{"id":"W4413190589","doi":"10.1016/j.atech.2025.101299","title":"Lightweight patch-level attention for efficient pig behavior detection: A novel dataset and approach","year":2025,"lang":"en","type":"article","venue":"Smart Agricultural Technology","topic":"Animal Behavior and Welfare Studies","field":"Veterinary","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ministry of Agriculture","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence","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":[0.0005719411,0.001160274,0.0008191519,0.001645979,0.0006851723,0.0008234414,0.001939537,0.001605952,0.002682424],"category_scores_gemma":[0.001083498,0.0002299831,0.0009834063,0.001115343,0.0004793372,0.00067534,0.001408059,0.001078607,0.001872191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007641347,"about_ca_system_score_gemma":0.00101401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01281653,"about_ca_topic_score_gemma":0.02175914,"domain_scores_codex":[0.999483,0.00006719982,0.00003534454,0.0002264197,0.0001057378,0.00008224422],"domain_scores_gemma":[0.9995939,0.00006601885,0.00003220743,0.0001297859,0.0001229299,0.00005517007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002106957,0.003698873,0.06423157,0.001075572,0.0004053348,0.00158946,0.0002573734,0.03585276,0.07972982,0.003721525,0.1413615,0.6659693],"study_design_scores_gemma":[0.0004752262,0.001612285,0.08267429,0.0001620814,0.0002922818,0.002701903,0.0007336551,0.7706792,0.04650528,0.008563448,0.08537326,0.0002270697],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6097307,0.0050545,0.2665096,0.002251336,0.001269144,0.001908533,0.08338562,0.01440479,0.01548572],"genre_scores_gemma":[0.5870534,0.001295784,0.2007886,0.0009579919,0.0004128453,0.001382312,0.195799,0.000309393,0.01200073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01281653,"threshold_uncertainty_score":0.02548385,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04812507289198443,"score_gpt":0.306253477903031,"score_spread":0.2581284050110466,"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."}}