{"id":"W2982283130","doi":"10.48550/arxiv.1910.11577","title":"CrevNet: Conditionally Reversible Video Prediction","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Autoencoder; Computer science; Bijection; Property (philosophy); Feature (linguistics); Artificial intelligence; Conditional independence; Feature extraction; Resolution (logic); Pattern recognition (psychology); Algorithm; Theoretical computer science; Machine learning; Deep learning; Mathematics; Discrete mathematics","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":[0.0002323752,0.0003229461,0.0003113413,0.0003353646,0.0001671372,0.0001668691,0.002145079,0.0003258885,0.00005279528],"category_scores_gemma":[0.00005919043,0.0004057621,0.0001731187,0.0005253989,0.0001247753,0.001328456,0.002265358,0.0006848131,0.0002187756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003753107,"about_ca_system_score_gemma":0.0003850438,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002439633,"about_ca_topic_score_gemma":0.000003138368,"domain_scores_codex":[0.9979011,0.00009336421,0.0002203063,0.001303662,0.0001481001,0.0003334139],"domain_scores_gemma":[0.9976388,0.00009291533,0.0003552249,0.001456349,0.0003345623,0.0001221753],"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":[0.0001176414,0.0004501585,0.009549589,0.001057879,0.0003694539,0.0007808089,0.0004694307,0.2760281,0.002499445,0.6580075,0.04821191,0.002458077],"study_design_scores_gemma":[0.000408789,0.00008069821,0.0010133,0.0003348741,0.00005450855,0.0000147682,0.00001544783,0.6268837,0.0008176627,0.3652528,0.00455534,0.0005681042],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003697877,0.0001142476,0.9865713,0.0001631952,0.0006249711,0.000368383,0.00005785979,0.001256081,0.00714605],"genre_scores_gemma":[0.8718786,0.0002297283,0.1213967,0.0002955591,0.0001000397,0.000002929854,0.00008279035,0.0000300808,0.005983582],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8681807,"threshold_uncertainty_score":0.9998394,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05244919599965824,"score_gpt":0.1981883633876888,"score_spread":0.1457391673880306,"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."}}