{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GBAEVHM5CH7GXMBJJZ44IK4X5M","short_pith_number":"pith:GBAEVHM5","schema_version":"1.0","canonical_sha256":"30404a9d9d11fe6bb0294e79c42b97eb260d4f07b06158b6ab562151c85cde61","source":{"kind":"arxiv","id":"1807.00301","version":1},"attestation_state":"computed","paper":{"title":"SYQ: Learning Symmetric Quantization For Efficient Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Julian Faraone, Michaela Blott, Nicholas Fraser, Philip H.W. Leong","submitted_at":"2018-07-01T09:29:19Z","abstract_excerpt":"Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight parameters and/or activations during training by approximating their distributions with a limited entry codebook. For very low-precisions, such as binary or ternary networks with 1-8-bit activations, the information loss from quantization leads to significant accuracy degradation due to large gradient mismatches between the forward and backward functions. In this paper, we int"},"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":"1807.00301","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-01T09:29:19Z","cross_cats_sorted":[],"title_canon_sha256":"ea0e758d8bd58fefb2d93927f432561740ebeae3d7341e22545caff28ffc6c67","abstract_canon_sha256":"8f3989ce63b163b67d9000064a4c7988a5bb92ecec451564f604a893898248cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:55.327628Z","signature_b64":"FBPl/7krrdeCgEl7IwQMYZuVUQEz8qcA2ooAfpzytzikFBkw4nF7l4w4b41+6RV3jzv87wD2SAHBs8duUvtmCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30404a9d9d11fe6bb0294e79c42b97eb260d4f07b06158b6ab562151c85cde61","last_reissued_at":"2026-05-18T00:11:55.327004Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:55.327004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SYQ: Learning Symmetric Quantization For Efficient Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Julian Faraone, Michaela Blott, Nicholas Fraser, Philip H.W. Leong","submitted_at":"2018-07-01T09:29:19Z","abstract_excerpt":"Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight parameters and/or activations during training by approximating their distributions with a limited entry codebook. For very low-precisions, such as binary or ternary networks with 1-8-bit activations, the information loss from quantization leads to significant accuracy degradation due to large gradient mismatches between the forward and backward functions. In this paper, we int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00301","kind":"arxiv","version":1},"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":"1807.00301","created_at":"2026-05-18T00:11:55.327115+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.00301v1","created_at":"2026-05-18T00:11:55.327115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00301","created_at":"2026-05-18T00:11:55.327115+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBAEVHM5CH7G","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBAEVHM5CH7GXMBJ","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBAEVHM5","created_at":"2026-05-18T12:32:25.280505+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/GBAEVHM5CH7GXMBJJZ44IK4X5M","json":"https://pith.science/pith/GBAEVHM5CH7GXMBJJZ44IK4X5M.json","graph_json":"https://pith.science/api/pith-number/GBAEVHM5CH7GXMBJJZ44IK4X5M/graph.json","events_json":"https://pith.science/api/pith-number/GBAEVHM5CH7GXMBJJZ44IK4X5M/events.json","paper":"https://pith.science/paper/GBAEVHM5"},"agent_actions":{"view_html":"https://pith.science/pith/GBAEVHM5CH7GXMBJJZ44IK4X5M","download_json":"https://pith.science/pith/GBAEVHM5CH7GXMBJJZ44IK4X5M.json","view_paper":"https://pith.science/paper/GBAEVHM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.00301&json=true","fetch_graph":"https://pith.science/api/pith-number/GBAEVHM5CH7GXMBJJZ44IK4X5M/graph.json","fetch_events":"https://pith.science/api/pith-number/GBAEVHM5CH7GXMBJJZ44IK4X5M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBAEVHM5CH7GXMBJJZ44IK4X5M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBAEVHM5CH7GXMBJJZ44IK4X5M/action/storage_attestation","attest_author":"https://pith.science/pith/GBAEVHM5CH7GXMBJJZ44IK4X5M/action/author_attestation","sign_citation":"https://pith.science/pith/GBAEVHM5CH7GXMBJJZ44IK4X5M/action/citation_signature","submit_replication":"https://pith.science/pith/GBAEVHM5CH7GXMBJJZ44IK4X5M/action/replication_record"}},"created_at":"2026-05-18T00:11:55.327115+00:00","updated_at":"2026-05-18T00:11:55.327115+00:00"}