{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HNO3NEZGTGNBWKPWMIUWQM5DYJ","short_pith_number":"pith:HNO3NEZG","schema_version":"1.0","canonical_sha256":"3b5db69326999a1b29f662296833a3c25f6e25895da2f9985f8f3c3df9a3ce6c","source":{"kind":"arxiv","id":"1812.08011","version":1},"attestation_state":"computed","paper":{"title":"Training Deep Neural Networks with 8-bit Floating Point Numbers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chia-Yu Chen, Daniel Brand, Jungwook Choi, Kailash Gopalakrishnan, Naigang Wang","submitted_at":"2018-12-19T15:15:55Z","abstract_excerpt":"The state-of-the-art hardware platforms for training Deep Neural Networks (DNNs) are moving from traditional single precision (32-bit) computations towards 16 bits of precision -- in large part due to the high energy efficiency and smaller bit storage associated with using reduced-precision representations. However, unlike inference, training with numbers represented with less than 16 bits has been challenging due to the need to maintain fidelity of the gradient computations during back-propagation. Here we demonstrate, for the first time, the successful training of DNNs using 8-bit floating p"},"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":"1812.08011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-19T15:15:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"cb368b9384240da3743539074d11101b66d936e1993d4be795542193ce62c8d5","abstract_canon_sha256":"0996a5f20557764be0c780b8335e71efabfd553c4d49ed6bf9158a35b178fb68"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:55.192223Z","signature_b64":"+395RpkDotuCbzg/AANY9HyV8Z2aGK26tBq7KLG4os1xQ+xgYo5HI8/BwMULEnlwsFhMNRb/44rOEvunywowCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b5db69326999a1b29f662296833a3c25f6e25895da2f9985f8f3c3df9a3ce6c","last_reissued_at":"2026-05-17T23:57:55.191577Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:55.191577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Deep Neural Networks with 8-bit Floating Point Numbers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chia-Yu Chen, Daniel Brand, Jungwook Choi, Kailash Gopalakrishnan, Naigang Wang","submitted_at":"2018-12-19T15:15:55Z","abstract_excerpt":"The state-of-the-art hardware platforms for training Deep Neural Networks (DNNs) are moving from traditional single precision (32-bit) computations towards 16 bits of precision -- in large part due to the high energy efficiency and smaller bit storage associated with using reduced-precision representations. However, unlike inference, training with numbers represented with less than 16 bits has been challenging due to the need to maintain fidelity of the gradient computations during back-propagation. Here we demonstrate, for the first time, the successful training of DNNs using 8-bit floating p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08011","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":"1812.08011","created_at":"2026-05-17T23:57:55.191684+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.08011v1","created_at":"2026-05-17T23:57:55.191684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08011","created_at":"2026-05-17T23:57:55.191684+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNO3NEZGTGNB","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNO3NEZGTGNBWKPW","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNO3NEZG","created_at":"2026-05-18T12:32:28.185984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10885","citing_title":"Slimming Down LLMs Without Losing Their Minds","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNO3NEZGTGNBWKPWMIUWQM5DYJ","json":"https://pith.science/pith/HNO3NEZGTGNBWKPWMIUWQM5DYJ.json","graph_json":"https://pith.science/api/pith-number/HNO3NEZGTGNBWKPWMIUWQM5DYJ/graph.json","events_json":"https://pith.science/api/pith-number/HNO3NEZGTGNBWKPWMIUWQM5DYJ/events.json","paper":"https://pith.science/paper/HNO3NEZG"},"agent_actions":{"view_html":"https://pith.science/pith/HNO3NEZGTGNBWKPWMIUWQM5DYJ","download_json":"https://pith.science/pith/HNO3NEZGTGNBWKPWMIUWQM5DYJ.json","view_paper":"https://pith.science/paper/HNO3NEZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.08011&json=true","fetch_graph":"https://pith.science/api/pith-number/HNO3NEZGTGNBWKPWMIUWQM5DYJ/graph.json","fetch_events":"https://pith.science/api/pith-number/HNO3NEZGTGNBWKPWMIUWQM5DYJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNO3NEZGTGNBWKPWMIUWQM5DYJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNO3NEZGTGNBWKPWMIUWQM5DYJ/action/storage_attestation","attest_author":"https://pith.science/pith/HNO3NEZGTGNBWKPWMIUWQM5DYJ/action/author_attestation","sign_citation":"https://pith.science/pith/HNO3NEZGTGNBWKPWMIUWQM5DYJ/action/citation_signature","submit_replication":"https://pith.science/pith/HNO3NEZGTGNBWKPWMIUWQM5DYJ/action/replication_record"}},"created_at":"2026-05-17T23:57:55.191684+00:00","updated_at":"2026-05-17T23:57:55.191684+00:00"}