{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:WGXL3LOEN6Z5DZ2PFUH46LJCEB","short_pith_number":"pith:WGXL3LOE","schema_version":"1.0","canonical_sha256":"b1aebdadc46fb3d1e74f2d0fcf2d222072625d019fe5214e7fca1232fee2e811","source":{"kind":"arxiv","id":"1612.06052","version":2},"attestation_state":"computed","paper":{"title":"Quantization and Training of Low Bit-Width Convolutional Neural Networks for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jack Xin, Penghang Yin, Shuai Zhang, Yingyong Qi","submitted_at":"2016-12-19T05:54:18Z","abstract_excerpt":"We present LBW-Net, an efficient optimization based method for quantization and training of the low bit-width convolutional neural networks (CNNs). Specifically, we quantize the weights to zero or powers of two by minimizing the Euclidean distance between full-precision weights and quantized weights during backpropagation. We characterize the combinatorial nature of the low bit-width quantization problem. For 2-bit (ternary) CNNs, the quantization of $N$ weights can be done by an exact formula in $O(N\\log N)$ complexity. When the bit-width is three and above, we further propose a semi-analytic"},"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":"1612.06052","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-12-19T05:54:18Z","cross_cats_sorted":[],"title_canon_sha256":"c599e3558495085fd8e4997f286ff00ca34665f5757655937ad5c6f3bb5a09b5","abstract_canon_sha256":"3ea1f4eea5a1160f89e4539d04453fb520dd8c77dd6e142d322546e961a36713"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:37:54.683939Z","signature_b64":"6B1DX730pxD9Ljwj0ZdLmBO0suycHb0/DtlPVM3DtcCUf0eLOBf1xlL1/fj3js3ij1cX3yW3bVChaP+kUBOFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1aebdadc46fb3d1e74f2d0fcf2d222072625d019fe5214e7fca1232fee2e811","last_reissued_at":"2026-05-18T00:37:54.683459Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:37:54.683459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantization and Training of Low Bit-Width Convolutional Neural Networks for Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jack Xin, Penghang Yin, Shuai Zhang, Yingyong Qi","submitted_at":"2016-12-19T05:54:18Z","abstract_excerpt":"We present LBW-Net, an efficient optimization based method for quantization and training of the low bit-width convolutional neural networks (CNNs). Specifically, we quantize the weights to zero or powers of two by minimizing the Euclidean distance between full-precision weights and quantized weights during backpropagation. We characterize the combinatorial nature of the low bit-width quantization problem. For 2-bit (ternary) CNNs, the quantization of $N$ weights can be done by an exact formula in $O(N\\log N)$ complexity. When the bit-width is three and above, we further propose a semi-analytic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.06052","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":"1612.06052","created_at":"2026-05-18T00:37:54.683533+00:00"},{"alias_kind":"arxiv_version","alias_value":"1612.06052v2","created_at":"2026-05-18T00:37:54.683533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.06052","created_at":"2026-05-18T00:37:54.683533+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGXL3LOEN6Z5","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGXL3LOEN6Z5DZ2P","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGXL3LOE","created_at":"2026-05-18T12:30:48.956258+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/WGXL3LOEN6Z5DZ2PFUH46LJCEB","json":"https://pith.science/pith/WGXL3LOEN6Z5DZ2PFUH46LJCEB.json","graph_json":"https://pith.science/api/pith-number/WGXL3LOEN6Z5DZ2PFUH46LJCEB/graph.json","events_json":"https://pith.science/api/pith-number/WGXL3LOEN6Z5DZ2PFUH46LJCEB/events.json","paper":"https://pith.science/paper/WGXL3LOE"},"agent_actions":{"view_html":"https://pith.science/pith/WGXL3LOEN6Z5DZ2PFUH46LJCEB","download_json":"https://pith.science/pith/WGXL3LOEN6Z5DZ2PFUH46LJCEB.json","view_paper":"https://pith.science/paper/WGXL3LOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1612.06052&json=true","fetch_graph":"https://pith.science/api/pith-number/WGXL3LOEN6Z5DZ2PFUH46LJCEB/graph.json","fetch_events":"https://pith.science/api/pith-number/WGXL3LOEN6Z5DZ2PFUH46LJCEB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGXL3LOEN6Z5DZ2PFUH46LJCEB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGXL3LOEN6Z5DZ2PFUH46LJCEB/action/storage_attestation","attest_author":"https://pith.science/pith/WGXL3LOEN6Z5DZ2PFUH46LJCEB/action/author_attestation","sign_citation":"https://pith.science/pith/WGXL3LOEN6Z5DZ2PFUH46LJCEB/action/citation_signature","submit_replication":"https://pith.science/pith/WGXL3LOEN6Z5DZ2PFUH46LJCEB/action/replication_record"}},"created_at":"2026-05-18T00:37:54.683533+00:00","updated_at":"2026-05-18T00:37:54.683533+00:00"}