{"id":"W2748195089","doi":"10.48550/arxiv.1708.04320","title":"Situation Recognition with Graph Neural Networks","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Computer science; Salient; Graph; Artificial intelligence; Artificial neural network; Action (physics); Verb; Noun; Task (project management); Machine learning; Natural language processing; Pattern recognition (psychology); Theoretical computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004033314,0.001048278,0.0004512409,0.001527532,0.0004906286,0.001034222,0.001161408,0.001218072,0.002103773],"category_scores_gemma":[0.002336823,0.0005001323,0.0009200366,0.001209793,0.0006376696,0.00283972,0.0008291478,0.001366994,0.0006767607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001149035,"about_ca_system_score_gemma":0.0004987119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01130078,"about_ca_topic_score_gemma":0.01514759,"domain_scores_codex":[0.999637,0.00008840249,0.00001584496,0.0001612971,0.00005352334,0.00004396882],"domain_scores_gemma":[0.99936,0.0002886998,0.0001123544,0.00009848086,0.00009492189,0.00004552404],"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":[0.0002827988,0.0002830346,0.006293825,0.0002011901,0.0001894243,0.0003674467,0.0002835455,0.6321286,0.01064134,0.02417592,0.008488323,0.3166646],"study_design_scores_gemma":[0.0000052965,0.00001832766,0.0005312774,0.000008991418,0.00001465236,0.00003276564,0.00002597058,0.9672903,0.00141318,0.02987769,0.0007723251,0.000009145816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1275025,0.001301587,0.8556032,0.001436762,0.0002108791,0.0001233603,0.0008953142,0.004502176,0.008424185],"genre_scores_gemma":[0.8256938,0.0005011963,0.1689024,0.0003027851,0.00007714616,0.00007758768,0.001280435,0.000132992,0.003031628],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01130078,"threshold_uncertainty_score":0.02247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07201039835022935,"score_gpt":0.2047485201465925,"score_spread":0.1327381217963632,"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."}}