{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VE4MLESY6PFXGGH7JVIUBUVH4B","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":"34e90a4325f072689909425498170f533fd4aea627ca74ec505492f943b250a7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-31T17:19:57Z","title_canon_sha256":"db575acf30e99ae7390268d1bd0c381a380a5e5cbe88f810f2fd1e508663ebb7"},"schema_version":"1.0","source":{"id":"2501.19324","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.19324","created_at":"2026-07-05T11:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2501.19324v3","created_at":"2026-07-05T11:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19324","created_at":"2026-07-05T11:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"VE4MLESY6PFX","created_at":"2026-07-05T11:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"VE4MLESY6PFXGGH7","created_at":"2026-07-05T11:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"VE4MLESY","created_at":"2026-07-05T11:27:23Z"}],"graph_snapshots":[{"event_id":"sha256:1ed6a8c912125759105d69eb1a91d170cf8b94ab8a658b752516b1a15b62d73f","target":"graph","created_at":"2026-07-05T11:27:23Z","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/2501.19324/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Reward-Guided Speculative Decoding (RSD), a novel framework aimed at improving the efficiency of inference in large language models (LLMs). RSD synergistically combines a lightweight draft model with a more powerful target model, incorporating a controlled bias to prioritize high-reward outputs, in contrast to existing speculative decoding methods that enforce strict unbiasedness. RSD employs a process reward model to evaluate intermediate decoding steps and dynamically decide whether to invoke the target model, optimizing the trade-off between computational cost and output qualit","authors_text":"Baohao Liao, Caiming Xiong, Christof Monz, Doyen Sahoo, HanZe Dong, Junnan Li, Silvio Savarese, Yuhui Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-31T17:19:57Z","title":"Reward-Guided Speculative Decoding for Efficient LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19324","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":"sha256:15de4d2b0a37ba0fb62eb2b8e735722f8fc46240459fd11ce486f154c4a953cb","target":"record","created_at":"2026-07-05T11:27:23Z","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":"34e90a4325f072689909425498170f533fd4aea627ca74ec505492f943b250a7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-31T17:19:57Z","title_canon_sha256":"db575acf30e99ae7390268d1bd0c381a380a5e5cbe88f810f2fd1e508663ebb7"},"schema_version":"1.0","source":{"id":"2501.19324","kind":"arxiv","version":3}},"canonical_sha256":"a938c59258f3cb7318ff4d5140d2a7e041c3294e8e15f54ff0380e8c29275319","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a938c59258f3cb7318ff4d5140d2a7e041c3294e8e15f54ff0380e8c29275319","first_computed_at":"2026-07-05T11:27:23.763810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:23.763810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CCJx/thvck4D4FaHzoYpZZRPXrhaXt8pzgmZWv+m3ESIipFEOjRWKsVbg+9VH9FYTSc2H2Jh1wn1fREFdHX+AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:23.764374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.19324","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15de4d2b0a37ba0fb62eb2b8e735722f8fc46240459fd11ce486f154c4a953cb","sha256:1ed6a8c912125759105d69eb1a91d170cf8b94ab8a658b752516b1a15b62d73f"],"state_sha256":"dda7cb40bed58a6c353a1263af2654031aac5b0a217ed7220f25454cbaa3498b"}