{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:25977788", "kind": "science-record", "revision": 6, "content_hash": "sha256:cb3d6d9a37ce1d26a239fccdcda3ccf21938938b9364d2ec2b8ed6af6a3e3e3b", "created_at": "2026-11-01T15:40:08Z", "updated_at": "2026-11-01T21:20:00Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A repository of assays to quantify 10,000 human proteins by SWATH-MS.", "doi": "10.1038/sdata.2014.31", "pmid": "25977788", "authors": ["George Rosenberger", "Ching Chiek Koh", "Tiannan Guo", "Hannes L Röst", "Petri Kouvonen", "Ben C Collins", "Moritz Heusel", "Yansheng Liu", "Etienne Caron", "Anton Vichalkovski", "Marco Faini", "Olga T Schubert", "Pouya Faridi", "H Alexander Ebhardt", "Mariette Matondo", "Henry Lam", "Samuel L Bader", "David S Campbell", "Eric W Deutsch", "Robert L Moritz", "Stephen Tate", "Ruedi Aebersold"], "journal": "Scientific data", "year": 2014, "abstract": "Mass spectrometry is the method of choice for deep and reliable exploration of the (human) proteome. Targeted mass spectrometry reliably detects and quantifies pre-determined sets of proteins in a complex biological matrix and is used in studies that rely on the quantitatively accurate and reproducible measurement of proteins across multiple samples. It requires the one-time, a priori generation of a specific measurement assay for each targeted protein. SWATH-MS is a mass spectrometric method that combines data-independent acquisition (DIA) and targeted data analysis and vastly extends the throughput of proteins that can be targeted in a sample compared to selected reaction monitoring (SRM). Here we present a compendium of highly specific assays covering more than 10,000 human proteins and enabling their targeted analysis in SWATH-MS datasets acquired from research or clinical specimens. This resource supports the confident detection and quantification of 50.9% of all human proteins annotated by UniProtKB/Swiss-Prot and is therefore expected to find wide application in basic and clinical research. Data are available via ProteomeXchange (PXD000953-954) and SWATHAtlas (SAL00016-35).", "claims": [{"id": "claim-method", "statement": "False discovery rate (FDR) control was conducted using MAYU.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:25977788", "locator": "sections[3] \"Sample overview\" paragraph 4", "quote": "False discovery rate (FDR) control was conducted using MAYU."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Data are available via ProteomeXchange (PXD000953-954) and SWATHAtlas (SAL00016-35).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:25977788", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange (PXD000953-954) and SWATHAtlas (SAL00016-35)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Using MAYU-based statistical filtering, the study produced a combined human SWATH-MS assay library for more than 10,000 proteins, covering 50.9% of UniProtKB/Swiss-Prot proteins; the source data are available through ProteomeXchange (PXD000953–954) and SWATHAtlas (SAL00016–35).", "kind": "quantitative", "target": {"value": 50.9, "unit": "per cent", "tolerance": null, "source": "This resource supports the confident detection and quantification of 50.9% of all human proteins annotated by UniProtKB/Swiss-Prot and is therefore expected to find wide application in basic and clinical research."}, "evidence": [{"asset": "source:pmid:25977788", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Here we present a compendium of highly specific assays covering more than 10,000 human proteins and enabling their targeted analysis in SWATH-MS datasets acquired from research or clinical specimens."}, {"asset": "source:pmid:25977788", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "This resource supports the confident detection and quantification of 50.9% of all human proteins annotated by UniProtKB/Swiss-Prot and is therefore expected to find wide application in basic and clinical research."}, {"asset": "source:pmid:25977788", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange (PXD000953-954) and SWATHAtlas (SAL00016-35)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Using MAYU-based statistical filtering, the study produced a combined human SWATH-MS assay library for more than 10,000 proteins, covering 50.9% of UniProtKB/Swiss-Prot proteins; the source data are available through ProteomeXchange (PXD000953–954) and SWATHAtlas (SAL00016–35).", "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:25977788"], "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:PXD000953"], "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:PXD000953"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:25977788", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/sdata.2014.31", "sha256": "sha256:47d1b46544e8b229b2636e8d2822cd95f0be6a9926ae6b9f582ccf0736f14d5b", "bytes": 62793, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/sdata.2014.31", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4322573", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD000953", "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=PXD000953", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD000953", "version": null, "note": "Data are available via ProteomeXchange (PXD000953-954) and SWATHAtlas (SAL00016-35).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange (PXD000953-954) and SWATHAtlas (SAL00016-35).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "The Pan-Human Library: A repository of assays to quantify 10 000 proteins by SWATH-MS", "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:PXD000954", "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=PXD000954", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD000954", "version": null, "note": "Data are available via ProteomeXchange (PXD000953-954) and SWATHAtlas (SAL00016-35).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Data are available via ProteomeXchange (PXD000953-954) and SWATHAtlas (SAL00016-35).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "The Pan-Human Library: A repository of assays to quantify 10 000 proteins by SWATH-MS / SWATH-MS validation data", "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:25977788:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8a61ebc7326303b3e60a4cc82ce1f21285f6a3091f0447e0fce674d052194a67", "bytes": 1571, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#t1", "version": null, "note": "Overview of the contents of the combined assay library.", "structure": {"pmcid": "PMC4322573", "section_index": 3, "section_title": "Sample overview", "row_count": 27, "column_count": 5}, "table": {"label": "Table 1", "caption": "Overview of the contents of the combined assay library.", "rows": [["Sample type", "Protein fractionation", "Proteolytic digestion", "Peptide fractionation", "MS injections"], ["CL refers to cell line and T refers to tissue, indicating the source of the specimen. The full sample annotation is provided in Supplementary Table 1.", "", "", "", ""], ["HEK293 (CL)", "AP (Kinases)", "Trypsin", "None", "12"], ["HEK293 (CL)", "AP (14-3-3)", "Trypsin", "None", "29"], ["HEK293 (CL)", "SEC", "Trypsin", "None", "81"], ["HEK293 (CL)", "None", "Trypsin", "OGE", "11"], ["HEK293 (CL)", "None", "Trypsin", "None", "1"], ["U2OS (CL)", "None", "PCT", "None", "13"], ["HeLa (CL)", "None", "PCT", "None", "9"], ["U2OS and HeLa (CL)", "None", "Trypsin", "OGE", "24"], ["NCI60 (CL)", "None", "PCT", "None", "13"], ["NCI60 (CL)", "None", "Trypsin", "OGE", "24"], ["CAL51 (CL)", "None", "Trypsin", "None", "5"], ["CAL51 (CL)", "None", "Trypsin", "1D GE", "2"], ["THP1 (CL)", "None", "Trypsin", "OGE", "27"], ["LNCaP (CL)", "None", "Trypsin", "SAX", "6"], ["LNCaP (CL)", "None", "Trypsin", "None", "1"], ["Kidney (T)", "None", "Trypsin", "1D GE", "15"], ["Kidney (T)", "None", "PCT", "None", "16"], ["Large intestine (T)", "None", "Trypsin", "OGE", "24"], ["Muscle (T)", "None", "PCT", "None", "3"], ["Lung (T)", "None", "PCT", "None", "2"], ["Blood plasma (T)", "None", "Trypsin", "SAX", "8"], ["Monocytes (T)", "None", "Trypsin", "None", "1"], ["Neutrophils (T)", "None", "Trypsin", "None", "1"], ["Purified platelets (T)", "None", "Trypsin", "None", "3"], ["Total", "331", "", "", ""]], "row_count": 27, "column_count": 5, "numeric_cells": 38, "header_rows": 1, "locator": "section[3]/table-wrap[1]#t1"}}, {"id": "asset:table:pmid:25977788:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:48f0c46537a5d0352435976ac178ba3536618848a484c1fd93b7debf04bb1a9b", "bytes": 631, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[28]/table-wrap[1]#t2", "version": null, "note": "Assay statistics of the combined assay library.", "structure": {"pmcid": "PMC4322573", "section_index": 28, "section_title": "Relation to present state of proteome discovery", "row_count": 6, "column_count": 3}, "table": {"label": "Table 2", "caption": "Assay statistics of the combined assay library.", "rows": [["", "Proteotypic", "Proteotypic+Shared"], ["The number of proteins, peptides, precursors and transitions, filtered at protein FDR 1% is depicted. The combined assay library is provided with all target and decoy assays, but only proteotypic assays were considered for all downstream analysis.", "", ""], ["Proteins", "10,316", "11,588"], ["Peptides", "139,449", "146,576"], ["Precursors", "194,052", "204,545"], ["Transitions", "1,164,312", "1,227,270"]], "row_count": 6, "column_count": 3, "numeric_cells": 9, "header_rows": 1, "locator": "section[28]/table-wrap[1]#t2"}}, {"id": "asset:table:pmid:25977788:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:72cccbc69088f279bba68b9d13b5185a5d12a1330995173153869da624149fad", "bytes": 1331, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[29]/table-wrap[1]#t3", "version": null, "note": "Identification statistics of the combined and sample-specific assay libraries.", "structure": {"pmcid": "PMC4322573", "section_index": 29, "section_title": "Applicability of the combined assay library for SWATH-MS targeted data analysis", "row_count": 9, "column_count": 9}, "table": {"label": "Table 3", "caption": "Identification statistics of the combined and sample-specific assay libraries.", "rows": [["Protein FDR", "CAL HeLa", "", "ss HeLa", "CAL U2OS", "ss U2OS"], ["", "prot", "pep", "prot", "pep", "prot", "pep", "prot", "pep"], ["The number of identified proteotypic peptides and proteins in SWATH-MS datasets of whole cell lysates of HeLa and U2OS cell lines at commonly used protein FDR cutoffs using combined (CAL) and sample-specific (ss) assay libraries is reported. Protein FDR cutoffs are either reported for all identifications or non-single hits (NS). The true positive protein (prot) and peptide (pep) identifications for the combined assay library and sample-specific assay libraries are reported as estimated by MAYU.", "", "", "", "", "", "", "", ""], ["1%", "2,417", "14,930", "2,353", "14,635", "2,617", "15,608", "2,452", "14,360"], ["2%", "2,730", "17,294", "2,467", "15,416", "2,989", "18,321", "2,541", "14,982"], ["5%", "3,246", "21,128", "2,514", "15,672", "3,486", "21,893", "2,552", "15,003"], ["NS 1%", "2,608", "23,075", "1,750", "14,999", "2,803", "24,009", "1,763", "14,599"], ["NS 2%", "2,804", "25,005", "1,798", "15,537", "2,965", "25,497", "1,815", "15,002"], ["NS 5%", "3,111", "28,002", "1,820", "15,668", "3,241", "28,442", "1,819", "14,999"]], "row_count": 9, "column_count": 9, "numeric_cells": 54, "header_rows": 2, "locator": "section[29]/table-wrap[1]#t3"}}], "gaps": ["asset:data:geo:PXD000953 not downloaded", "asset:data:geo:PXD000953 licence not read", "asset:data:geo:PXD000954 not downloaded", "asset:data:geo:PXD000954 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "MAYU", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "False discovery rate (FDR) control was conducted using MAYU."}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": null, "expected_value": 50.9, "unit": "per cent", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "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 (MAYU), 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": ["PXD000953", "PXD000954"], "resolved_accessions": ["PXD000953", "PXD000954"], "statements": ["Data are available via ProteomeXchange (PXD000953-954) and SWATHAtlas (SAL00016-35)."], "basis": "The paper names PXD000953, PXD000954 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:25977788", "data:geo:PXD000953", "asset:table:pmid:25977788:1", "asset:table:pmid:25977788:2", "asset:table:pmid:25977788:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD000953"]}, "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": "2026-10-31T18:23:58Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 123772, "completion_tokens": 5054, "cached_tokens": 1824}}, "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:25977788", "type": "paper", "label": "pmid:25977788"}, {"id": "source:pmid:25977788", "type": "manuscript", "label": "PMID 25977788 full text"}, {"id": "data:geo:PXD000953", "type": "dataset", "label": "GEO PXD000953"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:25977788", "type": "paper", "label": "pmid:25977788"}, {"id": "source:pmid:25977788", "type": "manuscript", "label": "PMID 25977788 full text"}, {"id": "data:geo:PXD000953", "type": "dataset", "label": "GEO PXD000953"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-25977788", "type": "extraction", "used": ["source:pmid:25977788"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD000953", "type": "accession_resolution", "used": ["data:geo:PXD000953"], "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:25977788", "parent_hash": "sha256:b61dcc6d9490c21ca603980d17ca421a4d65d39be73909a87f6a4c3ae280f2bf", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD000953 licence not read", "asset:data:geo:PXD000953 not downloaded", "asset:data:geo:PXD000954 licence not read", "asset:data:geo:PXD000954 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": ["Mass spectrometry is the method of choice for deep and reliabl", "xploration of the (human) proteome. Targeted mass spectrometry reliably detects and quantifies pre-determin", "say for each targeted protein. SWATH-MS is a mass spectrometric method that combines data-independent acquis", "g PCT), (optional) peptide fractionation and LC-MS/MS analysis in discovery proteomics mode. (b) D"], "order_basis": "paper_text_order:70", "id": "assay:1"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ng and protein-level separation Cell culture HEK293 cell samples were essentially generated as d", "essentially generated as described before30. HeLa and U2OS cells were obtained from ATCC and g", "ly generated as described before30. HeLa and U2OS cells were obtained from ATCC and grown in D", "uded SEC and OGE fractionated samples from a HEK293 cell line, SAX fractionated samples from pla"], "order_basis": "paper_text_order:2721", "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":"2026-11-04T01:49:01+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}}}