{"id":"W7131097258","doi":"10.1109/iccvw69036.2025.00708","title":"Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Preprocessor; Task (project management); Distillation; Matching (statistics); Sampling (signal processing); Transformation (genetics); Downstream (manufacturing); Focus (optics)","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":[0.0005090953,0.0004176003,0.0003540024,0.0002648402,0.0008148275,0.00129413,0.00100143,0.0001374032,0.0001742399],"category_scores_gemma":[0.000121974,0.0003242564,0.00005547051,0.001352641,0.0001690154,0.0008296205,0.0004428093,0.0004268094,0.0002104611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001522197,"about_ca_system_score_gemma":0.000234726,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001694066,"about_ca_topic_score_gemma":0.00009663845,"domain_scores_codex":[0.9966908,0.0003148759,0.0006588302,0.001391804,0.0004807214,0.0004629318],"domain_scores_gemma":[0.9972634,0.000224337,0.0003219706,0.001782355,0.0002566845,0.0001512985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001105216,0.0003756535,0.00392873,0.0001155314,0.0001678295,0.00001155917,0.001083575,0.01405278,0.003872177,0.5302452,0.2366083,0.2094282],"study_design_scores_gemma":[0.0008473718,0.0001109553,0.03665388,0.0001384487,0.00004524568,0.00001195446,0.0001103628,0.4859015,0.0004172406,0.0003348866,0.47494,0.0004881883],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002150526,0.0004240073,0.9830711,0.005651094,0.0005780986,0.000444596,0.000879818,0.0001885859,0.00661212],"genre_scores_gemma":[0.8100345,0.0003563199,0.1651204,0.001214049,0.0003277985,0.00004664216,0.01731238,0.00002701474,0.005560845],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8179507,"threshold_uncertainty_score":0.999921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04802980133914164,"score_gpt":0.319385498422392,"score_spread":0.2713556970832504,"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."}}