{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FXK5PQRFSO5SXLBDNSEHUE2C3I","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":"e0aaccbb17c102fc42c2171a5cb3aee98c99c6ccb29e2e587ff94d620436f737","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-28T21:02:13Z","title_canon_sha256":"e4ca3faaf12b1da8ccaa060ba30104b9d0c54468b83e7dd0b247595b386f9946"},"schema_version":"1.0","source":{"id":"2410.21533","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.21533","created_at":"2026-07-05T10:31:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.21533v3","created_at":"2026-07-05T10:31:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.21533","created_at":"2026-07-05T10:31:49Z"},{"alias_kind":"pith_short_12","alias_value":"FXK5PQRFSO5S","created_at":"2026-07-05T10:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"FXK5PQRFSO5SXLBD","created_at":"2026-07-05T10:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"FXK5PQRF","created_at":"2026-07-05T10:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:cd13a4ef434cdd358680f12811b13a2f78f880e3119e283282cf25bbcbb5aa5f","target":"graph","created_at":"2026-07-05T10:31:49Z","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/2410.21533/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised fine-tuning (SFT) and alignment of large language models (LLMs) are key steps in providing a good user experience. However, the concept of an appropriate alignment is inherently application-dependent, and current methods often rely on heuristic choices to drive optimization. In this work, we formulate SFT and alignment as a constrained optimization problem: the LLM is fine-tuned on a task while being required to meet application-specific requirements, without resorting to heuristics. To solve this, we propose Lagrange Large Language Models (L3Ms), which employ logarithmic barriers t","authors_text":"Alex Smola, Guneet S. Dhillon, Xingjian Shi, Yee Whye Teh","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-28T21:02:13Z","title":"L3Ms -- Lagrange Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.21533","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":"sha256:82ab5a2d232ef6042cc9e0ab3ab80f54a578718a28000ca39681fa1e9e2a2464","target":"record","created_at":"2026-07-05T10:31:49Z","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":"e0aaccbb17c102fc42c2171a5cb3aee98c99c6ccb29e2e587ff94d620436f737","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-28T21:02:13Z","title_canon_sha256":"e4ca3faaf12b1da8ccaa060ba30104b9d0c54468b83e7dd0b247595b386f9946"},"schema_version":"1.0","source":{"id":"2410.21533","kind":"arxiv","version":3}},"canonical_sha256":"2dd5d7c22593bb2bac236c887a1342da2cb61c9720e5fec7a307f41013b83681","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2dd5d7c22593bb2bac236c887a1342da2cb61c9720e5fec7a307f41013b83681","first_computed_at":"2026-07-05T10:31:49.270524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:49.270524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k00TFsx2gDjk/qcanwUh0BkDac+1voXD+qoMC4MTGHijqy77LEQIh6LyzjyBjnUI0twyn/zie4zZ/UsMsstGDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:49.271060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.21533","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82ab5a2d232ef6042cc9e0ab3ab80f54a578718a28000ca39681fa1e9e2a2464","sha256:cd13a4ef434cdd358680f12811b13a2f78f880e3119e283282cf25bbcbb5aa5f"],"state_sha256":"70b76fc2c20b88c37b21f6fad63bc66e2b32c3e8f27dda264e2af60551cb3f97"}