{"id":"W3042990756","doi":"10.48550/arxiv.2007.09598","title":"Adaptive Video Highlight Detection by Learning from User History","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Normalization (sociology); Artificial intelligence; Affine transformation; User modeling; Machine learning; Encoder; Multi-user; Human–computer interaction; User interface; Computer network","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":[0.0001305957,0.0002877742,0.0003699049,0.0001961737,0.0001604017,0.00009861375,0.001095562,0.0003046815,0.0001083095],"category_scores_gemma":[0.00004204865,0.0003470863,0.0002603597,0.0003828831,0.00005205806,0.0005276744,0.001134877,0.0007357386,0.0001974218],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007926788,"about_ca_system_score_gemma":0.0001276879,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001228786,"about_ca_topic_score_gemma":0.0001539906,"domain_scores_codex":[0.9978262,0.0003009599,0.0002149546,0.001296193,0.0001371431,0.0002245139],"domain_scores_gemma":[0.9985709,0.00009130505,0.000360221,0.0006576124,0.0001491341,0.0001708843],"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":[0.0002190485,0.0002861789,0.00666043,0.00007679084,0.001500397,0.0006379584,0.003190126,0.8370101,0.01131804,0.1033585,0.02545648,0.01028592],"study_design_scores_gemma":[0.0002550453,0.00005650682,0.0006258775,0.00002553623,0.0001462968,2.928132e-7,0.00005216831,0.9643632,0.000688044,0.005734988,0.02761999,0.000432096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02182226,0.0002450285,0.9752765,0.0001704347,0.0006385371,0.0001229851,0.000006963506,0.0003316313,0.001385625],"genre_scores_gemma":[0.9956862,0.0001705372,0.0007892183,0.0001719688,0.0001074433,9.082105e-7,0.00007291145,0.00001933202,0.002981537],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9744873,"threshold_uncertainty_score":0.9998981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05813559320292488,"score_gpt":0.1524139935223934,"score_spread":0.09427840031946849,"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."}}