{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:23272654", "kind": "science-record", "revision": 4, "content_hash": "sha256:db74912377355e81e9fb8daa9400d6b4b9c9da55f684a3c97c223aaef4d5197b", "created_at": "2026-11-01T15:40:02Z", "updated_at": "2026-11-01T21:19:40Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "PROGmiR: a tool for identifying prognostic miRNA biomarkers in multiple cancers using publicly available data.", "doi": "10.1186/2043-9113-2-23", "pmid": "23272654", "authors": ["Chirayu Pankaj Goswami", "Harikrishna Nakshatri"], "journal": "Journal of clinical bioinformatics", "year": 2012, "abstract": "BACKGROUND: Identification of prognostic biomarkers is hallmark of cancer genomics. Since miRNAs regulate expression of multiple genes, they act as potent biomarkers in several cancers. Identification of miRNAs that are prognostically important has been done sporadically, but no resource is available till date that allows users to study prognostics of miRNAs of interest, utilizing the wealth of available data, in major cancer types.\nDESCRIPTION: In this paper, we present a web based tool that allows users to study prognostic properties of miRNAs in several cancer types, using publicly available data. We have compiled data from Gene Expression Omnibus (GEO), and recently developed \"The Cancer Genome Atlas (TCGA)\", to create this tool. The tool is called \"PROGmiR\" and it is available at http://www.compbio.iupui.edu/progmir. Currently, our tool can be used to study overall survival implications for approximately 1050 human miRNAs in 16 major cancer types.\nCONCLUSIONS: We believe this resource, as a hypothesis generation tool, will be helpful for researchers to link miRNA expression with cancer outcome and to design mechanistic studies. We studied performance of our tool using identified miRNA biomarkers from published studies. The prognostic plots created using our tool for specific miRNAs in specific cancer types corroborated with the findings in the studies.", "claims": [{"id": "claim-method", "statement": "Hazard ratio and p value are then calculated using function ‘coxph’ and prognostic plots are visualized using function ‘survfit’, both functions in library ‘survival’ for R.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:23272654", "locator": "sections[3] \"Workflow\" paragraph 4", "quote": "Hazard ratio and p value are then calculated using function ‘coxph’ and prognostic plots are visualized using function ‘survfit’, both functions in library ‘survival’ for R."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The database is available freely for non commercial and academic usage at http://www.compbio.iupui.edu/progmir.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:23272654", "locator": "sections[8] \"Availability and requirements\" paragraph 2", "quote": "The database is available freely for non commercial and academic usage at http://www.compbio.iupui.edu/progmir."}], "state": "complete"}, {"id": "claim-target-result", "statement": "PROGmiR uses miRNA expression data from GEO and TCGA to generate overall-survival Kaplan–Meier prognostic plots for approximately 1050 human miRNAs across 16 major cancer types.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:23272654", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "In this paper, we present a web based tool that allows users to study prognostic properties of miRNAs in several cancer types, using publicly available data."}, {"asset": "source:pmid:23272654", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We have compiled data from Gene Expression Omnibus (GEO), and recently developed “The Cancer Genome Atlas (TCGA)”, to create this tool."}, {"asset": "source:pmid:23272654", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "Currently, our tool can be used to study overall survival implications for approximately 1050 human miRNAs in 16 major cancer types."}, {"asset": "source:pmid:23272654", "locator": "sections[1] \"Background\" paragraph 8", "quote": "PROGmiR allows users to study overall survival in form of prognostic plots using miRNA expression data from several publically available patient series. The data in our tool comes from Gene Expression Omnibus (GEO) and The Cancer Genome Atlas (TCGA) [51]."}, {"asset": "source:pmid:23272654", "locator": "sections[1] \"Background\" paragraph 8", "quote": "Our tool uses miRNA expression data from these datasets to create overall survival Kaplan-Meier (K-M) plots."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "PROGmiR uses miRNA expression data from GEO and TCGA to generate overall-survival Kaplan–Meier prognostic plots for approximately 1050 human miRNAs across 16 major cancer types.", "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:23272654"], "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:23272654", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/2043-9113-2-23", "sha256": "sha256:292b5b65364f3b114aad1aee04868c83fe5b5400f87c54a2698f65494e97e15c", "bytes": 21959, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/2043-9113-2-23", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC3564827", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:23272654:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e03e13d3aa0407e4a66fb4bd5396d966c1286c928ce0b7f96d60ef0d1d74e3e8", "bytes": 1831, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[1]/table-wrap[1]#T1", "version": null, "note": "Description of various data sources included in progmir database", "structure": {"pmcid": "PMC3564827", "section_index": 1, "section_title": "Background", "row_count": 17, "column_count": 8}, "table": {"label": "Table 1", "caption": "Description of various data sources included in progmir database", "rows": [["", "Cancer type", "Dataset", "Source", "Platform", "No of samples", "No of miRNAs*", "Reference"], ["1", "Adrenocortial Carcinoma", "GSE22816", "GEO", "Agilent-025987 Human miRNA Microarray Release 14.0", "22", "200", "[52]"], ["2", "Acute Myeloid Leukemia", "LAML", "TCGA", "Illumina GA miRNA Seq", "164", "704", "[51]"], ["3", "Brain Lower Grade Glioma", "LGG", "TCGA", "Illumina HISeq miRNA Seq", "29", "1046", "[51]"], ["4", "Glioblastoma multiforme", "GBM", "TCGA", "UNC miRNA 8X15K", "487", "470", "[51]"], ["5", "Breast Invasive Carcinoma", "BRCA", "TCGA", "Illumina GA and HISeq", "727", "1046", "[51]"], ["6", "Non-small-cell Lung Cancer", "GSE16025", "GEO", "mirVANA miRNA Bioarray V2", "60", "328", "[53]"], ["7", "Small Cell Lung Cancer", "GSE27435", "GEO", "Capitalbio mammal microRNA V3.0", "42", "1638", "[54]"], ["8", "Lung Adenocarcinoma", "LUAD", "TCGA", "Illumina GA and HISeq", "79", "1046", "[51]"], ["9", "Lung Squamous Cell Carcinoma", "LUSC", "TCGA", "Illumina GA and HISeq", "185", "1046", "[51]"], ["10", "Hepatocellular Carcinoma", "GSE31384", "GEO", "CapitalBio custom Human microRNA array", "166", "682", "[55]"], ["11", "Head and Neck Squamous Cell Carcinoma", "HNSC", "TCGA", "Illumina GA and HISeq", "89", "1046", "[51]"], ["12", "Ovarian Cystadenocarcinoma", "OV", "TCGA", "UNC miRNA 8X15K", "46", "705", "[51]"], ["13", "Rectal Adenocarcinoma", "READ", "TCGA", "Illumina GA miRNA Seq", "38", "705", "[51]"], ["14", "Renal Clear Cell Carcinoma", "KIRC", "TCGA", "Illumina GA and HISeq", "546", "1046", "[51]"], ["15", "Stomach Ademocarcinoma", "STAD", "TCGA", "Illumina GA and HISeq", "79", "1046", "[51]"], ["16", "Uterine Corpus Endometroid Carcinoma", "UCEC", "TCGA", "Illumina GA and HISeq", "358", "1046", "[51]"]], "row_count": 17, "column_count": 8, "numeric_cells": 72, "header_rows": 1, "locator": "section[1]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:23272654:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:51589efb5aab6138654af723adeb48724d6e0a97b5d6f0a86d8bf041b0e43185", "bytes": 1910, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#T2", "version": null, "note": "Global statistics on survival related variables for the datasets available in PROGmiR", "structure": {"pmcid": "PMC3564827", "section_index": 6, "section_title": "Utility and discussion", "row_count": 18, "column_count": 8}, "table": {"label": "Table 2", "caption": "Global statistics on survival related variables for the datasets available in PROGmiR", "rows": [["", "", "", "", "Survival event", "No event"], ["", "Cancer type", "Dataset", "Total no of samples", "No of samples", "Median survival§ (range)", "No of samples", "Median survival§* (range)"], ["1", "Adrenocortial Carcinoma", "GSE22816", "22", "6", "600 (120-4860)", "16", "885 (60-4980)"], ["2", "Acute Myeloid Leukemia", "LAML", "164", "100", "303 (28-1706)", "64", "699 (28-2861)"], ["3", "Brain Lower Grade Glioma", "LGG", "29", "23", "788 (96-1915)", "6", "1317 (242-6423)"], ["4", "Glioblastoma multiforme", "GBM", "487", "383", "377 (3-3880)", "104", "266 (3-2817)"], ["5", "Breast Invasive Carcinoma", "BRCA", "727", "91", "1563 (157-4456)", "636", "466 (1-6795)"], ["6", "Non-small-cell Lung Cancer", "GSE16025", "60", "26", "1980 (210-2490)", "34", "1500 (120-2580)"], ["7", "Small Cell Lung Cancer", "GSE27435", "42", "18", "743 (234-2400)", "24", "1314 (426 -2490)"], ["8", "Lung Adenocarcinoma", "LUAD", "79", "27", "701 (22-1318)", "52", "400 (1-2161)"], ["9", "Lung Squamous Cell Carcinoma", "LUSC", "185", "77", "544 (12-5296)", "108", "640 (3-4299)"], ["10", "Hepatocellular Carcinoma", "GSE31384", "166", "73", "450 (30 – 2280)", "93", "1320 (420-2430)"], ["11", "Head and Neck Squamous Cell Carcinoma", "HNSC", "89", "27", "395 (128 – 2318)", "62", "359 (45 – 4115)"], ["12", "Ovarian Cystadenocarcinoma", "OV", "46", "21", "887 (9-1756)", "25", "912 (141 – 2099)"], ["13", "Rectal Adenocarcinoma", "READ", "38", "3", "316 (59 – 1184)", "35", "183 (28 – 2192)"], ["14", "Renal Clear Cell Carcinoma", "KIRC", "546", "173", "722 (2-2830)", "373", "1307 (4 – 3377)"], ["15", "Stomach Adenocarcinoma", "STAD", "79", "14", "258 (19 – 881)", "65", "109 (2 – 2131)"], ["16", "Uterine Corpus Endometroid Carcinoma", "UCEC", "358", "27", "413 (58 – 3251)", "331", "527 (1 – 5690)"]], "row_count": 18, "column_count": 8, "numeric_cells": 100, "header_rows": 2, "locator": "section[6]/table-wrap[1]#T2"}}], "gaps": []}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Hazard ratio and p value are then calculated using function ‘coxph’ and prognostic plots are visualized using function ‘survfit’, both functions in library ‘survival’ for R."}}], "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": "blocked", "tier": "R4", "blocking_axis": "data", "blocked_on": "data:accession_absent", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["The database is available freely for non commercial and academic usage at http://www.compbio.iupui.edu/progmir."], "basis": "The paper names no accession to its source data, so the data has to come from the authors."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:23272654", "asset:table:pmid:23272654:1", "asset:table:pmid:23272654:2"], "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": "2026-10-31T18:21:15Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 41817, "completion_tokens": 2484, "cached_tokens": 31790}}, "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:23272654", "type": "paper", "label": "pmid:23272654"}, {"id": "source:pmid:23272654", "type": "manuscript", "label": "PMID 23272654 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:23272654", "type": "paper", "label": "pmid:23272654"}, {"id": "source:pmid:23272654", "type": "manuscript", "label": "PMID 23272654 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-23272654", "type": "extraction", "used": ["source:pmid:23272654"], "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:23272654", "parent_hash": "sha256:87b9b331348978d5bdcfe64c6f70a1065571f44cab1c51ae545df0e7ea78193b", "fork_of": null, "generation": 3}, "gaps": ["execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Hazard ratio and p value are then calculated using function ‘coxph’ and prognostic plots are visualized using function ‘survfit’, both functions in library ‘survival’ for R."], "order_basis": "analysis_only", "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":"2026-11-04T00:42:49+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}}}