{"id":"W7009548693","doi":"","title":"Enhancing Text Annotation with Few-shot and Active Learning: A Comprehensive Study and Tool Development","year":2023,"lang":"en","type":"dissertation","venue":"Spectrum Research Repository (Concordia University)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Concordia University","keywords":"Process (computing); Task (project management); Field (mathematics); Feature (linguistics); Matching (statistics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004301281,0.001113449,0.001305386,0.003122274,0.001324403,0.002777156,0.00359784,0.002212129,0.00273038],"category_scores_gemma":[0.01301702,0.0007202657,0.001337783,0.002464945,0.001407923,0.006253894,0.002110442,0.002561107,0.002656991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001043694,"about_ca_system_score_gemma":0.001474449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003227553,"about_ca_topic_score_gemma":0.003158501,"domain_scores_codex":[0.9963896,0.001117153,0.0002101349,0.0008377619,0.001324452,0.0001208984],"domain_scores_gemma":[0.9883782,0.007339674,0.0004400882,0.001138355,0.002430306,0.0002733745],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001223868,0.0002074738,0.0004797076,0.0006329861,0.00005427345,0.000118505,0.000546247,0.008754752,0.01361001,0.006406158,0.005845149,0.9632222],"study_design_scores_gemma":[0.000048945,0.0004134614,0.001820043,0.0005886185,0.0001372135,0.0008020925,0.001110356,0.781117,0.08840194,0.03435613,0.09101566,0.0001886608],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006846137,0.005159077,0.9784445,0.0005973243,0.0002572091,0.0001751513,0.000162228,0.005031965,0.003326316],"genre_scores_gemma":[0.117654,0.006747602,0.8581312,0.0006989719,0.0003733549,0.0004312327,0.001532559,0.001007346,0.01342381],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004301281,"threshold_uncertainty_score":0.02274764,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04011149522743568,"score_gpt":0.2951301077823477,"score_spread":0.255018612554912,"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."}}