{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DCIG4EOJ27M24CDLYMR7ILCK7I","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":"236688c77c24bf92f443dbb0e66701cbc5d09475e7f0c5ccef427021633e92b7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T16:58:41Z","title_canon_sha256":"fb543e0e7d09303e3abc8f00dcce1131c49e999fa1bafd68870b1a1c6967fd86"},"schema_version":"1.0","source":{"id":"2406.08414","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08414","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08414v3","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08414","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"pith_short_12","alias_value":"DCIG4EOJ27M2","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"pith_short_16","alias_value":"DCIG4EOJ27M24CDL","created_at":"2026-07-05T09:30:17Z"},{"alias_kind":"pith_short_8","alias_value":"DCIG4EOJ","created_at":"2026-07-05T09:30:17Z"}],"graph_snapshots":[{"event_id":"sha256:f59671771e4de9b2bdeccc1c49b49fc6f5da85a684dcc17f7c19fe4b04b6afa3","target":"graph","created_at":"2026-07-05T09:30:17Z","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/2406.08414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. Typically, preference optimization is approached as an offline supervised learning task using manually-crafted convex loss functions. While these methods are based on theoretical insights, they are inherently constrained by human creativity, so the large search space of possible loss functions remains under explored. We address this by performing LLM-driven objective discovery to automatically discover new state-of-the-art preference optimization algorithms without (","authors_text":"Alex J. Chan, Chris Lu, Claudio Fanconi, Jakob Foerster, Mihaela van der Schaar, Robert Tjarko Lange, Samuel Holt","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T16:58:41Z","title":"Discovering Preference Optimization Algorithms with and for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08414","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:cdb8ebaa340ee0f429acaf8708043f6538a71b69424ab24b074977d3cca1d47b","target":"record","created_at":"2026-07-05T09:30:17Z","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":"236688c77c24bf92f443dbb0e66701cbc5d09475e7f0c5ccef427021633e92b7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T16:58:41Z","title_canon_sha256":"fb543e0e7d09303e3abc8f00dcce1131c49e999fa1bafd68870b1a1c6967fd86"},"schema_version":"1.0","source":{"id":"2406.08414","kind":"arxiv","version":3}},"canonical_sha256":"18906e11c9d7d9ae086bc323f42c4afa3f71b2043b610336b18b877423ef0b5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18906e11c9d7d9ae086bc323f42c4afa3f71b2043b610336b18b877423ef0b5d","first_computed_at":"2026-07-05T09:30:17.055821Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:17.055821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ch+5YHbT8Gn+v0QtFSu7XyDASOzaNPc1NWlDmTmb3WrTCfFg7ibrLW3RQGKGs2C+L9THiN8AES4zJq58e/UdDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:17.056324Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08414","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdb8ebaa340ee0f429acaf8708043f6538a71b69424ab24b074977d3cca1d47b","sha256:f59671771e4de9b2bdeccc1c49b49fc6f5da85a684dcc17f7c19fe4b04b6afa3"],"state_sha256":"d9731decf39f0aca364cf680959f585066b46988edf775cacb41c08c16f3f7e4"}