{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34490121", "kind": "science-record", "revision": 2, "content_hash": "sha256:c8aeeae752d7cb35bb62083e6a5aac9587e0320e45a2501c843a21f368e84b78", "created_at": "2026-11-01T10:25:48Z", "updated_at": "2026-11-01T14:01:31Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Overall Survival Prediction for Gliomas Using a Novel Compound Approach", "doi": "10.3389/fonc.2021.724191", "pmid": "34490121", "authors": null, "journal": "Frontiers in Oncology", "year": 2021, "abstract": null, "claims": [{"id": "claim-1", "statement": "the root mean squared error of the survival prediction task on the BraTS 2019 and BraTS 2020 datasets", "kind": "quantitative", "state": "complete", "target": {"value": 311.5, "unit": "days", "tolerance": null, "source": "chars 1455-1588 of source sha256 534e1cfbb5511144bb862b745d1447089adf15edb21fc9ff3553adc2210f414c"}, "evidence": [{"asset": "source:pmid:34490121", "locator": "chars 1455-1588 of source sha256 534e1cfbb5511144bb862b745d1447089adf15edb21fc9ff3553adc2210f414c", "quote": "The average Dice of brain tumor segmentation tasks up to 79% and the average RMSE of the survival predictive task is as low as 311.5."}]}], "gaps": ["abstract", "authors"]}, "experiment": {"state": "partial", "objective": "the root mean squared error of the survival prediction task on the BraTS 2019 and BraTS 2020 datasets", "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:34490121"], "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": "method:image_quantification_segmentation", "description": "Re-run the paper's analysis on the source data and produce the registered result.", "duration_hours": null, "parameters": {}, "inputs": ["materials:the source data behind pmid:34490121, at the location the paper names"], "outputs": ["the registered result"], "instruments": [], "reagents": []}, {"id": "provide_capability_bench_workcell", "order": 4, "name": "Provide General bench workcell (liquid transfer, plate handling, incubation)", "kind": "computational", "state": "blocked", "blocked_on": "instrument not yet purchased", "description": "Make this capability available to the experiment: amplicon_seq, animal_model, apoptosis_assay, cell_culture, cell_imaging, chip_seq, clinical_cohort, clinical_trial, elisa, flow_cytometry, ihc, image_quantification, mass_spectrometry, methylation_array, microarray, qpcr, rna_seq, transfection, western_blot", "duration_hours": null, "parameters": {}, "inputs": [], "outputs": [], "instruments": [], "reagents": []}], "materials": ["the source data behind pmid:34490121, at the location the paper names", "the analysis programme that recomputes the published estimate"], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:obtain_source_data blocked on data:not_downloaded", "step:provide_capability_bench_workcell blocked on instrument not yet purchased", "step:run_analysis blocked on method:image_quantification_segmentation"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34490121", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fonc.2021.724191", "sha256": "sha256:534e1cfbb5511144bb862b745d1447089adf15edb21fc9ff3553adc2210f414c", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fonc.2021.724191", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "materials:the source data behind pmid:34490121, at the location the paper names", "role": "raw", "format": "html", "media_type": "application/octet-stream", "uri": "https://www.med.upenn.edu/cbica/brats2020/data.html", "sha256": null, "bytes": null, "access": "unknown", "state": "declared", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the source data behind pmid:34490121, at the location the paper names", "structure": {"material_kind": "dataset", "access_state": "named_not_verified"}}, {"id": "materials:the analysis programme that recomputes the published estimate", "role": "code", "format": "unknown", "media_type": "application/octet-stream", "uri": null, "sha256": null, "bytes": null, "access": "unknown", "state": "unavailable", "reader": null, "reader_status": "unknown", "identifier": null, "version": null, "note": "the analysis programme that recomputes the published estimate", "structure": {"material_kind": "code", "access_state": "absent"}}, {"id": "data:availability", "role": "raw", "format": "html", "media_type": "application/octet-stream", "uri": "https://www.med.upenn.edu/cbica/brats2020/data.html", "sha256": null, "bytes": null, "access": "open", "state": "declared", "reader": null, "reader_status": "unknown", "identifier": "https://www.med.upenn.edu/cbica/brats2020/data.html", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.med.upenn.edu/cbica/brats2020/data.html.", "structure": {"access_route": "repository_accession", "location": "section [data-availability]: Data Availability Statement"}}, {"id": "asset:table:pmid:34490121:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d0bf53748ae8e0c02651a59a992a2994bb5cfc31c2d7a549f86170a9c4b1e537", "bytes": 2841, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T1", "version": null, "note": "Types and contents of extracted features.", "structure": {"pmcid": "PMC8416476", "section_index": 13, "section_title": "Radiological Feature Extraction", "row_count": 8, "column_count": 2}, "table": {"label": "Table 1", "caption": "Types and contents of extracted features.", "rows": [["Feature Category", "Name of the features"], ["First Order Statistic", "Energy, Total Energy, Entropy, Minimum, 10th percentile, 90th percentile, Maximum, Mean, Median, Interquartile Range, Range, Mean Absolute Deviation, Robust Mean Absolute Deviation, Root Mean Squared, Standard Deviation, Skewness, Kurtosis, Variance, Uniformity."], ["Shape", "Mesh Volume, Voxel Volume, Surface Area, Surface Area to Volume ratio, Sphericity, Compactness 1, Compactness 2, Spherical Disproportion, Maximum 3D diameter, Maximum 2D diameter (Slice), Maximum 2D diameter (Column), Maximum 2D diameter (Row), Major Axis Length, Minor Axis Length, Least Axis Length, Elongation, Flatness."], ["GLCM", "Autocorrelation, Joint Average, Cluster Prominence, Cluster Shade, Cluster Tendency, Contrast, Correlation, Difference Average, Difference Entropy, Difference Variance, Joint Energy, Joint Entropy, Informational Measure of Correlation, Informational Measure of Correlation, Inverse Difference Moment, Maximal Correlation Coefficient, Inverse Difference Moment Normalized, Inverse Difference, Inverse Difference Normalized, Inverse Variance, Maximum Probability, Sum Average, Sum Entropy, Sum of Squares."], ["GLRLM", "Short Run Emphasis, Long Run Emphasis, Gray Level Non Uniformity, Gray Level Non-Uniformity Normalized, Run Length Non-Uniformity, Run Length Non-Uniformity Normalized, Run Percentage, Gray Level Variance, Run Variance, Run Entropy, Low Gray Level Run Emphasis, High Gray Level Run Emphasis, Short Run Low Gray Level Emphasis, Short Run High Gray Level Emphasis, Long Run Low Gray Level Emphasis, Long Run High Gray Level Emphasis."], ["GLSZM", "Small Area Emphasis, Large Area Emphasis, Gray Level Non Uniformity, Gray Level Non-Uniformity Normalized, Size Zone Non-Uniformity, Size-Zone Non-Uniformity Normalized, Zone Percentage, Gray Level Variance, Zone Variance, Zone Entropy, Low Gray Level Zone Emphasis, High Gray Level Zone Emphasis, Small Area Low Gray Level Emphasis, Small Area High Gray Level Emphasis, Large Area Low Gray Level Emphasis, Large Area High Gray Level Emphasis."], ["GLDM", "Small Dependence Emphasis, Large Dependence Emphasis, Gray Level Non-Uniformity, Gray Level Non-Uniformity Normalized, Dependence Non-Uniformity, Dependence Non-Uniformity Normalized, Gray Level Variance, Dependence Variance, Dependence Entropy, Dependence Percentage, Low Gray Level Emphasis, High Gray Level Emphasis, Small Dependence Low Gray Level Emphasis, Small Dependence High Gray Level Emphasis, Large Dependence Low Gray Level Emphasis, Large Dependence High Gray Level Emphasis."], ["NGTDM", "Coarseness, Contrast, Busyness, Complexity, Strength."]], "row_count": 8, "column_count": 2, "numeric_cells": 2, "header_rows": 1, "locator": "section[13]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:34490121:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:f408e34a4f01dba51422b6f1c3e50e59fe62d9532b770bcc89a20879c1742205", "bytes": 531, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[1]#T2", "version": null, "note": "Segmentation results of different models for BraTS 2019 and BraTS 2020.", "structure": {"pmcid": "PMC8416476", "section_index": 20, "section_title": "Segmentation Result", "row_count": 4, "column_count": 13}, "table": {"label": "Table 2", "caption": "Segmentation results of different models for BraTS 2019 and BraTS 2020.", "rows": [["", "Dice", "Sensitivity", "Specificity", "Hausdorff95"], ["", "ET", "WT", "TC", "ET", "WT", "TC", "ET", "WT", "TC", "ET", "WT", "TC"], ["BraTS2019", "0.70", "0.87", "0.74", "0.73", "0.87", "0.70", "0.99", "0.99", "0.99", "5.7", "7.4", "9.8"], ["BraTS2020", "0.73", "0.88", "0.79", "0.77", "0.89", "0.82", "0.99", "0.99", "0.99", "36.9", "6.5", "10.0"]], "row_count": 4, "column_count": 13, "numeric_cells": 27, "header_rows": 2, "locator": "section[20]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:34490121:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:5da8427cbfd174ef8898fa27c153aff046af8f3f4d866105d596f0ca3347b244", "bytes": 743, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[20]/table-wrap[2]#T3", "version": null, "note": "Segmentation results of ablation experiments on the BraTS 2020 dataset.", "structure": {"pmcid": "PMC8416476", "section_index": 20, "section_title": "Segmentation Result", "row_count": 6, "column_count": 13}, "table": {"label": "Table 3", "caption": "Segmentation results of ablation experiments on the BraTS 2020 dataset.", "rows": [["Segmentation", "Dice", "Sensitivity", "Specificity", "Hausdorff95"], ["Model", "ET", "WT", "TC", "ET", "WT", "TC", "ET", "WT", "TC", "ET", "WT", "TC"], ["NL-VNet", "0.68", "0.83", "0.74", "0.78", "0.90", "0.78", "0.99", "0.99", "0.99", "44.66", "11.16", "15.38"], ["SE-VNet", "0.72", "0.88", "0.78", "0.75", "0.88", "0.79", "0.99", "0.99", "0.99", "40.76", "6.94", "12.46"], ["VNet", "0.65", "0.86", "0.76", "0.75", "0.89", "0.84", "0.99", "0.99", "0.99", "55.04", "9.21", "13.28"], ["CNN", "0.69", "0.86", "0.74", "0.70", "0.87", "0.75", "0.99", "0.99", "0.99", "52.88", "12.07", "18.02"]], "row_count": 6, "column_count": 13, "numeric_cells": 49, "header_rows": 2, "locator": "section[20]/table-wrap[2]#T3"}}, {"id": "asset:table:pmid:34490121:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6ccba84fe295fcea43784d1d5e9bb60cf51d16a8cf35873d2a5f3e006cf29aa5", "bytes": 327, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[21]/table-wrap[1]#T4", "version": null, "note": "The survival prediction result of BraTS 2019 and BraTS 2020.", "structure": {"pmcid": "PMC8416476", "section_index": 21, "section_title": "Overall Survival Prediction Results", "row_count": 3, "column_count": 4}, "table": {"label": "Table 4", "caption": "The survival prediction result of BraTS 2019 and BraTS 2020.", "rows": [["Dataset", "MSE", "MAE", "RMSE"], ["BraTS 2019", "96470.98", "229.07", "306.78"], ["BraTS 2020", "100053.08", "240.05", "316.31"]], "row_count": 3, "column_count": 4, "numeric_cells": 8, "header_rows": 1, "locator": "section[21]/table-wrap[1]#T4"}}, {"id": "asset:table:pmid:34490121:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:377f3347f2e2d8894d177a134eff363616d823f6ed1ab472f7742da2d2482778", "bytes": 668, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[21]/table-wrap[2]#T5", "version": null, "note": "Survival prediction results of different types of feature on BraTS 2020.", "structure": {"pmcid": "PMC8416476", "section_index": 21, "section_title": "Overall Survival Prediction Results", "row_count": 9, "column_count": 5}, "table": {"label": "Table 5", "caption": "Survival prediction results of different types of feature on BraTS 2020.", "rows": [["", "Method", "MSE", "MAE", "RMSE"], ["Mask", "CNN+ Radiology+ Clinical", "87679.85", "225.59", "288.84"], ["Radiology+ Clinical", "88899.18", "228.04", "292.25"], ["CNN (RF)", "91838.87", "235.86", "297.16"], ["", "CNN(DL)", "113472.38", "257.71", "336.86"], ["Predict", "CNN+ Radiology+ Clinical", "100053.08", "240.05", "316.31"], ["Radiology+ Clinical", "162904.10", "284.54", "392.51"], ["CNN(RF)", "153998.46", "284.13", "378.85"], ["", "CNN(DL)", "136770.59", "269.37", "358.92"]], "row_count": 9, "column_count": 5, "numeric_cells": 24, "header_rows": 1, "locator": "section[21]/table-wrap[2]#T5"}}, {"id": "asset:table:pmid:34490121:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4948f31069fa61fd0e58fc3c290e3b255150855da74571e0d0546986284bb307", "bytes": 651, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[21]/table-wrap[3]#T6", "version": null, "note": "Survival prediction results of different radiological features on BraTS 2020.", "structure": {"pmcid": "PMC8416476", "section_index": 21, "section_title": "Overall Survival Prediction Results", "row_count": 9, "column_count": 5}, "table": {"label": "Table 6", "caption": "Survival prediction results of different radiological features on BraTS 2020.", "rows": [["", "Method", "MSE", "MAE", "RMSE"], ["Mask", "Original+ Clinical", "92542.55", "233.08", "297.83"], ["Wavelet+ Clinical", "89551.18", "236.87", "296.02"], ["Original", "95207.94", "235.46", "301.94"], ["Wavelet", "88840.27", "236.17", "294.93"], ["Predict", "Original+ Clinical", "158230.24", "280.82", "389.52"], ["Wavelet+ Clinical", "167600.90", "292.26", "400.93"], ["Original", "157355.79", "279.59", "388.28"], ["Wavelet", "167466.49", "292.26", "401.19"]], "row_count": 9, "column_count": 5, "numeric_cells": 24, "header_rows": 1, "locator": "section[21]/table-wrap[3]#T6"}}, {"id": "asset:table:pmid:34490121:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:68146d23c4f4a517e3a0c34af581c9f8c91c0f3f739e2d332d22afed6096123f", "bytes": 935, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[22]/table-wrap[1]#T7", "version": null, "note": "Comparison of the results of the segmentation task.", "structure": {"pmcid": "PMC8416476", "section_index": 22, "section_title": "Comparison", "row_count": 12, "column_count": 8}, "table": {"label": "Table 7", "caption": "Comparison of the results of the segmentation task.", "rows": [["", "", "Dice", "Hausdorff95"], ["", "ET", "WT", "TC", "ET", "WT", "TC"], ["BraTS 2019", "Proposed", "0.70", "0.87", "0.74", "5.7", "7.4", "9.8"], ["Kim S. et al. (30)", "0.67", "0.87", "0.76", "8.8", "14.2", "11.7"], ["Amian M. et al. (31)", "071", "0.86", "0.77", "6.9", "8.5", "11.6"], ["Shi W. et al. (32)", "0.69", "0.87", "0.77", "5.9", "21.2", "12.2"], ["Agravat R.R. et al. (33)", "0.60", "0.70", "0.63", "11.7", "14.3", "17.1"], ["BraTS 2020", "Proposed", "0.73", "0.88", "0.79", "36.9", "6.5", "10.0"], ["Tarasiewicz T. et al. (34)", "0.70", "0.89", "0.75", "40.1", "4.6", "10.7"], ["Mchugh H. et al. (35)", "0.71", "0.88", "0.79", "40.6", "6.7", "10.2"], ["Zhao C. et al. (36)", "0.67", "0.86", "0.62", "47.3", "12.6", "50.1"], ["Savadikar C. et al. (37)", "0.69", "0.82", "0.72", "36.9", "41.5", "26.3"]], "row_count": 12, "column_count": 8, "numeric_cells": 71, "header_rows": 2, "locator": "section[22]/table-wrap[1]#T7"}}, {"id": "asset:table:pmid:34490121:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1ef1ea86233ccd12f5cf4748458e262abf87e84e434b08225ed3da66ab1e6f22", "bytes": 602, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[22]/table-wrap[2]#T8", "version": null, "note": "Comparison of the results of survival prediction task.", "structure": {"pmcid": "PMC8416476", "section_index": 22, "section_title": "Comparison", "row_count": 11, "column_count": 3}, "table": {"label": "Table 8", "caption": "Comparison of the results of survival prediction task.", "rows": [["", "Team", "MSE"], ["BraTS 2019", "Proposed", "96470.98"], ["Kim S. et al. (30)", "121778.60"], ["Amian M. et al. (31)", "104253.00"], ["Kofler F. et al. (38)", "101877.80"], ["Islam M. et al. (39)", "127478.65"], ["BraTS 2020", "Proposed", "100053.08"], ["Soltaninejad M. et al. (40)", "109564.00"], ["Agravat R.R. et al. (41)", "116083.48"], ["Patel J. et al. (42)", "152467.00"], ["Ali M.J. et al. (43)", "105079.40"]], "row_count": 11, "column_count": 3, "numeric_cells": 20, "header_rows": 1, "locator": "section[22]/table-wrap[2]#T8"}}, {"id": "asset:table:pmid:34490121:9", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b22db98644d6c26b168671b1c5da6e2c36b6305cd3f2e2738e6a01b72c9a7ec0", "bytes": 443, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[23]/table-wrap[1]#T9", "version": null, "note": "Survival prediction results of different CNN network structures.", "structure": {"pmcid": "PMC8416476", "section_index": 23, "section_title": "Discussion", "row_count": 4, "column_count": 4}, "table": {"label": "Table 9", "caption": "Survival prediction results of different CNN network structures.", "rows": [["Method", "MSE", "MAE", "RMSE"], ["CNN with 4 layers of convolution", "136770.59", "269.37", "358.92"], ["CNN with 6 layers of convolution", "138065.90", "269.83", "363.64"], ["CNN with 8 layers of convolution", "144921.16", "301.79", "380.69"]], "row_count": 4, "column_count": 4, "numeric_cells": 12, "header_rows": 1, "locator": "section[23]/table-wrap[1]#T9"}}], "gaps": ["asset:data:availability not verified", "asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind pmid:34490121, at the location the paper names not verified", "asset:source:pmid:34490121 not verified"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "random forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["image_quantification_segmentation", "machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "In the survival prediction task, we extract radiological features such as intensity, texture, and filtering, and then build a CNN network to extract deep features. This network can also be used to predict survival. Subsequently, factor analysis is used to reduce the dimensions of the above two types of features to remove redundant features. Finally, the dimensionality reduction features combined with clinical factors such as age and tumor grade are input into the random forest regression model for survival prediction. The entire flow chart is shown in Figure 6."}}], "targets": [{"id": "target-1", "claim_id": "claim-1", "operation": null, "expected_value": 311.5, "unit": "days", "tolerance": null, "state": "complete"}], "gaps": ["operations"]}, "capability": {"state": "partial", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["differential_expression", "gwas", "machine_learning", "meta_analysis", "molecular_docking", "network_analysis", "pca", "statistical_regression", "survival_analysis"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}, {"capability_id": "capability:bench_workcell", "label": "General bench workcell (liquid transfer, plate handling, incubation)", "assay_families": ["amplicon_seq", "animal_model", "apoptosis_assay", "cell_culture", "cell_imaging", "chip_seq", "clinical_cohort", "clinical_trial", "elisa", "flow_cytometry", "ihc", "image_quantification", "mass_spectrometry", "methylation_array", "microarray", "qpcr", "rna_seq", "transfection", "western_blot"], "availability_state": "purchasable", "tier_unlocked": "R3", "candidate": "Supplier-neutral 96/384-well liquid handler"}], "gaps": ["capability:capability:bench_workcell purchasable"]}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:image_quantification_segmentation", "axes": {"method": {"axis": "method", "tier": "R4", "blocker": "method:image_quantification_segmentation", "detail": {"outcome": "determined", "family": "machine_learning", "specific_method": "random_forest", "required_operations": ["image_quantification_segmentation", "machine_learning_random_forest"], "missing_operations": ["image_quantification_segmentation", "machine_learning_random_forest"], "basis": "The DSL has no operation for image_quantification_segmentation, machine_learning_random_forest. Writing the first one is a bounded piece of work."}}, "capability": {"axis": "capability", "tier": "R1", "blocker": null, "detail": {"families": [], "applies": false, "basis": "This paper needs no bench capability: it computes on data it already has."}}, "data": {"axis": "data", "tier": "R4", "blocker": "data:accession_absent", "detail": {"applies": true, "reachable": false, "basis": "The record names no repository accession and no data-availability statement, so the source data has to be requested from the authors."}}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:34490121", "asset:table:pmid:34490121:1", "asset:table:pmid:34490121:2", "asset:table:pmid:34490121:3", "asset:table:pmid:34490121:4", "asset:table:pmid:34490121:5", "asset:table:pmid:34490121:6", "asset:table:pmid:34490121:7", "asset:table:pmid:34490121:8", "asset:table:pmid:34490121:9"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [{"operation": "image_quantification_segmentation", "unlocks_papers": 14, "priority": 3}, {"operation": "machine_learning_random_forest", "unlocks_papers": 4, "priority": 11}], "converters": [], "readers": ["html", "unknown", "xml"], "capabilities": ["capability:bench_workcell"], "data_gaps": ["source:pmid:34490121", "materials:the source data behind pmid:34490121, at the location the paper names", "materials:the analysis programme that recomputes the published estimate", "data:availability"]}, "gaps": ["method:image_quantification_segmentation"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [{"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "peer-review-reading-v1", "prompt_hash": "4371ec8f08819c5c558c1a8b4bfb2769d05601f752dd7b939b634103982faf3d", "source_hash": "534e1cfbb5511144bb862b745d1447089adf15edb21fc9ff3553adc2210f414c", "raw_response_sha256": "sha256:66c26234aedf99fef4023a1925e5fc496638734bb3e4db42abdd70142ba8ea3d", "raw_response_chars": 3372}], "target_providers": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "prompt_version": "replication-target-v2", "prompt_hash": "01531d151e73dc34164ace06ee95bd557acac833540d32bc753c645dc17ad481", "source_hash": "534e1cfbb5511144bb862b745d1447089adf15edb21fc9ff3553adc2210f414c", "raw_response": "{\"parent_value\":311.5,\"unit\":\"days\",\"evidence\":\"The average Dice of brain tumor segmentation tasks up to 79% and the average RMSE of the survival predictive task is as low as 311.5.\",\"target_result\":\"The paper states an average RMSE of 311.5 for the survival prediction task evaluated on the BraTS 2019 and BraTS 2020 datasets.\",\"number_stated\":true}", "reading": {"parent_value": 311.5, "unit": "days", "evidence": "The average Dice of brain tumor segmentation tasks up to 79% and the average RMSE of the survival predictive task is as low as 311.5.", "target_result": "The paper states an average RMSE of 311.5 for the survival prediction task evaluated on the BraTS 2019 and BraTS 2020 datasets.", "number_stated": true, "source_locator": "chars 1455-1588 of source sha256 534e1cfbb5511144bb862b745d1447089adf15edb21fc9ff3553adc2210f414c"}, "recorded_at": "2026-10-31T14:36:48.824045+00:00"}, {"provider": "minimax-m3", "model": "MiniMax-M3", "prompt_version": "replication-target-v2", "prompt_hash": "3f2d49af188b8004d21ce84c3fb7d2ce6c49061c9e9efe032441bc1654f96a33", "source_hash": "534e1cfbb5511144bb862b745d1447089adf15edb21fc9ff3553adc2210f414c", "raw_response": "{\"parent_value\":311.5,\"unit\":\"days\",\"evidence\":\"We evaluate the effect on the BraTS 2019 and BraTS 2020 datasets. The average Dice of brain tumor segmentation tasks up to 79% and the average RMSE of the survival predictive task is as low as 311.5.\",\"target_result\":\"311.5\",\"number_stated\":true}", "reading": {"parent_value": 311.5, "unit": "days", "evidence": "We evaluate the effect on the BraTS 2019 and BraTS 2020 datasets. The average Dice of brain tumor segmentation tasks up to 79% and the average RMSE of the survival predictive task is as low as 311.5.", "target_result": "311.5", "number_stated": true, "source_locator": "chars 1389-1588 of source sha256 534e1cfbb5511144bb862b745d1447089adf15edb21fc9ff3553adc2210f414c"}, "recorded_at": "2026-10-31T14:37:00.204249+00:00"}], "agreement": false, "disagreements": [], "agreement_basis": {"policy": "decisive_fields", "decisive_fields": ["number_stated", "parent_value", "unit", "work_type"], "advisory_fields": []}, "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 reading stage and the target extraction did not both return two readings, so the package claims no agreement.", "evidence": {"provider_errors": [{"provider": "minimax-m3-1-flash", "model": "MiniMax-M3.1-Flash", "reason": "a quoted span is absent from the supplied text"}]}}, {"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:78eee4a11d215c9b0f6860facf7643aff0711d2002ce03b30deb412d660e20d7", "type": "sep_package", "label": "SEP v1 package for pmid:34490121"}], "activities": [{"id": "activity:conversion:pmid:34490121", "type": "conversion", "used": ["package:78eee4a11d215c9b0f6860facf7643aff0711d2002ce03b30deb412d660e20d7"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:minimax-m3", "type": "model", "label": "minimax-m3"}, {"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:34490121", "parent_hash": "sha256:96783d8a0da6d252dabae533bda94ea052e2331f06c79fb6cf5de532904e6547", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:data:availability not verified", "asset:materials:the analysis programme that recomputes the published estimate not verified", "asset:materials:the source data behind pmid:34490121, at the location the paper names not verified", "asset:source:pmid:34490121 not verified", "authors", "capability:capability:bench_workcell purchasable", "execution.not_run", "method:image_quantification_segmentation", "operations", "review.human_critique", "review.machine_critique.blocked", "step:obtain_source_data blocked on data:not_downloaded", "step:provide_capability_bench_workcell blocked on instrument not yet purchased", "step:run_analysis blocked on method:image_quantification_segmentation"]},"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":"2026-11-04T02:46:36+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}}}