{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:W7VL7HK3AC2IZ7EGHUG6RI76IT","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":"781b705135601ecc7d6543dc4da2cc3f236bdd71c57aded33076fc63fc7985eb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T07:11:05Z","title_canon_sha256":"65885eb6c29aff4c3af8b4b6713b8eb1d3418fd863d63bd8dce47604fb0b0fc5"},"schema_version":"1.0","source":{"id":"2405.17888","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17888","created_at":"2026-07-05T09:26:27Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17888v3","created_at":"2026-07-05T09:26:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17888","created_at":"2026-07-05T09:26:27Z"},{"alias_kind":"pith_short_12","alias_value":"W7VL7HK3AC2I","created_at":"2026-07-05T09:26:27Z"},{"alias_kind":"pith_short_16","alias_value":"W7VL7HK3AC2IZ7EG","created_at":"2026-07-05T09:26:27Z"},{"alias_kind":"pith_short_8","alias_value":"W7VL7HK3","created_at":"2026-07-05T09:26:27Z"}],"graph_snapshots":[{"event_id":"sha256:f3b8999b5b9241d3e87a30a0ca12f87a3670340a37841c75aebb1f2b0dba24be","target":"graph","created_at":"2026-07-05T09:26:27Z","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/2405.17888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning human preference and value is an important requirement for contemporary foundation models. State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning (SFT), where the model is fine-tuned by learning from human demonstration data; 2) Preference learning, where preference data is used to learn a reward model, which is in turn used by a reinforcement learning (RL) step to fine-tune the model. Such reward model serves as a proxy to human preference, and it is critical to guide the RL step towards improving t","authors_text":"Alfredo Garcia, Chenliang Li, Hoi-To Wai, Jiaxiang Li, Mingyi Hong, Siliang Zeng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T07:11:05Z","title":"Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17888","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:ed0836be2fc206252471b2db930317324e427747f9122be33285611261ca6e3c","target":"record","created_at":"2026-07-05T09:26:27Z","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":"781b705135601ecc7d6543dc4da2cc3f236bdd71c57aded33076fc63fc7985eb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-28T07:11:05Z","title_canon_sha256":"65885eb6c29aff4c3af8b4b6713b8eb1d3418fd863d63bd8dce47604fb0b0fc5"},"schema_version":"1.0","source":{"id":"2405.17888","kind":"arxiv","version":3}},"canonical_sha256":"b7eabf9d5b00b48cfc863d0de8a3fe44e20b7397ee9283bab61d8651152c0072","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7eabf9d5b00b48cfc863d0de8a3fe44e20b7397ee9283bab61d8651152c0072","first_computed_at":"2026-07-05T09:26:27.079935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:27.079935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HQdhLoEVeeU2BlfhPwZoWBjvEKpIytA1iwDk+NjiARtzdtG+o6ZXaaoE+iE3eSdqh7wXzUlyrZ/GqkYqZTDWBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:27.080456Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17888","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed0836be2fc206252471b2db930317324e427747f9122be33285611261ca6e3c","sha256:f3b8999b5b9241d3e87a30a0ca12f87a3670340a37841c75aebb1f2b0dba24be"],"state_sha256":"ffe49686c31f999c2c3aee776ff5efb75f4ecab4e6977493ddcd16c460f542ab"}