{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:PQDCSFQZ4GGTFDAXAPSVSE5LBJ","short_pith_number":"pith:PQDCSFQZ","canonical_record":{"source":{"id":"1902.07239","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-19T19:15:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a51f30508c59bda972836c1682493039fe986dd21f2e0153c0e4ce48eb6d5c0b","abstract_canon_sha256":"d65045bf93c8de2424d0777fcc5bdbbcb54afe906ff64c4fa9a13dbda3007d1a"},"schema_version":"1.0"},"canonical_sha256":"7c06291619e18d328c1703e55913ab0a531af0ef64e60577481f29991454b5c0","source":{"kind":"arxiv","id":"1902.07239","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.07239","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"1902.07239v1","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07239","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"PQDCSFQZ4GGT","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PQDCSFQZ4GGTFDAX","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PQDCSFQZ","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:PQDCSFQZ4GGTFDAXAPSVSE5LBJ","target":"record","payload":{"canonical_record":{"source":{"id":"1902.07239","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-19T19:15:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a51f30508c59bda972836c1682493039fe986dd21f2e0153c0e4ce48eb6d5c0b","abstract_canon_sha256":"d65045bf93c8de2424d0777fcc5bdbbcb54afe906ff64c4fa9a13dbda3007d1a"},"schema_version":"1.0"},"canonical_sha256":"7c06291619e18d328c1703e55913ab0a531af0ef64e60577481f29991454b5c0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:08.510432Z","signature_b64":"21SAGJuUYSj96DprYWUoCM58NoFca/uVJFT2MVADF05JE3y4dIyQQjeuIp9sEPE8XZ+lfdFpWpECWyhXKE2vDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c06291619e18d328c1703e55913ab0a531af0ef64e60577481f29991454b5c0","last_reissued_at":"2026-05-17T23:53:08.509833Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:08.509833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.07239","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":"2026-05-17T23:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uH2lfFyt75XSPHEWZLiE5TcuNsnYT0aUbIiM/5ZY93x5LN4bhVtATPzHUTuo+5lXVCMrL4ChscClmXwdmz4UCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:06:02.196970Z"},"content_sha256":"1e8f6b1b9389bb97f02227fdf8f98ac927bb402aa1c9e1ede79481a84b89d26f","schema_version":"1.0","event_id":"sha256:1e8f6b1b9389bb97f02227fdf8f98ac927bb402aa1c9e1ede79481a84b89d26f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:PQDCSFQZ4GGTFDAXAPSVSE5LBJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable Thompson Sampling via Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Changyou Chen, Lawrence Carin, Ruiyi Zhang, Zheng Wen","submitted_at":"2019-02-19T19:15:08Z","abstract_excerpt":"Thompson sampling (TS) is a class of algorithms for sequential decision-making, which requires maintaining a posterior distribution over a model. However, calculating exact posterior distributions is intractable for all but the simplest models. Consequently, efficient computation of an approximate posterior distribution is a crucial problem for scalable TS with complex models, such as neural networks. In this paper, we use distribution optimization techniques to approximate the posterior distribution, solved via Wasserstein gradient flows. Based on the framework, a principled particle-optimiza"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07239","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":"2026-05-17T23:53:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GdcYZy9a+ThjhMCPXr9sNFshj+8vq27xw7bzd+ReXlhoGKXXRhtXKCf6PV5aiJbwbSfGcrHueYMP5b9zB0ukCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:06:02.197342Z"},"content_sha256":"30791c272122da707aedba3e1fb1075a0e2e1b1adae9648521fa16a0a94473c6","schema_version":"1.0","event_id":"sha256:30791c272122da707aedba3e1fb1075a0e2e1b1adae9648521fa16a0a94473c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQDCSFQZ4GGTFDAXAPSVSE5LBJ/bundle.json","state_url":"https://pith.science/pith/PQDCSFQZ4GGTFDAXAPSVSE5LBJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQDCSFQZ4GGTFDAXAPSVSE5LBJ/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":"2026-05-30T05:06:02Z","links":{"resolver":"https://pith.science/pith/PQDCSFQZ4GGTFDAXAPSVSE5LBJ","bundle":"https://pith.science/pith/PQDCSFQZ4GGTFDAXAPSVSE5LBJ/bundle.json","state":"https://pith.science/pith/PQDCSFQZ4GGTFDAXAPSVSE5LBJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQDCSFQZ4GGTFDAXAPSVSE5LBJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:PQDCSFQZ4GGTFDAXAPSVSE5LBJ","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":"d65045bf93c8de2424d0777fcc5bdbbcb54afe906ff64c4fa9a13dbda3007d1a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-19T19:15:08Z","title_canon_sha256":"a51f30508c59bda972836c1682493039fe986dd21f2e0153c0e4ce48eb6d5c0b"},"schema_version":"1.0","source":{"id":"1902.07239","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.07239","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"arxiv_version","alias_value":"1902.07239v1","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.07239","created_at":"2026-05-17T23:53:08Z"},{"alias_kind":"pith_short_12","alias_value":"PQDCSFQZ4GGT","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"PQDCSFQZ4GGTFDAX","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"PQDCSFQZ","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:30791c272122da707aedba3e1fb1075a0e2e1b1adae9648521fa16a0a94473c6","target":"graph","created_at":"2026-05-17T23:53:08Z","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":"Thompson sampling (TS) is a class of algorithms for sequential decision-making, which requires maintaining a posterior distribution over a model. However, calculating exact posterior distributions is intractable for all but the simplest models. Consequently, efficient computation of an approximate posterior distribution is a crucial problem for scalable TS with complex models, such as neural networks. In this paper, we use distribution optimization techniques to approximate the posterior distribution, solved via Wasserstein gradient flows. Based on the framework, a principled particle-optimiza","authors_text":"Changyou Chen, Lawrence Carin, Ruiyi Zhang, Zheng Wen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-19T19:15:08Z","title":"Scalable Thompson Sampling via Optimal Transport"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.07239","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":"sha256:1e8f6b1b9389bb97f02227fdf8f98ac927bb402aa1c9e1ede79481a84b89d26f","target":"record","created_at":"2026-05-17T23:53:08Z","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":"d65045bf93c8de2424d0777fcc5bdbbcb54afe906ff64c4fa9a13dbda3007d1a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-19T19:15:08Z","title_canon_sha256":"a51f30508c59bda972836c1682493039fe986dd21f2e0153c0e4ce48eb6d5c0b"},"schema_version":"1.0","source":{"id":"1902.07239","kind":"arxiv","version":1}},"canonical_sha256":"7c06291619e18d328c1703e55913ab0a531af0ef64e60577481f29991454b5c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c06291619e18d328c1703e55913ab0a531af0ef64e60577481f29991454b5c0","first_computed_at":"2026-05-17T23:53:08.509833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:08.509833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"21SAGJuUYSj96DprYWUoCM58NoFca/uVJFT2MVADF05JE3y4dIyQQjeuIp9sEPE8XZ+lfdFpWpECWyhXKE2vDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:08.510432Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.07239","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e8f6b1b9389bb97f02227fdf8f98ac927bb402aa1c9e1ede79481a84b89d26f","sha256:30791c272122da707aedba3e1fb1075a0e2e1b1adae9648521fa16a0a94473c6"],"state_sha256":"7a7a6263b9e489bad3b5fcee2c028ee5b5b13e2bd21ebb44f83ac2aad0aa11c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mtCsBdyVqtH2y/dESw2FPD+cuQt752I7u0noL8k1dFwXsD7emitOXXIf/exSKAelEVqinAfB/IvXw6iGbsvaDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T05:06:02.199712Z","bundle_sha256":"df02545b59467795c482831c3eaf7283e339f7ef4d2a18162954e7bf2eea097d"}}