{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002063069,0.0004042337,0.0004319485,0.0003373463,0.0002368286,0.0001569204,0.0005443264,0.0003519289,0.0003111097],"category_scores_gemma":[0.00007002742,0.0004626521,0.0004043144,0.0004033037,0.00008591325,0.00008745187,0.001078031,0.001256025,0.0007381628],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002308047,"about_ca_system_score_gemma":0.0000449541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004364757,"about_ca_topic_score_gemma":0.00003266443,"domain_scores_codex":[0.998016,0.00009633235,0.0003480671,0.001084583,0.0001006001,0.0003544368],"domain_scores_gemma":[0.9982801,0.0003129232,0.000265394,0.0008158623,0.0001480356,0.0001776675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001908833,0.0007703331,0.00364878,0.001404204,0.0009860179,0.0008834701,0.001123223,0.1088371,0.003512192,0.8711852,0.005785149,0.001673516],"study_design_scores_gemma":[0.0003495986,0.00004065171,0.0003292722,0.0002661525,0.0004305603,0.00002179986,0.00008817963,0.2975247,0.0003332203,0.6994984,0.0005891373,0.0005283736],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.905834,0.00003062938,0.08744086,0.0003253458,0.0002759237,0.0005522003,0.00004521954,0.0009142462,0.004581586],"genre_scores_gemma":[0.9872184,0.0000266135,0.004662232,0.00006555409,0.0001459624,0.000009641729,0.0001340485,0.00007882561,0.007658659],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1886877,"threshold_uncertainty_score":0.9997825,"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."}}