{"id":"W2550082179","doi":"10.1142/s1793351x16400122","title":"An Empirical Study of the Textual Content of Online Videos","year":2016,"lang":"en","type":"article","venue":"International Journal of Semantic Computing","topic":"Video Analysis and Summarization","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Information retrieval; Cluster analysis; Multimedia; Video retrieval; Annotation; Empirical research; Content (measure theory); World Wide Web; 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":[],"consensus_categories":[],"category_scores_codex":[0.0006234527,0.00007487783,0.0002340346,0.0001789611,0.00003550477,0.0000378079,0.001434302,0.00002220775,0.000007539042],"category_scores_gemma":[0.0002275644,0.00003892112,0.0001435753,0.0001975386,0.00003948379,0.0002696372,0.0002625838,0.00008494982,5.405195e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003700063,"about_ca_system_score_gemma":0.00008290371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000427241,"about_ca_topic_score_gemma":0.000035027,"domain_scores_codex":[0.9979469,0.0001582197,0.0008683206,0.0001233495,0.0008185922,0.0000846667],"domain_scores_gemma":[0.9973997,0.0002351399,0.0009763727,0.000229252,0.001118207,0.00004131137],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004732717,0.002355355,0.7976269,0.000007095958,0.000528728,0.00003084715,0.003366141,0.004332627,0.03797957,0.002000347,0.00009674246,0.1516284],"study_design_scores_gemma":[0.001747655,0.0006753302,0.8300751,0.0003848235,0.0000558124,0.0000919282,0.001205573,0.1618651,0.003199302,0.0005537677,0.00004085492,0.0001047537],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6758097,0.00001255681,0.3225,0.00129209,0.0003310361,0.00003800922,0.000001215942,0.000003566726,0.00001182007],"genre_scores_gemma":[0.9976529,0.000003868187,0.002063046,0.00009447198,0.0001676617,8.466412e-8,2.83307e-7,0.000003493142,0.00001418826],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3218432,"threshold_uncertainty_score":0.2665314,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04197526496538793,"score_gpt":0.3309049403531081,"score_spread":0.2889296753877201,"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."}}