{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WF7VBPRV6KQ4N7FLAT73KCJERL","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":"1d94efda89e460e2c8484ab7e57551c5eeefc29ade7ef8994ddf90f123a6b52a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-24T09:57:11Z","title_canon_sha256":"a565980bd3b0b44afde7d7ea45f99e6de2b7e3860ccc2fa210f9991e0e6bf68c"},"schema_version":"1.0","source":{"id":"2404.15778","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.15778","created_at":"2026-07-05T08:37:06Z"},{"alias_kind":"arxiv_version","alias_value":"2404.15778v2","created_at":"2026-07-05T08:37:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15778","created_at":"2026-07-05T08:37:06Z"},{"alias_kind":"pith_short_12","alias_value":"WF7VBPRV6KQ4","created_at":"2026-07-05T08:37:06Z"},{"alias_kind":"pith_short_16","alias_value":"WF7VBPRV6KQ4N7FL","created_at":"2026-07-05T08:37:06Z"},{"alias_kind":"pith_short_8","alias_value":"WF7VBPRV","created_at":"2026-07-05T08:37:06Z"}],"graph_snapshots":[{"event_id":"sha256:55aa4e53ab9f4e2da4b3ec9ce712f99a224255a4162ab40d4dcc0f009f96afae","target":"graph","created_at":"2026-07-05T08:37:06Z","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/2404.15778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speculative decoding has emerged as a powerful method to improve latency and throughput in hosting large language models. However, most existing implementations focus on generating a single sequence. Real-world generative AI applications often require multiple responses and how to perform speculative decoding in a batched setting while preserving its latency benefits poses non-trivial challenges. This paper describes a system of batched speculative decoding that sets a new state of the art in multi-sequence generation latency and that demonstrates superior GPU utilization as well as quality of","authors_text":"Anoop Deoras, Haifeng Qian, Mingyue Shang, Ramesh Nallapati, Sanjay Krishna Gouda, Sudipta Sengupta, Sujan Kumar Gonugondla, Sungsoo Ha, Xiaofei Ma","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-24T09:57:11Z","title":"BASS: Batched Attention-optimized Speculative Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15778","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":"sha256:4d9cc254e6457cdd8385498e758823344977213b82250fa1d542259af0338520","target":"record","created_at":"2026-07-05T08:37:06Z","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":"1d94efda89e460e2c8484ab7e57551c5eeefc29ade7ef8994ddf90f123a6b52a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-24T09:57:11Z","title_canon_sha256":"a565980bd3b0b44afde7d7ea45f99e6de2b7e3860ccc2fa210f9991e0e6bf68c"},"schema_version":"1.0","source":{"id":"2404.15778","kind":"arxiv","version":2}},"canonical_sha256":"b17f50be35f2a1c6fcab04ffb509248ac23aedbc73caa76e8911ed969c1e4cf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b17f50be35f2a1c6fcab04ffb509248ac23aedbc73caa76e8911ed969c1e4cf1","first_computed_at":"2026-07-05T08:37:06.877094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:06.877094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aAWX49LMumI2nnHzwmroJUXt97yGLCIZJ8zA1gXzFwOIHDaj3slhWFTMKb9gv6AmGhgMKxrOlB+M+U5qIa+pDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:06.877584Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.15778","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d9cc254e6457cdd8385498e758823344977213b82250fa1d542259af0338520","sha256:55aa4e53ab9f4e2da4b3ec9ce712f99a224255a4162ab40d4dcc0f009f96afae"],"state_sha256":"03ad0379ac20dc33e512fc59c2e423a1ddf160e8ec3a66aec6d0361e2b6906d8"}