{"id":"W4391940619","doi":"10.1145/3640543.3645143","title":"LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Digital Games and Media","field":"Social Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Workflow; Embodied cognition; Flexibility (engineering); Human–computer interaction; Video editing; Multimedia; Process (computing); Creativity; Non-linear editing system; Collaborative editing; World Wide Web; Artificial intelligence; Programming language; Database","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":[0.0003972616,0.0001107274,0.0001444616,0.00004094874,0.00005932031,0.0004250568,0.0001092413,0.0001015285,0.0001001438],"category_scores_gemma":[0.0002385021,0.0001012409,0.00007930708,0.00005497839,0.00008042999,0.00006985697,0.0001974193,0.0001365772,0.00001782038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001012885,"about_ca_system_score_gemma":0.0001435691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003653438,"about_ca_topic_score_gemma":0.002709321,"domain_scores_codex":[0.9990572,0.00002271134,0.0001614691,0.0003106303,0.0002380729,0.0002099302],"domain_scores_gemma":[0.9995632,0.0001021183,0.00008023441,0.0001002662,0.00004683662,0.0001073974],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002599487,0.00007454154,0.0001319199,0.001020373,0.0001160502,0.00002979193,0.07550001,0.000007156034,0.0002399366,0.07771089,0.05894635,0.786197],"study_design_scores_gemma":[0.0002715618,0.00003660503,0.0003245069,0.0004238755,0.00007758585,4.812056e-7,0.04296614,0.0001691943,0.0002667822,0.01600662,0.9391351,0.0003215313],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.06310539,0.003213918,0.001137728,0.003328681,0.005939739,0.001197334,0.0002212651,0.0002911211,0.9215648],"genre_scores_gemma":[0.7371765,0.0003091702,0.00444866,0.0008047367,0.002692139,0.0002563739,0.0001484843,0.00003733825,0.2541266],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8801888,"threshold_uncertainty_score":0.4128484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02565173515562348,"score_gpt":0.3521939052225032,"score_spread":0.3265421700668797,"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."}}