{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MST33XZPVM73JX7PMMV3IOYS42","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":"276cedeb1cbb82b584c97005c728727a7b27b3f8ffb66f1b6d42130950705582","cross_cats_sorted":["cs.CL","cs.DS","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T17:47:34Z","title_canon_sha256":"1f0e304eb6d84d8bc36f3be5a80f1554898de91c83a2a0bc5982d3a03426eec6"},"schema_version":"1.0","source":{"id":"2310.15141","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15141","created_at":"2026-07-05T07:34:51Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15141v2","created_at":"2026-07-05T07:34:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15141","created_at":"2026-07-05T07:34:51Z"},{"alias_kind":"pith_short_12","alias_value":"MST33XZPVM73","created_at":"2026-07-05T07:34:51Z"},{"alias_kind":"pith_short_16","alias_value":"MST33XZPVM73JX7P","created_at":"2026-07-05T07:34:51Z"},{"alias_kind":"pith_short_8","alias_value":"MST33XZP","created_at":"2026-07-05T07:34:51Z"}],"graph_snapshots":[{"event_id":"sha256:a7873a3307758301d8eed601a8af7b68f9685b9dbaf043af4c2df499857a461d","target":"graph","created_at":"2026-07-05T07:34:51Z","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/2310.15141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autoregressive sampling from large language models has led to state-of-the-art results in several natural language tasks. However, autoregressive sampling generates tokens one at a time making it slow, and even prohibitive in certain tasks. One way to speed up sampling is $\\textit{speculative decoding}$: use a small model to sample a $\\textit{draft}$ (block or sequence of tokens), and then score all tokens in the draft by the large language model in parallel. A subset of the tokens in the draft are accepted (and the rest rejected) based on a statistical method to guarantee that the final outpu","authors_text":"Ahmad Beirami, Ananda Theertha Suresh, Felix Yu, Himanshu Jain, Jae Hun Ro, Ziteng Sun","cross_cats":["cs.CL","cs.DS","cs.IT","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T17:47:34Z","title":"SpecTr: Fast Speculative Decoding via Optimal Transport"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15141","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":"sha256:0f3a2095efefb7b0a4dc8b10a7f8a2f169bc1b050033c16f3619dabb803f9f1c","target":"record","created_at":"2026-07-05T07:34:51Z","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":"276cedeb1cbb82b584c97005c728727a7b27b3f8ffb66f1b6d42130950705582","cross_cats_sorted":["cs.CL","cs.DS","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T17:47:34Z","title_canon_sha256":"1f0e304eb6d84d8bc36f3be5a80f1554898de91c83a2a0bc5982d3a03426eec6"},"schema_version":"1.0","source":{"id":"2310.15141","kind":"arxiv","version":2}},"canonical_sha256":"64a7bddf2fab3fb4dfef632bb43b12e68743dbfd3237570b2267b1e46294dd0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64a7bddf2fab3fb4dfef632bb43b12e68743dbfd3237570b2267b1e46294dd0f","first_computed_at":"2026-07-05T07:34:51.785221Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:34:51.785221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p3V49uk21DDAjCJEyHfhX15LBIiFqZkmKPMljxX99XVpq6RwrHBzGoRp8stpU/XqIYgyuSzKyergZZlLCAUmDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:34:51.785746Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.15141","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f3a2095efefb7b0a4dc8b10a7f8a2f169bc1b050033c16f3619dabb803f9f1c","sha256:a7873a3307758301d8eed601a8af7b68f9685b9dbaf043af4c2df499857a461d"],"state_sha256":"8f32b623f06d8f93922fc6ff5584fd890475fc3b25ab7c8b5caa92100de9ba85"}