{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Q6C5DHQ2AQIRZ2TGFGA4QVNCBB","short_pith_number":"pith:Q6C5DHQ2","canonical_record":{"source":{"id":"2507.02639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T14:03:47Z","cross_cats_sorted":[],"title_canon_sha256":"27b99f68a633b0c9ec7d3358b168c3a65c8ebba7a1524baaecb52b94efa193a6","abstract_canon_sha256":"6fe455de6f6ba772ffbca64df2705924f9984eaf1ff212793c43b5bf7c1152a3"},"schema_version":"1.0"},"canonical_sha256":"8785d19e1a04111cea662981c855a20852f5548ee2afc39feb046e35677bfbd6","source":{"kind":"arxiv","id":"2507.02639","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02639","created_at":"2026-07-05T11:31:32Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02639v1","created_at":"2026-07-05T11:31:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02639","created_at":"2026-07-05T11:31:32Z"},{"alias_kind":"pith_short_12","alias_value":"Q6C5DHQ2AQIR","created_at":"2026-07-05T11:31:32Z"},{"alias_kind":"pith_short_16","alias_value":"Q6C5DHQ2AQIRZ2TG","created_at":"2026-07-05T11:31:32Z"},{"alias_kind":"pith_short_8","alias_value":"Q6C5DHQ2","created_at":"2026-07-05T11:31:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Q6C5DHQ2AQIRZ2TGFGA4QVNCBB","target":"record","payload":{"canonical_record":{"source":{"id":"2507.02639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T14:03:47Z","cross_cats_sorted":[],"title_canon_sha256":"27b99f68a633b0c9ec7d3358b168c3a65c8ebba7a1524baaecb52b94efa193a6","abstract_canon_sha256":"6fe455de6f6ba772ffbca64df2705924f9984eaf1ff212793c43b5bf7c1152a3"},"schema_version":"1.0"},"canonical_sha256":"8785d19e1a04111cea662981c855a20852f5548ee2afc39feb046e35677bfbd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:32.206903Z","signature_b64":"EfRQC/nk6TNOA4ZHgKJww9QNA78QXrWilajc6CjdbKm8yqdB97u+KU1EygN2p89d+hqEvQR02LQ6jnqH56kVBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8785d19e1a04111cea662981c855a20852f5548ee2afc39feb046e35677bfbd6","last_reissued_at":"2026-07-05T11:31:32.206477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:32.206477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.02639","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":"2026-07-05T11:31:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+hhJ+ocdGZGy/hgGYlOmst8Vuzb0rbbYSlOdYB4wvXCtyjovjE0Jf+AHMeezmunEo4T7qnjAZpvL7kThbuJtCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:39:52.424392Z"},"content_sha256":"17b9b7098bafac239dd3b03b687bb8c5ba789aee2d33660f8924ef613b026087","schema_version":"1.0","event_id":"sha256:17b9b7098bafac239dd3b03b687bb8c5ba789aee2d33660f8924ef613b026087"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Q6C5DHQ2AQIRZ2TGFGA4QVNCBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Efficient Bayesian Exploration in Model-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alberto Caron, Chris Hicks, Vasilios Mavroudis","submitted_at":"2025-07-03T14:03:47Z","abstract_excerpt":"In this work, we address the challenge of data-efficient exploration in reinforcement learning by examining existing principled, information-theoretic approaches to intrinsic motivation. Specifically, we focus on a class of exploration bonuses that targets epistemic uncertainty rather than the aleatoric noise inherent in the environment. We prove that these bonuses naturally signal epistemic information gains and converge to zero once the agent becomes sufficiently certain about the environment's dynamics and rewards, thereby aligning exploration with genuine knowledge gaps. Our analysis provi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02639","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.02639/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":"2026-07-05T11:31:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"phoQJJgqDdQ+ebDfCltb2NJqrEahV3BBT9KVN2v43l/jQ5LJHaUP/dBgIxxCgukBZI5n010Yz/GohqL7VlrSCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T20:39:52.425325Z"},"content_sha256":"36439219905cafaaff4568ea2bc7a6a22d9298649fee39a0ae5fbc2284e6d2b8","schema_version":"1.0","event_id":"sha256:36439219905cafaaff4568ea2bc7a6a22d9298649fee39a0ae5fbc2284e6d2b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q6C5DHQ2AQIRZ2TGFGA4QVNCBB/bundle.json","state_url":"https://pith.science/pith/Q6C5DHQ2AQIRZ2TGFGA4QVNCBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q6C5DHQ2AQIRZ2TGFGA4QVNCBB/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":"2026-08-11T20:39:52Z","links":{"resolver":"https://pith.science/pith/Q6C5DHQ2AQIRZ2TGFGA4QVNCBB","bundle":"https://pith.science/pith/Q6C5DHQ2AQIRZ2TGFGA4QVNCBB/bundle.json","state":"https://pith.science/pith/Q6C5DHQ2AQIRZ2TGFGA4QVNCBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q6C5DHQ2AQIRZ2TGFGA4QVNCBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q6C5DHQ2AQIRZ2TGFGA4QVNCBB","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":"6fe455de6f6ba772ffbca64df2705924f9984eaf1ff212793c43b5bf7c1152a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T14:03:47Z","title_canon_sha256":"27b99f68a633b0c9ec7d3358b168c3a65c8ebba7a1524baaecb52b94efa193a6"},"schema_version":"1.0","source":{"id":"2507.02639","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02639","created_at":"2026-07-05T11:31:32Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02639v1","created_at":"2026-07-05T11:31:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02639","created_at":"2026-07-05T11:31:32Z"},{"alias_kind":"pith_short_12","alias_value":"Q6C5DHQ2AQIR","created_at":"2026-07-05T11:31:32Z"},{"alias_kind":"pith_short_16","alias_value":"Q6C5DHQ2AQIRZ2TG","created_at":"2026-07-05T11:31:32Z"},{"alias_kind":"pith_short_8","alias_value":"Q6C5DHQ2","created_at":"2026-07-05T11:31:32Z"}],"graph_snapshots":[{"event_id":"sha256:36439219905cafaaff4568ea2bc7a6a22d9298649fee39a0ae5fbc2284e6d2b8","target":"graph","created_at":"2026-07-05T11:31:32Z","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/2507.02639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we address the challenge of data-efficient exploration in reinforcement learning by examining existing principled, information-theoretic approaches to intrinsic motivation. Specifically, we focus on a class of exploration bonuses that targets epistemic uncertainty rather than the aleatoric noise inherent in the environment. We prove that these bonuses naturally signal epistemic information gains and converge to zero once the agent becomes sufficiently certain about the environment's dynamics and rewards, thereby aligning exploration with genuine knowledge gaps. Our analysis provi","authors_text":"Alberto Caron, Chris Hicks, Vasilios Mavroudis","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T14:03:47Z","title":"On Efficient Bayesian Exploration in Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02639","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":"sha256:17b9b7098bafac239dd3b03b687bb8c5ba789aee2d33660f8924ef613b026087","target":"record","created_at":"2026-07-05T11:31:32Z","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":"6fe455de6f6ba772ffbca64df2705924f9984eaf1ff212793c43b5bf7c1152a3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T14:03:47Z","title_canon_sha256":"27b99f68a633b0c9ec7d3358b168c3a65c8ebba7a1524baaecb52b94efa193a6"},"schema_version":"1.0","source":{"id":"2507.02639","kind":"arxiv","version":1}},"canonical_sha256":"8785d19e1a04111cea662981c855a20852f5548ee2afc39feb046e35677bfbd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8785d19e1a04111cea662981c855a20852f5548ee2afc39feb046e35677bfbd6","first_computed_at":"2026-07-05T11:31:32.206477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:32.206477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EfRQC/nk6TNOA4ZHgKJww9QNA78QXrWilajc6CjdbKm8yqdB97u+KU1EygN2p89d+hqEvQR02LQ6jnqH56kVBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:32.206903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02639","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17b9b7098bafac239dd3b03b687bb8c5ba789aee2d33660f8924ef613b026087","sha256:36439219905cafaaff4568ea2bc7a6a22d9298649fee39a0ae5fbc2284e6d2b8"],"state_sha256":"c5ac2dbdcb813191693b4e42d72284f67fce7f4671813320fb67d36cdfffc326"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fb4pYjdmwqMDI2frCQ4++rcKGnDQMOtHERYwLGJ7ow0bvXrG9MZz4kJ4C7Lbj4FOxITXgWtUESCl8/wVNI/ICg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T20:39:52.430269Z","bundle_sha256":"ac9d1abe9426b11df0a468282ec0d0d3852ed41573dee6524111c77db5d9c299"}}