{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QD3WHZ3EUQHGASKRYWHCSR63E5","short_pith_number":"pith:QD3WHZ3E","canonical_record":{"source":{"id":"2306.11987","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T02:45:01Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"4fbda36f20c695ffc211ae220c96a1649d9c3a48b05ab0c411acadec4f1a78ba","abstract_canon_sha256":"4565fafa9371f51b240ec5847d7f3695eaabb3af505ba314f3fbbaf0232083e0"},"schema_version":"1.0"},"canonical_sha256":"80f763e764a40e604951c58e2947db277bbffbf05c84685abe8d8a881d647f7f","source":{"kind":"arxiv","id":"2306.11987","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11987","created_at":"2026-07-05T06:24:01Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11987v2","created_at":"2026-07-05T06:24:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11987","created_at":"2026-07-05T06:24:01Z"},{"alias_kind":"pith_short_12","alias_value":"QD3WHZ3EUQHG","created_at":"2026-07-05T06:24:01Z"},{"alias_kind":"pith_short_16","alias_value":"QD3WHZ3EUQHGASKR","created_at":"2026-07-05T06:24:01Z"},{"alias_kind":"pith_short_8","alias_value":"QD3WHZ3E","created_at":"2026-07-05T06:24:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QD3WHZ3EUQHGASKRYWHCSR63E5","target":"record","payload":{"canonical_record":{"source":{"id":"2306.11987","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T02:45:01Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"4fbda36f20c695ffc211ae220c96a1649d9c3a48b05ab0c411acadec4f1a78ba","abstract_canon_sha256":"4565fafa9371f51b240ec5847d7f3695eaabb3af505ba314f3fbbaf0232083e0"},"schema_version":"1.0"},"canonical_sha256":"80f763e764a40e604951c58e2947db277bbffbf05c84685abe8d8a881d647f7f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:01.140988Z","signature_b64":"0F3Y0tsuR+x5oq6gsvNA+fSLNe32815LVJj3z99RvsozB/r9dbftxQ4aTlFaMHzVUXyG4XPP3hBGc+aNqdb3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80f763e764a40e604951c58e2947db277bbffbf05c84685abe8d8a881d647f7f","last_reissued_at":"2026-07-05T06:24:01.140542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:01.140542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.11987","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:24:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cNbo6MiTDYnzHdVF2WMnwEp1h2DyCJYey4BmpsBB+RLnvu4cvXxYx6ho6LwADSwNnoBb2vjlbaF3PYq8EPoMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:45:41.103442Z"},"content_sha256":"b9e7599d330c22fa2ea43beec3f4374e37cdce7b1176f10a898ae360cde43742","schema_version":"1.0","event_id":"sha256:b9e7599d330c22fa2ea43beec3f4374e37cdce7b1176f10a898ae360cde43742"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QD3WHZ3EUQHGASKRYWHCSR63E5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Transformers with 4-bit Integers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.LG","authors_text":"Changhao Li, Haocheng Xi, Jianfei Chen, Jun Zhu","submitted_at":"2023-06-21T02:45:01Z","abstract_excerpt":"Quantizing the activation, weight, and gradient to 4-bit is promising to accelerate neural network training. However, existing 4-bit training methods require custom numerical formats which are not supported by contemporary hardware. In this work, we propose a training method for transformers with all matrix multiplications implemented with the INT4 arithmetic. Training with an ultra-low INT4 precision is challenging. To achieve this, we carefully analyze the specific structures of activation and gradients in transformers to propose dedicated quantizers for them. For forward propagation, we ide"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11987","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.11987/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:24:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"elX9SUSwxkL+GfnE9LOKbXv6fqdSN8vP0ApMfPHahxQG5kZbvFNp3pwpPIk4Z7MvyNcc1t/yvJ/wT050h5mkCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:45:41.103955Z"},"content_sha256":"c52f03907b8678c21f89647400b219d323a8a96febf91af5837cd0177095498f","schema_version":"1.0","event_id":"sha256:c52f03907b8678c21f89647400b219d323a8a96febf91af5837cd0177095498f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QD3WHZ3EUQHGASKRYWHCSR63E5/bundle.json","state_url":"https://pith.science/pith/QD3WHZ3EUQHGASKRYWHCSR63E5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QD3WHZ3EUQHGASKRYWHCSR63E5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T06:45:41Z","links":{"resolver":"https://pith.science/pith/QD3WHZ3EUQHGASKRYWHCSR63E5","bundle":"https://pith.science/pith/QD3WHZ3EUQHGASKRYWHCSR63E5/bundle.json","state":"https://pith.science/pith/QD3WHZ3EUQHGASKRYWHCSR63E5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QD3WHZ3EUQHGASKRYWHCSR63E5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QD3WHZ3EUQHGASKRYWHCSR63E5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4565fafa9371f51b240ec5847d7f3695eaabb3af505ba314f3fbbaf0232083e0","cross_cats_sorted":["cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T02:45:01Z","title_canon_sha256":"4fbda36f20c695ffc211ae220c96a1649d9c3a48b05ab0c411acadec4f1a78ba"},"schema_version":"1.0","source":{"id":"2306.11987","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11987","created_at":"2026-07-05T06:24:01Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11987v2","created_at":"2026-07-05T06:24:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11987","created_at":"2026-07-05T06:24:01Z"},{"alias_kind":"pith_short_12","alias_value":"QD3WHZ3EUQHG","created_at":"2026-07-05T06:24:01Z"},{"alias_kind":"pith_short_16","alias_value":"QD3WHZ3EUQHGASKR","created_at":"2026-07-05T06:24:01Z"},{"alias_kind":"pith_short_8","alias_value":"QD3WHZ3E","created_at":"2026-07-05T06:24:01Z"}],"graph_snapshots":[{"event_id":"sha256:c52f03907b8678c21f89647400b219d323a8a96febf91af5837cd0177095498f","target":"graph","created_at":"2026-07-05T06:24:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.11987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Quantizing the activation, weight, and gradient to 4-bit is promising to accelerate neural network training. However, existing 4-bit training methods require custom numerical formats which are not supported by contemporary hardware. In this work, we propose a training method for transformers with all matrix multiplications implemented with the INT4 arithmetic. Training with an ultra-low INT4 precision is challenging. To achieve this, we carefully analyze the specific structures of activation and gradients in transformers to propose dedicated quantizers for them. For forward propagation, we ide","authors_text":"Changhao Li, Haocheng Xi, Jianfei Chen, Jun Zhu","cross_cats":["cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T02:45:01Z","title":"Training Transformers with 4-bit Integers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11987","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b9e7599d330c22fa2ea43beec3f4374e37cdce7b1176f10a898ae360cde43742","target":"record","created_at":"2026-07-05T06:24:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4565fafa9371f51b240ec5847d7f3695eaabb3af505ba314f3fbbaf0232083e0","cross_cats_sorted":["cs.NE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T02:45:01Z","title_canon_sha256":"4fbda36f20c695ffc211ae220c96a1649d9c3a48b05ab0c411acadec4f1a78ba"},"schema_version":"1.0","source":{"id":"2306.11987","kind":"arxiv","version":2}},"canonical_sha256":"80f763e764a40e604951c58e2947db277bbffbf05c84685abe8d8a881d647f7f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80f763e764a40e604951c58e2947db277bbffbf05c84685abe8d8a881d647f7f","first_computed_at":"2026-07-05T06:24:01.140542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:01.140542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0F3Y0tsuR+x5oq6gsvNA+fSLNe32815LVJj3z99RvsozB/r9dbftxQ4aTlFaMHzVUXyG4XPP3hBGc+aNqdb3DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:01.140988Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.11987","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b9e7599d330c22fa2ea43beec3f4374e37cdce7b1176f10a898ae360cde43742","sha256:c52f03907b8678c21f89647400b219d323a8a96febf91af5837cd0177095498f"],"state_sha256":"4b73ef621d3dd8a7f0ac0a9095d94de1d71e7118f108d0df156968ca7b4e2d16"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ALA4cibWr0pvGykL0c5TV6q+kTe8wd/zYBFjccnRfvE/jOC+ZGceDGreCfnTIAMMZkoyT8IFcM767ndJLAVJCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:45:41.108055Z","bundle_sha256":"7c41e4e5534f1bc1675ca1b6a35bb69eb5cb3bc0d8f21dfb23687ffe824a0e8c"}}