{"id":"W3022835052","doi":"10.48550/arxiv.2005.06583","title":"Do Saliency Models Detect Odd-One-Out Targets? New Datasets and Evaluations","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Salience (neuroscience); Computer science; Singleton; Artificial intelligence; Fixation (population genetics); Machine learning; Training set; Field (mathematics); Pattern recognition (psychology); Mathematics","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":[0.0001502324,0.0001355982,0.0001341929,0.0001046133,0.0002275115,0.0001185865,0.0005424449,0.00006200286,0.00006058255],"category_scores_gemma":[0.00004567516,0.0001549946,0.00006206192,0.0006550566,0.00004604947,0.001276936,0.0002999719,0.0001306669,0.0001714706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003906719,"about_ca_system_score_gemma":0.00007866877,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000440479,"about_ca_topic_score_gemma":0.00003106553,"domain_scores_codex":[0.9987828,0.00009992952,0.0001384719,0.0006390257,0.0001212889,0.0002185282],"domain_scores_gemma":[0.9991375,0.00003414064,0.00007914785,0.0003810379,0.00006033737,0.0003078133],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000138285,0.0003073103,0.002010411,0.00008425461,0.0001815278,0.0001872841,0.005346095,0.1049805,0.008355848,0.8049833,0.01246024,0.06096491],"study_design_scores_gemma":[0.0007276271,0.000189591,0.0008754976,0.00001138284,0.00004139381,0.00000416618,0.00009294518,0.9464174,0.0006385479,0.04880301,0.001922653,0.0002757764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04621088,0.00009211026,0.9516215,0.0005000082,0.0001428866,0.0001569157,0.0000167356,0.0002057895,0.001053192],"genre_scores_gemma":[0.9969937,0.00008438677,0.002079776,0.0005277461,0.00004660344,3.850648e-7,0.00001254435,0.000007148728,0.0002477143],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9507828,"threshold_uncertainty_score":0.6320496,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1759575913605596,"score_gpt":0.2441337347209249,"score_spread":0.06817614336036537,"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."}}