{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3FSGNBUVSRZXJ3ZHYDIKIZBDZ4","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":"8c1614fabe669f8587361d9b69e498b1dd0f3cee4967cba536e439ef7af34da5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T18:58:31Z","title_canon_sha256":"08128ac739bf0198d5670b6d1fc86ab00974d65e2e3785a7acc205bc6468436b"},"schema_version":"1.0","source":{"id":"2402.10207","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10207","created_at":"2026-07-05T09:21:02Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10207v6","created_at":"2026-07-05T09:21:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10207","created_at":"2026-07-05T09:21:02Z"},{"alias_kind":"pith_short_12","alias_value":"3FSGNBUVSRZX","created_at":"2026-07-05T09:21:02Z"},{"alias_kind":"pith_short_16","alias_value":"3FSGNBUVSRZXJ3ZH","created_at":"2026-07-05T09:21:02Z"},{"alias_kind":"pith_short_8","alias_value":"3FSGNBUV","created_at":"2026-07-05T09:21:02Z"}],"graph_snapshots":[{"event_id":"sha256:92717a9137dece038b6fbb7916057029c95233e61e1828487b67e9453fe535c6","target":"graph","created_at":"2026-07-05T09:21:02Z","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/2402.10207/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems. However, it is generally costly and unstable to fine-tune large foundation models using reinforcement learning (RL), and the multi-dimensionality, heterogeneity, and conflicting nature of human preferences further complicate the alignment process. In this paper, we introduce Rewards-in-Context (RiC), which conditions the response of a foundation model on multiple rewards in its prompt context and applies supervised fine-tuning for a","authors_text":"Dong Yu, Feng Luo, Han Zhong, Jianshu Chen, Rui Yang, Shuang Qiu, Xiaoman Pan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T18:58:31Z","title":"Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10207","kind":"arxiv","version":6},"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":"sha256:3562516428882bcc120582a9f84a8d840178976f6a63d57a722ef824c17af784","target":"record","created_at":"2026-07-05T09:21:02Z","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":"8c1614fabe669f8587361d9b69e498b1dd0f3cee4967cba536e439ef7af34da5","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T18:58:31Z","title_canon_sha256":"08128ac739bf0198d5670b6d1fc86ab00974d65e2e3785a7acc205bc6468436b"},"schema_version":"1.0","source":{"id":"2402.10207","kind":"arxiv","version":6}},"canonical_sha256":"d964668695947374ef27c0d0a46423cf1ba893b9494ebae6bb8d4b888fdbdf93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d964668695947374ef27c0d0a46423cf1ba893b9494ebae6bb8d4b888fdbdf93","first_computed_at":"2026-07-05T09:21:02.693222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:02.693222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LI52r76sMyQpabHtXNQOo3V6ph7k+Y+NnjNbHMhLgmdbM1511v8R+Jn7PEbiqswYNyxLn5FNG08YscLhy+U7AA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:02.693742Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.10207","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3562516428882bcc120582a9f84a8d840178976f6a63d57a722ef824c17af784","sha256:92717a9137dece038b6fbb7916057029c95233e61e1828487b67e9453fe535c6"],"state_sha256":"d102f58271b32431c909cdbdf3451e45255dd645397c5972e1d9e7d02d93b440"}