{"id":"W4408815702","doi":"10.5194/oos2025-44","title":"Scaling marine mammals monitoring using AI: A human-in-the-loop solution to analyze aerial datasets","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Marine animal studies overview","field":"Environmental Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Wildlife; Artificial intelligence; Machine learning; Data mining; Ecology; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002358934,0.001519507,0.0006746417,0.002007001,0.0005979705,0.001443534,0.001714291,0.001061768,0.002775539],"category_scores_gemma":[0.006760063,0.0004471466,0.0007574002,0.001649549,0.0006982563,0.0020975,0.002020682,0.00148693,0.001839053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005411875,"about_ca_system_score_gemma":0.001017548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01434067,"about_ca_topic_score_gemma":0.02343361,"domain_scores_codex":[0.9982338,0.000470235,0.0001034114,0.0007137374,0.000364405,0.0001143702],"domain_scores_gemma":[0.9960127,0.001715102,0.0002820312,0.0008287414,0.0009682216,0.0001932163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003072199,0.0003476344,0.0170137,0.0003201489,0.0003525064,0.0003145069,0.000732773,0.05051129,0.04356303,0.001816511,0.01868908,0.8660316],"study_design_scores_gemma":[0.00006021995,0.0001562191,0.01205307,0.00006410784,0.0000845129,0.0002197364,0.0006277421,0.9369522,0.02234975,0.01133139,0.01605102,0.00005009808],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.0649507,0.0007939849,0.9014537,0.001184111,0.0002236752,0.0003278657,0.001421021,0.02487556,0.004769292],"genre_scores_gemma":[0.3131155,0.0002998469,0.6780106,0.0006348389,0.0001538269,0.0002524299,0.003518511,0.0009237045,0.003090794],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01434067,"threshold_uncertainty_score":0.02851439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05716156529853008,"score_gpt":0.3441741025108357,"score_spread":0.2870125372123057,"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."}}