{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6YEEQNVRVEGJDXCVNRHZAVJH2M","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":"235e5a91709bbf4c508a76670621a8b44961b376517e0e9433a6ab508234b56b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T04:46:21Z","title_canon_sha256":"a62d6e6153932bad584f56ca66c3a8f819f08072c396fa552ba1078a4dc4a73b"},"schema_version":"1.0","source":{"id":"2603.00040","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.00040","created_at":"2026-08-11T01:24:39Z"},{"alias_kind":"arxiv_version","alias_value":"2603.00040v3","created_at":"2026-08-11T01:24:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00040","created_at":"2026-08-11T01:24:39Z"},{"alias_kind":"pith_short_12","alias_value":"6YEEQNVRVEGJ","created_at":"2026-08-11T01:24:39Z"},{"alias_kind":"pith_short_16","alias_value":"6YEEQNVRVEGJDXCV","created_at":"2026-08-11T01:24:39Z"},{"alias_kind":"pith_short_8","alias_value":"6YEEQNVR","created_at":"2026-08-11T01:24:39Z"}],"graph_snapshots":[{"event_id":"sha256:7a1ad350a190031448584c223058d1769e19b213902f05cbb1a2cfc95cdac5c7","target":"graph","created_at":"2026-08-11T01:24:39Z","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/2603.00040/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Achieving reliable 4-bit attention is a prerequisite for end-to-end FP4 computation on emerging FP4-capable GPUs, yet attention remains the main obstacle due to FP4's tiny dynamic range and attention's heavy-tailed activations. This paper presents the first systematic study of 4-bit quantization-aware training (QAT) for attention. We find ``drop-in'' QAT -- naively combining an FP4 forward pass with high-precision Flash Attention (FA)-style backward pass -- leads to training instability. We identify two key principles for stable FP4 attention: (1) matching low-precision recomputation of attent","authors_text":"Chengquan Jiang, Hao Zhang, Matthew Noto, Peiyuan Zhang, Wei Zhou, Wenxuan Tan, Will Lin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T04:46:21Z","title":"Attn-QAT: 4-Bit Attention With Quantization-Aware Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00040","kind":"arxiv","version":3},"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:b7f1c879cbc38c02bdee5cb8e39700fa9aaaa20c442a37af6b3e7404b151da2d","target":"record","created_at":"2026-08-11T01:24:39Z","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":"235e5a91709bbf4c508a76670621a8b44961b376517e0e9433a6ab508234b56b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-09T04:46:21Z","title_canon_sha256":"a62d6e6153932bad584f56ca66c3a8f819f08072c396fa552ba1078a4dc4a73b"},"schema_version":"1.0","source":{"id":"2603.00040","kind":"arxiv","version":3}},"canonical_sha256":"f6084836b1a90c91dc556c4f905527d33a9bd06ca8b363e326fa0b57e624629b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6084836b1a90c91dc556c4f905527d33a9bd06ca8b363e326fa0b57e624629b","first_computed_at":"2026-08-11T01:24:39.222650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:24:39.222650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f+gD1X5O/99ksb49IKixj06RvduG97DotTQgUpTjpeadq6UkLqLZOzZziqeIqmF5tUMYgoyS4f4G4LYgIy3xCw==","signature_status":"signed_v1","signed_at":"2026-08-11T01:24:39.225242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.00040","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7f1c879cbc38c02bdee5cb8e39700fa9aaaa20c442a37af6b3e7404b151da2d","sha256:7a1ad350a190031448584c223058d1769e19b213902f05cbb1a2cfc95cdac5c7"],"state_sha256":"77566f3093cddce876f411ddf30ae5260df65c2fbb3fe22a075b8d6a0f223ff0"}