{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IVF6V2KMDHJ736Y7XZPNCN5SF3","short_pith_number":"pith:IVF6V2KM","canonical_record":{"source":{"id":"2506.22203","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-27T13:16:31Z","cross_cats_sorted":[],"title_canon_sha256":"1afd10eef5cc68e7a92d7a1f670fcb911f2233b3b4dc9346fdc3115a004dff36","abstract_canon_sha256":"c773ae35f8173df2da98ec9dac229a5ceedc690e5f7239fe4d7d9ebb8634ee58"},"schema_version":"1.0"},"canonical_sha256":"454beae94c19d3fdfb1fbe5ed137b22ec99296cf47af8e173ed51356f0275c99","source":{"kind":"arxiv","id":"2506.22203","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22203","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22203v2","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22203","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"pith_short_12","alias_value":"IVF6V2KMDHJ7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"IVF6V2KMDHJ736Y7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"IVF6V2KM","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IVF6V2KMDHJ736Y7XZPNCN5SF3","target":"record","payload":{"canonical_record":{"source":{"id":"2506.22203","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-27T13:16:31Z","cross_cats_sorted":[],"title_canon_sha256":"1afd10eef5cc68e7a92d7a1f670fcb911f2233b3b4dc9346fdc3115a004dff36","abstract_canon_sha256":"c773ae35f8173df2da98ec9dac229a5ceedc690e5f7239fe4d7d9ebb8634ee58"},"schema_version":"1.0"},"canonical_sha256":"454beae94c19d3fdfb1fbe5ed137b22ec99296cf47af8e173ed51356f0275c99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:09:35.333090Z","signature_b64":"TfXFejl6PFAVpEPLHgABmDdZwJ/qGuHRZpk9/HWdYwSnKgrzaSixxxQyOsr/wXmQYZadrK4po+cRMu2qbOVTDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"454beae94c19d3fdfb1fbe5ed137b22ec99296cf47af8e173ed51356f0275c99","last_reissued_at":"2026-05-18T03:09:35.332414Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:09:35.332414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.22203","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W2P27s74jttWEUYN2wzVBRaTG0CWJgekdm3p0ZarFrGxq2dI7hvnx9UfIYWELc/bNhsyYfermaf5KxlhCWo+Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T16:11:36.335307Z"},"content_sha256":"db42efe34902c98f982d967b0a18426107c065ca21f8598bff69b34d17c52443","schema_version":"1.0","event_id":"sha256:db42efe34902c98f982d967b0a18426107c065ca21f8598bff69b34d17c52443"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IVF6V2KMDHJ736Y7XZPNCN5SF3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Reinforcement Learning Framework for Some Singular Stochastic Control Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Xiang Yu, Xiaodong Luo, Zongxia Liang","submitted_at":"2025-06-27T13:16:31Z","abstract_excerpt":"We develop a continuous-time reinforcement learning framework for a class of singular stochastic control problems without entropy regularization. The optimal singular control is characterized as the optimal singular control law, which is a pair of regions of time and the augmented states. The goal of learning is to identify such an optimal region via the trial-and-error procedure. In this context, we generalize the existing policy evaluation theories with regular controls to learn our optimal singular control law and develop a policy improvement theorem via the region iteration. To facilitate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22203","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:09:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7dUmMzrAONCTnEglWxqfdbDVGdmzv7i36TZB9CBweJCAALAfXuPI0yWXmY5DraIKZKEsv4WkfRyuNltOswhOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T16:11:36.335823Z"},"content_sha256":"6967630c4272e32b67c01ef19def4f43b40988eff1073f8654bb0b111bf8bb37","schema_version":"1.0","event_id":"sha256:6967630c4272e32b67c01ef19def4f43b40988eff1073f8654bb0b111bf8bb37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IVF6V2KMDHJ736Y7XZPNCN5SF3/bundle.json","state_url":"https://pith.science/pith/IVF6V2KMDHJ736Y7XZPNCN5SF3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IVF6V2KMDHJ736Y7XZPNCN5SF3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-21T16:11:36Z","links":{"resolver":"https://pith.science/pith/IVF6V2KMDHJ736Y7XZPNCN5SF3","bundle":"https://pith.science/pith/IVF6V2KMDHJ736Y7XZPNCN5SF3/bundle.json","state":"https://pith.science/pith/IVF6V2KMDHJ736Y7XZPNCN5SF3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IVF6V2KMDHJ736Y7XZPNCN5SF3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IVF6V2KMDHJ736Y7XZPNCN5SF3","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":"c773ae35f8173df2da98ec9dac229a5ceedc690e5f7239fe4d7d9ebb8634ee58","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-27T13:16:31Z","title_canon_sha256":"1afd10eef5cc68e7a92d7a1f670fcb911f2233b3b4dc9346fdc3115a004dff36"},"schema_version":"1.0","source":{"id":"2506.22203","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22203","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22203v2","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22203","created_at":"2026-05-18T03:09:35Z"},{"alias_kind":"pith_short_12","alias_value":"IVF6V2KMDHJ7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"IVF6V2KMDHJ736Y7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"IVF6V2KM","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:6967630c4272e32b67c01ef19def4f43b40988eff1073f8654bb0b111bf8bb37","target":"graph","created_at":"2026-05-18T03:09:35Z","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"},"paper":{"abstract_excerpt":"We develop a continuous-time reinforcement learning framework for a class of singular stochastic control problems without entropy regularization. The optimal singular control is characterized as the optimal singular control law, which is a pair of regions of time and the augmented states. The goal of learning is to identify such an optimal region via the trial-and-error procedure. In this context, we generalize the existing policy evaluation theories with regular controls to learn our optimal singular control law and develop a policy improvement theorem via the region iteration. To facilitate ","authors_text":"Xiang Yu, Xiaodong Luo, Zongxia Liang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-27T13:16:31Z","title":"A Reinforcement Learning Framework for Some Singular Stochastic Control Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22203","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:db42efe34902c98f982d967b0a18426107c065ca21f8598bff69b34d17c52443","target":"record","created_at":"2026-05-18T03:09:35Z","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":"c773ae35f8173df2da98ec9dac229a5ceedc690e5f7239fe4d7d9ebb8634ee58","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-06-27T13:16:31Z","title_canon_sha256":"1afd10eef5cc68e7a92d7a1f670fcb911f2233b3b4dc9346fdc3115a004dff36"},"schema_version":"1.0","source":{"id":"2506.22203","kind":"arxiv","version":2}},"canonical_sha256":"454beae94c19d3fdfb1fbe5ed137b22ec99296cf47af8e173ed51356f0275c99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"454beae94c19d3fdfb1fbe5ed137b22ec99296cf47af8e173ed51356f0275c99","first_computed_at":"2026-05-18T03:09:35.332414Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:35.332414Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TfXFejl6PFAVpEPLHgABmDdZwJ/qGuHRZpk9/HWdYwSnKgrzaSixxxQyOsr/wXmQYZadrK4po+cRMu2qbOVTDA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:35.333090Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22203","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db42efe34902c98f982d967b0a18426107c065ca21f8598bff69b34d17c52443","sha256:6967630c4272e32b67c01ef19def4f43b40988eff1073f8654bb0b111bf8bb37"],"state_sha256":"2498e775f308630379691717e8009f3f6815c4235564202321c2b13742ed570c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m4MpJZ2I47L/CCg8UNFlVwJ70+dNZXxyioRXEoBYfNbVegKnY8XSg8bLNfy4/yGta8V2SMC0AlKmtWUzqXAZAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T16:11:36.338060Z","bundle_sha256":"7afeee048dfb6f3dc63a73a837cfd0c849340a7cc4a3641dbba60188177478a6"}}