{"id":"W4399369602","doi":"10.21428/d82e957c.fbc3ba91","title":"Meta Episodic Learning with Dynamic Task Sampling for CLIP-based Point Cloud Classification","year":2024,"lang":"en","type":"article","venue":"","topic":"3D Shape Modeling and Analysis","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; University of Manitoba","funders":"","keywords":"Computer science; Task (project management); Sampling (signal processing); Cloud computing; Point cloud; Artificial intelligence; Point (geometry); Machine learning; Computer vision; Mathematics; Engineering; Operating system","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":[],"consensus_categories":[],"category_scores_codex":[0.0002715293,0.0001491263,0.0002100984,0.0001538091,0.00008176285,0.0001119748,0.00007433035,0.00005571538,0.00006475444],"category_scores_gemma":[0.00001555243,0.0001116652,0.0001836378,0.0002445886,0.00001332612,0.00007452088,0.00000536108,0.0001779718,0.00003914257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000661997,"about_ca_system_score_gemma":0.00002211547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001419462,"about_ca_topic_score_gemma":0.00002773185,"domain_scores_codex":[0.99923,0.00001489408,0.0001997315,0.0002422836,0.0001127191,0.0002003387],"domain_scores_gemma":[0.999597,0.000146041,0.00001640621,0.0001551895,0.00003712934,0.00004824862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005153309,0.000005935679,0.00002645398,0.0001593314,0.0006326078,9.414448e-7,0.00006101419,0.9895957,0.002960406,0.000392848,0.00009612277,0.00606353],"study_design_scores_gemma":[0.0001101575,0.00002985769,0.00001883846,0.00004467394,0.000922335,8.972976e-7,0.00009500887,0.9965201,0.0002764382,0.0002358036,0.001579767,0.0001661161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01906602,0.001031898,0.9777938,0.0003547343,0.0001082197,0.0001036303,0.000007412516,0.001015661,0.0005186499],"genre_scores_gemma":[0.9784818,0.00003221683,0.02043151,0.00003388289,0.00006189694,0.00006623467,0.00008746605,0.00005645996,0.000748514],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9594158,"threshold_uncertainty_score":0.4553576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04440647181948334,"score_gpt":0.2659223999452176,"score_spread":0.2215159281257343,"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."}}