{"id":"W4403940973","doi":"10.1007/978-3-031-73226-3_16","title":"Model Breadcrumbs: Scaling Multi-task Model Merging with Sparse Masks","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Scaling; Task (project management); Algorithm; Artificial intelligence; Theoretical computer science; Mathematics; Geometry","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":[0.001528057,0.00200317,0.002150286,0.001004669,0.0009034511,0.002010611,0.003122209,0.002045725,0.01114595],"category_scores_gemma":[0.005032686,0.00143199,0.00210074,0.001692197,0.0006345602,0.003264433,0.004312898,0.003068795,0.00438534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008094863,"about_ca_system_score_gemma":0.001630448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01342368,"about_ca_topic_score_gemma":0.01992542,"domain_scores_codex":[0.9991348,0.0001778212,0.0000491928,0.0002670714,0.0002555987,0.0001155432],"domain_scores_gemma":[0.9983982,0.000537436,0.00007509822,0.0006252474,0.0002475283,0.0001164566],"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":[0.0008443292,0.0002910137,0.0006942491,0.0002585764,0.0004090092,0.0002226862,0.0003074476,0.1925912,0.02995463,0.008459045,0.02613387,0.739834],"study_design_scores_gemma":[0.00003251174,0.00006114625,0.0001566988,0.00001213228,0.00004185301,0.00005955586,0.00003873009,0.9783508,0.006174095,0.01100872,0.004042516,0.00002126245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008108763,0.0003736245,0.9815756,0.0001872631,0.0001868941,0.0000932839,0.0002368004,0.007454699,0.001783074],"genre_scores_gemma":[0.166531,0.000389019,0.8213387,0.000464925,0.0002075533,0.0002580131,0.001861051,0.002966364,0.005983332],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01342368,"threshold_uncertainty_score":0.03728694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03907107415938375,"score_gpt":0.2588326428358412,"score_spread":0.2197615686764574,"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."}}