{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HOFSSDHI4T6GDO5ZL3MVBIWUPB","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":"22e2f2f28555172501498c0e00d3afaa624f4c949e78b48fd1e5239a018d439d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-23T23:42:41Z","title_canon_sha256":"e01c13d50b98177b1e84e909c6eae764cc54f3d1ef63b6c1d580eda5f58f4207"},"schema_version":"1.0","source":{"id":"2402.01694","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01694","created_at":"2026-07-05T07:41:05Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01694v1","created_at":"2026-07-05T07:41:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01694","created_at":"2026-07-05T07:41:05Z"},{"alias_kind":"pith_short_12","alias_value":"HOFSSDHI4T6G","created_at":"2026-07-05T07:41:05Z"},{"alias_kind":"pith_short_16","alias_value":"HOFSSDHI4T6GDO5Z","created_at":"2026-07-05T07:41:05Z"},{"alias_kind":"pith_short_8","alias_value":"HOFSSDHI","created_at":"2026-07-05T07:41:05Z"}],"graph_snapshots":[{"event_id":"sha256:8489038d2249aafd0e2bcd715df1a40e6b543d61dbf2b3248683f2b3b705c3d9","target":"graph","created_at":"2026-07-05T07:41:05Z","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/2402.01694/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning large language models with human objectives is paramount, yet common approaches including RLHF suffer from unstable and resource-intensive training. In response to this challenge, we introduce ARGS, Alignment as Reward-Guided Search, a novel framework that integrates alignment into the decoding process, eliminating the need for expensive RL training. By adjusting the model's probabilistic predictions using a reward signal, ARGS generates texts with semantic diversity while being aligned with human preferences, offering a promising and flexible solution for aligning language models. No","authors_text":"Jirayu Burapacheep, Maxim Khanov, Yixuan Li","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-23T23:42:41Z","title":"ARGS: Alignment as Reward-Guided Search"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01694","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":"sha256:02731030b9c04d1fa5d4898996029602a0ec8cb52dc7c22775df409ae0353b16","target":"record","created_at":"2026-07-05T07:41:05Z","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":"22e2f2f28555172501498c0e00d3afaa624f4c949e78b48fd1e5239a018d439d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-23T23:42:41Z","title_canon_sha256":"e01c13d50b98177b1e84e909c6eae764cc54f3d1ef63b6c1d580eda5f58f4207"},"schema_version":"1.0","source":{"id":"2402.01694","kind":"arxiv","version":1}},"canonical_sha256":"3b8b290ce8e4fc61bbb95ed950a2d4786ac0a6520c24042d79dd4faad22084fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b8b290ce8e4fc61bbb95ed950a2d4786ac0a6520c24042d79dd4faad22084fe","first_computed_at":"2026-07-05T07:41:05.197191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:05.197191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6kA889uYrB1Vnboce6X7WYQ9GnymYwowXONLP9PacS+92rahbBa6joIbUOgXrp/TCM9TH7SITYuOdFCWaHHpDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:05.197634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01694","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02731030b9c04d1fa5d4898996029602a0ec8cb52dc7c22775df409ae0353b16","sha256:8489038d2249aafd0e2bcd715df1a40e6b543d61dbf2b3248683f2b3b705c3d9"],"state_sha256":"eb0cd3d1b831a4bb4cff6b35bf3f9a2e187ccd0fe9053d7328f95e27c7da5281"}