{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T7ZFHTWF5IV4BK55EHBUTMGYTU","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":"0f707695a28f6162398c07ef62a090c512986684e8cfb8e578f13c416b4a6a4f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-13T16:15:38Z","title_canon_sha256":"df0b34a9d016312f2962328126e856f744a206342fe63b66e3fa3503d33dce41"},"schema_version":"1.0","source":{"id":"2411.08733","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08733","created_at":"2026-07-05T09:35:15Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08733v2","created_at":"2026-07-05T09:35:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08733","created_at":"2026-07-05T09:35:15Z"},{"alias_kind":"pith_short_12","alias_value":"T7ZFHTWF5IV4","created_at":"2026-07-05T09:35:15Z"},{"alias_kind":"pith_short_16","alias_value":"T7ZFHTWF5IV4BK55","created_at":"2026-07-05T09:35:15Z"},{"alias_kind":"pith_short_8","alias_value":"T7ZFHTWF","created_at":"2026-07-05T09:35:15Z"}],"graph_snapshots":[{"event_id":"sha256:b3e87681ba9d4699e372a7a5adcaee4e4642fe26df59ff220380b51cc0664d6a","target":"graph","created_at":"2026-07-05T09:35:15Z","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/2411.08733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning Large Language Models (LLMs) traditionally relies on costly training and human preference annotations. Self-alignment seeks to reduce these expenses by enabling models to align themselves. To further lower costs and achieve alignment without any expensive tuning or annotations, we introduce a new tuning-free approach for self-alignment, Dynamic Rewarding with Prompt Optimization (DRPO). Our approach leverages a search-based optimization framework that allows LLMs to iteratively self-improve and craft the optimal alignment instructions, all without additional training or human interven","authors_text":"Abdullah Ashfaq, Eric P. Xing, Somanshu Singla, Tianyang Liu, Zhen Wang, Zhiting Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-13T16:15:38Z","title":"Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08733","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:dfb03ec6b8bff87a1870a3733bc63bba277f417bd6db763b7e1b933c3c1a7e05","target":"record","created_at":"2026-07-05T09:35:15Z","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":"0f707695a28f6162398c07ef62a090c512986684e8cfb8e578f13c416b4a6a4f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-13T16:15:38Z","title_canon_sha256":"df0b34a9d016312f2962328126e856f744a206342fe63b66e3fa3503d33dce41"},"schema_version":"1.0","source":{"id":"2411.08733","kind":"arxiv","version":2}},"canonical_sha256":"9ff253cec5ea2bc0abbd21c349b0d89d1ab10ef8e7f0ae053f7fb7e39ab86af0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ff253cec5ea2bc0abbd21c349b0d89d1ab10ef8e7f0ae053f7fb7e39ab86af0","first_computed_at":"2026-07-05T09:35:15.440784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:15.440784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+6zc/cdFcp1bI0PrltlC7HJ+I9uE9qwqiDm85plTiESoz3hG/ezrkJ45knucr/0+50anbl1E6JYcjqnIHQmtDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:15.441253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.08733","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfb03ec6b8bff87a1870a3733bc63bba277f417bd6db763b7e1b933c3c1a7e05","sha256:b3e87681ba9d4699e372a7a5adcaee4e4642fe26df59ff220380b51cc0664d6a"],"state_sha256":"f7f777acc670f5b3b312a4dc0a9adcd71f5c05a348245744c4bb65b165bcc8f4"}