{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZVSRX5LNNDEDH7C26I4GOPMJIP","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":"2b1aae88a6f23cc8ae3cd374b868019e65645e680d7aa7d3ebd78e7e65b6127c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T21:36:12Z","title_canon_sha256":"74dbb6ce66e8c66aaa6bc7589a1e26a474286c545e41bda18c7c9187211c3f26"},"schema_version":"1.0","source":{"id":"2405.20495","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20495","created_at":"2026-07-05T08:25:38Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20495v1","created_at":"2026-07-05T08:25:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20495","created_at":"2026-07-05T08:25:38Z"},{"alias_kind":"pith_short_12","alias_value":"ZVSRX5LNNDED","created_at":"2026-07-05T08:25:38Z"},{"alias_kind":"pith_short_16","alias_value":"ZVSRX5LNNDEDH7C2","created_at":"2026-07-05T08:25:38Z"},{"alias_kind":"pith_short_8","alias_value":"ZVSRX5LN","created_at":"2026-07-05T08:25:38Z"}],"graph_snapshots":[{"event_id":"sha256:2af2f3e99a3f6d94f8d8cb14207a81b1682e151bdc849e0f095c2688b706bb7c","target":"graph","created_at":"2026-07-05T08:25:38Z","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/2405.20495/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning foundation models is essential for their safe and trustworthy deployment. However, traditional fine-tuning methods are computationally intensive and require updating billions of model parameters. A promising alternative, alignment via decoding, adjusts the response distribution directly without model updates to maximize a target reward $r$, thus providing a lightweight and adaptable framework for alignment. However, principled decoding methods rely on oracle access to an optimal Q-function ($Q^*$), which is often unavailable in practice. Hence, prior SoTA methods either approximate th","authors_text":"Amrit Singh Bedi, Dinesh Manocha, Furong Huang, Mengdi Wang, Ming Yin, Soumya Suvra Ghosal, Souradip Chakraborty","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T21:36:12Z","title":"Transfer Q Star: Principled Decoding for LLM Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20495","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:e9b4d6703746cefb847e09bb780aff4c2bbb4b92b07d9c013d03a2a44332d908","target":"record","created_at":"2026-07-05T08:25:38Z","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":"2b1aae88a6f23cc8ae3cd374b868019e65645e680d7aa7d3ebd78e7e65b6127c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-30T21:36:12Z","title_canon_sha256":"74dbb6ce66e8c66aaa6bc7589a1e26a474286c545e41bda18c7c9187211c3f26"},"schema_version":"1.0","source":{"id":"2405.20495","kind":"arxiv","version":1}},"canonical_sha256":"cd651bf56d68c833fc5af238673d8943ec338dd08aeafaebadf771c1171b7b11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd651bf56d68c833fc5af238673d8943ec338dd08aeafaebadf771c1171b7b11","first_computed_at":"2026-07-05T08:25:38.156346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:38.156346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KndiA+aELqY6exBBrD7jvxe3BH4dmvzGWgg+9uYcyeOGhr63Jca1E7b3OlLWu33d+KCELvYo5SA99yY7XSk3Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:38.156804Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20495","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9b4d6703746cefb847e09bb780aff4c2bbb4b92b07d9c013d03a2a44332d908","sha256:2af2f3e99a3f6d94f8d8cb14207a81b1682e151bdc849e0f095c2688b706bb7c"],"state_sha256":"a4df6102de10284211b259ce2484bef494ef1d769e6913606ef123ed67ec40e7"}