{"id":"W2573425638","doi":"","title":"Distraction-based neural networks for modeling documents","year":2016,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Automatic summarization; Computer science; Distraction; GRASP; Artificial neural network; Representation (politics); Artificial intelligence; Natural language processing; Traverse; Information retrieval; Machine learning; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001133525,0.00100516,0.0007083417,0.001234916,0.0003610871,0.0008548521,0.001705898,0.001367037,0.001706061],"category_scores_gemma":[0.004334306,0.0003835753,0.0007674712,0.001625191,0.0004856942,0.001800916,0.0006992488,0.002224764,0.0005663378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001507738,"about_ca_system_score_gemma":0.000487492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007560385,"about_ca_topic_score_gemma":0.009002744,"domain_scores_codex":[0.9996195,0.0001348726,0.00002425653,0.0001268029,0.00005370995,0.00004071113],"domain_scores_gemma":[0.9988685,0.0007273203,0.0001229742,0.0000871127,0.0001557915,0.00003836815],"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":[0.0001788505,0.00010644,0.001660289,0.0001047629,0.00006743332,0.0000801744,0.0001418137,0.9070443,0.002310797,0.01058839,0.002160335,0.07555647],"study_design_scores_gemma":[0.000004975131,0.00001118073,0.0001016277,0.000004022051,0.00000500141,0.00000647212,0.000004694368,0.995483,0.0002547498,0.003826982,0.0002940553,0.000003250125],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1277213,0.003166227,0.8617611,0.00105975,0.0002323304,0.0001394108,0.0008907966,0.00189478,0.003134407],"genre_scores_gemma":[0.862803,0.001249006,0.1254451,0.0003461314,0.0002266591,0.0004108938,0.001842603,0.0001128783,0.007563742],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007560385,"threshold_uncertainty_score":0.01503271,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1398677867114096,"score_gpt":0.3404630588579287,"score_spread":0.2005952721465191,"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."}}