{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:P4RRV65AL3IEJI732U4MWNWV4J","short_pith_number":"pith:P4RRV65A","canonical_record":{"source":{"id":"1806.02315","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-06T17:32:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7fe4dbc3ca729ca3d4099890529e45f02d78946741082c5d15a0d8b47f1f7d8a","abstract_canon_sha256":"e2641fee371b53b3a96488ec09be0d7314596a40aaa793e2ea4e1998e8f9b949"},"schema_version":"1.0"},"canonical_sha256":"7f231afba05ed044a3fbd538cb36d5e274a6a027c6da9e88404a203b73a1af8d","source":{"kind":"arxiv","id":"1806.02315","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.02315","created_at":"2026-05-17T23:41:58Z"},{"alias_kind":"arxiv_version","alias_value":"1806.02315v3","created_at":"2026-05-17T23:41:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02315","created_at":"2026-05-17T23:41:58Z"},{"alias_kind":"pith_short_12","alias_value":"P4RRV65AL3IE","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"P4RRV65AL3IEJI73","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"P4RRV65A","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:P4RRV65AL3IEJI732U4MWNWV4J","target":"record","payload":{"canonical_record":{"source":{"id":"1806.02315","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-06T17:32:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7fe4dbc3ca729ca3d4099890529e45f02d78946741082c5d15a0d8b47f1f7d8a","abstract_canon_sha256":"e2641fee371b53b3a96488ec09be0d7314596a40aaa793e2ea4e1998e8f9b949"},"schema_version":"1.0"},"canonical_sha256":"7f231afba05ed044a3fbd538cb36d5e274a6a027c6da9e88404a203b73a1af8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:58.276983Z","signature_b64":"XyJrf2W63dbu6oVK0Qv0w9ZIN4LbmycbBIss6bxXCn131jMNb6GXT2sPIHQv/xF9dg6cOWn9BK1TkC4tv5hOBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f231afba05ed044a3fbd538cb36d5e274a6a027c6da9e88404a203b73a1af8d","last_reissued_at":"2026-05-17T23:41:58.276383Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:58.276383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.02315","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":"2026-05-17T23:41:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DK/Scs2ckJJE8VSBB0i43COFysXUC3rjqmwfhgENwakRYrGgpJr2OLqvsU+nLEFyI4aqFdeN9g/8FR+n5HSlCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T02:55:04.295736Z"},"content_sha256":"c0bccba02461b936cdcbd887a5c0cee81b7df3a883a5f26533518fd971fc5a82","schema_version":"1.0","event_id":"sha256:c0bccba02461b936cdcbd887a5c0cee81b7df3a883a5f26533518fd971fc5a82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:P4RRV65AL3IEJI732U4MWNWV4J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Randomized Value Functions via Multiplicative Normalizing Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ahmed Touati, Harsh Satija, Joelle Pineau, Joshua Romoff, Pascal Vincent","submitted_at":"2018-06-06T17:32:24Z","abstract_excerpt":"Randomized value functions offer a promising approach towards the challenge of efficient exploration in complex environments with high dimensional state and action spaces. Unlike traditional point estimate methods, randomized value functions maintain a posterior distribution over action-space values. This prevents the agent's behavior policy from prematurely exploiting early estimates and falling into local optima. In this work, we leverage recent advances in variational Bayesian neural networks and combine these with traditional Deep Q-Networks (DQN) and Deep Deterministic Policy Gradient (DD"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02315","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":""},"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":"2026-05-17T23:41:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s73Cf7pk6FykJnPEb2fB1D3InUAMx7yqMwwBH3CJ6p1G2stXwFbg4WrN6v/u7UJR7H9ytNO3JJIW16LFHr97BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T02:55:04.296075Z"},"content_sha256":"5bbc0a3357b57fb12b108904ad75ca1a5c197b1dbbd85e5435d000a5c53b7f28","schema_version":"1.0","event_id":"sha256:5bbc0a3357b57fb12b108904ad75ca1a5c197b1dbbd85e5435d000a5c53b7f28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P4RRV65AL3IEJI732U4MWNWV4J/bundle.json","state_url":"https://pith.science/pith/P4RRV65AL3IEJI732U4MWNWV4J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P4RRV65AL3IEJI732U4MWNWV4J/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":"2026-06-03T02:55:04Z","links":{"resolver":"https://pith.science/pith/P4RRV65AL3IEJI732U4MWNWV4J","bundle":"https://pith.science/pith/P4RRV65AL3IEJI732U4MWNWV4J/bundle.json","state":"https://pith.science/pith/P4RRV65AL3IEJI732U4MWNWV4J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P4RRV65AL3IEJI732U4MWNWV4J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:P4RRV65AL3IEJI732U4MWNWV4J","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":"e2641fee371b53b3a96488ec09be0d7314596a40aaa793e2ea4e1998e8f9b949","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-06T17:32:24Z","title_canon_sha256":"7fe4dbc3ca729ca3d4099890529e45f02d78946741082c5d15a0d8b47f1f7d8a"},"schema_version":"1.0","source":{"id":"1806.02315","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.02315","created_at":"2026-05-17T23:41:58Z"},{"alias_kind":"arxiv_version","alias_value":"1806.02315v3","created_at":"2026-05-17T23:41:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02315","created_at":"2026-05-17T23:41:58Z"},{"alias_kind":"pith_short_12","alias_value":"P4RRV65AL3IE","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"P4RRV65AL3IEJI73","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"P4RRV65A","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:5bbc0a3357b57fb12b108904ad75ca1a5c197b1dbbd85e5435d000a5c53b7f28","target":"graph","created_at":"2026-05-17T23:41:58Z","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":"Randomized value functions offer a promising approach towards the challenge of efficient exploration in complex environments with high dimensional state and action spaces. Unlike traditional point estimate methods, randomized value functions maintain a posterior distribution over action-space values. This prevents the agent's behavior policy from prematurely exploiting early estimates and falling into local optima. In this work, we leverage recent advances in variational Bayesian neural networks and combine these with traditional Deep Q-Networks (DQN) and Deep Deterministic Policy Gradient (DD","authors_text":"Ahmed Touati, Harsh Satija, Joelle Pineau, Joshua Romoff, Pascal Vincent","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-06T17:32:24Z","title":"Randomized Value Functions via Multiplicative Normalizing Flows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02315","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:c0bccba02461b936cdcbd887a5c0cee81b7df3a883a5f26533518fd971fc5a82","target":"record","created_at":"2026-05-17T23:41:58Z","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":"e2641fee371b53b3a96488ec09be0d7314596a40aaa793e2ea4e1998e8f9b949","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-06T17:32:24Z","title_canon_sha256":"7fe4dbc3ca729ca3d4099890529e45f02d78946741082c5d15a0d8b47f1f7d8a"},"schema_version":"1.0","source":{"id":"1806.02315","kind":"arxiv","version":3}},"canonical_sha256":"7f231afba05ed044a3fbd538cb36d5e274a6a027c6da9e88404a203b73a1af8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7f231afba05ed044a3fbd538cb36d5e274a6a027c6da9e88404a203b73a1af8d","first_computed_at":"2026-05-17T23:41:58.276383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:58.276383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XyJrf2W63dbu6oVK0Qv0w9ZIN4LbmycbBIss6bxXCn131jMNb6GXT2sPIHQv/xF9dg6cOWn9BK1TkC4tv5hOBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:58.276983Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.02315","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0bccba02461b936cdcbd887a5c0cee81b7df3a883a5f26533518fd971fc5a82","sha256:5bbc0a3357b57fb12b108904ad75ca1a5c197b1dbbd85e5435d000a5c53b7f28"],"state_sha256":"abdc1305bce9f1eec05d833653529983dcdbeb50a33b003294bcf12a03ee7346"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vnDzOsTenQw5bvqwmd++SpDQk//nfo7RvNF+S3eJoqHBeOiNkLfbzWk9QrkcB1MIkg83Ua28/5LdqrZn9GJBDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T02:55:04.297993Z","bundle_sha256":"fa0933447630b4dc9d278def8c23f83cf11452801e5c26af6124e8b490e570b3"}}