{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:ULOYLN4MTDB6P5D4EQEU4RQ6TD","short_pith_number":"pith:ULOYLN4M","canonical_record":{"source":{"id":"1108.3711","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-08-18T10:47:16Z","cross_cats_sorted":[],"title_canon_sha256":"deb9cb8cb66d13f34275b4bb35fc4049fad4f5912d7a9f4db4966288af23a400","abstract_canon_sha256":"17bae33fefc4c3b0251cb38c2aeee1ed83e57ae372e08836303ac370098536ae"},"schema_version":"1.0"},"canonical_sha256":"a2dd85b78c98c3e7f47c24094e461e98d9f0719501447812d772653eed0edeba","source":{"kind":"arxiv","id":"1108.3711","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1108.3711","created_at":"2026-05-18T03:50:10Z"},{"alias_kind":"arxiv_version","alias_value":"1108.3711v2","created_at":"2026-05-18T03:50:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1108.3711","created_at":"2026-05-18T03:50:10Z"},{"alias_kind":"pith_short_12","alias_value":"ULOYLN4MTDB6","created_at":"2026-05-18T12:26:42Z"},{"alias_kind":"pith_short_16","alias_value":"ULOYLN4MTDB6P5D4","created_at":"2026-05-18T12:26:42Z"},{"alias_kind":"pith_short_8","alias_value":"ULOYLN4M","created_at":"2026-05-18T12:26:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:ULOYLN4MTDB6P5D4EQEU4RQ6TD","target":"record","payload":{"canonical_record":{"source":{"id":"1108.3711","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-08-18T10:47:16Z","cross_cats_sorted":[],"title_canon_sha256":"deb9cb8cb66d13f34275b4bb35fc4049fad4f5912d7a9f4db4966288af23a400","abstract_canon_sha256":"17bae33fefc4c3b0251cb38c2aeee1ed83e57ae372e08836303ac370098536ae"},"schema_version":"1.0"},"canonical_sha256":"a2dd85b78c98c3e7f47c24094e461e98d9f0719501447812d772653eed0edeba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:50:10.962825Z","signature_b64":"QSVBhku5086NKUxjDR9VvomVlCgVIpQSBWG8Pmg2v/O0UdnpyoUxh2hZTKtmBpMr4fsU3Pp6xjaSTLRKaq8hDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2dd85b78c98c3e7f47c24094e461e98d9f0719501447812d772653eed0edeba","last_reissued_at":"2026-05-18T03:50:10.962123Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:50:10.962123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1108.3711","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":"2026-05-18T03:50:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VkQZLpmiqNOnoZHOPAm+DyAKN2rBIQoaJyj1mSVi8MJft6svvaTdJh0cj7qquwYyc+xJJpL3FxpzARpMC53/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:59:29.390434Z"},"content_sha256":"ab34ee3ae319e76618473de1ac34deb49fd776d8b5660b723ba50d854c6cd27b","schema_version":"1.0","event_id":"sha256:ab34ee3ae319e76618473de1ac34deb49fd776d8b5660b723ba50d854c6cd27b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:ULOYLN4MTDB6P5D4EQEU4RQ6TD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Doing Better Than UCT: Rational Monte Carlo Sampling in Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"David Tolpin, Solomon Eyal Shimony","submitted_at":"2011-08-18T10:47:16Z","abstract_excerpt":"UCT, a state-of-the art algorithm for Monte Carlo tree sampling (MCTS), is based on UCB, a sampling policy for the Multi-armed Bandit Problem (MAB) that minimizes the accumulated regret. However, MCTS differs from MAB in that only the final choice, rather than all arm pulls, brings a reward, that is, the simple regret, as opposite to the cumulative regret, must be minimized. This ongoing work aims at applying meta-reasoning techniques to MCTS, which is non-trivial. We begin by introducing policies for multi-armed bandits with lower simple regret than UCB, and an algorithm for MCTS which combin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1108.3711","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":"2026-05-18T03:50:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ByJyiSu45jaEvoXUSO88R/4ko7AHr4tagABZRfgy3K9noEutQ9ZbeZm9nrc6X+wXg5mB/g4vf6JYj2nLdnsABw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T09:59:29.391077Z"},"content_sha256":"cd8b0281229f13ce985b9477dc7795a0a35431e76f88f5f73ebd9d83cea0fc3d","schema_version":"1.0","event_id":"sha256:cd8b0281229f13ce985b9477dc7795a0a35431e76f88f5f73ebd9d83cea0fc3d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ULOYLN4MTDB6P5D4EQEU4RQ6TD/bundle.json","state_url":"https://pith.science/pith/ULOYLN4MTDB6P5D4EQEU4RQ6TD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ULOYLN4MTDB6P5D4EQEU4RQ6TD/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":"2026-05-31T09:59:29Z","links":{"resolver":"https://pith.science/pith/ULOYLN4MTDB6P5D4EQEU4RQ6TD","bundle":"https://pith.science/pith/ULOYLN4MTDB6P5D4EQEU4RQ6TD/bundle.json","state":"https://pith.science/pith/ULOYLN4MTDB6P5D4EQEU4RQ6TD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ULOYLN4MTDB6P5D4EQEU4RQ6TD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:ULOYLN4MTDB6P5D4EQEU4RQ6TD","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":"17bae33fefc4c3b0251cb38c2aeee1ed83e57ae372e08836303ac370098536ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-08-18T10:47:16Z","title_canon_sha256":"deb9cb8cb66d13f34275b4bb35fc4049fad4f5912d7a9f4db4966288af23a400"},"schema_version":"1.0","source":{"id":"1108.3711","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1108.3711","created_at":"2026-05-18T03:50:10Z"},{"alias_kind":"arxiv_version","alias_value":"1108.3711v2","created_at":"2026-05-18T03:50:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1108.3711","created_at":"2026-05-18T03:50:10Z"},{"alias_kind":"pith_short_12","alias_value":"ULOYLN4MTDB6","created_at":"2026-05-18T12:26:42Z"},{"alias_kind":"pith_short_16","alias_value":"ULOYLN4MTDB6P5D4","created_at":"2026-05-18T12:26:42Z"},{"alias_kind":"pith_short_8","alias_value":"ULOYLN4M","created_at":"2026-05-18T12:26:42Z"}],"graph_snapshots":[{"event_id":"sha256:cd8b0281229f13ce985b9477dc7795a0a35431e76f88f5f73ebd9d83cea0fc3d","target":"graph","created_at":"2026-05-18T03:50:10Z","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":"UCT, a state-of-the art algorithm for Monte Carlo tree sampling (MCTS), is based on UCB, a sampling policy for the Multi-armed Bandit Problem (MAB) that minimizes the accumulated regret. However, MCTS differs from MAB in that only the final choice, rather than all arm pulls, brings a reward, that is, the simple regret, as opposite to the cumulative regret, must be minimized. This ongoing work aims at applying meta-reasoning techniques to MCTS, which is non-trivial. We begin by introducing policies for multi-armed bandits with lower simple regret than UCB, and an algorithm for MCTS which combin","authors_text":"David Tolpin, Solomon Eyal Shimony","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-08-18T10:47:16Z","title":"Doing Better Than UCT: Rational Monte Carlo Sampling in Trees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1108.3711","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:ab34ee3ae319e76618473de1ac34deb49fd776d8b5660b723ba50d854c6cd27b","target":"record","created_at":"2026-05-18T03:50:10Z","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":"17bae33fefc4c3b0251cb38c2aeee1ed83e57ae372e08836303ac370098536ae","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-08-18T10:47:16Z","title_canon_sha256":"deb9cb8cb66d13f34275b4bb35fc4049fad4f5912d7a9f4db4966288af23a400"},"schema_version":"1.0","source":{"id":"1108.3711","kind":"arxiv","version":2}},"canonical_sha256":"a2dd85b78c98c3e7f47c24094e461e98d9f0719501447812d772653eed0edeba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2dd85b78c98c3e7f47c24094e461e98d9f0719501447812d772653eed0edeba","first_computed_at":"2026-05-18T03:50:10.962123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:50:10.962123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QSVBhku5086NKUxjDR9VvomVlCgVIpQSBWG8Pmg2v/O0UdnpyoUxh2hZTKtmBpMr4fsU3Pp6xjaSTLRKaq8hDA==","signature_status":"signed_v1","signed_at":"2026-05-18T03:50:10.962825Z","signed_message":"canonical_sha256_bytes"},"source_id":"1108.3711","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab34ee3ae319e76618473de1ac34deb49fd776d8b5660b723ba50d854c6cd27b","sha256:cd8b0281229f13ce985b9477dc7795a0a35431e76f88f5f73ebd9d83cea0fc3d"],"state_sha256":"f278350a8a8d9d75723eecd61c5ad17dbdccdf9d74e13036093185d3e0f47526"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6MtE+x+4BXS32ku+6wmUhr1M1ucAY/BxF74GnEihF+QxC3dW7B+J9wztxAUdE8kHhp4shMrJe8PmAMXDmocgAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T09:59:29.394308Z","bundle_sha256":"9ba189cca737948df1626f58337aaf02764f43ce93e635c938334d68c411cdf8"}}