{"id":"W4404031565","doi":"10.1109/icccnt61001.2024.10724595","title":"Mitigating Annotation Burden in Active Learning with Transfer Learning and Iterative Acquisition Functions","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"American Water (Canada)","funders":"","keywords":"Computer science; Annotation; Transfer of learning; Active learning (machine learning); Iterative learning control; Artificial intelligence; Machine learning","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002170305,0.0001163197,0.0001004811,0.000192747,0.0002183497,0.0003978454,0.00006425672,0.00003871124,0.00003979999],"category_scores_gemma":[0.00002339327,0.00009381116,0.00002100807,0.0005210669,0.00002802143,0.0007804172,0.00002804007,0.0005373431,0.00001708786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003257118,"about_ca_system_score_gemma":0.00003159912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000105393,"about_ca_topic_score_gemma":0.00001885297,"domain_scores_codex":[0.9990231,0.0001659451,0.0001244579,0.0003643942,0.0001516347,0.0001704869],"domain_scores_gemma":[0.9996535,0.0001899487,0.00001584381,0.0000537171,0.00004340904,0.00004360408],"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":[0.00002583323,0.00002278197,0.004448404,0.00007882234,0.00005520533,0.00008657939,0.05036722,0.0856466,0.00444402,0.01426329,0.00001760204,0.8405436],"study_design_scores_gemma":[0.0002943863,0.0002936747,0.004235228,0.0002119151,0.000007191366,0.00004054194,0.002396884,0.9903396,0.0005003502,0.0002523478,0.00125081,0.0001770745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3230487,0.0001403851,0.6709946,0.0009950394,0.00006748785,0.00009097915,5.21231e-7,0.0003370135,0.004325308],"genre_scores_gemma":[0.9894931,0.00001041806,0.008198386,0.00003298954,0.00008221603,0.00001908271,0.00001228181,0.00001057131,0.002140941],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.904693,"threshold_uncertainty_score":0.3836433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005467159691514076,"score_gpt":0.2421948565442394,"score_spread":0.2367276968527253,"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."}}