{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KXWIDXKAFQKHJWHVKPOFRCW7JS","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":"655ed08bdb0659784615dc7c018b297b28aeba622423942cd7b47583b832d398","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-14T19:00:00Z","title_canon_sha256":"972504a4fb6b45f6b31613e468d3c4bea1bb11d2fa4003e12e4f10fd16d3be15"},"schema_version":"1.0","source":{"id":"2411.09731","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.09731","created_at":"2026-07-05T09:41:44Z"},{"alias_kind":"arxiv_version","alias_value":"2411.09731v2","created_at":"2026-07-05T09:41:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09731","created_at":"2026-07-05T09:41:44Z"},{"alias_kind":"pith_short_12","alias_value":"KXWIDXKAFQKH","created_at":"2026-07-05T09:41:44Z"},{"alias_kind":"pith_short_16","alias_value":"KXWIDXKAFQKHJWHV","created_at":"2026-07-05T09:41:44Z"},{"alias_kind":"pith_short_8","alias_value":"KXWIDXKA","created_at":"2026-07-05T09:41:44Z"}],"graph_snapshots":[{"event_id":"sha256:f0d6e461287db733a4c071ccc412ccb3309d80a06085c9daddadca88bebbd646","target":"graph","created_at":"2026-07-05T09:41:44Z","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/2411.09731/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bootstrapping and rollout are two fundamental principles for value function estimation in reinforcement learning (RL). We introduce a novel class of Bellman operators, called subgraph Bellman operators, that interpolate between bootstrapping and rollout methods. Our estimator, derived by solving the fixed point of the empirical subgraph Bellman operator, combines the strengths of the bootstrapping-based temporal difference (TD) estimator and the rollout-based Monte Carlo (MC) methods. Specifically, the error upper bound of our estimator approaches the optimal variance achieved by TD, with an a","authors_text":"Jian Qian, Wenlong Mou","cross_cats":["math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-14T19:00:00Z","title":"To bootstrap or to rollout? An optimal and adaptive interpolation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09731","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:e2a83b493ecbce71b23868e10dee950559081b4a569c900e93ba601f2d2948a1","target":"record","created_at":"2026-07-05T09:41:44Z","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":"655ed08bdb0659784615dc7c018b297b28aeba622423942cd7b47583b832d398","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-14T19:00:00Z","title_canon_sha256":"972504a4fb6b45f6b31613e468d3c4bea1bb11d2fa4003e12e4f10fd16d3be15"},"schema_version":"1.0","source":{"id":"2411.09731","kind":"arxiv","version":2}},"canonical_sha256":"55ec81dd402c1474d8f553dc588adf4c8e5cfe6878cae03c1bcb2d515ff54b3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55ec81dd402c1474d8f553dc588adf4c8e5cfe6878cae03c1bcb2d515ff54b3f","first_computed_at":"2026-07-05T09:41:44.823817Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:41:44.823817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7Iyjut2MgQO/6ibO7RwGj5a2nj8CkvxesRK96qyS5CnrBE6Cf/NoMO0gUEse870HgRt6+nA6dQJEby7yEvI0BA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:41:44.824269Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.09731","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2a83b493ecbce71b23868e10dee950559081b4a569c900e93ba601f2d2948a1","sha256:f0d6e461287db733a4c071ccc412ccb3309d80a06085c9daddadca88bebbd646"],"state_sha256":"d67df00c9e7608d1fe6026015300719efc3fad79d2735910cd3a4d78f341e931"}