{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VUM6XX3CSVZ5NASPUPQO5TLHKU","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":"50f6b7bed4f63312b3378a6dd85b3ce2b02f601ed0f782fa1eac3a4a534bb22c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T07:44:31Z","title_canon_sha256":"3bd4042b580615d0e709b6ca4fbd4c1d9ca0b79662c4470641071cb80e0ce827"},"schema_version":"1.0","source":{"id":"2506.02553","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.02553","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"2506.02553v1","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.02553","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"VUM6XX3CSVZ5","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"pith_short_16","alias_value":"VUM6XX3CSVZ5NASP","created_at":"2026-07-05T11:15:03Z"},{"alias_kind":"pith_short_8","alias_value":"VUM6XX3C","created_at":"2026-07-05T11:15:03Z"}],"graph_snapshots":[{"event_id":"sha256:2e2df6714d7a2f7bd4c55100a7a1ee4eb3a826aba57793bddee60372a38bb772","target":"graph","created_at":"2026-07-05T11:15:03Z","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/2506.02553/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study a common challenge in reinforcement learning for large language models (LLMs): the Zero-Reward Assumption, where non-terminal actions (i.e., intermediate token generations) receive zero task-specific immediate reward, while only the final token receives a reward for the entire response. This assumption arises frequently in practice, as precise token-level rewards are often difficult or infeasible to obtain in LLM applications. In this work, we provide a unifying theoretical perspective. We introduce the Trajectory Policy Gradient Theorem, which shows that the policy gradient based on ","authors_text":"Hui Wei, Shenghua He, Tian Xia, Xuan Zhou","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T07:44:31Z","title":"Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.02553","kind":"arxiv","version":1},"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":"sha256:907d50cad4dff4b50950aab1c0f79474e198379868475e6eea3b141a1e4ac5cd","target":"record","created_at":"2026-07-05T11:15:03Z","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":"50f6b7bed4f63312b3378a6dd85b3ce2b02f601ed0f782fa1eac3a4a534bb22c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-03T07:44:31Z","title_canon_sha256":"3bd4042b580615d0e709b6ca4fbd4c1d9ca0b79662c4470641071cb80e0ce827"},"schema_version":"1.0","source":{"id":"2506.02553","kind":"arxiv","version":1}},"canonical_sha256":"ad19ebdf629573d6824fa3e0eecd67550ef180bfe9168dd526178e1a1c1b2345","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad19ebdf629573d6824fa3e0eecd67550ef180bfe9168dd526178e1a1c1b2345","first_computed_at":"2026-07-05T11:15:03.941956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:03.941956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dUioU+5TqCEEq1PTxxm/lMbFxYzZMF7l81PLNs6w1F5Oma03nYIUK0UKznpteOBxO/fUVvhdTavhC5ZBq1+LBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:03.942457Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.02553","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:907d50cad4dff4b50950aab1c0f79474e198379868475e6eea3b141a1e4ac5cd","sha256:2e2df6714d7a2f7bd4c55100a7a1ee4eb3a826aba57793bddee60372a38bb772"],"state_sha256":"12dcf84dcc40bbf568ff20193208be759b458a52c20d47845bd9cb8ca057df3f"}