{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GYKAY2MLTSKP6HAQITVTNXYROU","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":"da9dbcfdd75d374eb8400374dec4c1089dd9e5b9d445a1c45bb36b6614c10c55","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-06T20:20:22Z","title_canon_sha256":"a6082061c76948768760f4148193f093167937b667303dd1197ce53aee979245"},"schema_version":"1.0","source":{"id":"2410.04612","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04612","created_at":"2026-07-05T10:53:12Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04612v2","created_at":"2026-07-05T10:53:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04612","created_at":"2026-07-05T10:53:12Z"},{"alias_kind":"pith_short_12","alias_value":"GYKAY2MLTSKP","created_at":"2026-07-05T10:53:12Z"},{"alias_kind":"pith_short_16","alias_value":"GYKAY2MLTSKP6HAQ","created_at":"2026-07-05T10:53:12Z"},{"alias_kind":"pith_short_8","alias_value":"GYKAY2ML","created_at":"2026-07-05T10:53:12Z"}],"graph_snapshots":[{"event_id":"sha256:d563ab28e433b4b98782881ac3be945f8e1678a8f1d11a7ac3a91073051f8052","target":"graph","created_at":"2026-07-05T10:53:12Z","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/2410.04612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable success at tasks like summarization that involve a single turn of interaction. However, they can still struggle with multi-turn tasks like dialogue that require long-term planning. Previous works on multi-turn dialogue extend single-turn reinforcement learning from human feedback (RLHF) methods to the multi-turn setting by treating all prior dialogue turns as a long context. Such approaches suffer from covariate shift: the conversations in the training set have previous turns generated by some reference policy, which means that low training","authors_text":"Gokul Swamy, Jason D. Lee, Jonathan D. Chang, Kiant\\'e Brantley, Wenhao Zhan, Wen Sun, Zhaolin Gao","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-06T20:20:22Z","title":"Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04612","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":"sha256:87c184f02a2762c3824e40491b0070f44021939da244a20d0222922a9ddc5678","target":"record","created_at":"2026-07-05T10:53:12Z","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":"da9dbcfdd75d374eb8400374dec4c1089dd9e5b9d445a1c45bb36b6614c10c55","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-06T20:20:22Z","title_canon_sha256":"a6082061c76948768760f4148193f093167937b667303dd1197ce53aee979245"},"schema_version":"1.0","source":{"id":"2410.04612","kind":"arxiv","version":2}},"canonical_sha256":"36140c698b9c94ff1c1044eb36df11752cb66150b1eb30e6357fb4f4fff3d17e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36140c698b9c94ff1c1044eb36df11752cb66150b1eb30e6357fb4f4fff3d17e","first_computed_at":"2026-07-05T10:53:12.283834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:12.283834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D7iJfzHMAKHWTajQuxez2Lh/vSdQojlmSjDHGgwk60vMPHRV5WbAXNNjYUASmWYF+9UgbQjTeKLgcCJ5TbgsDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:12.284326Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04612","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:87c184f02a2762c3824e40491b0070f44021939da244a20d0222922a9ddc5678","sha256:d563ab28e433b4b98782881ac3be945f8e1678a8f1d11a7ac3a91073051f8052"],"state_sha256":"f92c990157468e28ccfd103c9856bc1e6f7b70bba606d696ba8648c2656f5fe7"}