{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34221187", "kind": "science-record", "revision": 8, "content_hash": "sha256:f5e8ad40d265961277869a928cb56927c8f9bf34c9a04a2a0a8ebb4a2c4226e2", "created_at": "2026-11-01T15:41:41Z", "updated_at": "2026-11-01T22:47:00Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of an m6A-Related Signature as Biomarker for Hepatocellular Carcinoma Prognosis and Correlates with Sorafenib and Anti-PD-1 Immunotherapy Treatment Response.", "doi": "10.1155/2021/5576683", "pmid": "34221187", "authors": ["Hongye Jiang", "Gang Ning", "Yensheng Wang", "Weibiao Lv"], "journal": "Disease markers", "year": 2021, "abstract": "BACKGROUND: N6-methyladenosine (m6A) modification plays an essential role in diverse key biological processes and may take part in the development and progression of hepatocellular carcinoma (HCC). Here, we systematically analyzed the expression profiles and prognostic values of 13 widely reported m6A modification-related genes in HCC.\nMETHODS: The mRNA expression of 13 m6A modification-related genes and clinical parameters of HCC patients were downloaded from TCGA, ICGC, GSE109211, and GSE78220. Univariate and LASSO analyses were used to develop risk signature. Time-dependent ROC was performed to assess the predictive accuracy and sensitivity of risk signature.\nRESULTS: FTO, YTHDC1, YTHDC2, ALKBH5, KIAA1429, HNRNPC, METTL3, RBM15, YTHDF2, YTHDF1, and WTAP were significantly overexpressed in HCC patients. YTHDF1, HNRNPC, RBM15, METTL3, and YTHDF2 were independent prognostic factors for OS and DFS in HCC patients. Next, a risk signature was also developed and validated with five m6A modification-related genes in TCGA and ICGC HCC cohort. It could effectively stratify HCC patients into high-risk patients with shorter OS and DFS and low-risk patients with longer OS and DFS and showed good predictive efficiency in predicting OS and DFS. Moreover, significantly higher proportions of macrophages M0 cells, neutrophils, and Tregs were found to be enriched in HCC patients with high risk scores, while significantly higher proportions of memory CD4 T cells, gamma delta T cells, and naive B cells were found to be enriched in HCC patients with low scores. Finally, significantly lower risk scores were found at sorafenib treatment responders and anti-PD-1 immunotherapy responders compared to that in nonresponders, and anti-PD-1 immunotherapy-treated patients with lower risk scores had better OS than patients with higher risk scores.\nCONCLUSION: A risk signature developed with the expression of 5 m6A-related genes could improve the prediction of prognosis of HCC and correlated with sorafenib treatment and anti-PD-1 immunotherapy response.", "claims": [{"id": "claim-method", "statement": "Time-dependent ROC was carried out to analyze the predictive accuracy and sensitivity of risk signature.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34221187", "locator": "sections[8] \"2.6. Statistical Analysis\" paragraph 2", "quote": "Time-dependent ROC was carried out to analyze the predictive accuracy and sensitivity of risk signature."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data of the study are available from the corresponding web page link, including GDC Data portal (https://cancergenome.nih.gov/), ICGC portal (https://dcc.icgc.org/projects/LIRI-JP), and GEO database (https://www.ncbi.nlm.nih.gov/geo/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34221187", "locator": "sections[21] \"Data Availability\" paragraph 2", "quote": "The data of the study are available from the corresponding web page link, including GDC Data portal (https://cancergenome.nih.gov/), ICGC portal (https://dcc.icgc.org/projects/LIRI-JP), and GEO database (https://www.ncbi.nlm.nih.gov/geo/)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:34221187"], "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:GSE109211"], "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:GSE109211"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34221187", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1155/2021/5576683", "sha256": "sha256:254cd2650a4dd68985cecc74f346fda883153e01d41662c02ca408c45bd16d0c", "bytes": 43919, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1155/2021/5576683", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8213471", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE109211", "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=GSE109211", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE109211", "version": null, "note": "The data of the study are available from the corresponding web page link, including GDC Data portal (https://cancergenome.nih.gov/), ICGC portal (https://dcc.icgc.org/projects/LIRI-JP), and GEO database (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data of the study are available from the corresponding web page link, including GDC Data portal (https://cancergenome.nih.gov/), ICGC portal (https://dcc.icgc.org/projects/LIRI-JP), and GEO database (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2935278", "GSM2935279", "GSM2935280", "GSM2935281", "GSM2935282", "GSM2935283", "GSM2935284", "GSM2935285", "GSM2935286", "GSM2935287", "GSM2935288", "GSM2935289", "GSM2935290", "GSM2935291", "GSM2935292", "GSM2935293", "GSM2935294", "GSM2935295", "GSM2935296", "GSM2935297", "GSM2935298", "GSM2935299", "GSM2935300", "GSM2935301", "GSM2935302", "GSM2935303", "GSM2935304", "GSM2935305", "GSM2935306", "GSM2935307", "GSM2935308", "GSM2935309", "GSM2935310", "GSM2935311", "GSM2935312", "GSM2935313", "GSM2935314", "GSM2935315", "GSM2935316", "GSM2935317", "GSM2935318", "GSM2935319", "GSM2935320", "GSM2935321", "GSM2935322", "GSM2935323", "GSM2935324", "GSM2935325", "GSM2935326", "GSM2935327", "GSM2935328", "GSM2935329", "GSM2935330", "GSM2935331", "GSM2935332", "GSM2935333", "GSM2935334", "GSM2935335", "GSM2935336", "GSM2935337", "GSM2935338", "GSM2935339", "GSM2935340", "GSM2935341", "GSM2935342", "GSM2935343", "GSM2935344", "GSM2935345", "GSM2935346", "GSM2935347", "GSM2935348", "GSM2935349", "GSM2935350", "GSM2935351", "GSM2935352", "GSM2935353", "GSM2935354", "GSM2935355", "GSM2935356", "GSM2935357", "GSM2935358", "GSM2935359", "GSM2935360", "GSM2935361", "GSM2935362", "GSM2935363", "GSM2935364", "GSM2935365", "GSM2935366", "GSM2935367", "GSM2935368", "GSM2935369", "GSM2935370", "GSM2935371", "GSM2935372", "GSM2935373", "GSM2935374", "GSM2935375", "GSM2935376", "GSM2935377", "GSM2935378", "GSM2935379", "GSM2935380", "GSM2935381", "GSM2935382", "GSM2935383", "GSM2935384", "GSM2935385", "GSM2935386", "GSM2935387", "GSM2935388", "GSM2935389", "GSM2935390", "GSM2935391", "GSM2935392", "GSM2935393", "GSM2935394", "GSM2935395", "GSM2935396", "GSM2935397", "GSM2935398", "GSM2935399", "GSM2935400", "GSM2935401", "GSM2935402", "GSM2935403", "GSM2935404", "GSM2935405", "GSM2935406", "GSM2935407", "GSM2935408", "GSM2935409", "GSM2935410", "GSM2935411", "GSM2935412", "GSM2935413", "GSM2935414", "GSM2935415", "GSM2935416", "GSM2935417"], "sample_count": 140, "group_sizes": null, "group_sizes_basis": null, "platform": "13938", "taxon": "Homo sapiens", "title": "Molecular predictors of prevention of recurrence in hepatocellular carcinoma with sorafenib as adjuvant treatment in the phase 3 STORM trial", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE78220", "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=GSE78220", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE78220", "version": null, "note": "The data of the study are available from the corresponding web page link, including GDC Data portal (https://cancergenome.nih.gov/), ICGC portal (https://dcc.icgc.org/projects/LIRI-JP), and GEO database (https://www.ncbi.nlm.nih.gov/geo/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data of the study are available from the corresponding web page link, including GDC Data portal (https://cancergenome.nih.gov/), ICGC portal (https://dcc.icgc.org/projects/LIRI-JP), and GEO database (https://www.ncbi.nlm.nih.gov/geo/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2069823", "GSM2069824", "GSM2069825", "GSM2069826", "GSM2069827", "GSM2069828", "GSM2069829", "GSM2069830", "GSM2069831", "GSM2069832", "GSM2069833", "GSM2069834", "GSM2069835", "GSM2069836", "GSM2069837", "GSM2069838", "GSM2069839", "GSM2069840", "GSM2069841", "GSM2069842", "GSM2069843", "GSM2069844", "GSM2069845", "GSM2069846", "GSM2069847", "GSM2069848", "GSM2069849", "GSM2069850"], "sample_count": 28, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "mRNA expressions in pre-treatment melanomas undergoing anti-PD-1 checkpoint inhibition therapy", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:34221187:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:803059397fb129a966746dd4bc155194769ba88cd0b48282f3f792e057131b84", "bytes": 633, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[4]/table-wrap[1]#tab1", "version": null, "note": "Basic characteristics of 365 HCC patients from TCGA.", "structure": {"pmcid": "PMC8213471", "section_index": 4, "section_title": "2.2. Data Collection", "row_count": 8, "column_count": 2}, "table": {"label": "Table 1", "caption": "Basic characteristics of 365 HCC patients from TCGA.", "rows": [["Variables", "HCC patients (N = 365)"], ["Gender (male/female)", "246 (67%)/119 (33%)"], ["Age (years, ≤60/>60)", "173 (47%)/192 (53%)"], ["Histologic grade (G1+G2/G3+G4/NA)", "230 (63%)/130 (36%)/5 (1%)"], ["T stage (T1+T2/T3+T4/NA)", "271 (74%)/91 (25%)/3 (1%)"], ["N stage (N0/N1/NA)", "248 (68%)/4 (1%)/113 (31%)"], ["M stage (M0/N1/NA)", "263 (72%)/3 (1%)/99 (27%)"], ["TNM stage (stage1+II/stage III+IV/NA)", "254 (70%)/87 (24%)/24 (6%)"]], "row_count": 8, "column_count": 2, "numeric_cells": 9, "header_rows": 1, "locator": "section[4]/table-wrap[1]#tab1"}}], "gaps": ["asset:data:geo:GSE109211 not downloaded", "asset:data:geo:GSE109211 licence not read", "asset:data:geo:GSE78220 not downloaded", "asset:data:geo:GSE78220 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Time-dependent ROC was carried out to analyze the predictive accuracy and sensitivity of risk signature."}}, {"id": "method-2", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "ANOVA"}}, {"id": "method-3", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-4", "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": 0.8, "band": "high", "quote": "Cox regression"}}, {"id": "method-5", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-6", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Spearman correlation"}}, {"id": "method-7", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "Chi-square"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: roc."}, "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": ["GSE109211", "GSE78220"], "resolved_accessions": ["GSE109211", "GSE78220"], "statements": ["The data of the study are available from the corresponding web page link, including GDC Data portal (https://cancergenome.nih.gov/), ICGC portal (https://dcc.icgc.org/projects/LIRI-JP), and GEO database (https://www.ncbi.nlm.nih.gov/geo/)."], "basis": "The paper names GSE109211, GSE78220 in GEO database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "assets": ["source:pmid:34221187", "data:geo:GSE109211", "asset:table:pmid:34221187:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE109211"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:31:53Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 36811, "completion_tokens": 1948, "cached_tokens": 792}}, "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:34221187", "type": "paper", "label": "pmid:34221187"}, {"id": "source:pmid:34221187", "type": "manuscript", "label": "PMID 34221187 full text"}, {"id": "data:geo:GSE109211", "type": "dataset", "label": "GEO GSE109211"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34221187", "type": "paper", "label": "pmid:34221187"}, {"id": "source:pmid:34221187", "type": "manuscript", "label": "PMID 34221187 full text"}, {"id": "data:geo:GSE109211", "type": "dataset", "label": "GEO GSE109211"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34221187", "type": "extraction", "used": ["source:pmid:34221187"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE109211", "type": "accession_resolution", "used": ["data:geo:GSE109211"], "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:34221187", "parent_hash": "sha256:2ce9cf59f25123a3dd900e926d650147366d92e2ea685da44de89bd7e4c01cc4", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE109211 licence not read", "asset:data:geo:GSE109211 not downloaded", "asset:data:geo:GSE78220 licence not read", "asset:data:geo:GSE78220 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "diagnostic_evaluation", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Time-dependent ROC was carried out to analyze the predictive accuracy and sensitivity of risk signature."], "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":"2026-11-04T01:42:26+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}}}