{"data":{"sci_version": "1.0", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41053192", "kind": "science-record", "revision": 2, "content_hash": "sha256:1fd51d45c2c3eb6f348081bd464a32d1970be53687682db5a6f77016679567ec", "created_at": "2026-11-01T10:25:53Z", "updated_at": "2026-11-01T14:01:49Z", "generator": {"name": "corpus-assay-engine", "converter": "sep_to_sci_v1", "source_package_schema": "urn:bntrg:sep:1.0.0"}, "paper": {"state": "partial", "title": "Decision tree-based machine learning methods for identifying colorectal cancer-associated microRNA signatures and their regulatory networks.", "doi": "10.1038/s41598-025-17037-7", "pmid": "41053192", "authors": null, "journal": "Scientific reports", "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:41053192"], "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:41053192", "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:41053192' does not resolve to a declared asset"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41053192", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-025-17037-7", "sha256": "sha256:d2f4d440740fdc2e43d7a2c00bdb4d3f61e78330b264139c7ef7d4529c612215", "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-025-17037-7", "version": null, "note": "Source read by the package builder: full_text.", "structure": {"access_state": "full_text"}}, {"id": "asset:table:pmid:41053192:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1c7071212d30cd84a7a48c7ff025923f03df3c7c613daac3fdf3bc9d1e1b84fd", "bytes": 627, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "Information of datasets.", "structure": {"pmcid": "PMC12500991", "section_index": 3, "section_title": "Microarray data collection", "row_count": 5, "column_count": 8}, "table": {"label": "Table 1", "caption": "Information of datasets.", "rows": [["Dataset", "GEO accession", "Source", "Platform", "Number of samples", "Number of miRNAs", "Ref."], ["CRC", "Normal"], ["Internal", "GSE106817", "Serum microRNA profiles", "3D-Gene Human miRNA V21_1.0.0", "115", "2759", "2568", "99"], ["External validation", "GSE113486", "Serum microRNA profiles", "3D-Gene Human miRNA V21_1.0.0", "40", "100", "2566", "95"], ["External validation", "GSE113740", "Serum microRNA profiles", "3D-Gene Human miRNA V21_1.0.0", "25", "950", "2565", "100"]], "row_count": 5, "column_count": 8, "numeric_cells": 18, "header_rows": 2, "locator": "section[3]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:41053192:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:10729a5d09ffcc6b337aed1ab034d6e46835dfa67382f01cd7f0accdfbc1f701", "bytes": 2049, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#Tab2", "version": null, "note": "The significancevalue of MiRNAs in the RF and XGBoost models in the internal and external validation datasets.", "structure": {"pmcid": "PMC12500991", "section_index": 12, "section_title": "Differential expressed MiRNAs in models", "row_count": 40, "column_count": 5}, "table": {"label": "Table 2", "caption": "The significancevalue of MiRNAs in the RF and XGBoost models in the internal and external validation datasets.", "rows": [["miRNAs", "Significance value", "Mean of scores"], ["GSE106817", "GSE113786", "GSE113740"], ["Random forest model"], ["hsa-miR-6787-5p", "100.0", "93.58", "53.36", "82.31"], ["hsa-miR-1246", "88.65", "66.89", "38.49", "64.67"], ["hsa-miR-8073", "86.67", "28.67", "52.45", "55.93"], ["hsa-miR-920", "85.72", "31.9", "-", "36.45"], ["hsa-miR-5100", "85.26", "24.1", "51", "53.45"], ["hsa-miR-6717-5p", "79.58", "86.86", "66.29", "77.57"], ["hsa-miR-6746-5p", "76.97", "-", "44.37", "40.44"], ["hsa-miR-3622a-5p", "74.48", "-", "30.53", "35.00"], ["hsa-miR-1228-5p", "72.31", "78.09", "100.0", "83.46"], ["hsa-miR-4706", "69.8", "59.96", "57.65", "62.47"], ["hsa-miR-6765-5p", "69.11", "19.05", "35.27", "41.14"], ["hsa-miR-1268a", "65.33", "33.82", "11.9", "37.09"], ["hsa-miR-22-3p", "64.89", "58.04", "22.75", "48.56"], ["hsa-miR-29b-3p", "60.26", "42.31", "-", "34.2"], ["hsa-miR-92a-3p", "57.12", "49.34", "13.08", "39.84"], ["hsa-miR-3184-5p", "56.65", "100.0", "70.93", "75.86"], ["hsa-miR-6794-5p", "56.13", "-", "-", "18.71"], ["hsa-miR-1343-3p", "54.76", "93.71", "96.3", "81.59"], ["hsa-miR-451a", "52.37", "-", "37.86", "30.07"], ["hsa-miR-7977", "50.68", "36.19", "28.66", "38.51"], ["XGBoost model"], ["hsa-miR-1343-3p", "100.0", "-", "-", "33.3"], ["hsa-miR-1246", "69.15", "54.79", "-", "41.33"], ["hsa-miR-6746-5p", "39.0", "9.63", "-", "16.21"], ["hsa-miR-920", "24.03", "-", "-", "8.01"], ["hsa-miR-1290", "14.86", "-", "-", "4.95"], ["hsa-miR-6787-5p", "8.76", "100.0", "42.97", "50.57"], ["hsa-miR-6765-5p", "6.56", "-", "-", "2.18"], ["hsa-miR-1228-5p", "2.70", "-", "100.0", "34.23"], ["hsa-miR-937-5p", "1.39", "-", "-", "0.46"], ["hsa-miR-6511b-5p", "1.17", "-", "-", "0.39"], ["hsa-miR-1268a", "0.88", "-", "-", "0.29"], ["hsa-miR-5100", "0.38", "1.49", "-", "0.62"], ["hsa-miR-4417", "0.13", "-", "10.18", "3.43"], ["hsa-miR-6794-5p", "0.13", "-", "-", "0.04"], ["hsa-miR-4259", "0.12", "-", "-", "0.04"], ["hsa-miR-8060", "0.06", "-", "-", "0.02"]], "row_count": 40, "column_count": 5, "numeric_cells": 151, "header_rows": 2, "locator": "section[12]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:41053192:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:113bb5e0368f2589a1c93d1141137b9af77542b6c00055d36b26bf7f5b575ce5", "bytes": 4914, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#Tab3", "version": null, "note": "MiRNA statuses in external datasets.", "structure": {"pmcid": "PMC12500991", "section_index": 12, "section_title": "Differential expressed MiRNAs in models", "row_count": 53, "column_count": 8}, "table": {"label": "Table 3", "caption": "MiRNA statuses in external datasets.", "rows": [["miRNA ID list", "External dataset", "logFC1", "B2", "T3", "P.Value", "adj.P.Val", "miRNA status"], ["has-miR-1228-5p", "GSE113486", "-1.12301", "81.5169", "-18.8762", "1.67E-40", "8.59E-38", "Downregulated"], ["GSE113740", "-1.00306", "37.3036", "-12.24148", "5.33E-21", "9.11E-19", "Downregulated"], ["has-miR-6787-5p", "GSE113486", "1.61572", "70.5048", "16.85056", "1.18E-35", "4.31E-33", "Upregulated"], ["GSE113740", "1.325679", "30.2259", "10.72794", "7.01E-18", "4.49E-16", "Upregulated"], ["has-miR-3184-5p", "GSE113486", "-2.1625", "67.2127", "-16.262", "3.29E-34", "1.05E-31", "Downregulated"], ["GSE113740", "-2.24559", "30.8233", "-10.8543", "3.82E-18", "2.51E-16", "Downregulated"], ["has-miR-1343-3p", "GSE113486", "2.35511", "53.9927", "13.96019", "2.10E-28", "2.57E-26", "Upregulated"], ["GSE113740", "2.273051", "36.0928", "11.97954", "1.82E-20", "2.52E-18", "Upregulated"], ["has-miR-4706", "GSE113486", "1.27794", "43.0184", "12.09875", "1.38E-23", "6.41E-22", "Upregulated"], ["GSE113740", "1.097518", "27.8719", "10.23181", "7.63E-17", "3.88E-15", "Upregulated"], ["has-miR-92a-3p", "GSE113486", "2.85429", "42.4319", "11.99982", "2.49E-23", "1.08E-21", "Upregulated"], ["GSE113740", "2.575373", "14.9295", "7.50229", "3.89E-11", "2.63E-10", "Upregulated"], ["has-miR-6765-5p", "GSE113486", "-0.75138", "40.2323", "-11.6289", "2.30E-22", "7.53E-21", "Downregulated"], ["GSE113740", "-0.70819", "12.9282", "-7.06828", "2.99E-10", "1.56E-09", "Downregulated"], ["has-miR-6717-5p", "GSE113486", "3.16371", "40.0675", "11.60114", "2.71E-22", "8.59E-21", "Upregulated"], ["GSE113740", "3.356785", "28.018", "10.26253", "6.58E-17", "3.52E-15", "Upregulated"], ["has-miR-1246", "GSE113486", "6.61289", "37.5217", "11.1716", "3.55E-21", "9.03E-20", "Upregulated"], ["GSE113740", "7.478777", "38.6391", "12.53211", "1.37E-21", "2.71E-19", "Upregulated"], ["hsa-miR-22-3p", "GSE113486", "4.45026", "36.5836", "11.01313", "9.17E-21", "2.18E-19", "Upregulated"], ["GSE113740", "3.89971", "17.8072", "8.11673", "2.09E-12", "2.17E-11", "Upregulated"], ["hsa-miR-7977", "GSE113486", "2.04939", "34.4587", "10.65354", "7.86E-20", "1.54E-18", "Upregulated"], ["GSE113740", "1.81994", "27.4291", "10.13875", "1.20E-16", "5.55E-15", "Upregulated"], ["hsa-miR-6746-5p", "GSE113486", "1.30871", "33.34", "10.46376", "2.44E-19", "4.11E-18", "Upregulated"], ["GSE113740", "1.100958", "16.064", "7.74564", "1.23E-11", "9.81E-11", "Upregulated"], ["hsa-miR-920", "GSE113486", "2.23288", "25.1792", "9.0616", "9.41E-16", "7.18E-15", "Upregulated"], ["GSE113740", "1.06022", "-2.1119", "3.22282", "1.76E-03", "2.82E-03", "Upregulated"], ["hsa-miR-451a", "GSE113486", "5.06649", "24.6391", "8.9672", "1.63E-15", "1.18E-14", "Upregulated"], ["GSE113740", "5.070946", "19.9474", "8.56884", "2.37E-13", "3.30E-12", "Upregulated"], ["hsa-miR-1268a", "GSE113486", "-0.53666", "23.1903", "-8.7126", "7.06E-15", "4.51E-14", "Downregulated"], ["GSE113740", "-0.531", "9.6791", "-6.34588", "8.26E-09", "3.04E-08", "Downregulated"], ["hsa-miR-29b-3p", "GSE113486", "4.01697", "19.0763", "7.97638", "4.59E-13", "1.95E-12", "Upregulated"], ["GSE113740", "3.824398", "8.9099", "6.17056", "1.81E-08", "6.25E-08", "Upregulated"], ["hsa-miR-937-5p", "GSE113486", "0.58865", "12.3417", "6.70811", "4.36E-10", "1.13E-09", "Upregulated"], ["GSE113740", "0.342777", "-0.7875", "3.65661", "4.26E-04", "7.36E-04", "Upregulated"], ["hsa-miR-6511b-5p", "GSE113486", "1.5816", "10.4716", "6.33528", "2.95E-09", "6.79E-09", "Upregulated"], ["GSE113740", "1.30541", "1.9454", "4.45078", "2.40E-05", "4.85E-05", "Upregulated"], ["hsa-miR-1290", "GSE113486", "3.4776", "6.8586", "5.57661", "1.20E-07", "2.33E-07", "Upregulated"], ["GSE113740", "3.238315", "14.336", "7.37426", "7.13E-11", "4.43E-10", "Upregulated"], ["hsa-miR-4259", "GSE113486", "1.61476", "4.8961", "5.13623", "9.11E-07", "1.63E-06", "Upregulated"], ["GSE113740", "1.111774", "-3.0084", "2.90089", "4.66E-03", "7.11E-03", "Upregulated"], ["hsa-miR-3622a-5p", "GSE113486", "0.82532", "4.3369", "5.00603", "1.62E-06", "2.86E-06", "Upregulated"], ["GSE113740", "1.042126", "5.9791", "5.4815", "3.68E-07", "9.60E-07", "Upregulated"], ["hsa-miR-5100", "GSE113486", "2.9519", "32.9003", "10.38905", "3.80e-19", "6.21e-18", "Upregulated"], ["GSE113740", "2.871827", "26.7861", "10.00371", "2.30E-16", "9.35E-15", "Upregulated"], ["hsa-miR-6794-5p", "GSE113486", "0.33909", "1.1535", "4.21189", "4.48E-05", "6.98E-05", "Upregulated"], ["GSE113740", "0.215848", "-4.2335", "2.40483", "1.82E-02", "2.57E-02", "Upregulated"], ["hsa-miR-4417", "GSE113486", "0.10292", "-6.6008", "1.11003", "2.69E-01", "2.96E-01", "Upregulated"], ["GSE113740", "0.475273", "11.3483", "6.72027", "1.50E-09", "6.38E-09", "Upregulated"], ["hsa-miR-8060", "GSE113486", "1.03949", "-3.5327", "2.74732", "6.79E-03", "8.91E-03", "Upregulated"], ["GSE113740", "1.560191", "-2.1529", "3.20867", "1.84E-03", "2.94E-03", "Upregulated"], ["hsa-miR-8073", "GSE113486", "2.42001", "60.2832", "15.0446", "3.64E-31", "6.67E-29", "Upregulated"], ["GSE113740", "2.330846", "53.9467", "16.03388", "2.35E-28", "3.01E-25", "Upregulated"]], "row_count": 53, "column_count": 8, "numeric_cells": 338, "header_rows": 1, "locator": "section[12]/table-wrap[2]#Tab3"}}, {"id": "asset:table:pmid:41053192:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c3115ea547957f64407b4b05090fa9b56bdf60a815aeec1264da15892e7c84a0", "bytes": 614, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Tab4", "version": null, "note": "Optimal hyperparameters and performance metrics for the final models.", "structure": {"pmcid": "PMC12500991", "section_index": 13, "section_title": "Performance evaluation", "row_count": 3, "column_count": 8}, "table": {"label": "Table 4", "caption": "Optimal hyperparameters and performance metrics for the final models.", "rows": [["Classifier", "hyperparameters", "Accuracy", "AUC(%)", "Sensitivity(%)", "Specificity(%)", "Positive prediction value (PPV)", "Negative prediction value (NPV)"], ["RF", "Mtry4 = 2", "99.88", "100.0", "100.0", "100.0", "97.14", "100.0"], ["XGB", "nrounds = 50, max_depth = 1, eta = 0.3, gamma = 0, colsample_bytree= 0.6, min_child_weight = 1 and subsample = 0.5.", "99.71", "99.9", "97.05", "99.87", "97.05", "99.87"]], "row_count": 3, "column_count": 8, "numeric_cells": 14, "header_rows": 1, "locator": "section[13]/table-wrap[1]#Tab4"}}, {"id": "asset:table:pmid:41053192:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6a448c5a5cd228d4cdbb4919a94229ff0e60265c6e2a16d8d84b99aec9a3a524", "bytes": 2968, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#Tab5", "version": null, "note": "miRNA-associated pathways listed by miranno.", "structure": {"pmcid": "PMC12500991", "section_index": 14, "section_title": "Functional annotation of the identified MiRNAs", "row_count": 46, "column_count": 4}, "table": {"label": "Table 5", "caption": "miRNA-associated pathways listed by miranno.", "rows": [["miRNA", "Pathways (N)", "Cancer/tumor pathways", "Top 5 associated molecular pathways"], ["hsa-miR-1228-5p", "144", "Signaling by ligand-responsive EGFR variants in cancer", "Metabolism of ingested SeMet, Sec, MeSec into H2Se"], ["Signaling by EGFR in cancer", "Fructose metabolism"], ["Constitutive signaling by ligand-responsive EGFR cancer variants", "Mechanism of protein import into the nucleus"], ["Signaling by EGFRvIII in cancer", "Tyrosine degradation"], ["Thyroid cancer", "Geranylgeranyl diphosphate from farnesyl diphosphate and isopentenyl diphosphate"], ["hsa-miR-6787-5p", "153", "Constitutive signaling by AKT1 E17K in cancer", "FGFRL1 modulation of FGFR1 signaling"], ["MTF1 activates gene expression"], ["Phosphoinositides and their downstream targets"], ["Lidocaine (Local Anaesthetic) Metabolism Pathway"], ["WNT ligand secretion is abrogated by the PORCN inhibitor LGK974"], ["hsa-miR-1343-3p", "102", "Estrogen responsive protein efp controls cell cycle and breast tumors growth", "PTK6 Activates STAT3"], ["Ibuprofen_Pathway_Pharmacokinetics"], ["Signaling mediated by p38-alpha and p38-beta"], ["Urokinase-type plasminogen activator (uPA) and uPAR-mediated signaling"], ["UMP biosynthesis via de novo pathway"], ["hsa-miR-6717-5p", "146", "Bladder cancer", "Benzo(a)pyrene metabolism"], ["Synthesis of bile acids and bile salts via 27-hydroxycholesterol"], ["Synthesis of bile acids and bile salts via 24-hydroxycholesterol"], ["Synthesis of bile acids and bile salts via 7alpha-Hydroxycholesterol"], ["Allopregnanolone biosynthesis"], ["hsa-miR-3184-5p", "175", "-", "NFG and proNGF binds to p75NTR"], ["Putrescine biosynthesis via L-ornithine pathway"], ["Putrescine biosynthesis I"], ["Putrescine from L-ornithine"], ["Spermidine from putrescine"], ["hsa-miR-1246", "114", "Signaling by WNT in cancer", "Interaction With Cumulus Cells"], ["Dermatan sulfate degradation (metazoa)"], ["L-cysteine degradation I"], ["phosphocholine from choline"], ["Acyl carrier protein metabolism"], ["hsa-miR-4706", "203", "-", "WNT ligand secretion / PORCN inhibitor LGK974"], ["FGFRL1 modulation of FGFR1 signaling"], ["Microtubule-dependent trafficking of connexons from Golgi to the plasma membrane"], ["Beta agonist/Beta blocker Pathway"], ["Downstream signaling in naïve CD8 + T cells"], ["hsa-miR-8073", "131", "-", "Quinol/quinone metabolism"], ["Menaquinone biosynthesis"], ["Dopamine biosynthesis"], ["Dopamine from L-tyrosine"], ["Ascorbate and aldarate metabolism"], ["hsa-miR-5100", "89", "Methotrexate Pathway Cancer Cell Pharmacodynamics", "(S)-3-hydroxy-3-methylglutaryl-CoA degradation"], ["Acetoacetate from (S)-3-hydroxy-3-methylglutaryl-CoA"], ["TCA Cycle Nutrient Utilization and Invasiveness of Ovarian Cancer", "Metabolic intermediate metabolism"], ["Effects of Nitric Oxide"], ["4-hydroxy-2-nonenal detoxification"]], "row_count": 46, "column_count": 4, "numeric_cells": 30, "header_rows": 1, "locator": "section[14]/table-wrap[1]#Tab5"}}, {"id": "asset:table:pmid:41053192:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:08a9a99aa7133df8f6aeb5a6e057b0f12a10e08f9845e057061c4d99ea46788e", "bytes": 3831, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[2]#Tab6", "version": null, "note": "Gene ontology reported by ToppFun for target genes of the selected mirnas.", "structure": {"pmcid": "PMC12500991", "section_index": 14, "section_title": "Functional annotation of the identified MiRNAs", "row_count": 44, "column_count": 4}, "table": {"label": "Table 6", "caption": "Gene ontology reported by ToppFun for target genes of the selected mirnas.", "rows": [["GO: biological process", "GO: molecular function"], ["ID", "Name", "ID", "Name"], ["GO:0045934", "negative regulation of nucleobase-containing compound metabolic process", "GO:0043565", "sequence-specific DNA binding"], ["GO:0051253", "negative regulation of RNA metabolic process", "GO:0003690", "double-stranded DNA binding"], ["GO:0010558", "negative regulation of macromolecule biosynthetic process", "GO:1,990,837", "sequence-specific double-stranded DNA binding"], ["GO:0031327", "negative regulation of cellular biosynthetic process", "GO:0000976", "transcription cis-regulatory region binding"], ["GO:1,902,679", "negative regulation of RNA biosynthetic process", "GO:0019904", "protein domain specific binding"], ["GO:0045892", "negative regulation of DNA-templated transcription", "GO:0001067", "transcription regulatory region nucleic acid binding"], ["GO:0060322", "head development", "GO:0060090", "molecular adaptor activity"], ["GO:0031647", "regulation of protein stability", "GO:0008134", "transcription factor binding"], ["GO:0000122", "negative regulation of transcription by RNA polymerase II", "GO:0000977", "RNA polymerase II transcription regulatory region sequence-specific DNA binding"], ["GO:0043066", "negative regulation of apoptotic process", "GO:0003700", "DNA-binding transcription factor activity"], ["GO:0051960", "regulation of nervous system development", "GO:0000978", "RNA polymerase II cis-regulatory region sequence-specific DNA binding"], ["GO:0043069", "negative regulation of programmed cell death", "GO:0030674", "protein-macromolecule adaptor activity"], ["GO:0007420", "brain development", "GO:0044389", "ubiquitin-like protein ligase binding"], ["GO:0007417", "central nervous system development", "GO:0000987", "cis-regulatory region sequence-specific DNA binding"], ["GO:0050767", "regulation of neurogenesis", "GO:0140262", "mRNA cap binding complex binding"], ["GO:0045893", "positive regulation of DNA-templated transcription", "GO:0000981", "DNA-binding transcription factor activity, RNA polymerase II-specific"], ["GO:1,902,680", "positive regulation of RNA biosynthetic process", "GO:0031625", "ubiquitin protein ligase binding"], ["GO:0043067", "regulation of programmed cell death", "GO:0042393", "histone binding"], ["GO:0000902", "cell morphogenesis", "GO:0140110", "transcription regulator activity"], ["GO:0042981", "regulation of apoptotic process", "GO:0001221", "transcription coregulator binding"], ["GO:0050821", "protein stabilization", "", ""], ["GO:0007628", "adult walking behavior", "", ""], ["GO:1,903,169", "regulation of calcium ion transmembrane transport", "", ""], ["GO:0045597", "positive regulation of cell differentiation", "", ""], ["GO:0043523", "regulation of neuron apoptotic process", "", ""], ["GO:0048666", "neuron development", "", ""], ["GO:0044087", "regulation of cellular component biogenesis", "", ""], ["GO:0045184", "establishment of protein localization", "", ""], ["GO:0014009", "glial cell proliferation", "", ""], ["GO:0015031", "protein transport", "", ""], ["GO:0090659", "walking behavior", "", ""], ["GO:0042063", "gliogenesis", "", ""], ["GO:0051402", "neuron apoptotic process", "", ""], ["GO:0003181", "atrioventricular valve morphogenesis", "", ""], ["GO:0006974", "DNA damage response", "", ""], ["GO:0010626", "negative regulation of Schwann cell proliferation", "", ""], ["GO:0050768", "negative regulation of neurogenesis", "", ""], ["GO:0048598", "embryonic morphogenesis", "", ""], ["GO:1,901,339", "regulation of store-operated calcium channel activity", "", ""], ["GO:0043524", "negative regulation of neuron apoptotic process", "", ""], ["GO:0097193", "intrinsic apoptotic signaling pathway", "", ""], ["GO:0071824", "protein-DNA complex organization", "", ""]], "row_count": 44, "column_count": 4, "numeric_cells": 62, "header_rows": 2, "locator": "section[14]/table-wrap[2]#Tab6"}}], "gaps": ["asset:source:pmid:41053192 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:41053192", "asset:table:pmid:41053192:1", "asset:table:pmid:41053192:2", "asset:table:pmid:41053192:3", "asset:table:pmid:41053192:4", "asset:table:pmid:41053192:5", "asset:table:pmid:41053192:6"], "steps": ["read_published_estimate"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": ["xml"], "capabilities": [], "data_gaps": ["source:pmid:41053192"]}, "gaps": ["corpus_record_absent"]}, "review": {"state": "partial", "machine_critique": {"status": "blocked", "providers": [], "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": 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}, {"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", "review.machine_critique.providers"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "package:8b1d48df7c1296cff04c4f39fcade4562ad72287f7ede27c0efe051b7a342082", "type": "sep_package", "label": "SEP v1 package for pmid:41053192"}], "activities": [{"id": "activity:conversion:pmid:41053192", "type": "conversion", "used": ["package:8b1d48df7c1296cff04c4f39fcade4562ad72287f7ede27c0efe051b7a342082"], "agent": "agent:corpus-assay-engine"}], "agents": [{"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:41053192", "parent_hash": "sha256:0c181900335808cf9c8e501ea4691af364e8cb826b651031685d7c731f4502a4", "fork_of": null, "generation": 2}, "gaps": ["abstract", "asset:source:pmid:41053192 not verified", "authors", "capability", "corpus_record_absent", "execution.not_run", "method", "review.human_critique", "review.machine_critique.blocked", "review.machine_critique.providers", "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:41053192' 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":"2026-11-04T01:44:29+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}}}