{"id":"W2978562747","doi":"10.48550/arxiv.1910.01833","title":"Few-Shot Abstract Visual Reasoning With Spectral Features","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Preprocessor; Artificial intelligence; Computer science; Visual reasoning; Task (project management); Image (mathematics); Pattern recognition (psychology); One shot; Machine learning; Shot (pellet); Computer vision","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001883642,0.0003386017,0.0002996665,0.0002751732,0.0001820254,0.0002719952,0.001075393,0.0002742391,0.00005348169],"category_scores_gemma":[0.00001267172,0.0003341321,0.0002038934,0.0005081832,0.00007162536,0.000503404,0.000653968,0.0008177207,0.0002219068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001939238,"about_ca_system_score_gemma":0.000178875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001911936,"about_ca_topic_score_gemma":0.00009713362,"domain_scores_codex":[0.9980506,0.00007643425,0.0001603944,0.001148848,0.000170153,0.0003936204],"domain_scores_gemma":[0.9986457,0.00003860918,0.0002534768,0.0007801022,0.0001250692,0.0001570976],"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":[0.000622261,0.001024552,0.03862667,0.0005173898,0.0007511875,0.002456985,0.001461848,0.5320321,0.001879318,0.4129806,0.002285954,0.005361147],"study_design_scores_gemma":[0.002343232,0.0009844264,0.4094962,0.0007173177,0.0002091859,0.0001571508,0.0004904405,0.5680996,0.002541718,0.01098398,0.001397431,0.002579314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7453587,0.00003008884,0.2403253,0.00007107836,0.0008965185,0.0002693848,0.000004257352,0.0003985026,0.01264614],"genre_scores_gemma":[0.9941632,0.00003730974,0.0007896889,0.00008161891,0.0001036821,6.54564e-7,0.00001384961,0.00002019358,0.004789825],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4019967,"threshold_uncertainty_score":0.9999111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05233413039087991,"score_gpt":0.2163553003662032,"score_spread":0.1640211699753233,"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."}}