{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39839508", "kind": "science-record", "revision": 2, "content_hash": "sha256:188fa9857b1c91e006cf3033ab9d035d9c25e88a6e52b13f3c8e5c2ab8ae3e83", "created_at": "2026-11-01T10:25:49Z", "updated_at": "2026-11-01T14:01:33Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Development and validation of a biomarker-based prediction model for metastasis in patients with colorectal cancer: Application of machine learning algorithms.", "doi": "10.1016/j.heliyon.2024.e41443", "pmid": "39839508", "authors": null, "journal": "Heliyon", "year": 2025, "abstract": null, "claims": [{"id": "claim-1", "statement": "the headline numerical result the paper states for its main finding", "kind": "quantitative", "state": "complete", "target": {"value": 0.99, "unit": "auc", "tolerance": null, "source": "chars 1651-1795 of source sha256 ddc20ebfa8efe9bf54f38a60c7ec373a52e5df46db79e7a65d90978dbd9544de"}, "evidence": [{"asset": "source:pmid:39839508", "locator": "chars 1651-1795 of source sha256 ddc20ebfa8efe9bf54f38a60c7ec373a52e5df46db79e7a65d90978dbd9544de", "quote": "The RF model exhibited an accuracy of 0.97, a kappa value of 0.92, and an area under the curve (AUC) of 0.99 in the external validation dataset."}]}], "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:39839508"], "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:39839508", "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:39839508' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39839508", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.heliyon.2024.e41443", "sha256": "sha256:ddc20ebfa8efe9bf54f38a60c7ec373a52e5df46db79e7a65d90978dbd9544de", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.heliyon.2024.e41443", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:39839508:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:eeefb34a6ff75fc671c27272d1ff5328ad4fbcc6a3c510bcc7a0d39942968fa9", "bytes": 1613, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#tbl1", "version": null, "note": "Model performance of five ML algorithms in the internal training dataset.", "structure": {"pmcid": "PMC11748706", "section_index": 10, "section_title": "Development and validation of the model using the internal dataset", "row_count": 18, "column_count": 7}, "table": {"label": "Table 1", "caption": "Model performance of five ML algorithms in the internal training dataset.", "rows": [["Accuracy", "Min", "1st Q", "Median", "Mean", "3rd Q", "Max"], ["glmnet", "0.81 (0.05)", "0.93 (0.02)", "0.96 (0.02)", "0.95 (0.01)", "0.98 (0.03)", "1.00 (0.00)"], ["kNN", "0.85 (0.05)", "0.93 (0.02)", "0.95 (0.00)", "0.95 (0.01)", "1.00 (0.00)", "1.00 (0.00)"], ["RF", "0.88 (0.04)", "0.95 (0.00)", "0.97 (0.03)", "0.97 (0.01)", "1.00 (0.00)", "1.00 (0.00)"], ["SVM", "0.84 (0.04)", "0.94 (0.02)", "0.95 (0.01)", "0.95 (0.01)", "1.00 (0.00)", "1.00 (0.00)"], ["XGBoost", "0.81 (0.04)", "0.91 (0.02)", "0.95 (0.01)", "0.94 (0.01)", "0.98 (0.03)", "1.00 (0.00)"], ["Kappa"], ["glmnet", "0.48 (0.14)", "0.81 (0.05)", "0.88 (0.06)", "0.86 (0.03)", "0.96 (0.06)", "1.00 (0.00)"], ["kNN", "0.54 (0.11)", "0.81 (0.06)", "0.86 (0.00)", "0.87 (0.02)", "1.00 (0.01)", "1.00 (0.00)"], ["RF", "0.65 (0.13)", "0.85 (0.00)", "0.93 (0.07)", "0.91 (0.02)", "1.00 (0.00)", "1.00 (0.00)"], ["SVM", "0.55 (0.09)", "0.82 (0.04)", "0.87 (0.02)", "0.87 (0.03)", "1.00 (0.01)", "1.00 (0.00)"], ["XGBoost", "0.42 (0.11)", "0.74 (0.05)", "0.86 (0.03)", "0.83 (0.02)", "0.95 (0.07)", "1.00 (0.00)"], ["AUC"], ["glmnet"], ["kNN", "0.86 (0.03)", "0.98 (0.01)", "1.00 (0.00)", "0.98 (0.01)", "1.00 (0.00)", "1.00 (0.00)"], ["RF", "0.95 (0.02)", "1.00 (0.01)", "1.00 (0.00)", "0.99 (0.00)", "1.00 (0.00)", "1.00 (0.00)"], ["SVM", "0.92 (0.03)", "0.98 (0.01)", "1.00 (0.00)", "0.99 (0.00)", "1.00 (0.00)", "1.00 (0.00)"], ["XGBoost", "0.94 (0.03)", "1.00 (0.01)", "1.00 (0.00)", "0.99 (0.00)", "1.00 (0.00)", "1.00 (0.00)"]], "row_count": 18, "column_count": 7, "numeric_cells": 86, "header_rows": 1, "locator": "section[10]/table-wrap[1]#tbl1"}}, {"id": "asset:table:pmid:39839508:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:07bdeb3eb9c47e8f6bbadaacf1552907f70c40261c4dd6cb64bea86534922432", "bytes": 1622, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[2]#tbl2", "version": null, "note": "Characteristics of important genes as well as expression patterns according to metastatic and non-metastatic samples CRC.", "structure": {"pmcid": "PMC11748706", "section_index": 10, "section_title": "Development and validation of the model using the internal dataset", "row_count": 17, "column_count": 6}, "table": {"label": "Table 2", "caption": "Characteristics of important genes as well as expression patterns according to metastatic and non-metastatic samples CRC.", "rows": [["Biomarker", "Log FC", "adj.P-value", "Importance score (scaled score)a", "Non-metastatic CRCb (N = 195)", "Metastatic CRCb (N = 67)"], ["MMP3", "−2.67", "3.15E-26", "7.39 (1.00)", "248.31 (274.52)", "31.48 (24.91)"], ["CCDC102B", "1.91", "4.98E-13", "6.56 (0.80)", "9.61 (12.74)", "30.13 (22.60)"], ["CDH2", "1.65", "1.29E-12", "5.21 (0.49)", "17.36 (21.45)", "55.42 (61.83)"], ["VWF", "−1.45", "2.82E-10", "4.48 (0.31)", "236.03 (156.13)", "79.52 (222.18)"], ["MMP1", "−2.79", "6.15E-12", "4.28 (0.27)", "291.50 (557.26)", "20.10 (97.76)"], ["CYP1B1", "1.7", "3.25E-11", "4.27 (0.26)", "27.10 (47.13)", "89.30 (112.83)"], ["DIXDC1", "−1.34", "7.62E-16", "4.25 (0.26)", "71.21 (45.37)", "32.93 (44.20)"], ["LAMC3", "1.15", "5.64E-09", "4.09 (0.22)", "19.45 (26.04)", "45.54 (44.68)"], ["SERPINA1", "1.69", "1.14E-11", "3.99 (0.20)", "581.12 (990.25)", "1626.12 (3186.58)"], ["NKX3-2", "−1.33", "6.63E-12", "3.89 (0.17)", "15.45 (25.86)", "7.45 (4.01)"], ["ALB", "1.61", "3.48E-11", "3.76 (0.14)", "9.16 (16.04)", "27.84 (68.38)"], ["KRT7", "1.13", "3.99E-07", "3.65 (0.12)", "22.77 (19.85)", "42.57 (55.35)"], ["TMEM158", "−1.59", "2.69E-13", "3.61 (0.11)", "183.11 (153.64)", "67.26 (103.20)"], ["GADD45B", "1.04", "6.26E-09", "3.36 (0.05)", "10.14 (14.23)", "25.79 (39.43)"], ["CYP4B1", "1.21", "6.95E-07", "3.33 (0.04)", "3.47 (7.63)", "8.99 (22.39)"], ["SCGB1A1", "1.03", "2.45E-06", "3.15 (0.00)", "23.06 (19.41)", "20.10 (97.76)"]], "row_count": 17, "column_count": 6, "numeric_cells": 86, "header_rows": 1, "locator": "section[10]/table-wrap[2]#tbl2"}}, {"id": "asset:table:pmid:39839508:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:de631f3468def940206671ca353fa7080ac3c70b9be0abf2672e9125961dadaf", "bytes": 813, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[3]#tbl3", "version": null, "note": "Model performance of five machine learning algorithms in the internal validation dataset.", "structure": {"pmcid": "PMC11748706", "section_index": 10, "section_title": "Development and validation of the model using the internal dataset", "row_count": 8, "column_count": 6}, "table": {"label": "Table 3", "caption": "Model performance of five machine learning algorithms in the internal validation dataset.", "rows": [["Performance measure", "ML algorithm"], ["glmnet", "kNN", "RF", "SVM", "XGBoost"], ["Accuracy", "0.93 (0.03)", "0.93 (0.03)", "0.97 (0.02)", "0.92 (0.02)", "0.93 (0.02)"], ["Kappa", "0.82 (0.10)", "0.81 (0.07)", "0.91 (0.05)", "0.80 (0.06)", "0.81 (0.07)"], ["Specificity", "0.96 (0.03)", "0.96 (0.02)", "0.98 (0.01)", "0.96 (0.03)", "0.97 (0.02)"], ["Precision", "0.88 (0.08)", "0.88 (0.05)", "0.95 (0.03)", "0.89 (0.07)", "0.91 (0.06)"], ["Recall", "0.85 (0.10)", "0.84 (0.08)", "0.92 (0.05)", "0.81 (0.07)", "0.82 (0.09)"], ["F1 score", "0.86 (0.07)", "0.86 (0.05)", "0.93 (0.03)", "0.85 (0.04)", "0.85 (0.05)"]], "row_count": 8, "column_count": 6, "numeric_cells": 30, "header_rows": 2, "locator": "section[10]/table-wrap[3]#tbl3"}}], "gaps": ["asset:source:pmid:39839508 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:39839508", "asset:table:pmid:39839508:1", "asset:table:pmid:39839508:2", "asset:table:pmid:39839508:3"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:39839508"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "full-text-reading-v1", "prompt_hash": "18b3142e693698c91e13d0130fae1c40df9be0efe339ab979f2914804462565d", "source_hash": "ddc20ebfa8efe9bf54f38a60c7ec373a52e5df46db79e7a65d90978dbd9544de", "raw_response_sha256": "sha256:4f6c3120775e1bfcb9fbfc5846195dee847ee48045ed6b04ccf3d816749a4bd1", "raw_response_chars": 3388}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "full-text-reading-v1", "prompt_hash": "8776ce498153f7f3811bb98c0d6e5a5ae281d396c2e64d465f375688dda2418b", "source_hash": "ddc20ebfa8efe9bf54f38a60c7ec373a52e5df46db79e7a65d90978dbd9544de", "raw_response_sha256": "sha256:d6c122b511c938ee85aa54ab59113835d6b9b88d3b4d120a52dc309e83bb8827", "raw_response_chars": 62416}], "target_providers": [{"provider": "minimax", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "2fa27f2ada863dcfb283919484eb06f9f597effed0ed296031d9bf0b96789ef8", "source_hash": "ddc20ebfa8efe9bf54f38a60c7ec373a52e5df46db79e7a65d90978dbd9544de", "raw_response": "{\"parent_value\":0.99,\"unit\":\"AUC\",\"evidence\":\"The RF model exhibited an accuracy of 0.97, a kappa value of 0.92, and an area under the curve (AUC) of 0.99 in the external validation dataset.\",\"target_result\":\"The random forest model's external-validation area under the curve was 0.99.\",\"number_stated\":true}", "reading": {"parent_value": 0.99, "unit": "AUC", "evidence": "The RF model exhibited an accuracy of 0.97, a kappa value of 0.92, and an area under the curve (AUC) of 0.99 in the external validation dataset.", "target_result": "The random forest model's external-validation area under the curve was 0.99.", "number_stated": true, "source_locator": "chars 1651-1795 of source sha256 ddc20ebfa8efe9bf54f38a60c7ec373a52e5df46db79e7a65d90978dbd9544de"}, "recorded_at": "2026-10-31T15:21:39.747099+00:00"}, {"provider": "minimax_alt", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "3089b970ced4f88143445b4adb12ea9cf14153a782e5e0391305ef81e90b0720", "source_hash": "ddc20ebfa8efe9bf54f38a60c7ec373a52e5df46db79e7a65d90978dbd9544de", "raw_response": "<think>We need answer JSON object only. Need identify single numerical result replication registered target main finding headline number paper states. Need likely AUC 0.99, perhaps headline numerical result? Need parse instruction carefully: REGISTERED TARGET: \"the headline numerical result the paper states for its main finding\". Need report headline number only, value paper itself states, unit as printed. Evidence exact contiguous quote containing number. Could be RF model external validation with accuracy .97 kappa .92 AUC .99. Which single is headline? Main finding likely AUC 0.99? Need infer benchmark extraction expectation. They ask parent_value perhaps headline numerical result. We need choose likely 0.99, unit maybe \"AUC\" (printed as area under curve (AUC) of 0.99). Evidence full clause: \"The RF model exhibited an accuracy of 0.97, a kappa value of 0.92, and an area under the curve (AUC) of 0.99 in the external validation dataset.\" But report headline number only means parent_value 0.99. Unit string \"AUC\" perhaps. target_result concise says external validation AUC of 0.99. Evidence exact contiguous quote. Could they consider main result as accuracy 0.97? Let's deeply inspect wording.\n\nQuestion generated perhaps designed to extract target numerical value from abstract. Registered target generic. \"single numerical result that a replication of the registered target has to reproduce. Report the headline number only: the value the paper itself states for the registered target, not a value you calculated, converted, averaged or reconstructed. The unit must be the unit the paper prints.\" Registered target: \"the headline numerical result the paper states for its main finding\". In study abstract, final result sentence lists three performance measures. Headline likely AUC of 0.99. Could be accuracy because main model highest accuracy, but headline result often external validation metrics and AUC strongest. Need perhaps target result expected 0.97? Let's understand source likely paper and maybe title/abstract. The \"headline numerical result\" could be 0.99 as AUC. We need ensure unit exactly paper prints. \"area under the curve (AUC)\" perhaps unit is \"AUC\" not unit technically dimensionless. They require unit as paper prints. Could set unit \"AUC\". Evidence exact quote sentence. target_result perhaps \"External-validation AUC of 0.99 for the RF model.\" number_stated true.\n\nCould number be 16 key genes? Main finding is identified 16 key genes. Replication target might reproduce 16 biomarkers rather than performance. Yet \"headline numerical result the paper states for its main finding\" likely intended to select result metric. Let's inspect prompt wording perhaps from a benchmark where target entity is registered by question, and source gives multiple numbers. They want \"single numerical result that a replication ... has to reproduce.\" The registered target is defined abstractly here. Maybe headline number in paper's result is expected based on abstract: \"The RF model exhibited an accuracy of 0.97, a kappa value of 0.92, and an area under the curve (AUC) of 0.99 in external validation dataset.\" They ask single headline numerical result; likely AUC 0.99 because often headline performance metric. They emphasize attribution may be via list / respectively. Perhaps target could have been something like \"the headline numerical result ...\". Need choose.\n\n\"Report the headline number only: the value the paper itself states for the registered target\" Means answer fields parent_value etc. Parent_value likely numeric target value. Unit perhaps \"%\" if accuracy. Source prints accuracy = 0.97 not percent. AUC 0.99 no unit. Their schema requires string unit, could be empty? But if number stated, probably unit \"AUC\". Prompt: \"The unit must be the unit the paper prints.\" Here no physical unit. We can use \"AUC\" as metric label. Evidence whole clause if linked via words naming target. Exact quote can be sentence.\n\nCould target_result state \"The RF model's external-validation area under the curve (AUC) was 0.99.\" That's paraphrase but target_result not evidence. Fine.\n\nNeed JSON valid, no markdown. Ensure evidence exact contiguous. Parent value numeric 0.99.\n\nLet's not rush—could \"headline number\" be \"16 key genes\". Let's inspect abstract flow:\nPurpose.\nMethods.\nResults: Among 22,283 registered genes ... identified 16 key genes ... On internal validation ... metrics. Top five biomarkers ... RF model external validation accuracy .97, kappa .92, AUC .99.\nConclusion.\n\nMain finding is biomarker-based prediction model; headline numerical result perhaps model AUC. Usually when reporting classification model, headline result = AUC 0.99. The prompt singular suggests select one likely final/most salient metric. We need perhaps use exact full clause. We'll answer.\n\nNeed decide unit. \"area under the curve (AUC)\" perhaps unit string could be \"AUC\". The paper prints \"an area under the curve (AUC) of 0.99\", no unit. If unit must be unit paper prints, metric label qualifies. Could put \"AUC\" rather than \"area under the curve (AUC)\". Which exact printed term? \"area under the curve (AUC)\" is printed, but unit should likely \"AUC\". Better unit \"AUC\" because recognized metric. Yet perhaps schema expects empty if dimensionless? Prompt says leave unit empty only if no number. They likely expect \"AUC\" or \"%\". We can state \"AUC\". Evidence sentence exact.\n\n\"target_result\": should perhaps be \"The RF model achieved an AUC of 0.99 in the external validation dataset.\" This is clear. \"headline number only\" means only one number in target_result, but evidence necessarily contains all three numbers due full sentence. Does that violate headline number only? They explicitly ask quote whole clause for attribution; evidence may include multiple numbers. Fine. Could quote narrower exact contiguous fragment: \"an area under the curve (AUC) of 0.99 in the external validation dataset.\" Does that contain target attribution? It doesn't identify RF model, but metric and external validation. To let reader check attribution, whole sentence better. They say \"When that is how the text links them, quote the whole clause so a reader can check the attribution for themselves.\" So full sentence.\n\nCould quote \"The RF model exhibited an accuracy of 0.97, a kappa value of 0.92, and an area under the curve (AUC) of 0.99 in the external validation dataset.\" Exact. Great.\n\nLet's answer JSON only.</think>\n\n{\"parent_value\":0.99,\"unit\":\"AUC\",\"evidence\":\"The RF model exhibited an accuracy of 0.97, a kappa value of 0.92, and an area under the curve (AUC) of 0.99 in the external validation dataset.\",\"target_result\":\"The RF model achieved an AUC of 0.99 in the external validation dataset.\",\"number_stated\":true}", "reading": {"parent_value": 0.99, "unit": "AUC", "evidence": "The RF model exhibited an accuracy of 0.97, a kappa value of 0.92, and an area under the curve (AUC) of 0.99 in the external validation dataset.", "target_result": "The RF model achieved an AUC of 0.99 in the external validation dataset.", "number_stated": true, "source_locator": "chars 1651-1795 of source sha256 ddc20ebfa8efe9bf54f38a60c7ec373a52e5df46db79e7a65d90978dbd9544de"}, "recorded_at": "2026-10-31T15:21:46.855095+00:00"}], "agreement": false, "disagreements": {"analysis_methods": {"minimax": ["differential expression analysis", "redundancy analysis", "recursive feature elimination", "lasso and elastic-net regularized generalized linear model (glmnet)", "k-nearest neighbors (kNN)", "support vector machine (SVM) with Radial Basis Function Kernel", "random forest (RF)", "eXtreme Gradient Boosting (XGBoost)", "10-fold cross-validation with 3 repeats"], "minimax_alt": ["Differential expression analysis using GEO2R", "Benjamini-Hochberg adjustment with a Benjamini-Hochberg adjusted P-value threshold of less than 0.05", "Correlation-based redundancy analysis using the caret findCorrelation function", "Recursive feature elimination using the caret rfFuncs implementation", "10-fold cross-validation with 3 repeats and 10 repetitions of RFE", "Lasso and elastic-net regularized generalized linear model (glmnet)", "K-nearest neighbors (kNN)", "Support vector machine (SVM) with Radial Basis Function Kernel", "Random forest (RF)", "eXtreme Gradient Boosting (XGBoost)", "External validation on GSE41568"], "decisive": false}, "statistical_method": {"minimax": "random forest (RF)", "minimax_alt": "Random forest (RF) machine-learning model", "decisive": true}}, "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": []}}, {"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:814948aed846d0c278c3b4726459bf778ebebe001e91e657adf8705492c4a084", "type": "sep_package", "label": "SEP v1 package for pmid:39839508"}], "activities": [{"id": "activity:conversion:pmid:39839508", "type": "conversion", "used": ["package:814948aed846d0c278c3b4726459bf778ebebe001e91e657adf8705492c4a084"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax", "type": "model", "label": "minimax"}, {"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:39839508", "parent_hash": "sha256:39dbd4bba97fef67d3caad48123565d6bc151027eb84530785056db2b3111456", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:39839508 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:39839508' 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":"2026-11-04T03:14:02+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}}}