{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BDSCF23R7R4C7JKP3P6BGCI3IF","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":"8f2d10d2809ac8ed33e85ab38ca7adb1ce9d29bec72f427cbfae6493838b5bb6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2022-03-25T04:33:15Z","title_canon_sha256":"18e3ff1bf4edd6e66060d3e9dcb67924fbd56cbcc9f3eab7a17bc6926a96e67b"},"schema_version":"1.0","source":{"id":"2203.13446","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.13446","created_at":"2026-07-05T04:08:32Z"},{"alias_kind":"arxiv_version","alias_value":"2203.13446v1","created_at":"2026-07-05T04:08:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13446","created_at":"2026-07-05T04:08:32Z"},{"alias_kind":"pith_short_12","alias_value":"BDSCF23R7R4C","created_at":"2026-07-05T04:08:32Z"},{"alias_kind":"pith_short_16","alias_value":"BDSCF23R7R4C7JKP","created_at":"2026-07-05T04:08:32Z"},{"alias_kind":"pith_short_8","alias_value":"BDSCF23R","created_at":"2026-07-05T04:08:32Z"}],"graph_snapshots":[{"event_id":"sha256:1d1bcd2b3a1150edaeba338cca79330f52a25d4c2e40acfe2df90005f80c68c5","target":"graph","created_at":"2026-07-05T04:08:32Z","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/2203.13446/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Optimal stopping is the problem of determining when to stop a stochastic system in order to maximize reward, which is of practical importance in domains such as finance, operations management and healthcare. Existing methods for high-dimensional optimal stopping that are popular in practice produce deterministic linear policies -- policies that deterministically stop based on the sign of a weighted sum of basis functions -- but are not guaranteed to find the optimal policy within this policy class given a fixed basis function architecture. In this paper, we propose a new methodology for optima","authors_text":"Velibor V. Mi\\v{s}i\\'c, Xinyi Guan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2022-03-25T04:33:15Z","title":"Randomized Policy Optimization for Optimal Stopping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13446","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":"sha256:1002323df440887a351fbd0df6286b0cf027eb98d494ec486dd4f4a09508f2d0","target":"record","created_at":"2026-07-05T04:08:32Z","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":"8f2d10d2809ac8ed33e85ab38ca7adb1ce9d29bec72f427cbfae6493838b5bb6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2022-03-25T04:33:15Z","title_canon_sha256":"18e3ff1bf4edd6e66060d3e9dcb67924fbd56cbcc9f3eab7a17bc6926a96e67b"},"schema_version":"1.0","source":{"id":"2203.13446","kind":"arxiv","version":1}},"canonical_sha256":"08e422eb71fc782fa54fdbfc13091b414a2c6c21bde11e5810848deb22632e98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08e422eb71fc782fa54fdbfc13091b414a2c6c21bde11e5810848deb22632e98","first_computed_at":"2026-07-05T04:08:32.195817Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:32.195817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EAv5H4Hh8mg87Pp1Wb5C3/oWZUxJgPCK8eyl+L8FEt1AS3BNclamvIM82cna91sjBCI/DSwVqL5Cpu/s+aI1DA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:32.196191Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.13446","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1002323df440887a351fbd0df6286b0cf027eb98d494ec486dd4f4a09508f2d0","sha256:1d1bcd2b3a1150edaeba338cca79330f52a25d4c2e40acfe2df90005f80c68c5"],"state_sha256":"cc7d46aab5554bdc9957cbd3af204d77b38fe498170c4ab15b4ec8308c06cb09"}