{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002491972,0.0002842369,0.0003281337,0.001438741,0.001190103,0.0004917143,0.0006414248,0.0001918751,0.00000294694],"category_scores_gemma":[0.00007381913,0.0002868127,0.00003287692,0.001464131,0.0001896449,0.0006581364,0.0004220837,0.0009096107,0.00001664964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003893378,"about_ca_system_score_gemma":0.0007032749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001064269,"about_ca_topic_score_gemma":0.006114407,"domain_scores_codex":[0.9972519,0.0003512636,0.0002339139,0.0009787548,0.0007209927,0.000463233],"domain_scores_gemma":[0.998427,0.0003961643,0.0002337332,0.0004330636,0.0003831257,0.0001268884],"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":[0.005275387,0.001811797,0.2226695,0.00208764,0.003789425,0.006925119,0.1907636,0.00008339923,0.09522487,0.04908267,0.0009957202,0.4212909],"study_design_scores_gemma":[0.001195511,0.001478853,0.8336716,0.0001994583,0.00004415259,0.00002015125,0.1121117,0.0001840043,0.0405334,0.0002244263,0.009686698,0.00065007],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941661,0.00006857481,0.0005536767,0.0001842951,0.0001661585,0.0008861782,8.013255e-7,0.0004791592,0.003495058],"genre_scores_gemma":[0.9698238,0.000121417,0.0003179791,0.000002114529,0.0000279505,0.00002191556,0.00002827146,0.00002630874,0.02963028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.611002,"threshold_uncertainty_score":0.9999584,"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."}}