{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29699486", "kind": "science-record", "revision": 7, "content_hash": "sha256:221cac93c4e636ab1db60b96ef6075460882a0b24689a1cac056f77f437b5be7", "created_at": "2026-11-01T15:40:33Z", "updated_at": "2026-11-01T21:59:49Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Integrative analysis and machine learning on cancer genomics data using the Cancer Systems Biology Database (CancerSysDB).", "doi": "10.1186/s12859-018-2157-7", "pmid": "29699486", "authors": ["Rasmus Krempel", "Pranav Kulkarni", "Annie Yim", "Ulrich Lang", "Bianca Habermann", "Peter Frommolt"], "journal": "BMC bioinformatics", "year": 2018, "abstract": "BACKGROUND: Recent cancer genome studies on many human cancer types have relied on multiple molecular high-throughput technologies. Given the vast amount of data that has been generated, there are surprisingly few databases which facilitate access to these data and make them available for flexible analysis queries in the broad research community. If used in their entirety and provided at a high structural level, these data can be directed into constantly increasing databases which bear an enormous potential to serve as a basis for machine learning technologies with the goal to support research and healthcare with predictions of clinically relevant traits.\nRESULTS: We have developed the Cancer Systems Biology Database (CancerSysDB), a resource for highly flexible queries and analysis of cancer-related data across multiple data types and multiple studies. The CancerSysDB can be adopted by any center for the organization of their locally acquired data and its integration with publicly available data from multiple studies. A publicly available main instance of the CancerSysDB can be used to obtain highly flexible queries across multiple data types as shown by highly relevant use cases. In addition, we demonstrate how the CancerSysDB can be used for predictive cancer classification based on whole-exome data from 9091 patients in The Cancer Genome Atlas (TCGA) research network.\nCONCLUSIONS: Our database bears the potential to be used for large-scale integrative queries and predictive analytics of clinically relevant traits.", "claims": [{"id": "claim-data-access", "statement": "The datasets analysed in the current study are available on the in the Genomic Data Commons (GDC) Data Portal at https://gdc.cancer.gov/.\nDatabase URL: https://cancersys.uni-koeln.de.\nSource code: https://github.com/RRZK/CancerSysDB.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29699486", "locator": "sections[15] \"Availability of data and materials\" paragraphs 1-4", "quote": "The datasets analysed in the current study are available on the in the Genomic Data Commons (GDC) Data Portal at https://gdc.cancer.gov/.\nDatabase URL: https://cancersys.uni-koeln.de.\nSource code: https://github.com/RRZK/CancerSysDB."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The paper reports that a random forest trained on CancerSysDB somatic-mutation data from 9,091 TCGA patients classified 1,521 of 3,085 held-out patients correctly (49.3%), compared with 182 correct assignments (5.9%) for random guessing.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:29699486", "locator": "sections[8] \"Prediction of cancer types with random forests\" paragraph 3", "quote": "In the training phase, a random forest consisting of 1000 trees is trained on all data available in the CancerSysDB."}, {"asset": "source:pmid:29699486", "locator": "sections[5] \"Data preparation\" paragraph 2", "quote": "All TCGA data were obtained as level 3 data from the Legacy Archive of The Cancer Genome Atlas (TCGA) data portal. Data on somatic mutations were based on whole-exome sequencing with MAF files obtained from the Firehose pipeline of the Genome Data Analysis Center (GDAC) at the Broad Institute."}, {"asset": "source:pmid:29699486", "locator": "sections[8] \"Prediction of cancer types with random forests\" paragraph 4", "quote": "Out of these 3085 patients in the test set, 1521 (49.3%) were assigned to the correct class (Fig. 2), whereas a random guess of the class would have produced a correct class assignment in only 182 cases (5.9%)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "The paper reports that a random forest trained on CancerSysDB somatic-mutation data from 9,091 TCGA patients classified 1,521 of 3,085 held-out patients correctly (49.3%), compared with 182 correct assignments (5.9%) for random guessing.", "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:29699486"], "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": "blocked", "blocked_on": "method:machine_learning_random_forest", "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:run_analysis blocked on method:machine_learning_random_forest", "step:obtain_source_data blocked on data:accession_absent"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29699486", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12859-018-2157-7", "sha256": "sha256:a31f43048cefc9a9f397790eb01e349e2e59615b25b859fb3b3e9dd8901c4cfa", "bytes": 35785, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12859-018-2157-7", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC5921751", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "asset:table:pmid:29699486:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f0c456c47a18c87da3d17e1fc48a1a318a56704d9f47d3b2089eea9865b2ffd2", "bytes": 911, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "Comparison of various features of the CancerSysDB with those of other cancer genomics data integration tools", "structure": {"pmcid": "PMC5921751", "section_index": 3, "section_title": "Implementation", "row_count": 7, "column_count": 5}, "table": {"label": "Table 1", "caption": "Comparison of various features of the CancerSysDB with those of other cancer genomics data integration tools", "rows": [["", "CancerSysDB", "TCGAbiolinks", "RTCGA", "cBio portal"], ["GUI", "Web framework based on Groovy/Grails", "Based on Shiny", "None", "Web framework based on Spring Java"], ["Query schema", "Hibernate", "R scripting", "R scripting", "SQL"], ["Data upload", "Parametrized CSV file upload", "Direct access to GDC through API", "Data packages available on Bioconductor", "CSV files plus meta file"], ["Query definition", "JSON-based", "Combination of R commands", "Combination of R commands", "REST-based API"], ["Portability", "Native Docker implementation", "Hosted on Bioconductor", "Hosted on Bioconductor", "Hosted on GitHub"], ["Programming skills required", "No", "Yes", "Yes", "No"]], "row_count": 7, "column_count": 5, "numeric_cells": 0, "header_rows": 1, "locator": "section[3]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:29699486:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:29c52585c1d60da8a361d90aa17f7ed7aed81ef55521f80976fe2bdf345e8eeb", "bytes": 1123, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#Tab2", "version": null, "note": "Results of TP53-dependent analysis of genomic and clinical characteristics", "structure": {"pmcid": "PMC5921751", "section_index": 7, "section_title": "TP53-dependent analysis of overall survival, genome stability, and mutation types", "row_count": 17, "column_count": 8}, "table": {"label": "Table 2", "caption": "Results of TP53-dependent analysis of genomic and clinical characteristics", "rows": [["(a)"], ["", "Patients", "Events", "5-year survival rate [%]", "Median survival", "95% CI"], ["TP53 mutant", "3772", "1237", "47.4", "1670", "[1526; 1818]"], ["TP53 non-mutant", "5672", "1128", "66.9", "3736", "[3262; 4267]"], ["(b)"], ["", "Patients", "CNAs [Mb]"], ["TP53 mutant", "133", "74.5"], ["TP53 non-mutant", "246", "50.5"], ["(c)"], ["", "", "TP53", "ATM"], ["VarType", "All", "Mutant [%] (n = 320)", "Non-mutant [%] (n = 265)", "p-value", "Mutant [%] (n = 49)", "Non-mutant [%] (n = 536)", "p-value"], ["A > C or T > G", "3.5", "3.3", "3.6", "< 0.0001", "3.9", "3.4", "0.2160"], ["A > G or T > C", "9.9", "9.2", "10.7", "< 0.0001", "9.6", "9.9", "0.7695"], ["A > T or T > A", "8.1", "8.4", "7.8", "0.0005", "8.6", "8.1", "0.4584"], ["C > G or G > C", "13.6", "13.9", "13.1", "< 0.0001", "13.2", "13.6", "0.3790"], ["C > T or G > A", "32.7", "30.0", "36.0", "< 0.0001", "28.6", "33.0", "0.5121"], ["G > T or C > A", "32.3", "35.2", "28.8", "0.0001", "36.0", "32.0", "0.4940"]], "row_count": 17, "column_count": 8, "numeric_cells": 67, "header_rows": 0, "locator": "section[7]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:29699486:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b8db4be4bfdb918113a98b48d88a85347aca700e9f74c6197918285c579a419b", "bytes": 1830, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#Tab3", "version": null, "note": "Classes of carcinomas used for random forest prediction of cancer types", "structure": {"pmcid": "PMC5921751", "section_index": 8, "section_title": "Prediction of cancer types with random forests", "row_count": 32, "column_count": 5}, "table": {"label": "Table 3", "caption": "Classes of carcinomas used for random forest prediction of cancer types", "rows": [["Class name", "TCGA cohorts", "Sample size"], ["Total", "Training set", "Test set"], ["Adrenal gland", "Adrenocortical carcinoma (ACC)", "271", "179", "92"], ["Pheochromocytoma and paraganglioma (PCPG)"], ["Bladder", "Urothelial carcinoma (BLCA)", "411", "272", "139"], ["Brain", "Lower grade glioma (LGG)", "515", "340", "175"], ["Breast", "Breast invasive carcinoma (BRCA)", "1077", "711", "366"], ["Gastrointestinal", "Esophageal carcinoma (ESCA)", "1237", "817", "420"], ["Stomach adenocarcinoma (STAD)"], ["Colon adenocarcinoma (COAD)"], ["Rectum adenocarcinoma (READ)"], ["Cholangiocarcinoma (CHOL)"], ["Head & Neck", "Head and neck squamous cell carcinoma (HNSC)", "590", "390", "200"], ["Uveal melanoma (UVM)"], ["Hematologic", "Acute myeloid leukemia (LAML)", "321", "212", "109"], ["Diffuse large B-cell lymphoma (DLBC)"], ["Thymoma (THYM)"], ["Kidney", "Kidney Chromophobe (KICH)", "738", "488", "250"], ["Renal clear cell carcinoma (KIRC)"], ["Renal papillary cell carcinoma (KIRP)"], ["Liver", "Hepatocellular carcinoma (LIHC)", "321", "212", "109"], ["Ovary", "Ovarian serous cystadenocatcinoma (OV)", "437", "289", "148"], ["Pancreas", "Pancreatic adenocarcinoma (PAAD)", "184", "122", "62"], ["Prostate", "Prostate adenocarcinoma (PRAD)", "498", "329", "169"], ["Skin", "Cutaneous melanoma (SKCM)", "104", "69", "35"], ["Testis", "Testicular germ cell tumors (TGCT)", "150", "99", "51"], ["Thoracic", "Lung adenocarcinoma (LUAD)", "1143", "755", "388"], ["Lung squamous cell carcinoma (LUSC)"], ["Mesothelioma (MESO)"], ["Thyroid", "Thyroid carcinoma (THCA)", "496", "327", "169"], ["Uterus", "Uterine carcinosarcoma (UCS)", "598", "395", "203"], ["Uterine corpus endometrial carcinoma (UCEC)"]], "row_count": 32, "column_count": 5, "numeric_cells": 51, "header_rows": 2, "locator": "section[8]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:29699486:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3174b217d2e40be55ab57bbd4273ec906856448a795156b9dfc1029f4637c033", "bytes": 623, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#Tab4", "version": null, "note": "Averaged log2-fold changes of SUCLG1 and SUCLG2 mRNAs in different tumor stages of KIRP cancer patients", "structure": {"pmcid": "PMC5921751", "section_index": 9, "section_title": "Analyzing TCA-cycle genes in kidney renal papillary cell carcinoma (KIRP)", "row_count": 6, "column_count": 8}, "table": {"label": "Table 4", "caption": "Averaged log2-fold changes of SUCLG1 and SUCLG2 mRNAs in different tumor stages of KIRP cancer patients", "rows": [["Stage", "# Patients", "Female/Male", "Alive/Dead", "SUCLG1", "SUCLG2"], ["log2 FC", "p-value", "log2 FC", "p-value"], ["I", "15", "5 / 10", "13 / 2", "−0.473", "0.132", "−0.338", "0.307"], ["II", "1", "0 / 1", "1 / 0", "−1.163", "0.082", "0.137", "0.431"], ["III", "11", "5 / 6", "8 / 3", "−0.835", "0.018", "−0.760", "0.028"], ["IV", "4", "0 / 4", "3 / 1", "−1.975", "0.066", "−1.664", "0.054"]], "row_count": 6, "column_count": 8, "numeric_cells": 28, "header_rows": 2, "locator": "section[9]/table-wrap[1]#Tab4"}}], "gaps": []}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "random forest"}}], "targets": [], "gaps": ["method.machine_learning_random_forest"]}, "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": false, "required_operations": [], "missing_operations": ["machine_learning_random_forest"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: random_forest."}, "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 datasets analysed in the current study are available on the in the Genomic Data Commons (GDC) Data Portal at https://gdc.cancer.gov/.\nDatabase URL: https://cancersys.uni-koeln.de.\nSource code: https://github.com/RRZK/CancerSysDB."], "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:29699486", "asset:table:pmid:29699486:1", "asset:table:pmid:29699486:2", "asset:table:pmid:29699486:3", "asset:table:pmid:29699486:4"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "machine_learning_random_forest", "unlocks_papers": null, "priority": null}], "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": "2026-10-31T18:34:19Z", "independence": "same_provider"}, "evidence_check": {"method": null, "availability": "verbatim"}, "calls": 8, "usage": {"prompt_tokens": 69543, "completion_tokens": 4563, "cached_tokens": 1832}}, "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:29699486", "type": "paper", "label": "pmid:29699486"}, {"id": "source:pmid:29699486", "type": "manuscript", "label": "PMID 29699486 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29699486", "type": "paper", "label": "pmid:29699486"}, {"id": "source:pmid:29699486", "type": "manuscript", "label": "PMID 29699486 full text"}, {"id": "data:geo:None", "type": "dataset", "label": "GEO None"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29699486", "type": "extraction", "used": ["source:pmid:29699486"], "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:29699486", "parent_hash": "sha256:4004f24d3e137f180871fbc824f295602e53d1664e2d5e76277014eb747fe595", "fork_of": null, "generation": 6}, "gaps": ["execution.not_run", "method.machine_learning_random_forest", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:obtain_source_data blocked on data:accession_absent", "step:run_analysis blocked on method:machine_learning_random_forest"], "assays": [{"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["s likely caused by the impaired induction of apoptosis upon these exogenic damages.Genomic complexi", "ributed to the role of TP53 as a mediator of apoptosis in response to somatically acquired DNA dama"], "order_basis": "paper_text_order:2882", "id": "assay:1"}, {"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["random forest"], "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":"2026-11-04T03:00:05+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}}}