{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001916868,0.0002632682,0.0002164743,0.0002029738,0.0004361662,0.0002899283,0.001749089,0.000229072,0.00001264888],"category_scores_gemma":[0.00003199385,0.0002832422,0.000114526,0.000298677,0.0001081929,0.0004716887,0.0009220919,0.0007885898,0.00006333571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009081222,"about_ca_system_score_gemma":0.00007418852,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008569923,"about_ca_topic_score_gemma":0.0001341136,"domain_scores_codex":[0.9983748,0.0001313223,0.0001323128,0.001008106,0.00008488615,0.0002685865],"domain_scores_gemma":[0.9974461,0.00008382006,0.0004501399,0.001679902,0.0002097931,0.0001302497],"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":[0.00002089987,0.00005097728,0.006327004,0.00001809349,0.00004560778,0.00005051606,0.00009362588,0.9673151,0.000004641324,0.01374217,0.00005545367,0.01227592],"study_design_scores_gemma":[0.000313865,0.00004164541,0.02183422,0.0000518341,0.00005301856,0.000005772744,0.000006438674,0.9495686,0.000007244694,0.02775129,0.00002956708,0.000336494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2399393,0.00001416327,0.7575838,0.0002563244,0.0001987038,0.000294065,0.000005273532,0.0003221789,0.00138622],"genre_scores_gemma":[0.9938417,0.00003978615,0.005631281,0.00006742642,0.0001018025,0.000004863211,0.00009453394,0.00001870015,0.0001998796],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7539024,"threshold_uncertainty_score":0.999962,"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."}}