{"id":"W4400680152","doi":"10.1109/saner60148.2024.00044","title":"CEDAR: Continuous Testing of Deep Learning Libraries","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"National Science Foundation","keywords":"Computer science; Deep learning; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004915485,0.002009392,0.0007411081,0.002196815,0.0004913334,0.001750519,0.00479314,0.001103651,0.002926221],"category_scores_gemma":[0.02799028,0.0009081457,0.001140965,0.00103781,0.001729395,0.004655322,0.002519979,0.002203053,0.001157186],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001733838,"about_ca_system_score_gemma":0.002959643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007554784,"about_ca_topic_score_gemma":0.008895365,"domain_scores_codex":[0.9939197,0.001611967,0.0005486009,0.001374682,0.001950466,0.0005944926],"domain_scores_gemma":[0.9749399,0.01281748,0.002332706,0.00563722,0.003480511,0.0007922459],"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":[0.002233437,0.001247768,0.06881341,0.00115464,0.0004780501,0.0009298298,0.0005742507,0.1498224,0.05218881,0.009765559,0.03548342,0.6773085],"study_design_scores_gemma":[0.0002454363,0.0005799511,0.005521994,0.0000799621,0.0000730618,0.0002735477,0.0001005261,0.9214667,0.05902808,0.006263143,0.006285726,0.00008184149],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2841825,0.001716698,0.5058718,0.0009098482,0.0002456767,0.0003840585,0.001934292,0.2006373,0.004117771],"genre_scores_gemma":[0.7899831,0.0002713451,0.1999195,0.0006838855,0.00004644176,0.0002707332,0.003048365,0.003587255,0.002189312],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007554784,"threshold_uncertainty_score":0.02599591,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02153558194571753,"score_gpt":0.2542780030835139,"score_spread":0.2327424211377964,"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."}}