{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SUKGKFOJPUJKOG377QZTKAU7GE","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":"e1b54ea20bdc17782476f28776569ef10c84bc0405204cffe46261f6b41b7611","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T17:44:08Z","title_canon_sha256":"9d0de54fca53262ad0e8443c4f627f59bf4445c95dbccfa7f4a10ad7890a2f02"},"schema_version":"1.0","source":{"id":"2505.20268","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20268","created_at":"2026-07-05T11:42:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20268v2","created_at":"2026-07-05T11:42:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20268","created_at":"2026-07-05T11:42:29Z"},{"alias_kind":"pith_short_12","alias_value":"SUKGKFOJPUJK","created_at":"2026-07-05T11:42:29Z"},{"alias_kind":"pith_short_16","alias_value":"SUKGKFOJPUJKOG37","created_at":"2026-07-05T11:42:29Z"},{"alias_kind":"pith_short_8","alias_value":"SUKGKFOJ","created_at":"2026-07-05T11:42:29Z"}],"graph_snapshots":[{"event_id":"sha256:24c3db2c724755cd77b459122f734deb09dd028d21904c3cf850e9c5948311cd","target":"graph","created_at":"2026-07-05T11:42:29Z","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/2505.20268/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with outcome-based feedback faces a fundamental challenge: when rewards are only observed at trajectory endpoints, how do we assign credit to the right actions? This paper provides the first comprehensive analysis of this problem in online RL with general function approximation. We develop a provably sample-efficient algorithm achieving $\\widetilde{O}({C_{\\rm cov} H^3}/{\\epsilon^2})$ sample complexity, where $C_{\\rm cov}$ is the coverability coefficient of the underlying MDP. By leveraging general function approximation, our approach works effectively in large or infinit","authors_text":"Alexander Rakhlin, Fan Chen, Tengyang Xie, Zeyu Jia","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T17:44:08Z","title":"Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20268","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:bac33193cc824058dc1b8c79d7bda1516d91a8dbeb21ca0292e6eb335b4cc4b8","target":"record","created_at":"2026-07-05T11:42:29Z","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":"e1b54ea20bdc17782476f28776569ef10c84bc0405204cffe46261f6b41b7611","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-26T17:44:08Z","title_canon_sha256":"9d0de54fca53262ad0e8443c4f627f59bf4445c95dbccfa7f4a10ad7890a2f02"},"schema_version":"1.0","source":{"id":"2505.20268","kind":"arxiv","version":2}},"canonical_sha256":"95146515c97d12a71b7ffc3335029f3121cc21a81cf666f453af6ce6b908321e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95146515c97d12a71b7ffc3335029f3121cc21a81cf666f453af6ce6b908321e","first_computed_at":"2026-07-05T11:42:29.795657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:29.795657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VFUV+Ngl9MkGPCFv5XwNrt3ZQf7VxXjp7z6XBwWWDfVgPkCWehp9i1/LGs0HEC/jwvauP+5VFGkqp5kAz1rKCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:29.796173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20268","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bac33193cc824058dc1b8c79d7bda1516d91a8dbeb21ca0292e6eb335b4cc4b8","sha256:24c3db2c724755cd77b459122f734deb09dd028d21904c3cf850e9c5948311cd"],"state_sha256":"cf53f6b0466b75c15e72c401f8d61637ca2f20c96fe6df498df6f637daa78877"}