{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29254951", "kind": "science-record", "revision": 6, "content_hash": "sha256:4fb0891ac5e205faa5f812f8ceac92d4681a3fa70f8163a72e9eb0762d8e9191", "created_at": "2026-11-01T15:40:30Z", "updated_at": "2026-11-01T21:21:11Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Landscape of nuclear transport receptor cargo specificity.", "doi": "10.15252/msb.20177608", "pmid": "29254951", "authors": ["Marie-Therese Mackmull", "Bernd Klaus", "Ivonne Heinze", "Manopriya Chokkalingam", "Andreas Beyer", "Robert B Russell", "Alessandro Ori", "Martin Beck"], "journal": "Molecular systems biology", "year": 2017, "abstract": "Nuclear transport receptors (NTRs) recognize localization signals of cargos to facilitate their passage across the central channel of nuclear pore complexes (NPCs). About 30 different NTRs constitute different transport pathways in humans and bind to a multitude of different cargos. The exact cargo spectrum of the majority of NTRs, their specificity and even the extent to which active nucleocytoplasmic transport contributes to protein localization remains understudied because of the transient nature of these interactions and the wide dynamic range of cargo concentrations. To systematically map cargo-NTR relationships in situ, we used proximity ligation coupled to mass spectrometry (BioID). We systematically fused the engineered biotin ligase BirA* to 16 NTRs. We estimate that a considerable fraction of the human proteome is subject to active nuclear transport. We quantified the specificity and redundancy in NTR interactions and identified transport pathways for cargos. We extended the BioID method by the direct identification of biotinylation sites. This approach enabled us to identify interaction interfaces and to discriminate direct versus piggyback transport mechanisms. Data are available via ProteomeXchange with identifier PXD007976.", "claims": [{"id": "claim-data-access", "statement": "The data set generated in this study is available in the following database:\n\nMass spectrometry proteomics data: PRIDE PXD007976 (https://www.ebi.ac.uk/pride/archive/projects/PXD007976) (Vizcaino et al, 2013).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29254951", "locator": "sections[22] \"Data availability\" paragraphs 1-3", "quote": "The data set generated in this study is available in the following database:\n\nMass spectrometry proteomics data: PRIDE PXD007976 (https://www.ebi.ac.uk/pride/archive/projects/PXD007976) (Vizcaino et al, 2013)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper used BioID coupled to mass spectrometry with a statistical framework for estimating interaction specificity and false discovery rates to map NTR–cargo relationships in situ, and deposited the source data in ProteomeXchange under PXD007976.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:29254951", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "To systematically map cargo–NTR relationships in situ, we used proximity ligation coupled to mass spectrometry (BioID)."}, {"asset": "source:pmid:29254951", "locator": "sections[1] \"Introduction\" paragraph 7", "quote": "We implemented novel approaches to estimate the specificity of interactions and false discovery rate (FDR) in BioID experiments."}, {"asset": "source:pmid:29254951", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Data are available via ProteomeXchange with identifier PXD007976."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The paper used BioID coupled to mass spectrometry with a statistical framework for estimating interaction specificity and false discovery rates to map NTR–cargo relationships in situ, and deposited the source data in ProteomeXchange under PXD007976.", "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:29254951"], "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:PXD007976"], "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:PXD007976"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29254951", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.15252/msb.20177608", "sha256": "sha256:cbf06513df61419501c7d4f76f64acfcd8d0e160a6dc5fc6800b59bff5136cf3", "bytes": 74366, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.15252/msb.20177608", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5740495", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD007976", "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=PXD007976", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD007976", "version": null, "note": "The data set generated in this study is available in the following database:\n\nMass spectrometry proteomics data: PRIDE PXD007976 (https://www.ebi.ac.uk/pride/archive/projects/PXD007976) (Vizcaino et al, 2013).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data set generated in this study is available in the following database:\n\nMass spectrometry proteomics data: PRIDE PXD007976 (https://www.ebi.ac.uk/pride/archive/projects/PXD007976) (Vizcaino et al, 2013).", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Landscape of nuclear transport receptor cargo specificity", "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:29254951:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0c96d6520fb99198dc02870e79e4e308d4e9e8e80271f805422fead8bf9bbdec", "bytes": 3877, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#msb177608-tbl-0001", "version": null, "note": "Overview of enriched protein complexes and identified biotinylated subunits", "structure": {"pmcid": "PMC5740495", "section_index": 9, "section_title": "Discussion", "row_count": 55, "column_count": 5}, "table": {"label": "Table 1", "caption": "Overview of enriched protein complexes and identified biotinylated subunits", "rows": [["NTR", "Enriched protein complexes and proteins of similar biological function", "Number of identified subunits (ES > 25)", "Biotinylated subunit"], ["NTR‐BirA*", "BirA*‐NTR"], ["IMA1", "Condensin ll complex", "5 (5)", "4 (0)", "SMC4, hCAP‐D3"], ["H/ACA ribonucleoprotein complex", "5 (5)", "3 (0)", "DKC1"], ["DNA replication complex GINS", "3 (3)", "1 (0)", "–"], ["Little elongation complex", "4 (4)", "4 (3)", "ELL, ICE1"], ["Integrator complex", "8 (6)", "7 (0)", "INTS4, INTS10"], ["Exosome complex", "11 (10)", "11 (0)", "EXOSC9, EXOSC10, RRP44"], ["DNA‐directed RNA polymerase l", "9 (9)", "7 (5)", "–"], ["DNA‐directed RNA polymerase lll", "15 (14)", "11 (7)", "RPC3"], ["Chromodomain‐helicase‐DNA‐binding protein", "6 (5)", "6 (1)", "CHD4, CHD7, CHD8"], ["DNA mismatch repair protein", "5 (5)", "5 (2)", "MLH1, MSH6"], ["Mediator of RNA polymerase II transcription", "19 (17)", "13 (3)", "MED1, MED27"], ["MORC family CW‐type zinc finger protein", "3 (3)", "3 (1)", "–"], ["Negative elongation factor", "4 (4)", "4 (1)", "NELF‐A, NELF‐E"], ["Transcription initiation factor TFIID", "13 (13)", "11 (11)", "TAF1, TAF3, TAF7"], ["U6 snRNA‐associated Sm‐like protein", "7 (7)", "6 (6)", "–"], ["Putative polycomb group protein ASXL", "3 (3)", "2 (0)", "–"], ["IMA5", "Condensin ll complex", "4 (1)", "2 (0)", "SMC4"], ["H/ACA ribonucleoprotein complex", "5 (5)", "5 (4)", "DKC1"], ["Little elongation complex", "4 (3)", "4 (2)", "ELL"], ["Integrator complex", "9 (8)", "8 (5)", "INTS4, INTS10, INTS11"], ["Exosome complex", "10 (6)", "11 (1)", "EXOSC9, EXOSC10, RRP44"], ["DNA‐directed RNA polymerase l", "9 (7)", "7 (5)", "RPAC2"], ["DNA‐directed RNA polymerase lll", "13 (9)", "10 (5)", "RPAC2, RPC3"], ["Chromodomain‐helicase‐DNA‐binding protein", "6 (5)", "5 (2)", "CHDL1, CHD3, CHD7, CHD8"], ["DNA mismatch repair protein", "4 (3)", "5 (1)", "MLH1, MSH6"], ["IMA6", "H/ACA ribonucleoprotein complex", "5 (4)", "–", "DKC1"], ["Little elongation complex", "4 (3)", "–", "ICE1"], ["IPO4", "Anaphase‐promoting complex", "9 (3)", "9 (4)", "APC3"], ["AP2 adaptor complex", "5 (3)", "4 (1)", "–"], ["HAUS augmin‐like complex", "8 (8)", "8 (7)", "HAUS2*"], ["Eukaryotic translation initiation factor 3", "13 (9)", "13 (11)", "Subunit D, E, G, J"], ["Activating signal cointegrator (ASC‐1)", "4 (4)", "4 (4)", "TRIP4, ASCC1"], ["Histone chaperone ASF1", "2 (2)", "2 (2)", "–"], ["Transforming acidic coiled‐coil‐containing protein", "3 (3)", "3 (3)", "TACC1, TACC3"], ["IPO5", "Anaphase‐promoting complex", "8 (0)", "9 (9)", "–"], ["AP2 adaptor complex", "5 (0)", "4 (4)", "–"], ["HAUS augmin‐like complex", "8 (2)", "8 (7)", "–"], ["Eukaryotic translation initiation factor 3", "12 (6)", "13 (13)", "Subunit A, D, E, G, J"], ["WASH complex", "4 (2)", "4 (4)", "–"], ["IPO11", "Basic leucine zipper and W2 domain‐containing protein", "2 (2)", "–", "BZW1, BZW2"], ["IPO13", "Special AT‐rich sequence‐binding protein", "–", "2 (2)", "SATB1"], ["TNPO1", "Argonaute protein family", "–", "2 (2)", "–"], ["Nuclear receptor coactivator", "", "6 (5)", "SRC2*"], ["TNPO2", "Argonaute protein family", "3 (3)", "3 (3)", "–"], ["Nuclear receptor coactivator", "6 (6)", "6 (6)", "–"], ["CREB‐regulated transcription coactivator and binding protein", "4 (4)", "4 (4)", "CRTC1, CRTC2, CRTC3"], ["Far upstream element‐binding protein", "3 (2)", "3 (3)", "FUBP1, FUBP2, FUBP3"], ["CCAAT‐box‐binding transcription factor (CTF)", "3 (3)", "3 (2)", "–"], ["XPO1", "Little elongation complex", "4 (4)", "–", "–"], ["Exosome complex", "10 (2)", "", "EXOSC10"], ["XPO2", "DNA replication complex GINS", "3 (3)", "2 (1)", "–"], ["Heterogeneous nuclear ribonucleoprotein", "11 (0)", "21 (17)", "Protein A1, F, M, U, UL1"], ["XPO7", "COP9 signalosome", "–", "9 (9)", "CSN4"]], "row_count": 55, "column_count": 5, "numeric_cells": 109, "header_rows": 2, "locator": "section[9]/table-wrap[1]#msb177608-tbl-0001"}}], "gaps": ["asset:data:geo:PXD007976 not downloaded", "asset:data:geo:PXD007976 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Pearson correlation"}}, {"id": "method-2", "family": null, "specific": null, "label": "Target-decoy strategy", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "“Peptide and protein hits were filtered at a false discovery rate of 1% using a target‐decoy strategy (Elias & Gygi, 2007).”"}}], "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": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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": ["PXD007976"], "resolved_accessions": ["PXD007976"], "statements": ["The data set generated in this study is available in the following database:\n\nMass spectrometry proteomics data: PRIDE PXD007976 (https://www.ebi.ac.uk/pride/archive/projects/PXD007976) (Vizcaino et al, 2013)."], "basis": "The paper names PXD007976 in PRIDE and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pearson_r"], "assets": ["source:pmid:29254951", "data:geo:PXD007976", "asset:table:pmid:29254951:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD007976"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:33:04Z", "independence": "same_provider"}, "evidence_check": {"method": "reordered", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 141881, "completion_tokens": 3328, "cached_tokens": 36384}}, "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:29254951", "type": "paper", "label": "pmid:29254951"}, {"id": "source:pmid:29254951", "type": "manuscript", "label": "PMID 29254951 full text"}, {"id": "data:geo:PXD007976", "type": "dataset", "label": "GEO PXD007976"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29254951", "type": "paper", "label": "pmid:29254951"}, {"id": "source:pmid:29254951", "type": "manuscript", "label": "PMID 29254951 full text"}, {"id": "data:geo:PXD007976", "type": "dataset", "label": "GEO PXD007976"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29254951", "type": "extraction", "used": ["source:pmid:29254951"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD007976", "type": "accession_resolution", "used": ["data:geo:PXD007976"], "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:29254951", "parent_hash": "sha256:12d721c58e782dac7cb75a879f3d12d6632d2e1040a6c1362414df1cd048bbba", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD007976 licence not read", "asset:data:geo:PXD007976 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": ["situ, we used proximity ligation coupled to mass spectrometry (BioID). We systematically fused the enginee", "asm, but non‐straight forward to identify by mass spectrometry. We tagged NTRs with the engineered biotin l", "ic peptides from on‐bead digestion by tandem mass spectrometry in technical duplicates and used label‐free", "NTF2, NXT1, and NXT2 (Table EV1). Due to the proteomic nature of our methodology, we decided to pri"], "order_basis": "paper_text_order:687", "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": ["vated fetal bovine serum (FBS). The parental cell line was grown with the addition of 100 μg/ml Zeocin (Invit", "n proteins in stable human embryonic kidney (HEK293) cell lines for 24 h (Fig 2A). In agreement"], "order_basis": "paper_text_order:2388", "id": "assay:2"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Pearson correlation"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T01:48:53+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}}}