{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HHJDJ43DACN4U53ZYRTM3Y6QFD","short_pith_number":"pith:HHJDJ43D","canonical_record":{"source":{"id":"1906.02870","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T02:36:00Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"eacb05a1c07518a476f8a93f3846b3581c9d2ce5421a9b1b90d27cebd50bd1b4","abstract_canon_sha256":"b21611b07be5aefbe90569e95d23afb4d9be239e5224326ab5ba4589075c7f35"},"schema_version":"1.0"},"canonical_sha256":"39d234f363009bca7779c466cde3d028db97d3ba32cf36891604cd65987e8bfa","source":{"kind":"arxiv","id":"1906.02870","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.02870","created_at":"2026-07-05T09:09:45Z"},{"alias_kind":"arxiv_version","alias_value":"1906.02870v3","created_at":"2026-07-05T09:09:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02870","created_at":"2026-07-05T09:09:45Z"},{"alias_kind":"pith_short_12","alias_value":"HHJDJ43DACN4","created_at":"2026-07-05T09:09:45Z"},{"alias_kind":"pith_short_16","alias_value":"HHJDJ43DACN4U53Z","created_at":"2026-07-05T09:09:45Z"},{"alias_kind":"pith_short_8","alias_value":"HHJDJ43D","created_at":"2026-07-05T09:09:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HHJDJ43DACN4U53ZYRTM3Y6QFD","target":"record","payload":{"canonical_record":{"source":{"id":"1906.02870","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T02:36:00Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","stat.ML"],"title_canon_sha256":"eacb05a1c07518a476f8a93f3846b3581c9d2ce5421a9b1b90d27cebd50bd1b4","abstract_canon_sha256":"b21611b07be5aefbe90569e95d23afb4d9be239e5224326ab5ba4589075c7f35"},"schema_version":"1.0"},"canonical_sha256":"39d234f363009bca7779c466cde3d028db97d3ba32cf36891604cd65987e8bfa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:45.168313Z","signature_b64":"o2bhptpYQOfMERDbg00SQ1D720HveizLVxQ84fW15Z+rhAaeRhn701beikx5M+r3PxkGos6ND+JDuOKB0JdHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39d234f363009bca7779c466cde3d028db97d3ba32cf36891604cd65987e8bfa","last_reissued_at":"2026-07-05T09:09:45.167859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:45.167859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.02870","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":"2026-07-05T09:09:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NTNIsItWnjhIFzBcy5ZxogA2N9dmryL5KK7scFekcX8slXoakMHPRqH4zNQARY9B+cCV/OgWwfWw/6rwtIFeBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:51:53.478644Z"},"content_sha256":"e2299f3d8164ebb04a035b0065fd4d7ef4bef4551a232886953655f47c487c28","schema_version":"1.0","event_id":"sha256:e2299f3d8164ebb04a035b0065fd4d7ef4bef4551a232886953655f47c487c28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HHJDJ43DACN4U53ZYRTM3Y6QFD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Worst-Case Regret Bounds for Exploration via Randomized Value Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Daniel Russo","submitted_at":"2019-06-07T02:36:00Z","abstract_excerpt":"This paper studies a recent proposal to use randomized value functions to drive exploration in reinforcement learning. These randomized value functions are generated by injecting random noise into the training data, making the approach compatible with many popular methods for estimating parameterized value functions. By providing a worst-case regret bound for tabular finite-horizon Markov decision processes, we show that planning with respect to these randomized value functions can induce provably efficient exploration."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02870","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/1906.02870/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":"2026-07-05T09:09:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zx2BFwkI3tOa3Kxa3jECNI+UfoGhVN3vG5GdCddndvzrd/IMlxkrfEog/8pq/SPaKqQcMTwUyxD+/W6NeDnZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:51:53.479523Z"},"content_sha256":"4d28d1f2b616b5f2420c0bf55f82e87c70a7d4c9a94330e4837be10bfcc219a9","schema_version":"1.0","event_id":"sha256:4d28d1f2b616b5f2420c0bf55f82e87c70a7d4c9a94330e4837be10bfcc219a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HHJDJ43DACN4U53ZYRTM3Y6QFD/bundle.json","state_url":"https://pith.science/pith/HHJDJ43DACN4U53ZYRTM3Y6QFD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HHJDJ43DACN4U53ZYRTM3Y6QFD/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":"2026-08-08T11:51:53Z","links":{"resolver":"https://pith.science/pith/HHJDJ43DACN4U53ZYRTM3Y6QFD","bundle":"https://pith.science/pith/HHJDJ43DACN4U53ZYRTM3Y6QFD/bundle.json","state":"https://pith.science/pith/HHJDJ43DACN4U53ZYRTM3Y6QFD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HHJDJ43DACN4U53ZYRTM3Y6QFD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HHJDJ43DACN4U53ZYRTM3Y6QFD","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":"b21611b07be5aefbe90569e95d23afb4d9be239e5224326ab5ba4589075c7f35","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T02:36:00Z","title_canon_sha256":"eacb05a1c07518a476f8a93f3846b3581c9d2ce5421a9b1b90d27cebd50bd1b4"},"schema_version":"1.0","source":{"id":"1906.02870","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.02870","created_at":"2026-07-05T09:09:45Z"},{"alias_kind":"arxiv_version","alias_value":"1906.02870v3","created_at":"2026-07-05T09:09:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02870","created_at":"2026-07-05T09:09:45Z"},{"alias_kind":"pith_short_12","alias_value":"HHJDJ43DACN4","created_at":"2026-07-05T09:09:45Z"},{"alias_kind":"pith_short_16","alias_value":"HHJDJ43DACN4U53Z","created_at":"2026-07-05T09:09:45Z"},{"alias_kind":"pith_short_8","alias_value":"HHJDJ43D","created_at":"2026-07-05T09:09:45Z"}],"graph_snapshots":[{"event_id":"sha256:4d28d1f2b616b5f2420c0bf55f82e87c70a7d4c9a94330e4837be10bfcc219a9","target":"graph","created_at":"2026-07-05T09:09:45Z","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/1906.02870/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies a recent proposal to use randomized value functions to drive exploration in reinforcement learning. These randomized value functions are generated by injecting random noise into the training data, making the approach compatible with many popular methods for estimating parameterized value functions. By providing a worst-case regret bound for tabular finite-horizon Markov decision processes, we show that planning with respect to these randomized value functions can induce provably efficient exploration.","authors_text":"Daniel Russo","cross_cats":["cs.AI","cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T02:36:00Z","title":"Worst-Case Regret Bounds for Exploration via Randomized Value Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02870","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:e2299f3d8164ebb04a035b0065fd4d7ef4bef4551a232886953655f47c487c28","target":"record","created_at":"2026-07-05T09:09:45Z","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":"b21611b07be5aefbe90569e95d23afb4d9be239e5224326ab5ba4589075c7f35","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-07T02:36:00Z","title_canon_sha256":"eacb05a1c07518a476f8a93f3846b3581c9d2ce5421a9b1b90d27cebd50bd1b4"},"schema_version":"1.0","source":{"id":"1906.02870","kind":"arxiv","version":3}},"canonical_sha256":"39d234f363009bca7779c466cde3d028db97d3ba32cf36891604cd65987e8bfa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39d234f363009bca7779c466cde3d028db97d3ba32cf36891604cd65987e8bfa","first_computed_at":"2026-07-05T09:09:45.167859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:45.167859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o2bhptpYQOfMERDbg00SQ1D720HveizLVxQ84fW15Z+rhAaeRhn701beikx5M+r3PxkGos6ND+JDuOKB0JdHBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:45.168313Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.02870","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2299f3d8164ebb04a035b0065fd4d7ef4bef4551a232886953655f47c487c28","sha256:4d28d1f2b616b5f2420c0bf55f82e87c70a7d4c9a94330e4837be10bfcc219a9"],"state_sha256":"c16ff4b3162d7ecbfd5e5f466b212cd41ffc3257927b3e5ff2598d98692ad093"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5sAv/4PXUDM16nQpYFUONjzM7kQcZ/m6YAm+KxfAm4LYLjnJLlytKV1K+0CsGz6tUXK8fkhKUy38jrlVjHrRCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:51:53.485022Z","bundle_sha256":"16d012f0a7df4a1dc42d88ef9483ea9f8d1f226dfebfb4208e5889bc4b0945d7"}}