{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40980067", "kind": "science-record", "revision": 2, "content_hash": "sha256:2d76a3bd07279f90bea8144a37c17ce2b990634ca6ae3c254df73fdbefaf0064", "created_at": "2026-11-01T10:25:53Z", "updated_at": "2026-11-01T14:01:48Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Prognostic significance and pathogenesis of RFC3 gene expression in diffuse large B-cell lymphoma.", "doi": "10.7717/peerj.20001", "pmid": "40980067", "authors": null, "journal": "PeerJ", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "qualitative", "state": "blocked", "target": {"value": null, "unit": null, "tolerance": null, "source": null}, "evidence": []}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the headline numerical result the paper states for its main finding", "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate and its interval from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The number a replication must land on, and the sentence it came from.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:40980067"], "outputs": ["the published estimate, its unit and its interval"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data behind the published result", "kind": "data-preparation", "state": "blocked", "blocked_on": "data:not_downloaded", "description": "The published result cannot be recomputed without the data the paper analysed.", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the source data with its provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the analysis programme", "kind": "analysis", "state": "blocked", "blocked_on": "no owned computational capability is bound to this experiment", "description": "Re-run the paper's analysis on the source data and produce the registered result. | SEP input not carried into the asset list: materials:the source data behind the published result in pmid:40980067", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": ["the registered result"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40980067' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40980067", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.20001", "sha256": "sha256:cde5d28e081f90f31ad92af084dfe3db7e7821d7c9aa9d92c9072c4ea55a9454", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.20001", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:40980067:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:66e48147b5be4aa25bd01b4ff087fcd40e8a2e2355c5dd08611456b0ce27d4fa", "bytes": 540, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#table-1", "version": null, "note": "Data included in present analysis.", "structure": {"pmcid": "PMC12447951", "section_index": 3, "section_title": "Data collection", "row_count": 8, "column_count": 4}, "table": {"label": "Table 1", "caption": "Data included in present analysis.", "rows": [["Dataset", "Platform", "Cases included", "Details"], ["GSE181063", "GPL14951", "732", "DLBCL"], ["GSE10846", "GPL570", "414", "DLBCL"], ["GSE32918", "GPL14951", "167", "DLBCL"], ["GSE31312", "GPL570", "470", "DLBCL"], ["GSE32018", "GPL6480", "29", "22 DLBCL/7 Lymph-node"], ["GSE12453", "GPL570", "21", "11 DLBCL/10 B-cells"], ["Samples collected", "/", "23", "15DLBCL/8 Lymph-node"]], "row_count": 8, "column_count": 4, "numeric_cells": 22, "header_rows": 1, "locator": "section[3]/table-wrap[1]#table-1"}}, {"id": "asset:table:pmid:40980067:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:53f966791e4bfb2ab1fc6065284ee9779399bde18676b7b7a0a991bb6a1d8db3", "bytes": 1433, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[16]/table-wrap[1]#table-2", "version": null, "note": "Correlation between RFC3 expression and clinicopathological features in DLBCL.", "structure": {"pmcid": "PMC12447951", "section_index": 16, "section_title": "Elevated RFC3 expression correlates with aggressive clinical features in DLBCL", "row_count": 30, "column_count": 5}, "table": {"label": "Table 2", "caption": "Correlation between RFC3 expression and clinicopathological features in DLBCL.", "rows": [["Characteristic", "Low expression of RFC3N (%)", "High expression of RFC3N (%)", "χ2", "P value"], ["COO", "", "", "63.37", "<0.001*"], ["UNC", "116 (20.6)", "10 (5.9)", "", ""], ["ABC", "171 (30.4)", "42 (24.7)", "", ""], ["GCB", "256 (45.6)", "86 (50.6)", "", ""], ["MHG", "19 (3.4)", "32 (18.8)", "", ""], ["Age", "", "", "2.45", "0.117"], ["≦60y", "174 (31)", "42 (24.7)", "", ""], [">60y", "388 (69)", "128 (75.3)", "", ""], ["Sex", "", "", "0.11", "0.745"], ["Female", "273 (48.6)", "85 (50)", "", ""], ["Male", "289 (51.4)", "85 (50)", "", ""], ["ECOG", "", "", "4.85", "0.028*"], ["ECOG ≦1", "425 (82.2)", "115 (74.2)", "", ""], ["ECOG >1", "92 (17.8)", "40 (25.8)", "", ""], ["Stage", "", "", "5.46", "0.019*"], ["Stage I–II", "202 (40.6)", "45 (30.0)", "", ""], ["Stage III–IV", "296 (59.4)", "105 (70.0)", "", ""], ["IPI", "", "", "25.27", "<0.001*"], ["Low-Risk", "270 (62.8)", "45 (37.2)", "", ""], ["High-Risk", "160 (37.2)", "76 (62.8)", "", ""], ["LDH", "", "", "8.62", "0.009*"], ["Normal", "239 (47.1)", "50 33.6)", "", ""], ["Raised", "268 (52.9)", "99 (66.4)", "", ""], ["Bs", "", "", "2.76", "0.096"], ["Not", "359 (63.9)", "96 (56.8)", "", ""], ["Have", "203 (36.1)", "73 (43.2)", "", ""], ["Extranodal", "", "", "4.28", "0.038*"], ["<2", "189 (83.6)", "50 (72.5)", "", ""], ["≥2", "37 (16.4)", "19 (27.5)", "", ""]], "row_count": 30, "column_count": 5, "numeric_cells": 65, "header_rows": 1, "locator": "section[16]/table-wrap[1]#table-2"}}, {"id": "asset:table:pmid:40980067:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3910bff4230e5a56245d8556b8f445f25112e4972b93e12f5c54b49aad8c3631", "bytes": 2046, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#table-3", "version": null, "note": "Results of the enrichment analysis of RFC3 expression in DLBCL.", "structure": {"pmcid": "PMC12447951", "section_index": 17, "section_title": "RFC3 plays a role in various tumor-related signaling pathways in DLBCL", "row_count": 27, "column_count": 5}, "table": {"label": "Table 3", "caption": "Results of the enrichment analysis of RFC3 expression in DLBCL.", "rows": [["", "setSize", "NES", "p value", "q value"], ["HALLMARK_E2F_TARGETS", "182", "4.1", "1.00E−10", "2.42E−10"], ["HALLMARK_MYC_TARGETS_V1", "185", "4.01", "1.00E−10", "2.42E−10"], ["HALLMARK_G2M_CHECKPOINT", "181", "3.79", "1.00E−10", "2.42E−10"], ["HALLMARK_OXIDATIVE_PHOSPHORYLATION", "179", "3.5", "1.00E−10", "2.42E−10"], ["HALLMARK_MTORC1_SIGNALING", "190", "3.3", "1.00E−10", "2.42E−10"], ["HALLMARK_DNA_REPAIR", "137", "3.3", "1.00E−10", "2.42E−10"], ["HALLMARK_MYC_TARGETS_V2", "56", "3.27", "1.00E−10", "2.42E−10"], ["HALLMARK_UNFOLDED_PROTEIN_RESPONSE", "106", "3.04", "1.00E−10", "2.42E−10"], ["HALLMARK_MITOTIC_SPINDLE", "194", "2.97", "1.00E−10", "2.42E−10"], ["HALLMARK_FATTY_ACID_METABOLISM", "151", "2.38", "4.08E−10", "8.98E−10"], ["HALLMARK_REACTIVE_OXYGEN_SPECIES_PATHWAY", "44", "2.29", "3.28E−06", "5.68E−06"], ["HALLMARK_PROTEIN_SECRETION", "95", "2.21", "1.46E−06", "2.71E−06"], ["HALLMARK_ADIPOGENESIS", "186", "2.08", "8.89E−08", "1.79E−07"], ["HALLMARK_PEROXISOME", "99", "2.07", "2.70E−05", "4.09E−05"], ["HALLMARK_CHOLESTEROL_HOMEOSTASIS", "70", "1.98", "9.92E−05", "0.000123"], ["HALLMARK_PI3K_AKT_MTOR_SIGNALING", "103", "1.93", "7.31E−05", "9.83E−05"], ["HALLMARK_GLYCOLYSIS", "193", "1.89", "9.78E−06", "1.58E−05"], ["HALLMARK_UV_RESPONSE_UP", "151", "1.88", "4.12E−05", "5.86E−05"], ["HALLMARK_ANDROGEN_RESPONSE", "96", "1.65", "0.006425", "0.006763"], ["HALLMARK_APOPTOSIS", "158", "1.49", "0.013551", "0.012619"], ["HALLMARK_P53_PATHWAY", "187", "1.48", "0.006792", "0.006851"], ["HALLMARK_INFLAMMATORY_RESPONSE", "197", "−1.37", "0.007781", "0.007535"], ["HALLMARK_EPITHELIAL_MESENCHYMAL_TRANSITION", "195", "−1.67", "0.000212", "0.000245"], ["HALLMARK_MYOGENESIS", "194", "−1.72", "0.000102", "0.000123"], ["HALLMARK_COAGULATION", "135", "−1.74", "0.000233", "0.000257"], ["HALLMARK_KRAS_SIGNALING_DN", "187", "−2.36", "1.00E−10", "2.42E−10"]], "row_count": 27, "column_count": 5, "numeric_cells": 105, "header_rows": 1, "locator": "section[17]/table-wrap[1]#table-3"}}], "gaps": ["asset:source:pmid:40980067 not verified"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "targets"]}, "capability": {"state": "absent", "requirements": [], "gaps": ["capability"]}, "readiness": {"state": "partial", "tier": null, "blocking_axis": null, "blocked_on": null, "axes": {}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:40980067", "asset:table:pmid:40980067:1", "asset:table:pmid:40980067:2", "asset:table:pmid:40980067:3"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:40980067"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "acabb31330c454bf5f4aca0c86c6cbfcd3128cdda28179e50291d82c005ee954", "source_hash": "cde5d28e081f90f31ad92af084dfe3db7e7821d7c9aa9d92c9072c4ea55a9454", "raw_response_sha256": "sha256:dff3c381587b991b5d11c3da80ea492ce13934d5ed17429ecc7cae4f62ecc1a2", "raw_response_chars": 72539}], "target_providers": [], "agreement": false, "disagreements": [], "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["work_type", "number_stated", "parent_value", "unit"]}, "blinded": true}, "human_critique": {"status": "not_run", "reviewer": null, "signed_at": null, "conflict_checked": false, "commentary": null}, "stages": [{"key": "target_materials", "status": "pending", "reason": null, "evidence": null}, {"key": "independent_readings", "status": "blocked", "reason": "The independent readings are incomplete or disagree; the source evidence must resolve the difference.", "evidence": {"provider_errors": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "reason": "a quoted span is absent from the supplied text", "raw_response": "{\n  \"target_result\": \"The headline finding is that RFC3 expression was significantly upregulated in DLBCL and that high RFC3 expression was associated with poor prognosis; no numerical effect size or numerical prognostic result is reported in the supplied text.\",\n  \"work_type\": \"analysis_plus_physical_validation\",\n  \"physical_methods\": [\n    \"Immunohistochemistry (IHC) validation of RFC3 expression in DLBCL samples\"\n  ],\n  \"analysis_methods\": [\n    \"Multi-omics analysis\",\n    \"Kaplan–Meier survival analysis\",\n    \"Chi-square test\",\n    \"Gene Set Enrichment Analysis (GSEA)\",\n    \"Immune infiltration analysis using the IOBR package\",\n    \"Single-sample gene set enrichment analysis (ssGSEA)\",\n    \"Spearman correlation analysis\",\n    \"IMvigor210 immunotherapy-response prediction using the IMvigor210CoreBiologics R package\",\n    \"Drug-susceptibility analysis using oncoPredict\",\n    \"Pan-cancer analysis using easyTCGA and TCGAplot\",\n    \"Cox proportional hazards model\"\n  ],\n  \"statistical_method\": \"Kaplan–Meier method\",\n  \"method_evidence\": \"Survival analysis was conducted using the Kaplan–Meier method.\",\n  \"repositories\": [\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE181063\",\n      \"data_description\": \"Multi-omics data used for the RFC3 analyses; GSE181063 was specifically used for immune infiltration analyses based on the tumor immune microenvironment.\",\n      \"evidence\": \"Multi-omics analyses were performed using data extracted from the Gene Expression Omnibus (GEO) project (GSE181063, GSE10846, GSE32918, GSE31312, GSE32018, and GSE12453) and The Cancer Genome Atlas (TCGA). The relationship between RFC3 expression and the tumor immune microenvironment (TIME) in DLBCL was investigated using immune infiltration analyses based on the GSE181063 dataset.\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE10846\",\n      \"data_description\": \"Multi-omics data used for the RFC3 analyses.\",\n      \"evidence\": \"Multi-omics analyses were performed using data extracted from the Gene Expression Omnibus (GEO) project (GSE181063, GSE10846, GSE32918, GSE31312, GSE32018, and GSE12453) and The Cancer Genome Atlas (TCGA).\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE32918\",\n      \"data_description\": \"Multi-omics data used for the RFC3 analyses.\",\n      \"evidence\": \"Multi-omics analyses were performed using data extracted from the Gene Expression Omnibus (GEO) project (GSE181063, GSE10846, GSE32918, GSE31312, GSE32018, and GSE12453) and The Cancer Genome Atlas (TCGA).\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE31312\",\n      \"data_description\": \"Multi-omics data used for the RFC3 analyses.\",\n      \"evidence\": \"Multi-omics analyses were performed using data extracted from the Gene Expression Omnibus (GEO) project (GSE181063, GSE10846, GSE32918, GSE31312, GSE32018, and GSE12453) and The Cancer Genome Atlas (TCGA).\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE32018\",\n      \"data_description\": \"Multi-omics data used for the RFC3 analyses.\",\n      \"evidence\": \"Multi-omics analyses were performed using data extracted from the Gene Expression Omnibus (GEO) project (GSE181063, GSE10846, GSE32918, GSE31312, GSE32018, and GSE12453) and The Cancer Genome Atlas (TCGA).\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"Gene Expression Omnibus (GEO)\",\n      \"accession\": \"GSE12453\",\n      \"data_description\": \"Multi-omics data used for the RFC3 analyses.\",\n      \"evidence\": \"Multi-omics analyses were performed using data extracted from the Gene Expression Omnibus (GEO) project (GSE181063, GSE10846, GSE32918, GSE31312, GSE32018, and GSE12453) and The Cancer Genome Atlas (TCGA).\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"The Cancer Genome Atlas (TCGA)\",\n      \"accession\": \"unknown\",\n      \"data_description\": \"Multi-omics data used for the RFC3 analyses, including pan-cancer expression and prognostic analyses.\",\n      \"evidence\": \"Multi-omics analyses were performed using data extracted from the Gene Expression Omnibus (GEO) project (GSE181063, GSE10846, GSE32918, GSE31312, GSE32018, and GSE12453) and The Cancer Genome Atlas (TCGA).\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"IMvigor210 dataset\",\n      \"accession\": \"unknown\",\n      \"data_description\": \"Transcriptomic and clinical data from patients with urothelial carcinoma treated with anti–PD-L1 therapy, used to assess associations between RFC3 expression and immunotherapy outcomes.\",\n      \"evidence\": \"The immunotherapy response was predicted using the IMvigor210 cohort through the IMvigor210CoreBiologics R package (Nickles & Bourgon, 2019). This dataset includes transcriptomic and clinical data from patients with urothelial carcinoma treated with anti–PD-L1 therapy, allowing us to assess potential associations between RFC3 expression and immunotherapy outcomes.\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"Genomics of Drug Sensitivity in Cancer (GDSC)\",\n      \"accession\": \"version 1 and version 2\",\n      \"data_description\": \"Pharmacogenomic profiles of cancer cell lines exposed to therapeutic agents, used to analyze the relationship between RFC3 expression and drug sensitivity.\",\n      \"evidence\": \"For this analysis, we obtained drug response data from the Genomics of Drug Sensitivity in Cancer (GDSC) data version 1 and 2 and the Cancer Therapeutics Response Portal, version 2 (CTRP2). These datasets include pharmacogenomic profiles of cancer cell lines exposed to a range of therapeutic agents for different RFC3 expression levels.\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"Cancer Therapeutics Response Portal\",\n      \"accession\": \"CTRP2\",\n      \"data_description\": \"Pharmacogenomic profiles of cancer cell lines exposed to a range of therapeutic agents, used to analyze the relationship between RFC3 expression and drug sensitivity.\",\n      \"evidence\": \"For this analysis, we obtained drug response data from the Genomics of Drug Sensitivity in Cancer (GDSC) data version 1 and 2 and the Cancer Therapeutics Response Portal, version 2 (CTRP2). These datasets include pharmacogenomic profiles of cancer cell lines exposed to a range of therapeutic agents for different RFC3 expression levels.\",\n      \"publicly_downloadable\": false\n    },\n    {\n      \"repository\": \"Supplemental Files\",\n      \"accession\": \"unknown\",\n      \"data_description\": \"Raw data underlying the study.\",\n      \"evidence\": \"The raw data is available in the Supplemental Files.\",\n      \"publicly_downloadable\": false\n    }\n  ],\n  \"availability_statement\": \"The raw data is available in the Supplemental Files.\",\n  \"data_on_request\": false,\n  \"source_claims\": [\n    \"RFC3 expression was significantly upregulated in DLBCL.\",\n    \"High RFC3 expression was closely associated with poor prognosis, adverse clinical features, and adverse tumor microenvironment characteristics in DLBCL patients.\",\n    \"RFC3 expression was validated via immunohistochemistry (IHC) in DLBCL samples.\",\n    \"Survival analysis was conducted using the Kaplan–Meier method.\",\n    \"The chi-square test was used to assess the association between RFC3 expression and clinical characteristics of DLBCL.\",\n    \"Gene Set Enrichment Analysis (GSEA) was employed to identify tumor signaling pathways associated with RFC3.\",\n    \"Elevated RFC3 expression is a negative prognostic indicator in DLBCL.\",\n    \"The raw data is available in the Supplemental Files.\"\n  ],\n  \"missing_information\": [\n    \"The supplied text does not report a numerical value for the headline RFC3 result, such as expression fold change, hazard ratio, log-rank P value, or survival difference.\",\n    \"The TCGA accession is not provided.\",\n    \"The IMvigor210 accession is not provided.\",\n    \"The paper does not explicitly state that the repositories or Supplemental Files can be downloaded without an application, embargo, or request.\"\n  ],\n  \"evidence_spans\": [\n    \"Multi-omics analyses were performed using data extracted from the Gene Expression Omnibus (GEO) project (GSE181063, GSE10846, GSE32918, GSE31312, GSE32018, and GSE12453) and The Cancer Genome Atlas (TCGA).\",\n    \"RFC3 expression was validated via immunohistochemistry (IHC) in DLBCL samples.\",\n    \"Survival analysis was conducted using the Kaplan–Meier method.\",\n    \"The chi-square test was used to assess the association between RFC3 expression and clinical characteristics of DLBCL.\",\n    \"Gene Set Enrichment Analysis (GSEA) was employed to identify tumor signaling pathways associated with RFC3.\",\n    \"RFC3 expression was significantly upregulated in DLBCL.\",\n    \"High RFC3 expression was closely associated with poor prognosis, adverse clinical features, and adverse tumor microenvironment characteristics in DLBCL patients.\",\n    \"The immunotherapy response was predicted using the IMvigor210 cohort through the IMvigor210CoreBiologics R package (Nickles & Bourgon, 2019).\",\n    \"For this analysis, we obtained drug response data from the Genomics of Drug Sensitivity in Cancer (GDSC) data version 1 and 2 and the Cancer Therapeutics Response Portal, version 2 (CTRP2).\",\n    \"The raw data is available in the Supplemental Files.\"\n  ]\n}"}, {"provider": "minimax", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}, {"provider": "minimax_alt", "model": null, "reason": "HTTP Error 429: Too Many Requests", "raw_response": null}]}}, {"key": "source_resolution", "status": "pending", "reason": null, "evidence": null}, {"key": "protocol_reconstruction", "status": "pending", "reason": null, "evidence": null}, {"key": "control_execution", "status": "pending", "reason": null, "evidence": null}, {"key": "control_comparison", "status": "pending", "reason": null, "evidence": null}, {"key": "publication", "status": "pending", "reason": null, "evidence": null}], "gaps": ["review.human_critique", "review.machine_critique.blocked"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:ba1da03396d81bf7f3fb4fd364a851c63855c568b328d291daf731ab845a576c", "type": "sep_package", "label": "SEP v1 package for pmid:40980067"}], "activities": [{"id": "activity:conversion:pmid:40980067", "type": "conversion", "used": ["package:ba1da03396d81bf7f3fb4fd364a851c63855c568b328d291daf731ab845a576c"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax_alt", "type": "model", "label": "minimax_alt"}, {"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}], "source_run_id": "run-20261023T122449232913", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:40980067", "parent_hash": "sha256:9b72666121706692b7d6c15e8b13c5bd09342634ff0be702566b524bc7730540", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:40980067 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:run_analysis blocked on no owned computational capability is bound to this experiment", "step:run_analysis input 'materials:the source data behind the published result in pmid:40980067' does not resolve to a declared asset", "targets"]},"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":"2026-11-04T03:14:04+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}