{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UNCOJKTKD56D5DBWAJZGJGDQ6N","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":"7b28ddf44b3b46d5876e9515c4d9e22bef9864356c955256fd106ab4c8cd8748","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T06:37:25Z","title_canon_sha256":"d15031d063cfda28d096d2471f4c5d0ec097d6e6b947befdda08ecb7975e351f"},"schema_version":"1.0","source":{"id":"2505.12759","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12759","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12759v1","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12759","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"UNCOJKTKD56D","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"UNCOJKTKD56D5DBW","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"UNCOJKTK","created_at":"2026-07-05T11:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:cc8a3cb3b55203bc2c38fe7a66e0eb60981163deb3681ca9c1faa29e4a241ad1","target":"graph","created_at":"2026-07-05T11:05:09Z","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/2505.12759/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) has shown significant promise for sequential portfolio optimization tasks, such as stock trading, where the objective is to maximize cumulative returns while minimizing risks using historical data. However, traditional RL approaches often produce policies that merely memorize the optimal yet impractical buying and selling behaviors within the fixed dataset. These offline policies are less generalizable as they fail to account for the non-stationary nature of the market. Our approach, MetaTrader, frames portfolio optimization as a new type of partial-offline RL probl","authors_text":"Haochen Yuan, Minting Pan, Philip S.Yu, Siyu Gao, Xiaokang Yang, Yunbo Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T06:37:25Z","title":"Your Offline Policy is Not Trustworthy: Bilevel Reinforcement Learning for Sequential Portfolio Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12759","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:d78e836a40176e2f360ccdaf9f9884b7a8db68974787044ff070e476de06288d","target":"record","created_at":"2026-07-05T11:05:09Z","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":"7b28ddf44b3b46d5876e9515c4d9e22bef9864356c955256fd106ab4c8cd8748","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T06:37:25Z","title_canon_sha256":"d15031d063cfda28d096d2471f4c5d0ec097d6e6b947befdda08ecb7975e351f"},"schema_version":"1.0","source":{"id":"2505.12759","kind":"arxiv","version":1}},"canonical_sha256":"a344e4aa6a1f7c3e8c360272649870f35abf8e79c6e087e1f5eb49d5476aa4de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a344e4aa6a1f7c3e8c360272649870f35abf8e79c6e087e1f5eb49d5476aa4de","first_computed_at":"2026-07-05T11:05:09.200107Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:09.200107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kOlo7aluHtCsUp7vz/uH4A6Woa7/rae/8Z2eY7+XHVZ1OoBTFg+6TArYbOTuXjAo5MkO6r/pWYQDWUCKdHtZDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:09.200570Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12759","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d78e836a40176e2f360ccdaf9f9884b7a8db68974787044ff070e476de06288d","sha256:cc8a3cb3b55203bc2c38fe7a66e0eb60981163deb3681ca9c1faa29e4a241ad1"],"state_sha256":"4f32154b8c85424fb443116d2a4127967c66c0dff90596fcfa201d83649ed629"}