{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:XIRKMCZV72TSPKIRPGCLXNQE7F","short_pith_number":"pith:XIRKMCZV","canonical_record":{"source":{"id":"1705.07041","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-19T15:10:21Z","cross_cats_sorted":[],"title_canon_sha256":"a48de096d25ba2b015c44a0f303dd8a28131867ff4c0c4e55b1dab7ef2786565","abstract_canon_sha256":"759a6eb976146c3372afbccc161e70f488cb93e9e4eae9d6cd823b16ac9ed5bf"},"schema_version":"1.0"},"canonical_sha256":"ba22a60b35fea727a9117984bbb604f94f7adac2d138d0f0d963c9d64011f520","source":{"kind":"arxiv","id":"1705.07041","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07041","created_at":"2026-07-05T00:51:25Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07041v3","created_at":"2026-07-05T00:51:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07041","created_at":"2026-07-05T00:51:25Z"},{"alias_kind":"pith_short_12","alias_value":"XIRKMCZV72TS","created_at":"2026-07-05T00:51:25Z"},{"alias_kind":"pith_short_16","alias_value":"XIRKMCZV72TSPKIR","created_at":"2026-07-05T00:51:25Z"},{"alias_kind":"pith_short_8","alias_value":"XIRKMCZV","created_at":"2026-07-05T00:51:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:XIRKMCZV72TSPKIRPGCLXNQE7F","target":"record","payload":{"canonical_record":{"source":{"id":"1705.07041","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-19T15:10:21Z","cross_cats_sorted":[],"title_canon_sha256":"a48de096d25ba2b015c44a0f303dd8a28131867ff4c0c4e55b1dab7ef2786565","abstract_canon_sha256":"759a6eb976146c3372afbccc161e70f488cb93e9e4eae9d6cd823b16ac9ed5bf"},"schema_version":"1.0"},"canonical_sha256":"ba22a60b35fea727a9117984bbb604f94f7adac2d138d0f0d963c9d64011f520","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:51:25.674862Z","signature_b64":"OkrqmCwxtZWO9AK8PU1DVjiJpvERSEcIVXTHLXgyJ81/782pAScA8RX0KrcedaCUZ+EMClfeAyQ2vu8VCGZuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba22a60b35fea727a9117984bbb604f94f7adac2d138d0f0d963c9d64011f520","last_reissued_at":"2026-07-05T00:51:25.674474Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:51:25.674474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.07041","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:51:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9N7nNpjHHJyjJeNXFEcko6q1eNXTWMkd0ILtH1BH70j82C+tlE04CieFkCHcrRTirbJIELrZrXQxVZudWS9qBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:34:56.638538Z"},"content_sha256":"16d6846d76dad17e6d8792f902a3c3bafc49bd95bb585f7bde5b10824de5d937","schema_version":"1.0","event_id":"sha256:16d6846d76dad17e6d8792f902a3c3bafc49bd95bb585f7bde5b10824de5d937"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:XIRKMCZV72TSPKIRPGCLXNQE7F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Posterior sampling for reinforcement learning: worst-case regret bounds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Randy Jia, Shipra Agrawal","submitted_at":"2017-05-19T15:10:21Z","abstract_excerpt":"We present an algorithm based on posterior sampling (aka Thompson sampling) that achieves near-optimal worst-case regret bounds when the underlying Markov Decision Process (MDP) is communicating with a finite, though unknown, diameter. Our main result is a high probability regret upper bound of $\\tilde{O}(DS\\sqrt{AT})$ for any communicating MDP with $S$ states, $A$ actions and diameter $D$. Here, regret compares the total reward achieved by the algorithm to the total expected reward of an optimal infinite-horizon undiscounted average reward policy, in time horizon $T$. This result closely matc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07041","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1705.07041/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:51:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1Szp/kWDkdPMbPzkJ3eS4c/wf05yZHWJX+H0fqJRWUxThnLN6/GQvwTPkntTz914TJ+793GayzLHL5VA/FMqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T07:34:56.640545Z"},"content_sha256":"b2066c110a2a9ae31cdf175b4cb903e7bea2930d261582352863d735fd8e8771","schema_version":"1.0","event_id":"sha256:b2066c110a2a9ae31cdf175b4cb903e7bea2930d261582352863d735fd8e8771"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XIRKMCZV72TSPKIRPGCLXNQE7F/bundle.json","state_url":"https://pith.science/pith/XIRKMCZV72TSPKIRPGCLXNQE7F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XIRKMCZV72TSPKIRPGCLXNQE7F/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":"2026-08-12T07:34:56Z","links":{"resolver":"https://pith.science/pith/XIRKMCZV72TSPKIRPGCLXNQE7F","bundle":"https://pith.science/pith/XIRKMCZV72TSPKIRPGCLXNQE7F/bundle.json","state":"https://pith.science/pith/XIRKMCZV72TSPKIRPGCLXNQE7F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XIRKMCZV72TSPKIRPGCLXNQE7F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XIRKMCZV72TSPKIRPGCLXNQE7F","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":"759a6eb976146c3372afbccc161e70f488cb93e9e4eae9d6cd823b16ac9ed5bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-19T15:10:21Z","title_canon_sha256":"a48de096d25ba2b015c44a0f303dd8a28131867ff4c0c4e55b1dab7ef2786565"},"schema_version":"1.0","source":{"id":"1705.07041","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.07041","created_at":"2026-07-05T00:51:25Z"},{"alias_kind":"arxiv_version","alias_value":"1705.07041v3","created_at":"2026-07-05T00:51:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.07041","created_at":"2026-07-05T00:51:25Z"},{"alias_kind":"pith_short_12","alias_value":"XIRKMCZV72TS","created_at":"2026-07-05T00:51:25Z"},{"alias_kind":"pith_short_16","alias_value":"XIRKMCZV72TSPKIR","created_at":"2026-07-05T00:51:25Z"},{"alias_kind":"pith_short_8","alias_value":"XIRKMCZV","created_at":"2026-07-05T00:51:25Z"}],"graph_snapshots":[{"event_id":"sha256:b2066c110a2a9ae31cdf175b4cb903e7bea2930d261582352863d735fd8e8771","target":"graph","created_at":"2026-07-05T00:51:25Z","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/1705.07041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an algorithm based on posterior sampling (aka Thompson sampling) that achieves near-optimal worst-case regret bounds when the underlying Markov Decision Process (MDP) is communicating with a finite, though unknown, diameter. Our main result is a high probability regret upper bound of $\\tilde{O}(DS\\sqrt{AT})$ for any communicating MDP with $S$ states, $A$ actions and diameter $D$. Here, regret compares the total reward achieved by the algorithm to the total expected reward of an optimal infinite-horizon undiscounted average reward policy, in time horizon $T$. This result closely matc","authors_text":"Randy Jia, Shipra Agrawal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-19T15:10:21Z","title":"Posterior sampling for reinforcement learning: worst-case regret bounds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.07041","kind":"arxiv","version":3},"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":"sha256:16d6846d76dad17e6d8792f902a3c3bafc49bd95bb585f7bde5b10824de5d937","target":"record","created_at":"2026-07-05T00:51:25Z","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":"759a6eb976146c3372afbccc161e70f488cb93e9e4eae9d6cd823b16ac9ed5bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-19T15:10:21Z","title_canon_sha256":"a48de096d25ba2b015c44a0f303dd8a28131867ff4c0c4e55b1dab7ef2786565"},"schema_version":"1.0","source":{"id":"1705.07041","kind":"arxiv","version":3}},"canonical_sha256":"ba22a60b35fea727a9117984bbb604f94f7adac2d138d0f0d963c9d64011f520","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba22a60b35fea727a9117984bbb604f94f7adac2d138d0f0d963c9d64011f520","first_computed_at":"2026-07-05T00:51:25.674474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:51:25.674474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OkrqmCwxtZWO9AK8PU1DVjiJpvERSEcIVXTHLXgyJ81/782pAScA8RX0KrcedaCUZ+EMClfeAyQ2vu8VCGZuCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:51:25.674862Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.07041","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16d6846d76dad17e6d8792f902a3c3bafc49bd95bb585f7bde5b10824de5d937","sha256:b2066c110a2a9ae31cdf175b4cb903e7bea2930d261582352863d735fd8e8771"],"state_sha256":"d72792fc33eb602fd35fb6441f69af8c64ac8437f7f8c672e05923161b976a1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fe588kfK3hmzq5FNBscjb+IXw0HnFGCIkRCU1FyvIvpg1stJn8mCSQu1X3TK9Be+VauIF+5PCjrR7NWLrY1WCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T07:34:56.644661Z","bundle_sha256":"ebf93ce3f79613027e18abeed4251040f5c177bb4eb2c14da57ea5e542d0a8f5"}}