{"id":"W4412737366","doi":"10.20944/preprints202507.2313.v1","title":"A Multimodal Scene Command Classification Method Based on Hybrid Deep Learning","year":2025,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Computer science; Deep learning; Pattern recognition (psychology); Machine learning","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":[0.002219494,0.0004611154,0.0006260571,0.0005719843,0.0003185123,0.0001975264,0.002826521,0.0002579771,0.0001252835],"category_scores_gemma":[0.0008094148,0.00048456,0.0003603006,0.000461617,0.00005952152,0.0001781532,0.003315329,0.001649378,0.0005632137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002039978,"about_ca_system_score_gemma":0.0002862079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002918725,"about_ca_topic_score_gemma":0.00001126056,"domain_scores_codex":[0.995392,0.0009668182,0.0006218348,0.001991236,0.0005945198,0.0004336286],"domain_scores_gemma":[0.9951771,0.0005614451,0.0005058245,0.003356337,0.0002257657,0.0001734616],"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":[0.00009391164,0.0008064287,0.3230392,0.0004704861,0.0005078022,0.00005858721,0.001194202,0.3492147,0.002582226,0.002174588,0.0002186381,0.3196392],"study_design_scores_gemma":[0.0003563465,0.00001826731,0.06950469,0.000277842,0.00008651145,0.000002026732,0.00002173251,0.9177061,0.00841337,0.0005380295,0.002654838,0.0004202817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04509041,0.00004826114,0.9398276,0.00147553,0.0004976651,0.0003448976,0.00003171177,0.000618503,0.01206543],"genre_scores_gemma":[0.8844998,0.00003717633,0.1132553,0.0003634525,0.0001030488,0.0001375191,0.0002436738,0.00002096199,0.001339099],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8394094,"threshold_uncertainty_score":0.9997606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1181249637036551,"score_gpt":0.3728834249469656,"score_spread":0.2547584612433104,"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."}}