{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004166583,0.001749218,0.001175471,0.001348559,0.0007122626,0.003676278,0.005106749,0.002285206,0.02443701],"category_scores_gemma":[0.01905547,0.001302034,0.003020637,0.00178429,0.001182798,0.004285204,0.004597764,0.006415279,0.02099271],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000861679,"about_ca_system_score_gemma":0.001548712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001591727,"about_ca_topic_score_gemma":0.003336636,"domain_scores_codex":[0.9971506,0.0008026091,0.0003340993,0.0007277009,0.0008286088,0.0001563164],"domain_scores_gemma":[0.9945016,0.003072341,0.0001982852,0.001425452,0.0006458523,0.0001564311],"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":[0.0005944629,0.0002832905,0.001916226,0.0007076861,0.0002650081,0.0003537921,0.0004233145,0.07422519,0.005135004,0.1333156,0.1559487,0.6268317],"study_design_scores_gemma":[0.0001331171,0.00006361375,0.0002739747,0.0001082441,0.00004562271,0.0002670208,0.00005726693,0.6084046,0.01216308,0.2386312,0.1397894,0.00006269635],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.0002784109,0.00005565802,0.9742556,0.0002015593,0.00008330515,0.00007508443,0.0009854676,0.02257445,0.001490513],"genre_scores_gemma":[0.01471864,0.0001607151,0.9660366,0.0005260731,0.0001364842,0.0008291421,0.003405623,0.009700862,0.004485851],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.02443701,"threshold_uncertainty_score":0.08174992,"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."}}