{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:28232861", "kind": "science-record", "revision": 4, "content_hash": "sha256:d08dac6afd1f7c2ce9480e3d593d3ab9cd42dc7af72b15d2dfcd58ac16f92932", "created_at": "2026-11-01T15:40:24Z", "updated_at": "2026-11-01T21:20:50Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "TCGA Workflow: Analyze cancer genomics and epigenomics data using Bioconductor packages.", "doi": "10.12688/f1000research.8923.2", "pmid": "28232861", "authors": ["Tiago C Silva", "Antonio Colaprico", "Catharina Olsen", "Fulvio D'Angelo", "Gianluca Bontempi", "Michele Ceccarelli", "Houtan Noushmehr"], "journal": "F1000Research", "year": 2016, "abstract": "Biotechnological advances in sequencing have led to an explosion of publicly available data via large international consortia such as The Cancer Genome Atlas (TCGA), The Encyclopedia of DNA Elements (ENCODE), and The NIH Roadmap Epigenomics Mapping Consortium (Roadmap). These projects have provided unprecedented opportunities to interrogate the epigenome of cultured cancer cell lines as well as normal and tumor tissues with high genomic resolution. The Bioconductor project offers more than 1,000 open-source software and statistical packages to analyze high-throughput genomic data. However, most packages are designed for specific data types (e.g. expression, epigenetics, genomics) and there is no one comprehensive tool that provides a complete integrative analysis of the resources and data provided by all three public projects. A need to create an integration of these different analyses was recently proposed. In this workflow, we provide a series of biologically focused integrative analyses of different molecular data. We describe how to download, process and prepare TCGA data and by harnessing several key Bioconductor packages, we describe how to extract biologically meaningful genomic and epigenomic data. Using Roadmap and ENCODE data, we provide a work plan to identify biologically relevant functional epigenomic elements associated with cancer. To illustrate our workflow, we analyzed two types of brain tumors: low-grade glioma (LGG) versus high-grade glioma (glioblastoma multiform or GBM). This workflow introduces the following Bioconductor packages: AnnotationHub, ChIPSeeker, ComplexHeatmap, pathview, ELMER, GAIA, MINET, RTCGAToolbox, TCGAbiolinks.", "claims": [{"id": "claim-method", "statement": "The most significant recurrent CNV were identified using GAIA 29, an iterative procedure where a statistical hypothesis framework is extended to take into account within-sample homogeneity. GAIA is based on a conservative permutation test allowing the estimation of the probability distribution of the contemporary mutations expected for non-driver markers.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:28232861", "locator": "sections[4] \"Genomic analysis\" paragraph 8", "quote": "The most significant recurrent CNV were identified using GAIA 29, an iterative procedure where a statistical hypothesis framework is extended to take into account within-sample homogeneity. GAIA is based on a conservative permutation test allowing the estimation of the probability distribution of the contemporary mutations expected for non-driver markers."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "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:28232861"], "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": "blocked", "blocked_on": "data:accession_absent", "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": [], "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": [], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:28232861", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.12688/f1000research.8923.2", "sha256": "sha256:d4d2fd9a404c4e11190d6985f4d5830fd503f463eba20905b689f138afcf674b", "bytes": 124452, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.12688/f1000research.8923.2", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5302158", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:28232861:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:017b220e27217b4c681b40f6156640310ece9b08bcc63fa7eb956181bcef9f04", "bytes": 722, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#T1", "version": null, "note": "Chromosome 20 recurrent deleted genes in LGG.", "structure": {"pmcid": "PMC5302158", "section_index": 4, "section_title": "Genomic analysis", "row_count": 6, "column_count": 6}, "table": {"label": "Table 1.", "caption": "Chromosome 20 recurrent deleted genes in LGG.", "rows": [["", "GeneSymbol", "Aberration", "q-value", "AberrantRegion", "GeneRegion"], ["1", "EIF4E2P1", "Del", "5.74967741935484e-05", "20:20540891-21005246", "20:20659710-20659964"], ["2", "LLPHP1", "Del", "5.74967741935484e-05", "20:20540891-21005246", "20:20721187-20721879"], ["3", "RN7SL607P", "Del", "5.74967741935484e-05", "20:20540891-21005246", "20:20738433-20738731"], ["4", "MRPS11P1", "Del", "5.74967741935484e-05", "20:20540891-21005246", "20:20854121-20854642"], ["5", "RPL24P2", "Del", "5.74967741935484e-05", "20:21091497-21220212", "20:21114723-21115197"]], "row_count": 6, "column_count": 6, "numeric_cells": 23, "header_rows": 1, "locator": "section[4]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:28232861:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e20e9fdbace0ab80946266e1f5fa700d549fbcacdacd6198e3330be31a5bba85", "bytes": 325, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[1]#T2", "version": null, "note": "Confusion matrix, comparing inferred network to network of validated interactions.", "structure": {"pmcid": "PMC5302158", "section_index": 5, "section_title": "Transcriptomic analysis", "row_count": 3, "column_count": 3}, "table": {"label": "Table 2.", "caption": "Confusion matrix, comparing inferred network to network of validated interactions.", "rows": [["", "validated", "not validated/non-existing"], ["inferred", "TP", "FP"], ["not inferred", "FN", "TN"]], "row_count": 3, "column_count": 3, "numeric_cells": 0, "header_rows": 1, "locator": "section[5]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:28232861:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c499da58a8a57955af21d622265ae639cf0b1b6e9df4e8051d1230407079a223", "bytes": 450, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[5]/table-wrap[2]#T3", "version": null, "note": "Number of edges in the inferred gene regulatory networks; first two lines: networks inferred using 2,901 differentially expressed genes.", "structure": {"pmcid": "PMC5302158", "section_index": 5, "section_title": "Transcriptomic analysis", "row_count": 3, "column_count": 6}, "table": {"label": "Table 3.", "caption": "Number of edges in the inferred gene regulatory networks; first two lines: networks inferred using 2,901 differentially expressed genes.", "rows": [["gene set", "inference algorithm", "aracne", "c3net", "clr", "mrnet"], ["DE", "GBM", "5,903", "2,678", "1,718,328", "1,682,334"], ["LGG", "4,443", "2,684", "1,939,142", "1,859,121"]], "row_count": 3, "column_count": 6, "numeric_cells": 8, "header_rows": 1, "locator": "section[5]/table-wrap[2]#T3"}}, {"id": "asset:table:pmid:28232861:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5cef8f90cfd7e71e26f32e8ef7d7f73971fc020fe7c8c91732d73a416990f5ac", "bytes": 1336, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#T5", "version": null, "note": "ChIP-seq data file types available in AnnotationHub.", "structure": {"pmcid": "PMC5302158", "section_index": 7, "section_title": "Integrative (Epigenomic & Transcriptomic) analysis", "row_count": 15, "column_count": 2}, "table": {"label": "Table 5.", "caption": "ChIP-seq data file types available in AnnotationHub.", "rows": [["File", "Description"], ["fc.signal.bigwig", "Bigwig File containing fold enrichment signal tracks"], ["pval.signal.bigwig", "Bigwig File containing -log10(p-value) signal tracks"], ["hotspot.fdr0.01.broad.bed.gz", "Broad domains on enrichment for DNase-seq for consolidated epigenomes"], ["hotspot.broad.bed.gz", "Broad domains on enrichment for DNase-seq for consolidated epigenomes"], ["broadPeak.gz", "Broad ChIP-seq peaks for consolidated epigenomes"], ["gappedPeak.gz", "Gapped ChIP-seq peaks for consolidated epigenomes"], ["narrowPeak.gz", "Narrow ChIP-seq peaks for consolidated epigenomes"], ["hotspot.fdr0.01.peaks.bed.gz", "Narrow DNasePeaks for consolidated epigenomes"], ["hotspot.all.peaks.bed.gz", "Narrow DNasePeaks for consolidated epigenomes"], [".macs2.narrowPeak.gz", "Narrow DNasePeaks for consolidated epigenomes"], ["coreMarks_mnemonics.bed.gz", "15 state chromatin segmentations"], ["mCRF_FractionalMethylation.bigwig", "MeDIP/MRE(mCRF) fractional methylation calls"], ["RRBS_FractionalMethylation.bigwig", "RRBS fractional methylation calls"], ["WGBS_FractionalMethylation.bigwig", "Whole genome bisulphite fractional methylation calls"]], "row_count": 15, "column_count": 2, "numeric_cells": 4, "header_rows": 1, "locator": "section[7]/table-wrap[1]#T5"}}, {"id": "asset:table:pmid:28232861:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:bab1562112e2fb7773e240e09220a595b58b37d4c2ecd52ffd07335350a48cc3", "bytes": 767, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[2]#T4", "version": null, "note": "Histone marks that define genomic elements.", "structure": {"pmcid": "PMC5302158", "section_index": 7, "section_title": "Integrative (Epigenomic & Transcriptomic) analysis", "row_count": 8, "column_count": 2}, "table": {"label": "Table 4.", "caption": "Histone marks that define genomic elements.", "rows": [["Histone marks", "Role"], ["Histone H3 lysine 4 trimethylation (H3K4me3)", "Promoter regions 58, 59"], ["Histone H3 lysine 4 monomethylation (H3K4me1)", "Enhancer regions 58"], ["Histone H3 lysine 36 trimethylation (H3K36me3)", "Transcribed regions"], ["Histone H3 lysine 27 trimethylation (H3K27me3)", "Polycomb repression 60"], ["Histone H3 lysine 9 trimethylation (H3K9me3)", "Heterochromatin regions 61"], ["Histone H3 acetylated at lysine 27 (H3K27ac)", "Increase activation of genomic elements 62– 64"], ["Histone H3 lysine 9 acetylation (H3K9ac)", "Transcriptional activation 65"]], "row_count": 8, "column_count": 2, "numeric_cells": 13, "header_rows": 1, "locator": "section[7]/table-wrap[2]#T4"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "GAIA", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The most significant recurrent CNV were identified using GAIA 29, an iterative procedure where a statistical hypothesis framework is extended to take into account within-sample homogeneity. GAIA is based on a conservative permutation test allowing the estimation of the probability distribution of the contemporary mutations expected for non-driver markers."}}], "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": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (GAIA), 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": "R4", "reachable": false, "accessions": [], "resolved_accessions": [], "statements": ["TCGA data is accessible via the the NCI Genomic Data Commons (GDC) data portal, GDC Legacy Archive and the Broad Institute’s GDAC Firehose. The GDC Data Portal provides access to the subset of TCGA data that has been harmonized against GRCh38 (hg38) using GDC Bioinformatics Pipelines which provides methods to the standardization of biospecimen and clinical data, the re-alignment of DNA and RNA sequence data against a common reference genome build GRCh38, and the generation of derived data. Whereas the GDC Legacy Archive provides access to an unmodified copy of data that was previously stored in CGHub 7 and in the TCGA Data Portal hosted by the TCGA Data Coordinating Center (DCC), in which uses as references GRCh37 (hg19) and GRCh36 (hg18).The previously stored data in CGHub, TCGA Data Portal and Broad Institute’s GDAC Firehose, were provided as different levels or tiers that were defined in terms of a specific combination of both processing level (raw, normalized, integrated) and access level (controlled or open access). Level 1 indicated raw and controlled data, level 2 indicated processed and controlled data, level 3 indicated Segmented or Interpreted Data and open access and level 4 indicated region of interest and open access data. While the TCGA data portal provided level 1 to 3 data, Firehose only provides level 3 and 4. An explanation of the different levels can be found at TCGA Wiki. However, the GDC data portal no longer uses this based classification model in levels. Instead a new data model was created, its documentation can be found in GDC documentation. In this new model, data can be open or controlled access. While the GDC open access data does not require authentication or authorization to access it and generally includes high level genomic data that is not individually identifiable, as well as most clinical and all biospecimen data elements, the GDC controlled access data requires dbGaP authorization and eRA Commons authentication and generally includes individually identifiable data such as low level genomic sequencing data, germline variants, SNP6 genotype data, and certain clinical data elements. The process to obtain access to controlled data is found in GDC web site."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:28232861", "asset:table:pmid:28232861:1", "asset:table:pmid:28232861:2", "asset:table:pmid:28232861:3", "asset:table:pmid:28232861:4", "asset:table:pmid:28232861:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:None"]}, "gaps": ["data:accession_absent"]}, "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:28232861", "type": "paper", "label": "pmid:28232861"}, {"id": "source:pmid:28232861", "type": "manuscript", "label": "PMID 28232861 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:28232861", "type": "paper", "label": "pmid:28232861"}, {"id": "source:pmid:28232861", "type": "manuscript", "label": "PMID 28232861 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-28232861", "type": "extraction", "used": ["source:pmid:28232861"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-None", "type": "accession_resolution", "used": ["data:geo:None"], "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:28232861", "parent_hash": "sha256:5ab7a39e384b337f9602d3a787ba511d886f217b035a89a43cb2e536e46df010", "fork_of": null, "generation": 3}, "gaps": ["execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["pportunities to interrogate the epigenome of cultured cancer cell lines as well as normal and tumo"], "order_basis": "paper_text_order:404", "id": "assay:1"}]},"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":"2026-11-04T02:50:04+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}}}