{"id":"W4287777770","doi":"10.48550/arxiv.2005.07839","title":"Joint Progressive Knowledge Distillation and Unsupervised Domain\\n Adaptation","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Genetec (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Domain adaptation; Domain (mathematical analysis); Divergence (linguistics); Machine learning; Set (abstract data type); Pattern recognition (psychology); Data mining; Classifier (UML)","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"],"consensus_categories":[],"category_scores_codex":[0.000203645,0.000290813,0.0002992352,0.0002065999,0.0002476545,0.0002514607,0.0005746011,0.0002087774,0.00001974729],"category_scores_gemma":[0.00006747044,0.0003375967,0.0001205003,0.000515752,0.0001247671,0.000418077,0.001119603,0.0004873094,0.00008473559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001412539,"about_ca_system_score_gemma":0.0002097664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001980231,"about_ca_topic_score_gemma":0.0000121534,"domain_scores_codex":[0.9981312,0.0002367138,0.000233019,0.001040762,0.0001071434,0.0002512124],"domain_scores_gemma":[0.9986533,0.00008775621,0.0003053421,0.0005065244,0.0002017805,0.0002453023],"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":[0.00007653244,0.0001256742,0.001843766,0.0003030849,0.0001548941,0.00038011,0.01360468,0.1165505,0.0001996694,0.8507397,0.0001590611,0.01586237],"study_design_scores_gemma":[0.0006303325,0.00006124512,0.008432088,0.0001000262,0.00003481587,0.000004908888,0.000605806,0.9304929,0.00002159475,0.05788118,0.001342906,0.0003921691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09613577,0.0002439157,0.8984366,0.0003949329,0.0003410512,0.0004091901,0.0000067494,0.0003382212,0.003693562],"genre_scores_gemma":[0.9865142,0.0000894133,0.01284915,0.00008184332,0.00008599404,0.000002186257,0.00004145222,0.00001933137,0.0003164837],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8903784,"threshold_uncertainty_score":0.9999076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1349601155401389,"score_gpt":0.204635095105935,"score_spread":0.0696749795657961,"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."}}