{"id":"W4404569111","doi":"10.48550/arxiv.2411.09816","title":"Learning Fine-grained Parameter Sharing via Sparse Tensor Decomposition","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Tensor decomposition and applications","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Alberta Innovates","keywords":"Tensor (intrinsic definition); Computer science; Mathematics; Artificial intelligence; Pure 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007604333,0.001720096,0.0007885633,0.0006956977,0.0003985864,0.001060164,0.001457488,0.0008520449,0.00308822],"category_scores_gemma":[0.003989913,0.000485392,0.0006116871,0.0008655257,0.0008296374,0.00352102,0.001652189,0.002075299,0.001673587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008500163,"about_ca_system_score_gemma":0.001497149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006173651,"about_ca_topic_score_gemma":0.01226782,"domain_scores_codex":[0.9993912,0.0001209383,0.00003679683,0.0001505199,0.0002142124,0.0000863489],"domain_scores_gemma":[0.9990374,0.000216586,0.00009062274,0.0004313304,0.0001680451,0.00005609373],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004085345,0.0001960346,0.001642633,0.0001595343,0.0001241224,0.0002127578,0.0001615114,0.4555891,0.03854996,0.01831092,0.0145848,0.4700601],"study_design_scores_gemma":[0.00001365314,0.00004535907,0.0001278451,0.000007189295,0.00001109751,0.00002869138,0.00002146474,0.9802535,0.008777649,0.008788731,0.001914095,0.00001085917],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05732762,0.0006612767,0.9270552,0.0004903835,0.0001509931,0.00007444792,0.0006513058,0.009801518,0.003787356],"genre_scores_gemma":[0.634059,0.0006188705,0.354787,0.0003628526,0.0001191688,0.0001877443,0.002787565,0.0009546846,0.006123156],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006173651,"threshold_uncertainty_score":0.0122754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1109507560374898,"score_gpt":0.2582313782133282,"score_spread":0.1472806221758384,"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."}}