{"id":"W4288568489","doi":"10.48550/arxiv.1902.09324","title":"Similarity Learning Networks for Animal Individual Re-Identification --\\n Beyond the Capabilities of a Human Observer","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Wildlife Ecology and Conservation","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Artificial intelligence; Identification (biology); Similarity (geometry); Convolutional neural network; Computer science; Machine learning; Deep learning; Population; Set (abstract data type); Range (aeronautics); Animal species; Task (project management); Pattern recognition (psychology); Ecology; Image (mathematics); Biology; Evolutionary biology","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":[0.00205872,0.001207855,0.0009482467,0.001792296,0.0005659792,0.001174747,0.001848166,0.001648177,0.002465698],"category_scores_gemma":[0.005315446,0.0002528469,0.0007721118,0.001139257,0.0007810106,0.003567964,0.002154395,0.001589083,0.001286754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00140719,"about_ca_system_score_gemma":0.0009821123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007396591,"about_ca_topic_score_gemma":0.007932276,"domain_scores_codex":[0.9986587,0.000273317,0.00007947949,0.0004870151,0.0003394281,0.0001620706],"domain_scores_gemma":[0.9987639,0.0003280909,0.000184657,0.0003614912,0.0002734323,0.00008832739],"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":[0.0007659865,0.0004283069,0.01276135,0.0003000908,0.0003315514,0.0002035291,0.0001610545,0.3263261,0.01068573,0.008300084,0.01236142,0.6273747],"study_design_scores_gemma":[0.00001701662,0.0001770472,0.002630915,0.00002677841,0.0000350549,0.0001101752,0.00007679407,0.9768456,0.008635336,0.008524383,0.002900812,0.00002011513],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4759516,0.008294786,0.4886757,0.001695719,0.0005577113,0.0003295155,0.002276648,0.008577243,0.01364106],"genre_scores_gemma":[0.87705,0.0007870875,0.1113259,0.0003578689,0.0001135609,0.000107182,0.00448744,0.0002448674,0.005526091],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007396591,"threshold_uncertainty_score":0.01470703,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07621065817328487,"score_gpt":0.2015430119256141,"score_spread":0.1253323537523293,"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."}}