{"id":"W4412944500","doi":"10.18653/v1/2025.findings-acl.1364","title":"NBDESCRIB: A Dataset for Text Description Generation from Tables and Code in Jupyter Notebooks with Guidelines","year":2025,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Code (set theory); Programming language; Data science; Natural language processing; Information retrieval","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009096581,0.003102669,0.0007657902,0.003256245,0.0008465665,0.001208326,0.002645266,0.002336027,0.01420489],"category_scores_gemma":[0.007577259,0.000643092,0.001389606,0.002375964,0.0005970872,0.002298606,0.001936557,0.002039701,0.01540794],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001808957,"about_ca_system_score_gemma":0.001907307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02239397,"about_ca_topic_score_gemma":0.05270658,"domain_scores_codex":[0.9986699,0.000265131,0.0001834947,0.0003779789,0.0004157308,0.0000879085],"domain_scores_gemma":[0.9963166,0.001712691,0.0002737596,0.0007486586,0.0006816312,0.0002666288],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008630514,0.0005344905,0.008339714,0.004373044,0.0001566387,0.001340264,0.0007076639,0.007674532,0.007567021,0.001923241,0.8582422,0.1082781],"study_design_scores_gemma":[0.001020484,0.0005453033,0.03091208,0.0008713881,0.0001366424,0.001523759,0.001202526,0.07985227,0.02772886,0.005110986,0.8507882,0.0003074269],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.03924312,0.002060993,0.01781419,0.000739035,0.0004035458,0.001083683,0.8558703,0.07376622,0.009018921],"genre_scores_gemma":[0.01780113,0.0002759386,0.02590804,0.0002172683,0.00002033391,0.0007380201,0.9512051,0.0009933211,0.002840885],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02239397,"threshold_uncertainty_score":0.0475201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05870056497911689,"score_gpt":0.3220833197584907,"score_spread":0.2633827547793738,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}