{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:APIXJFSO2ZHOPMTTMXPRL3USN7","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":"992acb844f7852103d68a02a7cb2497aa81171f3bb399a2db6640c73ac361f20","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-16T22:55:45Z","title_canon_sha256":"12bc0919d720f8f0d32b4984806e1ffa90717be3e15e26f080782522f76e909f"},"schema_version":"1.0","source":{"id":"2606.18531","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18531","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18531v1","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18531","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"APIXJFSO2ZHO","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"pith_short_16","alias_value":"APIXJFSO2ZHOPMTT","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"pith_short_8","alias_value":"APIXJFSO","created_at":"2026-06-19T16:11:40Z"}],"graph_snapshots":[{"event_id":"sha256:acbd2818f62a326afadf1b36d626abaf0b4880c3e4bfc805215f9fec3b926225","target":"graph","created_at":"2026-06-19T16:11:40Z","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/2606.18531/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning is typically analyzed under process-level reward supervision, yet many sequential decision datasets\n  record only trajectory-level outcomes. We develop a statistical theory for offline policy optimization from such outcome-level\n  supervision. We first study the canonical setting where the target remains the expected cumulative reward, but each offline trajectory\n  provides only a scalar label whose conditional mean is the cumulative return. We propose OPAC, a pessimistic actor-critic algorithm\n  that learns a latent reward model and optimizes a policy from traje","authors_text":"Tengyang Xie, Xuanfei Ren","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-16T22:55:45Z","title":"When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18531","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":"sha256:4b6b35ab3c2544eca64b24de127c74be6210de4040c4ae237349ca88cbf9f922","target":"record","created_at":"2026-06-19T16:11:40Z","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":"992acb844f7852103d68a02a7cb2497aa81171f3bb399a2db6640c73ac361f20","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-16T22:55:45Z","title_canon_sha256":"12bc0919d720f8f0d32b4984806e1ffa90717be3e15e26f080782522f76e909f"},"schema_version":"1.0","source":{"id":"2606.18531","kind":"arxiv","version":1}},"canonical_sha256":"03d174964ed64ee7b27365df15ee926fca4e64bb15efe0febdf22399f131c0fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"03d174964ed64ee7b27365df15ee926fca4e64bb15efe0febdf22399f131c0fc","first_computed_at":"2026-06-19T16:11:40.218431Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:40.218431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z8JfU2zdDWdbtSquNuo8ZC7Wf+aiBWHDI/kl4GKdXw9Ov+GHNNKa4E5/9uL7tPxGyFBKHjsZekz6r/OTT9d1BQ==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:40.218776Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18531","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4b6b35ab3c2544eca64b24de127c74be6210de4040c4ae237349ca88cbf9f922","sha256:acbd2818f62a326afadf1b36d626abaf0b4880c3e4bfc805215f9fec3b926225"],"state_sha256":"93d4ee3514504cfb76b4b9df4e1fb5512d121bd2916b01114d060371dc746b0c"}