{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NEYVBA627KANMD7AR7GTVDZY6D","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":"21be91904b91b77e5bcedc8257e0cc0c7cd733b661d2b06326a113577eb7c264","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T08:38:45Z","title_canon_sha256":"f614c579c62684eba31d55c3c110bf984f013a045d65bc8ae7b805a584db4dca"},"schema_version":"1.0","source":{"id":"2503.13565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13565","created_at":"2026-07-05T10:33:12Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13565v1","created_at":"2026-07-05T10:33:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13565","created_at":"2026-07-05T10:33:12Z"},{"alias_kind":"pith_short_12","alias_value":"NEYVBA627KAN","created_at":"2026-07-05T10:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"NEYVBA627KANMD7A","created_at":"2026-07-05T10:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"NEYVBA62","created_at":"2026-07-05T10:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:b253a01fc2c04588325830dede8e410fd7ce2686a2bab63584849ee9a93d20f8","target":"graph","created_at":"2026-07-05T10:33:12Z","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/2503.13565/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speculative decoding (SD) has emerged as a method to accelerate LLM inference without sacrificing any accuracy over the 16-bit model inference. In a typical SD setup, the idea is to use a full-precision, small, fast model as \"draft\" to generate the next few tokens and use the \"target\" large model to verify the draft-generated tokens. The efficacy of this method heavily relies on the acceptance ratio of the draft-generated tokens and the relative token throughput of the draft versus the target model. Nevertheless, an efficient SD pipeline requires pre-training and aligning the draft model to th","authors_text":"Alexander Heinecke, Alexander Kozlov, Dhiraj Kalamkar, Evangelos Georganas","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T08:38:45Z","title":"ML-SpecQD: Multi-Level Speculative Decoding with Quantized Drafts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13565","kind":"arxiv","version":1},"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":"sha256:9b5363314dce1ceace73383569fba82bb30284e8ba0d53cd262b1345a2360951","target":"record","created_at":"2026-07-05T10:33:12Z","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":"21be91904b91b77e5bcedc8257e0cc0c7cd733b661d2b06326a113577eb7c264","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-17T08:38:45Z","title_canon_sha256":"f614c579c62684eba31d55c3c110bf984f013a045d65bc8ae7b805a584db4dca"},"schema_version":"1.0","source":{"id":"2503.13565","kind":"arxiv","version":1}},"canonical_sha256":"69315083dafa80d60fe08fcd3a8f38f0e9f94e2aefbcaba22c70112c5310f998","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69315083dafa80d60fe08fcd3a8f38f0e9f94e2aefbcaba22c70112c5310f998","first_computed_at":"2026-07-05T10:33:12.969306Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:12.969306Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"guWA9B9bW1MKkHG1nf8v6U0D1wTmTZmaj+D1jWIT7ktu0LaHDDCe1z8HUMK+r6YtXpKTV2i54njemyNh8GgZBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:12.969814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b5363314dce1ceace73383569fba82bb30284e8ba0d53cd262b1345a2360951","sha256:b253a01fc2c04588325830dede8e410fd7ce2686a2bab63584849ee9a93d20f8"],"state_sha256":"0775083a0de55c3aa725078f31ae224905acd200d2200f180cf6af3335884b6c"}