{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LJ2QDUVIXPJMQZ3H7ZKIQTQ34D","short_pith_number":"pith:LJ2QDUVI","schema_version":"1.0","canonical_sha256":"5a7501d2a8bbd2c86767fe54884e1be0f1ee6db967df2eba83330e02fa89a822","source":{"kind":"arxiv","id":"1803.03289","version":2},"attestation_state":"computed","paper":{"title":"Deep Neural Network Compression with Single and Multiple Level Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aojun Zhou, Hongkai Xiong, Weiyao Lin, Yongzhuang Wang, Yuhui Xu","submitted_at":"2018-03-06T01:47:52Z","abstract_excerpt":"Network quantization is an effective solution to compress deep neural networks for practical usage. Existing network quantization methods cannot sufficiently exploit the depth information to generate low-bit compressed network. In this paper, we propose two novel network quantization approaches, single-level network quantization (SLQ) for high-bit quantization and multi-level network quantization (MLQ) for extremely low-bit quantization (ternary).We are the first to consider the network quantization from both width and depth level. In the width level, parameters are divided into two parts: one"},"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":"1803.03289","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-06T01:47:52Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8a880c412bdf4dd37d6736f565fd89173b1d9c8099e85518ba589256048586b1","abstract_canon_sha256":"474afc7af78b6723a34a1757c28e9ac8ee5bbf21f7123895bc2d618da048b248"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:14.533362Z","signature_b64":"1DE8Vu+sqiouQ3JQCMUys4pFEVMB2ddKs4XxCXUJCGVgBII33hzKIdY/vbEw6ZcvSdRjSxjJ8qLn+q99yaHgCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a7501d2a8bbd2c86767fe54884e1be0f1ee6db967df2eba83330e02fa89a822","last_reissued_at":"2026-05-17T23:58:14.532723Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:14.532723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Neural Network Compression with Single and Multiple Level Quantization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aojun Zhou, Hongkai Xiong, Weiyao Lin, Yongzhuang Wang, Yuhui Xu","submitted_at":"2018-03-06T01:47:52Z","abstract_excerpt":"Network quantization is an effective solution to compress deep neural networks for practical usage. Existing network quantization methods cannot sufficiently exploit the depth information to generate low-bit compressed network. In this paper, we propose two novel network quantization approaches, single-level network quantization (SLQ) for high-bit quantization and multi-level network quantization (MLQ) for extremely low-bit quantization (ternary).We are the first to consider the network quantization from both width and depth level. In the width level, parameters are divided into two parts: one"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.03289","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":""},"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":"1803.03289","created_at":"2026-05-17T23:58:14.532828+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.03289v2","created_at":"2026-05-17T23:58:14.532828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.03289","created_at":"2026-05-17T23:58:14.532828+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJ2QDUVIXPJM","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJ2QDUVIXPJMQZ3H","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJ2QDUVI","created_at":"2026-05-18T12:32:37.024351+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/LJ2QDUVIXPJMQZ3H7ZKIQTQ34D","json":"https://pith.science/pith/LJ2QDUVIXPJMQZ3H7ZKIQTQ34D.json","graph_json":"https://pith.science/api/pith-number/LJ2QDUVIXPJMQZ3H7ZKIQTQ34D/graph.json","events_json":"https://pith.science/api/pith-number/LJ2QDUVIXPJMQZ3H7ZKIQTQ34D/events.json","paper":"https://pith.science/paper/LJ2QDUVI"},"agent_actions":{"view_html":"https://pith.science/pith/LJ2QDUVIXPJMQZ3H7ZKIQTQ34D","download_json":"https://pith.science/pith/LJ2QDUVIXPJMQZ3H7ZKIQTQ34D.json","view_paper":"https://pith.science/paper/LJ2QDUVI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.03289&json=true","fetch_graph":"https://pith.science/api/pith-number/LJ2QDUVIXPJMQZ3H7ZKIQTQ34D/graph.json","fetch_events":"https://pith.science/api/pith-number/LJ2QDUVIXPJMQZ3H7ZKIQTQ34D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJ2QDUVIXPJMQZ3H7ZKIQTQ34D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJ2QDUVIXPJMQZ3H7ZKIQTQ34D/action/storage_attestation","attest_author":"https://pith.science/pith/LJ2QDUVIXPJMQZ3H7ZKIQTQ34D/action/author_attestation","sign_citation":"https://pith.science/pith/LJ2QDUVIXPJMQZ3H7ZKIQTQ34D/action/citation_signature","submit_replication":"https://pith.science/pith/LJ2QDUVIXPJMQZ3H7ZKIQTQ34D/action/replication_record"}},"created_at":"2026-05-17T23:58:14.532828+00:00","updated_at":"2026-05-17T23:58:14.532828+00:00"}