{"id":"W4225334559","doi":"10.21105/joss.04038","title":"ADaPT-ML: A Data Programming Template for MachineLearning","year":2022,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Mitacs","keywords":"Computer science; Task (project management); Class (philosophy); Machine learning; Domain (mathematical analysis); Point (geometry); Labeled data; Artificial intelligence; Training set; Data type; Software deployment; Software engineering; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.004369868,0.0001080622,0.0002155268,0.0000713396,0.0008657387,0.0004143338,0.009315145,0.00001791248,0.00003714752],"category_scores_gemma":[0.0003065873,0.00007760664,0.00006637642,0.0002380923,0.00002103021,0.0008776282,0.006279064,0.0005177417,0.000002168983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005233762,"about_ca_system_score_gemma":0.0001788039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008389377,"about_ca_topic_score_gemma":0.000005745082,"domain_scores_codex":[0.9983916,0.0002729636,0.0004075857,0.0002104536,0.0004535581,0.0002637956],"domain_scores_gemma":[0.9978279,0.0004270872,0.000546584,0.001023892,0.00009885869,0.00007568521],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001668137,0.00008318154,0.001279302,0.00002754067,0.000122752,0.00003335397,0.009033279,0.1286553,0.00006207552,0.0006202215,0.009533009,0.8503832],"study_design_scores_gemma":[0.001163106,0.0004108355,0.0001407404,0.00006093324,0.00006376177,0.001285383,0.002001593,0.2368142,0.00002077936,0.002039256,0.7557527,0.0002467159],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007916346,0.0004175773,0.9887637,0.002184208,0.0002570763,0.0003682388,0.000008078305,0.00004910822,0.00003565629],"genre_scores_gemma":[0.3112874,0.000008215107,0.6867549,0.0006494235,0.000235091,0.00002089121,0.000007353186,0.0000383243,0.0009983672],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8501365,"threshold_uncertainty_score":0.9960449,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09902702177909116,"score_gpt":0.3346960179557344,"score_spread":0.2356689961766432,"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."}}