{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29904688", "kind": "science-record", "revision": 6, "content_hash": "sha256:0c33b7036d1e9585a46f1d2241895f9cd113f38e9f85b6de8e64ed34c8091043", "created_at": "2026-11-01T15:40:34Z", "updated_at": "2026-11-01T21:21:29Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Data on mass spectrometry-based proteomics for studying the involvement of CYLD in the ubiquitination events downstream of EGFR activation.", "doi": "10.1016/j.dib.2018.04.049", "pmid": "29904688", "authors": ["Virginia Sanchez-Quiles", "Nerea Osinalde", "Vyacheslav Akimov", "Irina Kratchmarova", "Blagoy Blagoev"], "journal": "Data in brief", "year": 2018, "abstract": "The present data article corresponds to the proteomic data of the involvement of Cylindromatosis protein (CYLD) in the ubiquitination signaling initiated by EGF stimulation. CYLD tumor suppressor protein has Lys63-chain deubiquitinase activity that has been proved essential for the negative regulation of crucial signaling mechanisms, namely the NFkB pathway. Previous results have suggested the involvement of CYLD in the EGF-dependent signal transduction as well, showing its engagement within the tyrosine-phosphorylated complexes formed following the addition of the growth factor. EGFR signaling participates in central cellular processes and its tight regulation, partly through ubiquitination cascades, is decisive for a balanced cellular homeostasis. We carried out the substitution of the endogenous pool of ubiquitin for a His-FLAG-tagged ubiquitin (Stable Ubiquitin Exchange, StUbEx), in combination with the shRNA silencing of CYLD and SILAC-labeling on HeLa cells. The subsequent tandem affinity purification of ubiquitinated proteins in control and CYLD-depleted cells was followed by mass spectrometric analysis. Therefore, we present an unbiased study investigating the impact of CYLD in the EGF-dependent ubiquitination. The data supplied herein is related to the research article entitled \"Cylindromatosis tumor suppressor protein (CYLD) deubiquitinase is necessary for proper ubiquitination and degradation of the epidermal growth factor receptor\" (Sanchez-Quiles et al., 2017) [1]. We provide the associated mass spectrometry raw files, excel tables and gene ontology enrichments. The data have been deposited in the ProteomeXchange with the identifier PXD003423.", "claims": [{"id": "claim-method", "statement": "The calculation of significantly changed proteins was performed using the Perseus software [11].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29904688", "locator": "sections[10] \"Data analysis\" paragraph 2", "quote": "The calculation of significantly changed proteins was performed using the Perseus software [11]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All the data presented in this article are deposited in the ProteomeXchange consortium via de identifier PXD003423 (http://www.proteomexchange.org/). The list of the identified and quantified proteins obtained in the two replicas of the study are provided in the supplementary material of this article.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29904688", "locator": "sections[1] \"p\" paragraph 1", "quote": "All the data presented in this article are deposited in the ProteomeXchange consortium via de identifier PXD003423 (http://www.proteomexchange.org/). The list of the identified and quantified proteins obtained in the two replicas of the study are provided in the supplementary material of this article."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper reports that “the deubiquitinase CYLD is necessary for the correct ubiquitination of the activated receptor in a counterintuitive manner.”", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:29904688", "locator": "sections[2] \"p\" paragraph 1", "quote": "The workflow described herein resulted in the discovery of an unexpected role of CYLD in the signaling events downstream EGF stimulation, namely that the deubiquitinase CYLD is necessary for the correct ubiquitination of the activated receptor in a counterintuitive manner."}, {"asset": "source:pmid:29904688", "locator": "sections[10] \"Data analysis\" paragraph 2", "quote": "The calculation of significantly changed proteins was performed using the Perseus software [11]."}, {"asset": "source:pmid:29904688", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We provide the associated mass spectrometry raw files, excel tables and gene ontology enrichments. The data have been deposited in the ProteomeXchange with the identifier PXD003423."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The paper reports that “the deubiquitinase CYLD is necessary for the correct ubiquitination of the activated receptor in a counterintuitive manner.”", "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:29904688"], "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:PXD003423"], "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:PXD003423"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29904688", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.dib.2018.04.049", "sha256": "sha256:eee9e44f99567dd56fbe9b5cf453b27ce422052fa56f5565bb6e79cd9a73c25e", "bytes": 15484, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.dib.2018.04.049", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5997975", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:PXD003423", "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=PXD003423", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "PXD003423", "version": null, "note": "All the data presented in this article are deposited in the ProteomeXchange consortium via de identifier PXD003423 (http://www.proteomexchange.org/). The list of the identified and quantified proteins obtained in the two replicas of the study are provided in the supplementary material of this article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All the data presented in this article are deposited in the ProteomeXchange consortium via de identifier PXD003423 (http://www.proteomexchange.org/). The list of the identified and quantified proteins obtained in the two replicas of the study are provided in the supplementary material of this article.", "access_statement_kind": "data_availability_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": "EGF-dependent ubiquitinome, phosphorylation and interactome analysis in control and CYLD-deficient cells", "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:29904688:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:808ea76ec598e80dc3c9a00e89ab62915fb43fad47c0d13d377b4661dba689dd", "bytes": 1657, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0005", "version": null, "note": null, "structure": {"pmcid": "PMC5997975", "section_index": 1, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Cell signaling and ubiquitination"], ["More specific subject area", "EGFR Signaling and ubiquitinome"], ["Type of data", "Mass spectrometry (MS) data"], ["How data was acquired", "MS data was acquired on a Q-Exactive mass spectrometer (Thermo Scientific)."], ["Data format", "Raw and excel files"], ["Experimental factors", "Substitution of endogenous ubiquitin for a doubly-tagged version of ubiquitin in HeLa cells, combined with silencing of CYLD using shRNA and SILAC labeling of different conditions. shControl or shCYLD cells were either left starved or stimulated with EGF for 6 min."], ["Experimental features", "After the corresponding stimulation of shControl or shCYLD cells, protein extracts from two paralleled SILAC experiments were pooled accordingly and ubiquitinated proteins were enriched using a two steps procedure. An enrichment using Ni-NTA beads was performed, followed by immunoprecipitation of proteins using anti-FLAG specific antibodies. Enriched proteins were subjected to in-solution digestion and the resulting peptides were fractionated prior their LC–MS/MS analysis."], ["Data source location", "University of Southern Denmark, Odense, Denmark"], ["Data accessibility", "All the data presented in this article are deposited in the ProteomeXchange consortium via de identifier PXD003423 (http://www.proteomexchange.org/). The list of the identified and quantified proteins obtained in the two replicas of the study are provided in the supplementary material of this article."]], "row_count": 9, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t0005"}}, {"id": "asset:table:pmid:29904688:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:808ea76ec598e80dc3c9a00e89ab62915fb43fad47c0d13d377b4661dba689dd", "bytes": 1657, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#t0005", "version": null, "note": null, "structure": {"pmcid": "PMC5997975", "section_index": 2, "section_title": "p", "row_count": 9, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["Subject area", "Cell signaling and ubiquitination"], ["More specific subject area", "EGFR Signaling and ubiquitinome"], ["Type of data", "Mass spectrometry (MS) data"], ["How data was acquired", "MS data was acquired on a Q-Exactive mass spectrometer (Thermo Scientific)."], ["Data format", "Raw and excel files"], ["Experimental factors", "Substitution of endogenous ubiquitin for a doubly-tagged version of ubiquitin in HeLa cells, combined with silencing of CYLD using shRNA and SILAC labeling of different conditions. shControl or shCYLD cells were either left starved or stimulated with EGF for 6 min."], ["Experimental features", "After the corresponding stimulation of shControl or shCYLD cells, protein extracts from two paralleled SILAC experiments were pooled accordingly and ubiquitinated proteins were enriched using a two steps procedure. An enrichment using Ni-NTA beads was performed, followed by immunoprecipitation of proteins using anti-FLAG specific antibodies. Enriched proteins were subjected to in-solution digestion and the resulting peptides were fractionated prior their LC–MS/MS analysis."], ["Data source location", "University of Southern Denmark, Odense, Denmark"], ["Data accessibility", "All the data presented in this article are deposited in the ProteomeXchange consortium via de identifier PXD003423 (http://www.proteomexchange.org/). The list of the identified and quantified proteins obtained in the two replicas of the study are provided in the supplementary material of this article."]], "row_count": 9, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[1]/table-wrap[1]#t0005"}}], "gaps": ["asset:data:geo:PXD003423 not downloaded", "asset:data:geo:PXD003423 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Perseus software, using significance B with p<0.001", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The calculation of significantly changed proteins was performed using the Perseus software [11]."}}], "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": "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 (Perseus software, using significance B with p<0.001), 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": ["PXD003423"], "resolved_accessions": ["PXD003423"], "statements": ["All the data presented in this article are deposited in the ProteomeXchange consortium via de identifier PXD003423 (http://www.proteomexchange.org/). The list of the identified and quantified proteins obtained in the two replicas of the study are provided in the supplementary material of this article."], "basis": "The paper names PXD003423 in ProteomeXchange and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:29904688", "data:geo:PXD003423", "asset:table:pmid:29904688:1", "asset:table:pmid:29904688:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:PXD003423"]}, "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": "2026-10-31T18:34:44Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 31975, "completion_tokens": 2892, "cached_tokens": 2114}}, "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:29904688", "type": "paper", "label": "pmid:29904688"}, {"id": "source:pmid:29904688", "type": "manuscript", "label": "PMID 29904688 full text"}, {"id": "data:geo:PXD003423", "type": "dataset", "label": "GEO PXD003423"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29904688", "type": "paper", "label": "pmid:29904688"}, {"id": "source:pmid:29904688", "type": "manuscript", "label": "PMID 29904688 full text"}, {"id": "data:geo:PXD003423", "type": "dataset", "label": "GEO PXD003423"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29904688", "type": "extraction", "used": ["source:pmid:29904688"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-PXD003423", "type": "accession_resolution", "used": ["data:geo:PXD003423"], "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:29904688", "parent_hash": "sha256:91837c2e9db13d4b67e2957f8616d7ad34f3db77dec580f9ad56af0380f1abc3", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:PXD003423 licence not read", "asset:data:geo:PXD003423 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": ["Data on mass spectrometry-based proteomics for studying the involvemen", "trol and CYLD-depleted cells was followed by mass spectrometric analysis. Therefore, we present an unbiased", "et al., 2017) [1]. We provide the associated mass spectrometry raw files, excel tables and gene ontology en", "the indicated times. Sample preparation for mass spectrometry analysis For the enrichment of ubiquitinated"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["n Exchange, StUbEx), in combination with the shRNA silencing of CYLD and SILAC-labeling on HeLa", "e performed. Firstly, HeLa-StUbEx cells were transfected with a shRNA construct for the stable downre", "y, HeLa-StUbEx cells were transfected with a shRNA construct for the stable downregulation of C"], "order_basis": "paper_text_order:1016", "id": "assay:2"}, {"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": ["hRNA silencing of CYLD and SILAC-labeling on HeLa cells. The subsequent tandem affinity purifi", "ineering strategies were performed. Firstly, HeLa-StUbEx cells were transfected with a shRNA c", "ication tools against the two tags. Finally, HeLa-StUbEx cells were metabolically labeled usin", "ssays Human cervix epithelial adenocarcinoma HeLa cells were grown in Dulbecco's modified Eagl"], "order_basis": "paper_text_order:1062", "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":"2026-11-04T01:29:30+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}}}