{"id":"W4286902830","doi":"10.48550/arxiv.2110.08232","title":"Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Compute Canada","keywords":"FLOPS; Hyperparameter; Computer science; Regularization (linguistics); Artificial intelligence; Reduction (mathematics); Machine learning; Pruning; Artificial neural network; Pattern recognition (psychology); Algorithm; Mathematics","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":[0.000335346,0.0004472148,0.0004083862,0.0002189952,0.0003249918,0.0003849195,0.001357497,0.0003810269,0.00005827877],"category_scores_gemma":[0.00001938746,0.0004777774,0.0002060224,0.0009321631,0.00009325407,0.0006878788,0.001074837,0.0009817855,0.00002841581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003406119,"about_ca_system_score_gemma":0.0004088423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008006572,"about_ca_topic_score_gemma":0.00002941295,"domain_scores_codex":[0.9971635,0.0003571641,0.0002468586,0.001537427,0.0002366367,0.0004583904],"domain_scores_gemma":[0.9979195,0.00007080249,0.0002822251,0.001292267,0.0002157538,0.0002194521],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009845411,0.0004650445,0.009288909,0.0003758025,0.0006085126,0.0007485757,0.01516683,0.9483839,0.0001325408,0.01659574,0.00006879536,0.008066935],"study_design_scores_gemma":[0.0008347718,0.00008079752,0.001429576,0.0001834898,0.00009343965,0.00003127573,0.002446169,0.9934121,0.0000112369,0.0004888413,0.0004680055,0.0005202639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3072701,0.00009764785,0.6847852,0.0000707472,0.0002374573,0.0003553921,0.00000601215,0.0006831621,0.006494331],"genre_scores_gemma":[0.9430649,0.000126189,0.05384116,0.0001374051,0.00004656985,0.000005083816,0.00007692188,0.00004720959,0.002654563],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6357948,"threshold_uncertainty_score":0.9997674,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03543727667811387,"score_gpt":0.1717486076622883,"score_spread":0.1363113309841745,"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."}}