{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BVQT2WPERTZMD4UDIKBPVBKDLH","short_pith_number":"pith:BVQT2WPE","canonical_record":{"source":{"id":"1906.09340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T21:45:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6bac82a3fa64d3bfc1bd3585e5cbb90332e69c2d4a2ac20254dff8c08db71847","abstract_canon_sha256":"6dc2df134d2032ac2ee3ab888a6509f3a8a52d7b0462eca476f10c0340984a18"},"schema_version":"1.0"},"canonical_sha256":"0d613d59e48cf2c1f2834282fa854359fedd695f0dc3a3886163f91d4c229636","source":{"kind":"arxiv","id":"1906.09340","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09340","created_at":"2026-05-17T23:42:38Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09340v1","created_at":"2026-05-17T23:42:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09340","created_at":"2026-05-17T23:42:38Z"},{"alias_kind":"pith_short_12","alias_value":"BVQT2WPERTZM","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BVQT2WPERTZMD4UD","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BVQT2WPE","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BVQT2WPERTZMD4UDIKBPVBKDLH","target":"record","payload":{"canonical_record":{"source":{"id":"1906.09340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T21:45:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6bac82a3fa64d3bfc1bd3585e5cbb90332e69c2d4a2ac20254dff8c08db71847","abstract_canon_sha256":"6dc2df134d2032ac2ee3ab888a6509f3a8a52d7b0462eca476f10c0340984a18"},"schema_version":"1.0"},"canonical_sha256":"0d613d59e48cf2c1f2834282fa854359fedd695f0dc3a3886163f91d4c229636","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:38.428789Z","signature_b64":"pfhRlRV6tBYMpvCMTLQN4lrajGQSJI/VxbkWbgU9Cn8NdFGzqxgRrkAalDFZro018YnnUPsM860tNtzPFTUnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d613d59e48cf2c1f2834282fa854359fedd695f0dc3a3886163f91d4c229636","last_reissued_at":"2026-05-17T23:42:38.428251Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:38.428251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.09340","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"neCnl90YoyMDlM3RJIi3QIc19cDiX8V/qHGzkSz0KvFEnMvAlJ3wP/HtLNtr6PQcM4hkx099YRF6IEinO9m6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T12:58:36.551740Z"},"content_sha256":"bc462490446cde7b52e3efb9b31e7e8a93eea168e020251463cb7a8df02e8080","schema_version":"1.0","event_id":"sha256:bc462490446cde7b52e3efb9b31e7e8a93eea168e020251463cb7a8df02e8080"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BVQT2WPERTZMD4UDIKBPVBKDLH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Reinforcement Learning Techniques for Effective Policy Adoption and Validation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Clement H. C. Leung, Nikki Lijing Kuang","submitted_at":"2019-06-21T21:45:58Z","abstract_excerpt":"Rewards and punishments in different forms are pervasive and present in a wide variety of decision-making scenarios. By observing the outcome of a sufficient number of repeated trials, one would gradually learn the value and usefulness of a particular policy or strategy. However, in a given environment, the outcomes resulting from different trials are subject to chance influence and variations. In learning about the usefulness of a given policy, significant costs are involved in systematically undertaking the sequential trials; therefore, in most learning episodes, one would wish to keep the c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09340","kind":"arxiv","version":1},"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":"2026-05-17T23:42:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2r3zerPCfwi7yUCs6LyhZgaGYANEJO83NvMa56Qq4UO3Yjw+kqGMOhFfYqJRAPkIi3BN7IUof52wJJHM4taaCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T12:58:36.552478Z"},"content_sha256":"3c2cdfc57d669b24a0d992f46471b661831b147b8856fe127656498650d59da5","schema_version":"1.0","event_id":"sha256:3c2cdfc57d669b24a0d992f46471b661831b147b8856fe127656498650d59da5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BVQT2WPERTZMD4UDIKBPVBKDLH/bundle.json","state_url":"https://pith.science/pith/BVQT2WPERTZMD4UDIKBPVBKDLH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BVQT2WPERTZMD4UDIKBPVBKDLH/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":"2026-05-27T12:58:36Z","links":{"resolver":"https://pith.science/pith/BVQT2WPERTZMD4UDIKBPVBKDLH","bundle":"https://pith.science/pith/BVQT2WPERTZMD4UDIKBPVBKDLH/bundle.json","state":"https://pith.science/pith/BVQT2WPERTZMD4UDIKBPVBKDLH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BVQT2WPERTZMD4UDIKBPVBKDLH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BVQT2WPERTZMD4UDIKBPVBKDLH","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":"6dc2df134d2032ac2ee3ab888a6509f3a8a52d7b0462eca476f10c0340984a18","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T21:45:58Z","title_canon_sha256":"6bac82a3fa64d3bfc1bd3585e5cbb90332e69c2d4a2ac20254dff8c08db71847"},"schema_version":"1.0","source":{"id":"1906.09340","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09340","created_at":"2026-05-17T23:42:38Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09340v1","created_at":"2026-05-17T23:42:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09340","created_at":"2026-05-17T23:42:38Z"},{"alias_kind":"pith_short_12","alias_value":"BVQT2WPERTZM","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BVQT2WPERTZMD4UD","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BVQT2WPE","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:3c2cdfc57d669b24a0d992f46471b661831b147b8856fe127656498650d59da5","target":"graph","created_at":"2026-05-17T23:42:38Z","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":"Rewards and punishments in different forms are pervasive and present in a wide variety of decision-making scenarios. By observing the outcome of a sufficient number of repeated trials, one would gradually learn the value and usefulness of a particular policy or strategy. However, in a given environment, the outcomes resulting from different trials are subject to chance influence and variations. In learning about the usefulness of a given policy, significant costs are involved in systematically undertaking the sequential trials; therefore, in most learning episodes, one would wish to keep the c","authors_text":"Clement H. C. Leung, Nikki Lijing Kuang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T21:45:58Z","title":"Leveraging Reinforcement Learning Techniques for Effective Policy Adoption and Validation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09340","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:bc462490446cde7b52e3efb9b31e7e8a93eea168e020251463cb7a8df02e8080","target":"record","created_at":"2026-05-17T23:42:38Z","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":"6dc2df134d2032ac2ee3ab888a6509f3a8a52d7b0462eca476f10c0340984a18","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T21:45:58Z","title_canon_sha256":"6bac82a3fa64d3bfc1bd3585e5cbb90332e69c2d4a2ac20254dff8c08db71847"},"schema_version":"1.0","source":{"id":"1906.09340","kind":"arxiv","version":1}},"canonical_sha256":"0d613d59e48cf2c1f2834282fa854359fedd695f0dc3a3886163f91d4c229636","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d613d59e48cf2c1f2834282fa854359fedd695f0dc3a3886163f91d4c229636","first_computed_at":"2026-05-17T23:42:38.428251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:38.428251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pfhRlRV6tBYMpvCMTLQN4lrajGQSJI/VxbkWbgU9Cn8NdFGzqxgRrkAalDFZro018YnnUPsM860tNtzPFTUnBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:38.428789Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.09340","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc462490446cde7b52e3efb9b31e7e8a93eea168e020251463cb7a8df02e8080","sha256:3c2cdfc57d669b24a0d992f46471b661831b147b8856fe127656498650d59da5"],"state_sha256":"6513d8b14ed04193837faa732e5aba69aeb9fc3afeafa51ea7d12150cba1d582"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1A7AL6Apq7GDv+W78m/Q8pTI5Ck0NzaoR1diGMqGKRo1CHGvjwVDzcFdUimk2R8hWME1w9wa8a69s3KbYYA3Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T12:58:36.556860Z","bundle_sha256":"78112d2ac638f1160a68c050dfd5f4c676a0628c6c74ed1044ecb45340b4ec8c"}}