{"id":"W4399304331","doi":"10.1145/3650200.3656619","title":"Sylva: Sparse Embedded Adapters via Hierarchical Approximate Second-Order Information","year":2024,"lang":"en","type":"article","venue":"","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Order (exchange); Theoretical computer science; Artificial intelligence; Mathematics","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":[0.0009954177,0.001683038,0.001035074,0.0007635676,0.0005963191,0.001437257,0.003781665,0.001541266,0.008629056],"category_scores_gemma":[0.00574887,0.000924267,0.001202934,0.0007268341,0.0008884282,0.003214024,0.003355492,0.003136,0.0049914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009354054,"about_ca_system_score_gemma":0.001505426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009336999,"about_ca_topic_score_gemma":0.02012108,"domain_scores_codex":[0.9990987,0.0001743243,0.0000504548,0.0002440872,0.0003057279,0.0001267316],"domain_scores_gemma":[0.9987446,0.0004078695,0.00007162565,0.0005287302,0.0001697414,0.00007736666],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008303178,0.0003226363,0.002256925,0.0002823945,0.000274544,0.0004496151,0.0004320827,0.2641364,0.0441688,0.01744893,0.038702,0.6306953],"study_design_scores_gemma":[0.0000337341,0.00005665331,0.0001365437,0.000007652246,0.000009956814,0.00005244844,0.00002768212,0.981353,0.008565121,0.006402872,0.003333762,0.00002059611],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02556093,0.0004686602,0.8960657,0.0002659818,0.0001616677,0.0001413733,0.0005519879,0.07334075,0.003442918],"genre_scores_gemma":[0.4095765,0.0002499561,0.5734253,0.0007901507,0.00009022897,0.0004647538,0.00331048,0.00415648,0.007936258],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009336999,"threshold_uncertainty_score":0.02886707,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0118654741034358,"score_gpt":0.249274410906154,"score_spread":0.2374089368027182,"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."}}