{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WF7VBPRV6KQ4N7FLAT73KCJERL","short_pith_number":"pith:WF7VBPRV","canonical_record":{"source":{"id":"2404.15778","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-24T09:57:11Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a565980bd3b0b44afde7d7ea45f99e6de2b7e3860ccc2fa210f9991e0e6bf68c","abstract_canon_sha256":"1d94efda89e460e2c8484ab7e57551c5eeefc29ade7ef8994ddf90f123a6b52a"},"schema_version":"1.0"},"canonical_sha256":"b17f50be35f2a1c6fcab04ffb509248ac23aedbc73caa76e8911ed969c1e4cf1","source":{"kind":"arxiv","id":"2404.15778","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WF7VBPRV6KQ4N7FLAT73KCJERL","target":"record","payload":{"canonical_record":{"source":{"id":"2404.15778","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-24T09:57:11Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a565980bd3b0b44afde7d7ea45f99e6de2b7e3860ccc2fa210f9991e0e6bf68c","abstract_canon_sha256":"1d94efda89e460e2c8484ab7e57551c5eeefc29ade7ef8994ddf90f123a6b52a"},"schema_version":"1.0"},"canonical_sha256":"b17f50be35f2a1c6fcab04ffb509248ac23aedbc73caa76e8911ed969c1e4cf1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:06.877584Z","signature_b64":"aAWX49LMumI2nnHzwmroJUXt97yGLCIZJ8zA1gXzFwOIHDaj3slhWFTMKb9gv6AmGhgMKxrOlB+M+U5qIa+pDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b17f50be35f2a1c6fcab04ffb509248ac23aedbc73caa76e8911ed969c1e4cf1","last_reissued_at":"2026-07-05T08:37:06.877094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:06.877094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.15778","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":"2026-07-05T08:37:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0N/dTvzsG4FATr2hQseumuPKZFI68R0tO7cbZ2mJs2G83HDi0J6Dzf1Jk+D0sRSfXG3prHbs0TbJcbRjA4NJBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T14:08:35.402663Z"},"content_sha256":"4d9cc254e6457cdd8385498e758823344977213b82250fa1d542259af0338520","schema_version":"1.0","event_id":"sha256:4d9cc254e6457cdd8385498e758823344977213b82250fa1d542259af0338520"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WF7VBPRV6KQ4N7FLAT73KCJERL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BASS: Batched Attention-optimized Speculative Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Anoop Deoras, Haifeng Qian, Mingyue Shang, Ramesh Nallapati, Sanjay Krishna Gouda, Sudipta Sengupta, Sujan Kumar Gonugondla, Sungsoo Ha, Xiaofei Ma","submitted_at":"2024-04-24T09:57:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15778","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/2404.15778/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":"2026-07-05T08:37:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vzdy8VAmy58AeGKGib4ZH5fokzM2TSazdwuqdUsN0MErynp1QFnAwPnPdN+fpRjqZzL1HrtfiRLZa91pMIrGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T14:08:35.403036Z"},"content_sha256":"55aa4e53ab9f4e2da4b3ec9ce712f99a224255a4162ab40d4dcc0f009f96afae","schema_version":"1.0","event_id":"sha256:55aa4e53ab9f4e2da4b3ec9ce712f99a224255a4162ab40d4dcc0f009f96afae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WF7VBPRV6KQ4N7FLAT73KCJERL/bundle.json","state_url":"https://pith.science/pith/WF7VBPRV6KQ4N7FLAT73KCJERL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WF7VBPRV6KQ4N7FLAT73KCJERL/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":"2026-08-13T14:08:35Z","links":{"resolver":"https://pith.science/pith/WF7VBPRV6KQ4N7FLAT73KCJERL","bundle":"https://pith.science/pith/WF7VBPRV6KQ4N7FLAT73KCJERL/bundle.json","state":"https://pith.science/pith/WF7VBPRV6KQ4N7FLAT73KCJERL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WF7VBPRV6KQ4N7FLAT73KCJERL/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+9Xjk+zMck9lQPMVSJof1X3IkaKmZXfPOubcf7QmVpkhVAIXGWrND9YdmEBFk8Jd07PXAj4uGlC0026dVk93CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T14:08:35.406353Z","bundle_sha256":"6d852d4d982ffe0a250eb951524c29e54a435ab9857f5b6a8f676f2918b28432"}}