{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006874714,0.000826874,0.0006842617,0.001122138,0.0003605808,0.001150434,0.001943083,0.001088427,0.003971215],"category_scores_gemma":[0.004076664,0.0003575137,0.0009975438,0.0005722514,0.0005931027,0.002651178,0.00142517,0.001713151,0.001146403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005721931,"about_ca_system_score_gemma":0.0005691105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002201245,"about_ca_topic_score_gemma":0.003215045,"domain_scores_codex":[0.9994755,0.00006048242,0.00002612295,0.0001988166,0.0001716751,0.00006743506],"domain_scores_gemma":[0.998944,0.0003164996,0.000149588,0.0003232929,0.0001756701,0.00009099599],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000384958,0.0003441403,0.002778744,0.0002531587,0.0001113636,0.000274676,0.0002454185,0.04362217,0.09460083,0.0128883,0.007327861,0.8371683],"study_design_scores_gemma":[0.00001996736,0.0001388801,0.002244849,0.00002595965,0.00002946468,0.0001818353,0.00005994765,0.9293717,0.03655776,0.02849401,0.002850884,0.0000248104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04533472,0.0002687527,0.9473245,0.0002359297,0.00007781516,0.0001077044,0.0002335353,0.003692998,0.002724044],"genre_scores_gemma":[0.5746993,0.0002052129,0.420563,0.0002356071,0.00009109376,0.00006865025,0.001048225,0.0001676487,0.002921273],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003971215,"threshold_uncertainty_score":0.01328504,"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."}}