{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39749665", "kind": "science-record", "revision": 3, "content_hash": "sha256:ac675ef56dd47bad47980e2ef46df7a2c987d1a63b22688115ef4d9dcd3c425c", "created_at": "2026-11-01T20:30:05Z", "updated_at": "2026-11-01T22:13:29Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A transformer-based deep learning survival prediction model and an explainable XGBoost anti-PD-1/PD-L1 outcome prediction model based on the cGAS-STING-centered pathways in hepatocellular carcinoma.", "doi": "10.1093/bib/bbae686", "pmid": "39749665", "authors": ["Ren Wang", "Qiumei Liu", "Wenhua You", "Huiyu Wang", "Yun Chen"], "journal": "Briefings in bioinformatics", "year": 2024, "abstract": "Recent studies suggest cGAS-STING pathway may play a crucial role in the genesis and development of hepatocellular carcinoma (HCC), closely associated with classical pathways and tumor immunity. We aimed to develop models predicting survival and anti-PD-1/PD-L1 outcomes centered on the cGAS-STING pathway in HCC. We identified classical pathways highly correlated with cGAS-STING pathway and constructed transformer survival model preserving raw structure of pathways. We also developed explainable XGBoost model for predicting anti-PD-1/PD-L1 outcomes using SHAP algorithm. We trained and validated transformer survival model on pan-cancer cohort and tested it on three independent HCC cohorts. Using 0.5 as threshold across cohorts, we divided each HCC cohort into two groups and calculated P values with log-rank test. TCGA-LIHC: C-index = 0.750, P = 1.52e-11; ICGC-LIRI-JP: C-index = 0.741, P = .00138; GSE144269: C-index = 0.647, P = .0233. We trained and validated [area under the receiver operating characteristic curve (AUC) = 0.777] XGBoost model on immunotherapy datasets and tested it on GSE78220 (AUC = 0.789); we also tested XGBoost model on HCC anti-PD-L1 cohort (AUC = 0.719). Our deep learning model and XGBoost model demonstrate potential in predicting survival risks and anti-PD-1/PD-L1 outcomes in HCC. We deployed these two prediction models to the GitHub repository and provided detailed instructions for their usage: deep learning survival model, https://github.com/mlwalker123/CSP_survival_model; XGBoost immunotherapy model, https://github.com/mlwalker123/CSP_immunotherapy_model.", "claims": [{"id": "claim-method", "statement": "We utilized ROC curve to assess the diagnostic capability of continuous variable. The method used for testing comparisons between two independent datasets in this study was the Mann–Whitney U test. All correlation analyses mentioned in this study were conducted using Spearman correlation analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39749665", "locator": "sections[14] \"Statistics\" paragraph 2", "quote": "We utilized ROC curve to assess the diagnostic capability of continuous variable. The method used for testing comparisons between two independent datasets in this study was the Mann–Whitney U test. All correlation analyses mentioned in this study were conducted using Spearman correlation analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data utilized in this study can be downloaded in the public databases. The names, applications, and downloading methods of all datasets are explicitly detailed in the table (Table 1).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39749665", "locator": "sections[28] \"Data availability\" paragraph 2", "quote": "All data utilized in this study can be downloaded in the public databases. The names, applications, and downloading methods of all datasets are explicitly detailed in the table (Table 1)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The cGAS-STING pathway ssGSEA score distinguished HCC from normal liver tissue with an AUC of 0.756 (P value = 4.3e−09).", "kind": "quantitative", "target": {"value": 4.0, "unit": "p-value", "tolerance": null, "source": "We compared the ssGSEA scores of the cGAS-STING pathway between normal liver tissue samples and HCC samples (P value = 4.3e−09) (Fig. 2b)."}, "evidence": [{"asset": "source:pmid:39749665", "locator": "sections[17] \"The diagnostic value of the cGAS-STING pathway and screening of related classical pathways\" paragraph 2", "quote": "We calculated the single sample gene set enrichment analysis (ssGSEA) scores of the cGAS-STING pathway in normal liver tissue samples and HCC samples from the TCGA-LIHC cohort and evaluated the ability of these scores to distinguish HCC from normal liver tissue using receiver operating characteristic (ROC) curve [area under the ROC curve (AUC) = 0.756] (Fig. 2a)."}, {"asset": "source:pmid:39749665", "locator": "sections[17] \"The diagnostic value of the cGAS-STING pathway and screening of related classical pathways\" paragraph 2", "quote": "We compared the ssGSEA scores of the cGAS-STING pathway between normal liver tissue samples and HCC samples (P value = 4.3e−09) (Fig. 2b)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The cGAS-STING pathway ssGSEA score distinguished HCC from normal liver tissue with an AUC of 0.756 (P value = 4.3e−09).", "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:39749665"], "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:GSE144269"], "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:GSE144269"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39749665", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1093/bib/bbae686", "sha256": "sha256:91bfc754994b752d032259f2f6c8132b7ab104df94c3166e233bb3a8c63f0af3", "bytes": 92540, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1093/bib/bbae686", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11695900", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE144269", "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=GSE144269", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE144269", "version": null, "note": "All data utilized in this study can be downloaded in the public databases. The names, applications, and downloading methods of all datasets are explicitly detailed in the table (Table 1).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data utilized in this study can be downloaded in the public databases. The names, applications, and downloading methods of all datasets are explicitly detailed in the table (Table 1).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4284605", "GSM4284606", "GSM4284607", "GSM4284608", "GSM4284609", "GSM4284610", "GSM4284611", "GSM4284612", "GSM4284613", "GSM4284614", "GSM4284615", "GSM4284616", "GSM4284617", "GSM4284618", "GSM4284619", "GSM4284620", "GSM4284621", "GSM4284622", "GSM4284623", "GSM4284624", "GSM4284625", "GSM4284626", "GSM4284627", "GSM4284628", "GSM4284629", "GSM4284630", "GSM4284631", "GSM4284632", "GSM4284633", "GSM4284634", "GSM4284635", "GSM4284636", "GSM4284637", "GSM4284638", "GSM4284639", "GSM4284640", "GSM4284641", "GSM4284642", "GSM4284643", "GSM4284644", "GSM4284645", "GSM4284646", "GSM4284647", "GSM4284648", "GSM4284649", "GSM4284650", "GSM4284651", "GSM4284652", "GSM4284653", "GSM4284654", "GSM4284655", "GSM4284656", "GSM4284657", "GSM4284658", "GSM4284659", "GSM4284660", "GSM4284661", "GSM4284662", "GSM4284663", "GSM4284664", "GSM4284665", "GSM4284666", "GSM4284667", "GSM4284668", "GSM4284669", "GSM4284670", "GSM4284671", "GSM4284672", "GSM4284673", "GSM4284674", "GSM4284675", "GSM4284676", "GSM4284677", "GSM4284678", "GSM4284679", "GSM4284680", "GSM4284681", "GSM4284682", "GSM4284683", "GSM4284684", "GSM4284685", "GSM4284686", "GSM4284687", "GSM4284688", "GSM4284689", "GSM4284690", "GSM4284691", "GSM4284692", "GSM4284693", "GSM4284694", "GSM4284695", "GSM4284696", "GSM4284697", "GSM4284698", "GSM4284699", "GSM4284700", "GSM4284701", "GSM4284702", "GSM4284703", "GSM4284704", "GSM4284705", "GSM4284706", "GSM4284707", "GSM4284708", "GSM4284709", "GSM4284710", "GSM4284711", "GSM4284712", "GSM4284713", "GSM4284714", "GSM4284715", "GSM4284716", "GSM4284717", "GSM4284718", "GSM4284719", "GSM4284720", "GSM4284721", "GSM4284722", "GSM4284723", "GSM4284724", "GSM4284725", "GSM4284726", "GSM4284727", "GSM4284728", "GSM4284729", "GSM4284730", "GSM4284731", "GSM4284732", "GSM4284733", "GSM4284734", "GSM4284735", "GSM4284736", "GSM4284737", "GSM4284738", "GSM4284739", "GSM4284740", "GSM4284741", "GSM4284742", "GSM4284743", "GSM4284744"], "sample_count": 140, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "The genomic landscape of Mongolian hepatocellular carcinoma", "resolution_checked_at": "2026-11-01T17:30:42Z", "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": "All data utilized in this study can be downloaded in the public databases. The names, applications, and downloading methods of all datasets are explicitly detailed in the table (Table 1).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data utilized in this study can be downloaded in the public databases. The names, applications, and downloading methods of all datasets are explicitly detailed in the table (Table 1).", "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": "data:geo:GSE91061", "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=GSE91061", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE91061", "version": null, "note": "All data utilized in this study can be downloaded in the public databases. The names, applications, and downloading methods of all datasets are explicitly detailed in the table (Table 1).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data utilized in this study can be downloaded in the public databases. The names, applications, and downloading methods of all datasets are explicitly detailed in the table (Table 1).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2420259", "GSM2420260", "GSM2420261", "GSM2420262", "GSM2420263", "GSM2420264", "GSM2420265", "GSM2420266", "GSM2420267", "GSM2420268", "GSM2420269", "GSM2420270", "GSM2420271", "GSM2420272", "GSM2420273", "GSM2420274", "GSM2420275", "GSM2420276", "GSM2420277", "GSM2420278", "GSM2420279", "GSM2420280", "GSM2420281", "GSM2420282", "GSM2420283", "GSM2420284", "GSM2420285", "GSM2420286", "GSM2420287", "GSM2420288", "GSM2420289", "GSM2420290", "GSM2420291", "GSM2420292", "GSM2420293", "GSM2420294", "GSM2420295", "GSM2420296", "GSM2420297", "GSM2420298", "GSM2420299", "GSM2420300", "GSM2420301", "GSM2420302", "GSM2420303", "GSM2420304", "GSM2420305", "GSM2420306", "GSM2420307", "GSM2420308", "GSM2420310", "GSM2420311", "GSM2420312", "GSM2420313", "GSM2420316", "GSM2420317", "GSM2420318", "GSM2420319", "GSM2420320", "GSM2420323", "GSM2420324", "GSM2420325", "GSM2420326", "GSM2420328", "GSM2420329", "GSM2420331", "GSM2420332", "GSM2420333", "GSM2420334", "GSM2420335", "GSM2420336", "GSM2420337", "GSM2420338", "GSM2420339", "GSM2420340", "GSM2420341", "GSM2420342", "GSM2420343", "GSM2420344", "GSM2420345", "GSM2420346", "GSM2420349", "GSM2420350", "GSM2420351", "GSM2420352", "GSM2420353", "GSM2420354", "GSM2420355", "GSM2420356", "GSM2420357", "GSM2420358", "GSM2420359", "GSM2420360", "GSM2420361", "GSM2420362", "GSM2420363", "GSM2420364", "GSM2420365", "GSM2420366", "GSM2420367", "GSM2420368", "GSM2420369", "GSM2420370", "GSM2420371", "GSM2420372", "GSM2420373", "GSM2420374", "GSM2420375", "GSM2420376"], "sample_count": 109, "group_sizes": null, "group_sizes_basis": null, "platform": "9052", "taxon": "Homo sapiens", "title": "Molecular portraits of tumor mutational and micro-environmental sculpting by immune checkpoint blockade therapy", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE144269 not downloaded", "asset:data:geo:GSE144269 licence not read", "asset:data:geo:GSE78220 not downloaded", "asset:data:geo:GSE78220 licence not read", "asset:data:geo:GSE91061 not downloaded", "asset:data:geo:GSE91061 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We utilized ROC curve to assess the diagnostic capability of continuous variable. The method used for testing comparisons between two independent datasets in this study was the Mann–Whitney U test. All correlation analyses mentioned in this study were conducted using Spearman correlation analysis."}}, {"id": "method-2", "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": 0.7, "band": "medium", "quote": "log-rank"}}, {"id": "method-3", "family": "machine_learning", "specific": "gradient_boosting", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "XGBoost"}}, {"id": "method-4", "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": 0.8, "band": "high", "quote": "ROC curve"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "classification_metrics", "expected_value": 4.0, "unit": "p-value", "tolerance": null, "state": "complete", "note": "The threshold the paper applied to its own result, as the paper states it. A run that reproduces the effect is judged against this threshold."}], "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": ["spearman_rho"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: spearman."}, "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": ["GSE144269", "GSE91061", "GSE78220"], "resolved_accessions": ["GSE144269", "GSE91061", "GSE78220"], "statements": ["All data utilized in this study can be downloaded in the public databases. The names, applications, and downloading methods of all datasets are explicitly detailed in the table (Table 1)."], "basis": "The paper names GSE144269, GSE91061, GSE78220 in GEO database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["spearman_rho"], "assets": ["source:pmid:39749665", "data:geo:GSE144269"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE144269"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:44:14Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 23179, "completion_tokens": 1975, "cached_tokens": 264}}, "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:39749665", "type": "paper", "label": "pmid:39749665"}, {"id": "source:pmid:39749665", "type": "manuscript", "label": "PMID 39749665 full text"}, {"id": "data:geo:GSE144269", "type": "dataset", "label": "GEO GSE144269"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39749665", "type": "paper", "label": "pmid:39749665"}, {"id": "source:pmid:39749665", "type": "manuscript", "label": "PMID 39749665 full text"}, {"id": "data:geo:GSE144269", "type": "dataset", "label": "GEO GSE144269"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39749665", "type": "extraction", "used": ["source:pmid:39749665"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE144269", "type": "accession_resolution", "used": ["data:geo:GSE144269"], "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:39749665", "parent_hash": "sha256:40d940771af91c4a61667455ed8f4f169ea8cf2981fbf29b9f59cfe944bd9b49", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE144269 licence not read", "asset:data:geo:GSE144269 not downloaded", "asset:data:geo:GSE78220 licence not read", "asset:data:geo:GSE78220 not downloaded", "asset:data:geo:GSE91061 licence not read", "asset:data:geo:GSE91061 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["spearman_rho"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["We utilized ROC curve to assess the diagnostic capability of continuous variable. The method used for testing comparisons between two independent datasets in this study was the Mann–Whitney U test. All correlation analyses mentioned in this study were conducted using Spearman correlation analysis."], "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":"2026-11-04T01:19:54+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}}}