{"id":"W4360989756","doi":"10.1101/2023.03.25.534127","title":"RFIDeep: Unfolding the Potential of Deep Learning for Radio-Frequency Identification","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Avian ecology and behavior","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Moncton","funders":"Centre Scientifique de Monaco; Centre National de la Recherche Scientifique; Institut Polaire Français Paul Emile Victor; Deutsche Forschungsgemeinschaft","keywords":"Identification (biology); Deep learning; Phenology; Field (mathematics); Computer science; Workflow; Artificial intelligence; Machine learning; Convolutional neural network; Citizen science; Seabird; Data science; Ecology; Biology; Database","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":[0.001908309,0.0008412825,0.0003886288,0.0004500748,0.0003161893,0.001201251,0.001492768,0.001288553,0.001867954],"category_scores_gemma":[0.006107537,0.0004808144,0.000604569,0.000442578,0.001113178,0.002160589,0.002266863,0.002322399,0.0005623311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008741748,"about_ca_system_score_gemma":0.0008728669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005064408,"about_ca_topic_score_gemma":0.005412485,"domain_scores_codex":[0.9994172,0.0002235896,0.00002372739,0.0001462594,0.0001060457,0.00008318235],"domain_scores_gemma":[0.9980537,0.001253714,0.00009293624,0.0002551282,0.0002388698,0.0001056412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003438682,0.0003232643,0.008890977,0.0002359348,0.000173158,0.0002675519,0.0002620737,0.7501867,0.01017369,0.0200403,0.00690142,0.2022011],"study_design_scores_gemma":[0.000007993703,0.00003182729,0.0003803349,0.00001387497,0.000005688149,0.00001008918,0.00001426614,0.9863064,0.001854601,0.01059091,0.000777416,0.000006576619],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2194266,0.001583085,0.7617465,0.004540003,0.0002405092,0.00009435223,0.001079307,0.00585495,0.005434689],"genre_scores_gemma":[0.7950065,0.0004791042,0.1996232,0.0007835065,0.00008404969,0.0001562009,0.001011825,0.0003066945,0.002548915],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005064408,"threshold_uncertainty_score":0.0100922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01428940351682305,"score_gpt":0.2256775694541052,"score_spread":0.2113881659372822,"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."}}