{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:2653LNNCVVVSY7T5KHCBMP7DEQ","short_pith_number":"pith:2653LNNC","schema_version":"1.0","canonical_sha256":"d7bbb5b5a2ad6b2c7e7d51c4163fe32431714b8f686de3ada4032824830be449","source":{"kind":"arxiv","id":"2010.04354","version":3},"attestation_state":"computed","paper":{"title":"Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chen Lin, Chuming Li, Feng Liang, Fengwei Yu, Junjie Yan, Mingzhu Shen, Ruihao Gong, Wanli Ouyang, Yuhang Li","submitted_at":"2020-10-09T03:52:16Z","abstract_excerpt":"Quantization Neural Networks (QNN) have attracted a lot of attention due to their high efficiency. To enhance the quantization accuracy, prior works mainly focus on designing advanced quantization algorithms but still fail to achieve satisfactory results under the extremely low-bit case. In this work, we take an architecture perspective to investigate the potential of high-performance QNN. Therefore, we propose to combine Network Architecture Search methods with quantization to enjoy the merits of the two sides. However, a naive combination inevitably faces unacceptable time consumption or uns"},"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":"2010.04354","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-10-09T03:52:16Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"9200a743eb793daa0519c244f5d724ad368768885b4efabe9c6d55c2665ab465","abstract_canon_sha256":"69fd8e875b263a79d5cacfa80d8430bd436dd00c24c02ceb58dbb56fd788ba66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:17:45.545980Z","signature_b64":"vrlhzkbUk+peTG3iCJNIUbVWXHYwKPTmmhxSi3TtfSUhx28SSMOHyARhZK3UUKQ5RV0+SddL0J3m3+GtgttmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d7bbb5b5a2ad6b2c7e7d51c4163fe32431714b8f686de3ada4032824830be449","last_reissued_at":"2026-07-05T03:17:45.545436Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:17:45.545436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chen Lin, Chuming Li, Feng Liang, Fengwei Yu, Junjie Yan, Mingzhu Shen, Ruihao Gong, Wanli Ouyang, Yuhang Li","submitted_at":"2020-10-09T03:52:16Z","abstract_excerpt":"Quantization Neural Networks (QNN) have attracted a lot of attention due to their high efficiency. To enhance the quantization accuracy, prior works mainly focus on designing advanced quantization algorithms but still fail to achieve satisfactory results under the extremely low-bit case. In this work, we take an architecture perspective to investigate the potential of high-performance QNN. Therefore, we propose to combine Network Architecture Search methods with quantization to enjoy the merits of the two sides. However, a naive combination inevitably faces unacceptable time consumption or uns"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.04354","kind":"arxiv","version":3},"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/2010.04354/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":"2010.04354","created_at":"2026-07-05T03:17:45.545507+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.04354v3","created_at":"2026-07-05T03:17:45.545507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.04354","created_at":"2026-07-05T03:17:45.545507+00:00"},{"alias_kind":"pith_short_12","alias_value":"2653LNNCVVVS","created_at":"2026-07-05T03:17:45.545507+00:00"},{"alias_kind":"pith_short_16","alias_value":"2653LNNCVVVSY7T5","created_at":"2026-07-05T03:17:45.545507+00:00"},{"alias_kind":"pith_short_8","alias_value":"2653LNNC","created_at":"2026-07-05T03:17:45.545507+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/2653LNNCVVVSY7T5KHCBMP7DEQ","json":"https://pith.science/pith/2653LNNCVVVSY7T5KHCBMP7DEQ.json","graph_json":"https://pith.science/api/pith-number/2653LNNCVVVSY7T5KHCBMP7DEQ/graph.json","events_json":"https://pith.science/api/pith-number/2653LNNCVVVSY7T5KHCBMP7DEQ/events.json","paper":"https://pith.science/paper/2653LNNC"},"agent_actions":{"view_html":"https://pith.science/pith/2653LNNCVVVSY7T5KHCBMP7DEQ","download_json":"https://pith.science/pith/2653LNNCVVVSY7T5KHCBMP7DEQ.json","view_paper":"https://pith.science/paper/2653LNNC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.04354&json=true","fetch_graph":"https://pith.science/api/pith-number/2653LNNCVVVSY7T5KHCBMP7DEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/2653LNNCVVVSY7T5KHCBMP7DEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2653LNNCVVVSY7T5KHCBMP7DEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2653LNNCVVVSY7T5KHCBMP7DEQ/action/storage_attestation","attest_author":"https://pith.science/pith/2653LNNCVVVSY7T5KHCBMP7DEQ/action/author_attestation","sign_citation":"https://pith.science/pith/2653LNNCVVVSY7T5KHCBMP7DEQ/action/citation_signature","submit_replication":"https://pith.science/pith/2653LNNCVVVSY7T5KHCBMP7DEQ/action/replication_record"}},"created_at":"2026-07-05T03:17:45.545507+00:00","updated_at":"2026-07-05T03:17:45.545507+00:00"}