{"id":"W4396600247","doi":"10.48550/arxiv.2404.19132","title":"Integrating Present and Past in Unsupervised Continual Learning","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; National Science Foundation","keywords":"Unsupervised learning; Computer science; Artificial intelligence; Data science","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004830434,0.0003010727,0.0003496935,0.0003645431,0.0001186254,0.0003569397,0.0007237855,0.0002122753,0.000008178386],"category_scores_gemma":[0.00004174364,0.0003179626,0.0001188904,0.0004127552,0.00005265783,0.0001955407,0.002808062,0.001642418,0.00005145002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001725944,"about_ca_system_score_gemma":0.00009317085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006460179,"about_ca_topic_score_gemma":0.00004623871,"domain_scores_codex":[0.9979478,0.0002622722,0.0002584742,0.001076084,0.00009659648,0.0003588004],"domain_scores_gemma":[0.999097,0.0001606018,0.0001447319,0.0003983176,0.00009547335,0.0001039003],"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":[0.00001488462,0.00004167994,0.0245171,0.0003434566,0.00009311786,0.001130685,0.004912157,0.2012948,0.0001566236,0.7624987,0.0000964457,0.004900335],"study_design_scores_gemma":[0.0003127194,0.00008183801,0.00184628,0.001413145,0.00002757951,0.00001191193,0.001680565,0.9718381,0.000099327,0.01217051,0.009930649,0.0005873852],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.739552,0.0004850547,0.2527784,0.0002007929,0.0009686259,0.0003453729,0.000002487511,0.000372426,0.005294792],"genre_scores_gemma":[0.9863958,0.00004882335,0.0006300814,0.00001423944,0.0002360297,0.00000150029,0.000003297124,0.0000208294,0.01264944],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7705433,"threshold_uncertainty_score":0.9999272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0542853103253399,"score_gpt":0.1918385128842502,"score_spread":0.1375532025589103,"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."}}