{"id":"W4402034755","doi":"10.32920/26866606","title":"Few-Shot Learning for Text Classification and Its Applications in Essay Scoring and Software Engineering","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University; Systems, Applications & Products in Data Processing (Canada); Brock University","funders":"","keywords":"Computer science; Shot (pellet); Artificial intelligence; One shot; Natural language processing; Software; Software engineering; Data science; Machine learning; Engineering; Programming language; Chemistry; Mechanical engineering","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":[0.0002279147,0.0001333045,0.0001267478,0.0002323321,0.00008036778,0.0001493058,0.0002688496,0.0001672808,0.000001524604],"category_scores_gemma":[0.00009529405,0.0001343535,0.00002098977,0.0001671518,0.00001464896,0.00008819751,0.0007167967,0.0005097442,0.000003001922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007529808,"about_ca_system_score_gemma":0.000134191,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004874575,"about_ca_topic_score_gemma":0.000005155285,"domain_scores_codex":[0.9990902,0.00001009484,0.0001738668,0.000519364,0.00007106488,0.0001353969],"domain_scores_gemma":[0.9993773,0.0002812042,0.00005338057,0.0002069601,0.00004562812,0.0000355259],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[5.996973e-7,0.0000327711,0.006840779,0.0006556924,0.00002224019,4.680054e-7,0.0004159211,0.002009101,0.0005773974,0.9680372,0.0000293907,0.02137844],"study_design_scores_gemma":[0.0002156196,0.00003722505,0.06196196,0.0006734336,0.00003218807,0.0000125272,0.000369597,0.8217686,0.001717126,0.1057894,0.006768247,0.000654055],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09373,0.002297399,0.8993375,0.002818149,0.0002663085,0.0007840085,0.000003329544,0.000495375,0.0002679919],"genre_scores_gemma":[0.9149594,0.0001210786,0.08336989,0.00001451786,0.00004340432,0.0009939638,0.00001775748,0.00001095274,0.0004689835],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8622478,"threshold_uncertainty_score":0.5478776,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03958266275906991,"score_gpt":0.3173852605107172,"score_spread":0.2778025977516473,"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."}}