{"id":"W4403113340","doi":"10.1093/bioinformatics/btae589","title":"Learning to explain is a good biomedical few-shot learner","year":2024,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China; Fundamental Research Funds for the Central Universities; Institute for Catastrophic Loss Reduction","keywords":"Computer science; Shot (pellet); One shot; Artificial intelligence; Chemistry; Engineering; Mechanical engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.0006842389,0.0002050653,0.0001890722,0.0003823239,0.000212255,0.0008585477,0.0009559494,0.0001222466,0.0001688124],"category_scores_gemma":[0.0002237391,0.0001779664,0.0001019054,0.001373034,0.00006360257,0.001176355,0.0004868513,0.0003638254,0.009011252],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001045034,"about_ca_system_score_gemma":0.0001705402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003027955,"about_ca_topic_score_gemma":0.000005250083,"domain_scores_codex":[0.9979529,0.00004073828,0.0005378892,0.0002938246,0.0005977314,0.000576917],"domain_scores_gemma":[0.9988585,0.0001826227,0.0000566473,0.0005071816,0.00007729267,0.0003177384],"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":[0.000008806258,0.0001022729,0.00009936187,0.0003572509,0.00007211043,0.0001520492,0.1003853,0.00082361,0.001328994,0.1382489,0.08174791,0.6766735],"study_design_scores_gemma":[0.0000372579,0.0002370117,0.00001208266,0.0001007346,0.000005050728,0.00003419103,0.002103454,0.54781,0.004902814,0.0009027354,0.4436105,0.0002441513],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01251619,0.0001895357,0.9557982,0.007067724,0.001255703,0.0003205755,0.000006176235,0.001034876,0.02181103],"genre_scores_gemma":[0.6854168,0.00009861559,0.2954409,0.006416241,0.0005269985,0.00008907572,0.00002210421,0.00006624618,0.01192307],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6764293,"threshold_uncertainty_score":0.9917604,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03556238021742247,"score_gpt":0.2964944806966772,"score_spread":0.2609321004792547,"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."}}