{"id":"W4412719203","doi":"10.1007/978-3-031-97992-7_63","title":"Evaluating LLMs for Effective Object Search in Video Data","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Object (grammar); Computer science; Geography; Artificial intelligence","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":[0.002169978,0.000407422,0.0007862559,0.0003348165,0.00010472,0.0002643214,0.001130168,0.000559631,0.000001472588],"category_scores_gemma":[0.0005131835,0.0003519783,0.00007521817,0.0002483129,0.00005930339,0.0002941503,0.0008864681,0.0008992387,6.880265e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001556069,"about_ca_system_score_gemma":0.000116927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001264565,"about_ca_topic_score_gemma":0.0001691071,"domain_scores_codex":[0.9973391,0.0001686375,0.000568004,0.001160185,0.0003088963,0.0004552262],"domain_scores_gemma":[0.9951063,0.003279998,0.0001875922,0.001230119,0.0001397461,0.00005618616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006304967,0.00001238021,0.000121688,0.0005840662,0.00005095698,0.00003742193,0.0001715659,0.02909513,0.00002237187,0.01364648,0.0003599068,0.955835],"study_design_scores_gemma":[0.0004951822,0.0002982879,0.00003134875,0.003343177,0.0000207843,0.0000156288,0.000002114574,0.9655907,0.00007609247,0.02247868,0.007205966,0.0004420675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000007856043,0.02504613,0.9679564,0.00007435587,0.0005558698,0.002604014,0.00003048372,0.0001036996,0.003621246],"genre_scores_gemma":[0.7165014,0.01200878,0.2332438,0.002079937,0.005974909,0.002001579,0.001089952,0.0004748059,0.02662484],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9553929,"threshold_uncertainty_score":0.9998932,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06372081166989486,"score_gpt":0.3714293954147437,"score_spread":0.3077085837448489,"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."}}