{"id":"W4282038291","doi":"10.1007/s42991-022-00253-3","title":"Artificial intelligence for right whale photo identification: from data science competition to worldwide collaboration","year":2022,"lang":"en","type":"article","venue":"Mammalian Biology","topic":"Marine animal studies overview","field":"Environmental Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Marine Fisheries Service; Australian Antarctic Division; Bureau of Ocean Energy Management; National Oceanic and Atmospheric Administration","keywords":"Animal ecology; Biology; Identification (biology); Competition (biology); Citizen science; Whale; Data science; Fishery; Zoology; Ecology; Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008776204,0.0001112274,0.0001434364,0.0000577457,0.000833292,0.00006849832,0.001203365,0.00002384247,0.01012042],"category_scores_gemma":[0.0001742061,0.0001153847,0.00002158311,0.0009812035,0.0003100247,0.0002829013,0.002155448,0.00007694937,0.0005615564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003189039,"about_ca_system_score_gemma":0.00003365176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001999689,"about_ca_topic_score_gemma":0.009317257,"domain_scores_codex":[0.9982795,0.00009088401,0.0003371151,0.000771884,0.0002283547,0.0002922995],"domain_scores_gemma":[0.9990427,0.00008765235,0.0001211686,0.0006355274,0.0000314134,0.00008148213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0008254712,0.0008737193,0.06596693,0.00004269079,0.00006830517,0.00002108995,0.002438413,0.004270389,0.4262964,0.1288004,0.06663163,0.3037646],"study_design_scores_gemma":[0.00007713706,0.0003089324,0.03024598,0.000004127351,0.00002232747,0.000003418246,0.000731272,0.003872184,0.01986677,0.01332119,0.9311971,0.0003495601],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9274367,0.0001784556,0.03956284,0.01457489,0.002386802,0.002760004,0.003258238,0.0001389756,0.009703091],"genre_scores_gemma":[0.993843,0.00001038478,0.003613431,0.00115572,0.0001139322,0.0002870179,0.0006269088,0.000008951007,0.0003407185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8645655,"threshold_uncertainty_score":0.9907845,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05272410312660022,"score_gpt":0.3143610380498305,"score_spread":0.2616369349232303,"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."}}