{"id":"W2787598613","doi":"10.1109/aciiw.2017.8272586","title":"Multimodal cross-context recognition of negative interactions","year":2017,"lang":"en","type":"article","venue":"","topic":"Speech and Audio Processing","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Transport Canada","funders":"","keywords":"Computer science; Classifier (UML); Context (archaeology); Artificial intelligence; Perspective (graphical); Modality (human–computer interaction); Set (abstract data type); Context model; Speech recognition; Feature (linguistics); Machine learning; Human–computer interaction; Object (grammar)","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":[0.00007136303,0.00004886181,0.00006860351,0.00003466854,0.0002838566,0.0003420633,0.0004435226,0.00001823208,0.00008048329],"category_scores_gemma":[0.0002055307,0.00004173726,0.00003634291,0.00003355779,0.00007579623,0.001626667,0.0001213634,0.00006041101,0.00008772271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001065382,"about_ca_system_score_gemma":0.00002765578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001746273,"about_ca_topic_score_gemma":0.00009886919,"domain_scores_codex":[0.9995695,0.000007833458,0.0001113943,0.0001432486,0.00007640515,0.00009161115],"domain_scores_gemma":[0.9992926,0.0000477928,0.0001575933,0.0003118936,0.0001584514,0.00003168215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000007773643,0.00004275711,0.003341839,0.000006897468,0.000009950396,0.000002275981,0.0005534344,0.000002498892,0.01244756,0.0004342738,0.0001908667,0.9829599],"study_design_scores_gemma":[0.0003438239,0.00002514686,0.02445169,0.00003804935,0.000001742027,0.000006104206,0.00006413311,0.00377201,0.9623547,0.008651815,0.0002113018,0.00007949303],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5950978,0.00001056476,0.3413251,0.000795242,0.0005014947,0.00006976002,0.000003154311,0.00007808724,0.06211875],"genre_scores_gemma":[0.9126191,0.000001304233,0.08645764,0.0001065261,0.00003650401,0.000003211531,5.024229e-7,0.000002015074,0.0007732604],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9828804,"threshold_uncertainty_score":0.3298524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0477614163353707,"score_gpt":0.3402594354886167,"score_spread":0.292498019153246,"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."}}