{"id":"W4308222681","doi":"10.1145/3536221.3556597","title":"A Framework for Video-Text Retrieval with Noisy Supervision","year":2022,"lang":"en","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Closed captioning; Artificial intelligence; Modal; Relevance (law); Context (archaeology); Task (project management); Natural language processing; Domain (mathematical analysis); Machine learning; Information retrieval; Image (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":[],"consensus_categories":[],"category_scores_codex":[0.0003015545,0.00009403291,0.0001003568,0.00006879255,0.0005009005,0.00009218143,0.0009011822,0.00002263898,0.0002471747],"category_scores_gemma":[0.0000981612,0.00007803131,0.00004458937,0.0006109869,0.0000177296,0.000131745,0.0004303342,0.0002820367,0.00004443345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005184929,"about_ca_system_score_gemma":0.00006374994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001357122,"about_ca_topic_score_gemma":0.000003814255,"domain_scores_codex":[0.9988878,0.00005476085,0.000127191,0.0004045309,0.0003170483,0.0002086405],"domain_scores_gemma":[0.9987421,0.0004003487,0.00005421576,0.0006759172,0.00005747646,0.00006992476],"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":[0.00007298307,0.000128872,0.002279992,0.0000104331,0.000013407,0.000002800987,0.0006993723,0.005745654,0.0005936053,0.9733261,0.001307655,0.01581915],"study_design_scores_gemma":[0.0007701203,0.0008070837,0.01040065,0.00001123727,0.00000946195,0.00004233186,0.0001181898,0.8590173,0.0006860195,0.05715893,0.07060365,0.0003750697],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05246529,0.00002014429,0.9385199,0.007298754,0.00008333672,0.0003895341,0.000004361926,0.0003080958,0.0009106082],"genre_scores_gemma":[0.554049,2.673263e-7,0.4446126,0.0009776868,0.00002750496,0.0001161136,0.000003755646,0.000009285147,0.0002037938],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9161671,"threshold_uncertainty_score":0.3852572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01734851815095571,"score_gpt":0.2900835527978527,"score_spread":0.272735034646897,"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."}}