", "GSM306160", "GSM306161", "GSM306162", "GSM306163", "GSM306164", "GSM306165", "GSM306166", "GSM306167", "GSM306168", "GSM306169", "GSM306170", "GSM306171", "GSM306172", "GSM306173", "GSM306174", "GSM306175", "GSM306176", "GSM306177", "GSM306178", "GSM306179", "GSM306180", "GSM306181", "GSM306182", "GSM306183", "GSM306184", "GSM306185", "GSM306186", "GSM306187", "GSM306188", "GSM306189", "GSM306190", "GSM306191", "GSM306192", "GSM306193", "GSM306194", "GSM306195", "GSM306196", "GSM306197", "GSM306198", "GSM306199", "GSM306200", "GSM306201", "GSM306202", "GSM306203", "GSM306204", "GSM306205", "GSM306206", "GSM306207", "GSM306208", "GSM306209", "GSM306210", "GSM306211", "GSM306212", "GSM306213", "GSM306214", "GSM306215", "GSM306216", "GSM306217", "GSM306218", "GSM306219", "GSM306220", "GSM306221", "GSM306222", "GSM306223", "GSM306224", "GSM306225", "GSM306226", "GSM306227", "GSM306228", "GSM306229", "GSM306230", "GSM306231", "GSM306232", "GSM306233", "GSM306234", "GSM306235", "GSM306236", "GSM306237", "GSM306238", "GSM306239", "GSM306240", "GSM306241", "GSM306242", "GSM306243", "GSM306244", "GSM306245", "GSM306246", "GSM306247"], "sample_count": 90, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Common activation of RAS_MAPK pathway in serous LMP tumours", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:PXD001084", "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=PXD001084", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD001084", "version": null, "note": "The authors confirm that all data underlying the findings are fully available without restriction. The mass spectrometry proteomics data have been deposited to the ProteomeXchange consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001084.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The authors confirm that all data underlying the findings are fully available without restriction. The mass spectrometry proteomics data have been deposited to the ProteomeXchange consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001084.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Label-free LC-MSe in tissue and serum reveals protein networks underlying differences between benign and malignant serous ovarian tumors", "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:25265318:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1abe4273994123c3b163b7a5206f10cac07c41dcb8b8ab4395ecb48f80b7d7bd", "bytes": 733, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#pone-0108046-t001", "version": null, "note": "Patients characteristics.", "structure": {"pmcid": "PMC4180266", "section_index": 3, "section_title": "Patients and Ethics Statement", "row_count": 14, "column_count": 5}, "table": {"label": "Table 1", "caption": "Patients characteristics.", "rows": [["", "Serum", "Tissue"], ["", "Malignant", "Benign", "Malignant", "Benign"], ["Patients", "6", "6", "5", "6"], ["Age (mean, SD)", "53 (16.5)", "57 (7.2)", "51 (15.2)", "56 (9.8)"], ["BMI (mean, SD)", "25 (4.9)", "25 (5.1)", "23 (3.3)", "26 (4.8)"], ["Pre-menopausal", "3", "1", "2", "2"], ["Post-menopausal", "3", "5", "3", "4"], ["CA125 kU/L (median, range)", "6946 (113–14100)", "12 (7–26)", "2651 (113–7737)", "70 (7–376)"], ["Differentiation grade", "", "", "", ""], ["2", "1", "", "1", ""], ["3", "5", "", "4", ""], ["Figo Stage", "", "", "", ""], ["III", "5", "", "5", ""], ["IV", "1", "", "", ""]], "row_count": 14, "column_count": 5, "numeric_cells": 34, "header_rows": 2, "locator": "section[3]/table-wrap[1]#pone-0108046-t001"}}, {"id": "asset:table:pmid:25265318:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c25671ea6fd378b1299422927f3909fca83990527dd020cbe66e8b128a8b6453", "bytes": 637, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#pone-0108046-t002", "version": null, "note": "Interactions by protein function.", "structure": {"pmcid": "PMC4180266", "section_index": 14, "section_title": "Key proteins differentially expressed between benign and malignant ovarian tumors", "row_count": 6, "column_count": 9}, "table": {"label": "Table 2", "caption": "Interactions by protein function.", "rows": [["Protein", "Actual", "n", "R", "N", "Expected", "Ratio", "p-value", "z-score"], ["PCBP-1", "11", "108", "13", "296", "4.743", "2.319", "0.000402", "3.68"], ["Alpha-actinin 4", "14", "108", "19", "296", "6.932", "2.019", "0.000754", "3.476"], ["HSP60", "17", "108", "27", "296", "9.851", "1.726", "0.003122", "2.993"], ["14-3-3 beta/alpha", "34", "108", "56", "296", "20.43", "1.664", "3.71E-05", "4.176"], ["14-3-3 zeta/delta", "55", "108", "97", "296", "35.39", "1.554", "5.33E-07", "5.035"]], "row_count": 6, "column_count": 9, "numeric_cells": 45, "header_rows": 1, "locator": "section[14]/table-wrap[1]#pone-0108046-t002"}}], "gaps": ["asset:data:geo:GSE12172 not downloaded", "asset:data:geo:GSE12172 licence not read", "asset:data:geo:PXD001084 not downloaded", "asset:data:geo:PXD001084 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Hierarchical clustering"}}, {"id": "method-2", "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": 0.7, "band": "medium", "quote": "pathway enrichment"}}, {"id": "method-3", "family": null, "specific": null, "label": "Moderated t-test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "Differentially expressed proteins between benign and malignant tumors were detected using a moderated t-test. The mass spectrometry proteomics data have been deposited to the ProteomeXchange consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001084."}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["hierarchical_cluster"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: hierarchical."}, "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": ["PXD001084", "GSE12172"], "resolved_accessions": ["PXD001084", "GSE12172"], "statements": ["The authors confirm that all data underlying the findings are fully available without restriction. The mass spectrometry proteomics data have been deposited to the ProteomeXchange consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository with the dataset identifier PXD001084."], "basis": "The paper names PXD001084, GSE12172 in ProteomeXchange consortium and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["hierarchical_cluster"], "assets": ["source:pmid:25265318", "data:geo:GSE12172", "asset:table:pmid:25265318:1", "asset:table:pmid:25265318:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE12172"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:23:05Z", "independence": "same_provider"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 103897, "completion_tokens": 3805, "cached_tokens": 52860}}, "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:25265318", "type": "paper", "label": "pmid:25265318"}, {"id": "source:pmid:25265318", "type": "manuscript", "label": "PMID 25265318 full text"}, {"id": "data:geo:GSE12172", "type": "dataset", "label": "GEO GSE12172"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:25265318", "type": "paper", "label": "pmid:25265318"}, {"id": "source:pmid:25265318", "type": "manuscript", "label": "PMID 25265318 full text"}, {"id": "data:geo:GSE12172", "type": "dataset", "label": "GEO GSE12172"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-25265318", "type": "extraction", "used": ["source:pmid:25265318"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE12172", "type": "accession_resolution", "used": ["data:geo:GSE12172"], "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:25265318", "parent_hash": "sha256:ee264f5947a91e0e65bb5311d8eddcc6d357966d7dffc3bad84f21363c17bee0", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE12172 licence not read", "asset:data:geo:GSE12172 not downloaded", "asset:data:geo:PXD001084 licence not read", "asset:data:geo:PXD001084 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": ["oyed label-free liquid chromatography tandem mass spectrometry (LC-MSe) to identify proteins in these serum", "urther statistical and pathway analysis. The mass spectrometry proteomics data have been deposited to the P", "and pathway analysis. The mass spectrometry proteomics data have been deposited to the ProteomeXcha"], "order_basis": "paper_text_order:669", "id": "assay:1"}, {"role": "analysis", "definition_id": "clustering", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["hierarchical_cluster"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Hierarchical clustering"], "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":"2026-11-04T03:48:37+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}}}