{"id":"W4415332454","doi":"10.48550/arxiv.2509.23410","title":"PATCH: Learnable Tile-level Hybrid Sparsity for LLMs","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advancements in Photolithography Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Pruning; Selection (genetic algorithm); Speedup; Bridge (graph theory); Face (sociological concept); Class (philosophy); Heuristics; Process (computing); Range (aeronautics)","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":[0.0001634931,0.0004501354,0.0004675398,0.0003924425,0.0001413626,0.00003940079,0.0008888731,0.0002908515,0.00006248866],"category_scores_gemma":[0.00002679605,0.0006050315,0.0003510525,0.0003398634,0.00009498797,0.0001789571,0.0006887832,0.0006458126,0.00001319582],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003298874,"about_ca_system_score_gemma":0.00007217356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001255922,"about_ca_topic_score_gemma":0.00003908218,"domain_scores_codex":[0.9983703,0.00003352136,0.0002384495,0.0007764396,0.00007403913,0.0005072339],"domain_scores_gemma":[0.9985639,0.00009462487,0.000109296,0.0009702913,0.0001409777,0.0001209505],"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":[0.0001772167,0.0002308795,0.008854121,0.002354433,0.001041335,0.0002294052,0.0001302638,0.9106533,0.0002151942,0.04760228,0.02445156,0.00406001],"study_design_scores_gemma":[0.001760209,0.0001376539,0.0008894514,0.000867195,0.0007118708,0.000006251543,0.0001616959,0.617364,0.02232694,0.2419526,0.1112062,0.002615954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07936417,0.0001468636,0.8987656,0.000009537905,0.001025937,0.001115857,0.001091896,0.001607447,0.01687272],"genre_scores_gemma":[0.9795256,0.0007503987,0.01218976,0.000047018,0.00007886093,0.00001754655,0.0001453568,0.00005807728,0.007187397],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9001614,"threshold_uncertainty_score":0.9996401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1019054716866376,"score_gpt":0.2026944299194573,"score_spread":0.1007889582328197,"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."}}