{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:27833854", "kind": "science-record", "revision": 6, "content_hash": "sha256:53de9ed31690fbd524c8f552ec173a45bce0b7c8882eea711941755759f99ea0", "created_at": "2026-11-01T15:40:21Z", "updated_at": "2026-11-01T21:20:43Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Human promyelocytic leukemia protein is targeted to distinct subnuclear domains in plant nuclei and colocalizes with nucleolar constituents in a SUMO-dependent manner.", "doi": "10.1002/2211-5463.12134", "pmid": "27833854", "authors": ["Christian E Lamm", "Myriam Scherer", "Nina Reuter", "Bushra Amin", "Thomas Stamminger", "Uwe Sonnewald"], "journal": "FEBS open bio", "year": 2016, "abstract": "Eukaryotic nuclei are subdivided into subnuclear structures. Among the most prominent of these structures are the nucleolus and the PML nuclear bodies (PML-NBs). PML-NBs are spherical multiprotein aggregates of varying size localized in the interchromosomal area. PML-NB formation is dependent on the presence of the promyelocytic leukemia protein (PML) as well as on post-translational modification of core components by covalent attachment of the small ubiquitin-like modifier (SUMO). So far, PML-NBs as well as PML have been described in mammalian cells only, whereas no orthologs are known in the plant kingdom. In order to investigate conserved mechanisms in PML targeting, we expressed human PML (hPML) fused to the GFP in Nicotiana benthamiana. Using confocal laser scanning microscopy and coimmunoprecipitation followed by mass spectrometric analysis, we found the fusion protein in association with nucleolar constituents. Importantly, mutants of hPML, which are no longer SUMOylated, showed altered localizations, implying SUMO-dependent targeting of hPML in plants as has previously been shown for mammalian cells. Interestingly, in the presence of proteasome inhibitors, hPML could also be found in the nucleolus of mammalian cells suggesting conserved targeting mechanisms of PML across kingdoms. Finally, Solanum tuberosum COP1, a proposed PML-like protein from plants, was fused to the red fluorescent protein (RFP) and coexpressed with hPML::eGFP. Microscopic analysis confirmed the localization of COP1::RFP in nuclear speckles. However, hPML::eGFP did not colocalize with COP1::RFP. Hence, we conclude that plants do not possess specialized PML-NBs, but that their functions may be covered by other subnuclear structures like the nucleolus. Database Proteomics data have been deposited to the ProteomeXchange Consortium with the identifier PXD004254.", "claims": [{"id": "claim-method", "statement": "Statistical analysis of colocalization was carried out using Pearson's correlation coefficient as calculated by the las af software (Leica Microsystems) for Z‐stack micrographs covering the whole nucleus.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27833854", "locator": "sections[14] \"Transient expression in primary human fibroblast, N. benthamiana, and confocal laser scanning microscopy\" paragraph 2", "quote": "Statistical analysis of colocalization was carried out using Pearson's correlation coefficient as calculated by the las af software (Leica Microsystems) for Z‐stack micrographs covering the whole nucleus."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository 65 with the dataset identifier PXD004254.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:27833854", "locator": "sections[18] \"Nano‐LC‐MS/MS analysis\" paragraph 2", "quote": "All mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository 65 with the dataset identifier PXD004254."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:27833854"], "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:PXD004254"], "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:PXD004254"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:27833854", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1002/2211-5463.12134", "sha256": "sha256:cd914c48883e38f302c9eaf3bac3d24da478603b1c1d55974c6845c4357db165", "bytes": 50542, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1002/2211-5463.12134", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5095151", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD004254", "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=PXD004254", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD004254", "version": null, "note": "All mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository 65 with the dataset identifier PXD004254.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository 65 with the dataset identifier PXD004254.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "Identification of potential human PML interacting proteins in Nicotiana benthamiana", "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:27833854:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3d02b3532b182107d9ca9596f33147212652f183d4b1545298233a752716dafe", "bytes": 4041, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#feb412134-tbl-0001", "version": null, "note": "Nuclear Nicotiana benthamiana proteins identified as potential PML interactors via immunoprecipitation. Description and Accession number adopted from the N. benthamiana protein database, Best BLAST hit in Arabidopsis shows the respective locus identifier, Associated human PML interactor indicates proteins that interact with PML in mammalian cells as stated in the respective References", "structure": {"pmcid": "PMC5095151", "section_index": 6, "section_title": "Human PML is targeted to interchromosomal subnuclear domains and interacts with nuclear and nucleolar proteins in planta", "row_count": 30, "column_count": 6}, "table": {"label": "Table 1", "caption": "Nuclear Nicotiana benthamiana proteins identified as potential PML interactors via immunoprecipitation. Description and Accession number adopted from the N. benthamiana protein database, Best BLAST hit in Arabidopsis shows the respective locus identifier, Associated human PML interactor indicates proteins that interact with PML in mammalian cells as stated in the respective References", "rows": [["Description", "Accession Number N. benthamiana database", "Best BLAST hit Arabidopsis", "Annotated localization", "Associated human PML interactor", "Reference"], ["Nuclear pore complex protein NUP85", "Niben101Scf01611g04026.1", "AT4G32910", "Nuclear Pore Complex", "", ""], ["ATP‐dependent RNA helicase", "Niben101Scf06884 g00001.1", "AT5G62190", "Nucleolus", "", ""], ["Holliday junction ATP‐dependent DNA helicase RuvB", "Niben101Scf01281 g02006.1", "AT5G67630", "Nucleolus", "", ""], ["Importin subunit alpha", "Niben101Scf03390 g08002.1", "AT3G06720", "Nucleolus", "", ""], ["Nucleolar protein 16", "Niben101Scf04623 g02007.1", "AT1G02870", "Nucleolus", "", ""], ["Replication factor C subunit 3", "Niben101Scf01888 g07004.1", "AT1G21690", "Nucleolus", "Replication factor C4", "McNamara et al. 33"], ["Replication factor C subunit 3", "Niben101Scf02197 g01014.1", "AT1G77470", "Nucleolus", "Replication factor C4", "McNamara et al. 33"], ["Ribosomal RNA large subunit methyltransferase", "Niben101Scf23821 g00012.1", "AT3G28460", "Nucleolus", "", ""], ["RNA‐binding protein like", "Niben101Scf15360 g00006.1", "AT4G32720", "Nucleolus", "", ""], ["2‐oxoglutarate (2OG) and Fe(II)‐dependent oxygenase superfamily protein", "Niben101Scf06267 g03010.1", "AT2G17970", "Nucleus", "", ""], ["65‐kDa microtubule‐associated protein 6", "Niben101Scf07839 g00002.1", "AT2G01910", "Nucleus", "Microtubule‐associated protein 1 light chain 3 beta", "He et al. 40"], ["ATP‐dependent RNA helicase", "Niben101Scf05387 g09003.1", "AT3G06980", "Nucleus", "", ""], ["DNA‐directed RNA polymerase subunit D", "Niben101Scf00414 g09001.1", "AT1G60620", "Nucleus", "DNA‐directed RNA polymerase POLR2E", "Ravasi et al. 35"], ["FRIGIDA‐like protein 3", "Niben101Scf04181 g00024.1", "AT5G48385", "Nucleus", "", ""], ["Heavy metal transport/detoxification superfamily protein", "Niben101Scf07109 g05004.1", "AT4G35060", "Nucleus", "", ""], ["Histone‐lysine N‐methyltransferase", "Niben101Scf01020 g00014.1", "AT5G04940", "Nucleus", "Histone‐lysine N‐methyltransferase G9a", "Lusic et al. 34"], ["Histone‐lysine N‐methyltransferase 2A", "Niben101Scf12382 g00017.1", "AT1G73100", "Nucleus", "Histone‐lysine N‐methyltransferase G9a", "Lusic et al., 34"], ["Holliday junction ATP‐dependent DNA helicase RuvB", "Niben101Scf04267 g00016.1", "AT5G27740", "Nucleus", "Replication factor C4", "McNamara et al. 33"], ["Nuclear cap‐binding protein subunit 1", "Niben101Scf07629 g00001.1", "AT2G13540", "Nucleus", "", ""], ["Plastid transcriptionally active 12", "Niben101Scf08698 g02020.1", "AT2G34640", "Nucleus", "", ""], ["Protein IQ‐DOMAIN 31", "Niben101Scf06172 g01003.1", "AT1G74690", "Nucleus", "", ""], ["Protein IQ‐DOMAIN 31", "Niben101Scf01326 g08021.1", "AT1G74690", "Nucleus", "", ""], ["Replication factor C subunit 3", "Niben101Scf07391 g04027.1", "AT1G63160", "Nucleus", "Replication factor C4", "McNamara et al. 33"], ["Replication factor C subunit 4", "Niben101Scf01382 g04008.1", "AT5G22010", "Nucleus", "Replication factor C4", "McNamara et al. 33"], ["Replication factor C subunit 5", "Niben101Scf05056 g02015.1", "AT1G63160", "Nucleus", "Replication factor C4", "McNamara et al. 33"], ["RNA‐binding KH domain‐containing protein", "Niben101Scf03015 g05008.1", "AT5G15270", "Nucleus", "", ""], ["RNA‐binding protein 1", "Niben101Scf06105 g03006.1", "AT4G10110", "Nucleus", "", ""], ["snRK1‐interacting protein 1", "Niben101Scf03949 g06008.1", "AT1G71310", "Nucleus", "RAD51", "Boichuk et al. 38"], ["WD‐40 repeat family protein/small nuclear ribonucleoprotein", "Niben101Scf11084 g02025.1", "AT2G41500", "Nucleus", "", ""]], "row_count": 30, "column_count": 6, "numeric_cells": 89, "header_rows": 1, "locator": "section[6]/table-wrap[1]#feb412134-tbl-0001"}}], "gaps": ["asset:data:geo:PXD004254 not downloaded", "asset:data:geo:PXD004254 licence not read"]}, "analysis": {"state": "complete", "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": 1.0, "band": "verbatim", "quote": "Statistical analysis of colocalization was carried out using Pearson's correlation coefficient as calculated by the las af software (Leica Microsystems) for Z‐stack micrographs covering the whole nucleus."}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["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": ["PXD004254"], "resolved_accessions": ["PXD004254"], "statements": ["All mass spectrometry proteomics data have been deposited to the ProteomeXchange Consortium (http://proteomecentral.proteomexchange.org) via the PRIDE partner repository 65 with the dataset identifier PXD004254."], "basis": "The paper names PXD004254 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": ["pearson_r"], "assets": ["source:pmid:27833854", "data:geo:PXD004254", "asset:table:pmid:27833854:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD004254"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": null, "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 0, "usage": {}}, "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:27833854", "type": "paper", "label": "pmid:27833854"}, {"id": "source:pmid:27833854", "type": "manuscript", "label": "PMID 27833854 full text"}, {"id": "data:geo:PXD004254", "type": "dataset", "label": "GEO PXD004254"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:27833854", "type": "paper", "label": "pmid:27833854"}, {"id": "source:pmid:27833854", "type": "manuscript", "label": "PMID 27833854 full text"}, {"id": "data:geo:PXD004254", "type": "dataset", "label": "GEO PXD004254"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-27833854", "type": "extraction", "used": ["source:pmid:27833854"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD004254", "type": "accession_resolution", "used": ["data:geo:PXD004254"], "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:27833854", "parent_hash": "sha256:731c38c8a891208a9571b0d555eb7a14ea0dd11d9d9752418575b61493cb38f6", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD004254 licence not read", "asset:data:geo:PXD004254 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "mass_spectrometry", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["oscopy and coimmunoprecipitation followed by mass spectrometric analysis, we found the fusion protein in ass", "lear structures like the nucleolus. Database Proteomics data have been deposited to the ProteomeXcha"], "order_basis": "paper_text_order:954", "id": "assay:1"}, {"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": 1.0, "evidence": ["Statistical analysis of colocalization was carried out using Pearson's correlation coefficient as calculated by the las af software (Leica Microsystems) for Z‐stack micrographs covering the whole nucleus."], "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":"2026-11-04T03:50:34+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}}}