{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5BZKVMFJBW3LGGU24VIPIGQN2Y","short_pith_number":"pith:5BZKVMFJ","schema_version":"1.0","canonical_sha256":"e872aab0a90db6b31a9ae550f41a0dd60fc24e62bc3d6ec99abe32e0370506fe","source":{"kind":"arxiv","id":"2302.03213","version":2},"attestation_state":"computed","paper":{"title":"LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Deng Cai, Li Lyna Zhang, Mao Yang, Qi Chen, Ting Cao, Xiaohu Tang, Yang Wang, Yunxin Liu","submitted_at":"2023-02-07T02:51:10Z","abstract_excerpt":"On-device Deep Neural Network (DNN) inference consumes significant computing resources and development efforts. To alleviate that, we propose LUT-NN, the first system to empower inference by table lookup, to reduce inference cost. LUT-NN learns the typical features for each operator, named centroid, and precompute the results for these centroids to save in lookup tables. During inference, the results of the closest centroids with the inputs can be read directly from the table, as the approximated outputs without computations. LUT-NN integrates two major novel techniques: (1) differentiable cen"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2302.03213","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-07T02:51:10Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"819d41db3e3d302c6506bc44eba1e60358a3895933945e963656387453f9dabd","abstract_canon_sha256":"fed456fe1610bff574c8ca550e11a8dac7fe2148d8664544a3d877f2808be3ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:05.195640Z","signature_b64":"LQQLlEW11M52R8yObDlNhJN75Psy8TkFYy/UiGxKXeaWIdJB/eNSJBk1TtdWX28bzWJXxNRjmEo4xOhfkQouDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e872aab0a90db6b31a9ae550f41a0dd60fc24e62bc3d6ec99abe32e0370506fe","last_reissued_at":"2026-07-05T06:48:05.195061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:05.195061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Deng Cai, Li Lyna Zhang, Mao Yang, Qi Chen, Ting Cao, Xiaohu Tang, Yang Wang, Yunxin Liu","submitted_at":"2023-02-07T02:51:10Z","abstract_excerpt":"On-device Deep Neural Network (DNN) inference consumes significant computing resources and development efforts. To alleviate that, we propose LUT-NN, the first system to empower inference by table lookup, to reduce inference cost. LUT-NN learns the typical features for each operator, named centroid, and precompute the results for these centroids to save in lookup tables. During inference, the results of the closest centroids with the inputs can be read directly from the table, as the approximated outputs without computations. LUT-NN integrates two major novel techniques: (1) differentiable cen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.03213","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2302.03213/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2302.03213","created_at":"2026-07-05T06:48:05.195123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.03213v2","created_at":"2026-07-05T06:48:05.195123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.03213","created_at":"2026-07-05T06:48:05.195123+00:00"},{"alias_kind":"pith_short_12","alias_value":"5BZKVMFJBW3L","created_at":"2026-07-05T06:48:05.195123+00:00"},{"alias_kind":"pith_short_16","alias_value":"5BZKVMFJBW3LGGU2","created_at":"2026-07-05T06:48:05.195123+00:00"},{"alias_kind":"pith_short_8","alias_value":"5BZKVMFJ","created_at":"2026-07-05T06:48:05.195123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5BZKVMFJBW3LGGU24VIPIGQN2Y","json":"https://pith.science/pith/5BZKVMFJBW3LGGU24VIPIGQN2Y.json","graph_json":"https://pith.science/api/pith-number/5BZKVMFJBW3LGGU24VIPIGQN2Y/graph.json","events_json":"https://pith.science/api/pith-number/5BZKVMFJBW3LGGU24VIPIGQN2Y/events.json","paper":"https://pith.science/paper/5BZKVMFJ"},"agent_actions":{"view_html":"https://pith.science/pith/5BZKVMFJBW3LGGU24VIPIGQN2Y","download_json":"https://pith.science/pith/5BZKVMFJBW3LGGU24VIPIGQN2Y.json","view_paper":"https://pith.science/paper/5BZKVMFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.03213&json=true","fetch_graph":"https://pith.science/api/pith-number/5BZKVMFJBW3LGGU24VIPIGQN2Y/graph.json","fetch_events":"https://pith.science/api/pith-number/5BZKVMFJBW3LGGU24VIPIGQN2Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5BZKVMFJBW3LGGU24VIPIGQN2Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5BZKVMFJBW3LGGU24VIPIGQN2Y/action/storage_attestation","attest_author":"https://pith.science/pith/5BZKVMFJBW3LGGU24VIPIGQN2Y/action/author_attestation","sign_citation":"https://pith.science/pith/5BZKVMFJBW3LGGU24VIPIGQN2Y/action/citation_signature","submit_replication":"https://pith.science/pith/5BZKVMFJBW3LGGU24VIPIGQN2Y/action/replication_record"}},"created_at":"2026-07-05T06:48:05.195123+00:00","updated_at":"2026-07-05T06:48:05.195123+00:00"}