{"id":"W4313171465","doi":"10.1109/cvpr52688.2022.00037","title":"How Much More Data Do I Need? Estimating Requirements for Downstream Tasks","year":2022,"lang":"en","type":"article","venue":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Task (project management); Function (biology); Set (abstract data type); Downstream (manufacturing); Data set; Estimator; Data validation; Machine learning; Artificial intelligence; Data mining; Database; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007894691,0.0003830954,0.0003958053,0.000280611,0.0009076283,0.001375122,0.001507721,0.00007813188,0.0002977069],"category_scores_gemma":[0.00003947333,0.0003622783,0.00009649215,0.0003221546,0.00005716728,0.0007911531,0.001379268,0.000582374,0.00003273699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004591286,"about_ca_system_score_gemma":0.00007161596,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004364856,"about_ca_topic_score_gemma":0.000004606132,"domain_scores_codex":[0.9967421,0.0003226454,0.0004188525,0.001309065,0.0007296917,0.0004776789],"domain_scores_gemma":[0.9979623,0.0002496602,0.0003381194,0.001058416,0.0001786156,0.0002128986],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000237012,0.0001716414,0.0001999341,0.00005940116,0.00003200847,0.00002715895,0.0004156705,0.0001629992,0.0001560798,0.0001627825,0.01523857,0.98335],"study_design_scores_gemma":[0.001363955,0.0009829063,0.0002358632,0.0001703609,0.00001936858,0.00007483111,0.0002019901,0.9874207,0.000111404,0.001900707,0.007025153,0.0004928063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02504263,0.00003777078,0.9633465,0.007274434,0.002663228,0.0005858458,0.0005113598,0.0002742435,0.0002640274],"genre_scores_gemma":[0.8573268,0.00004274159,0.1339581,0.004831682,0.000948514,0.0002430476,0.001990978,0.00005713739,0.0006009526],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9872577,"threshold_uncertainty_score":0.9998829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09217580612085,"score_gpt":0.3321902057448282,"score_spread":0.2400143996239782,"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."}}