{"id":"W4389575029","doi":"10.1145/3610548.3618167","title":"Compact Neural Graphics Primitives with Learned Hash Probing","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Research Canada; University of Toronto","funders":"","keywords":"Computer science; Feature hashing; Hash function; Memory footprint; Hash table; Artificial neural network; Lookup table; Algorithm; Feature vector; Graphics; Grid; Feature (linguistics); Pattern recognition (psychology); Theoretical computer science; Artificial intelligence; Parallel computing; Double hashing; Computer graphics (images); 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":[0.000551221,0.0005714314,0.0007116158,0.0005046158,0.0003135136,0.00114339,0.002204473,0.0008708552,0.007200255],"category_scores_gemma":[0.005348819,0.0004342077,0.000393236,0.001087435,0.0009965013,0.005263453,0.001906782,0.001452713,0.001750541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001054858,"about_ca_system_score_gemma":0.00087639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002774838,"about_ca_topic_score_gemma":0.00369395,"domain_scores_codex":[0.9995789,0.00005507,0.00003730895,0.0001064308,0.0001786885,0.00004362253],"domain_scores_gemma":[0.9983349,0.000600445,0.0001173011,0.0007027871,0.0001869417,0.00005755107],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000828621,0.0001664596,0.002262192,0.0002611338,0.00005786298,0.0001465671,0.0001836022,0.2660863,0.02449514,0.07858617,0.01451765,0.6124083],"study_design_scores_gemma":[0.00005055535,0.0001455876,0.0002606309,0.00001224869,0.00001328053,0.00006323127,0.00003167879,0.9417131,0.01299287,0.04148961,0.003210915,0.00001621977],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05313893,0.0003481977,0.9304504,0.0004070321,0.00009997536,0.00009349243,0.0004448868,0.01085025,0.004166753],"genre_scores_gemma":[0.5365427,0.0002002841,0.4569311,0.0002941991,0.00005838513,0.0002365629,0.0009748437,0.0004113287,0.004350565],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007200255,"threshold_uncertainty_score":0.02408719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0497590092474771,"score_gpt":0.3154762216339212,"score_spread":0.2657172123864441,"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."}}