{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZDRB6FZB2E3BSWE7MN2UTHLJ4O","short_pith_number":"pith:ZDRB6FZB","canonical_record":{"source":{"id":"1806.03335","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-08T19:47:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"32c13bdf77fed701f579f6c3cbe8127a9d57e9cc82783a797eda8bb45dac6ad9","abstract_canon_sha256":"359220c2734c6f5de5002e82e7b30b61383fd2424a131a8ffe038ce41ad5c38b"},"schema_version":"1.0"},"canonical_sha256":"c8e21f1721d13619589f6375499d69e39a29fc76abe7d3c86e92f55e1713cde1","source":{"kind":"arxiv","id":"1806.03335","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03335","created_at":"2026-05-18T00:00:39Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03335v2","created_at":"2026-05-18T00:00:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03335","created_at":"2026-05-18T00:00:39Z"},{"alias_kind":"pith_short_12","alias_value":"ZDRB6FZB2E3B","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZDRB6FZB2E3BSWE7","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZDRB6FZB","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZDRB6FZB2E3BSWE7MN2UTHLJ4O","target":"record","payload":{"canonical_record":{"source":{"id":"1806.03335","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-08T19:47:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"32c13bdf77fed701f579f6c3cbe8127a9d57e9cc82783a797eda8bb45dac6ad9","abstract_canon_sha256":"359220c2734c6f5de5002e82e7b30b61383fd2424a131a8ffe038ce41ad5c38b"},"schema_version":"1.0"},"canonical_sha256":"c8e21f1721d13619589f6375499d69e39a29fc76abe7d3c86e92f55e1713cde1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:39.519828Z","signature_b64":"4fJY5Wwnxfw/vLxLLuPdhHOOix87eEmXAxJ8XUCQLu8pvs+ZLBPa4DOgb5+1kKjtcPrh1CyO22gv3j0pjTNNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8e21f1721d13619589f6375499d69e39a29fc76abe7d3c86e92f55e1713cde1","last_reissued_at":"2026-05-18T00:00:39.519360Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:39.519360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.03335","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":"2026-05-18T00:00:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1YE9b9p+pHTcndkp61u3EYXrcw7IEyPTXr05MG+9KSE6VXzTZODNvi2C2zxgzvPWpr8lSuEautafe70G4+CPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T17:39:58.228877Z"},"content_sha256":"356c78ba621cb15fac70f7c1c609d1adcb899b42f15b776c3152ae04392ecc44","schema_version":"1.0","event_id":"sha256:356c78ba621cb15fac70f7c1c609d1adcb899b42f15b776c3152ae04392ecc44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZDRB6FZB2E3BSWE7MN2UTHLJ4O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Randomized Prior Functions for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Albin Cassirer, Ian Osband, John Aslanides","submitted_at":"2018-06-08T19:47:54Z","abstract_excerpt":"Dealing with uncertainty is essential for efficient reinforcement learning. There is a growing literature on uncertainty estimation for deep learning from fixed datasets, but many of the most popular approaches are poorly-suited to sequential decision problems. Other methods, such as bootstrap sampling, have no mechanism for uncertainty that does not come from the observed data. We highlight why this can be a crucial shortcoming and propose a simple remedy through addition of a randomized untrainable `prior' network to each ensemble member. We prove that this approach is efficient with linear "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03335","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":"2026-05-18T00:00:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2ombJ9UdSSjlQ4jLFXmiaYqkv4Y7vo2DjteQ1xc+OxoZV+7yZR1bdgsDy6QTGLOmU7LtxZJKDIyQgGfoJ3q4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T17:39:58.229514Z"},"content_sha256":"b531842e1a5634453ff7a2d9c12adf5f380294353b742b34bf19576dead482d4","schema_version":"1.0","event_id":"sha256:b531842e1a5634453ff7a2d9c12adf5f380294353b742b34bf19576dead482d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZDRB6FZB2E3BSWE7MN2UTHLJ4O/bundle.json","state_url":"https://pith.science/pith/ZDRB6FZB2E3BSWE7MN2UTHLJ4O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZDRB6FZB2E3BSWE7MN2UTHLJ4O/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":"2026-05-27T17:39:58Z","links":{"resolver":"https://pith.science/pith/ZDRB6FZB2E3BSWE7MN2UTHLJ4O","bundle":"https://pith.science/pith/ZDRB6FZB2E3BSWE7MN2UTHLJ4O/bundle.json","state":"https://pith.science/pith/ZDRB6FZB2E3BSWE7MN2UTHLJ4O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZDRB6FZB2E3BSWE7MN2UTHLJ4O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZDRB6FZB2E3BSWE7MN2UTHLJ4O","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":"359220c2734c6f5de5002e82e7b30b61383fd2424a131a8ffe038ce41ad5c38b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-08T19:47:54Z","title_canon_sha256":"32c13bdf77fed701f579f6c3cbe8127a9d57e9cc82783a797eda8bb45dac6ad9"},"schema_version":"1.0","source":{"id":"1806.03335","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03335","created_at":"2026-05-18T00:00:39Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03335v2","created_at":"2026-05-18T00:00:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03335","created_at":"2026-05-18T00:00:39Z"},{"alias_kind":"pith_short_12","alias_value":"ZDRB6FZB2E3B","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZDRB6FZB2E3BSWE7","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZDRB6FZB","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:b531842e1a5634453ff7a2d9c12adf5f380294353b742b34bf19576dead482d4","target":"graph","created_at":"2026-05-18T00:00:39Z","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":"Dealing with uncertainty is essential for efficient reinforcement learning. There is a growing literature on uncertainty estimation for deep learning from fixed datasets, but many of the most popular approaches are poorly-suited to sequential decision problems. Other methods, such as bootstrap sampling, have no mechanism for uncertainty that does not come from the observed data. We highlight why this can be a crucial shortcoming and propose a simple remedy through addition of a randomized untrainable `prior' network to each ensemble member. We prove that this approach is efficient with linear ","authors_text":"Albin Cassirer, Ian Osband, John Aslanides","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-08T19:47:54Z","title":"Randomized Prior Functions for Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03335","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":"sha256:356c78ba621cb15fac70f7c1c609d1adcb899b42f15b776c3152ae04392ecc44","target":"record","created_at":"2026-05-18T00:00:39Z","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":"359220c2734c6f5de5002e82e7b30b61383fd2424a131a8ffe038ce41ad5c38b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-08T19:47:54Z","title_canon_sha256":"32c13bdf77fed701f579f6c3cbe8127a9d57e9cc82783a797eda8bb45dac6ad9"},"schema_version":"1.0","source":{"id":"1806.03335","kind":"arxiv","version":2}},"canonical_sha256":"c8e21f1721d13619589f6375499d69e39a29fc76abe7d3c86e92f55e1713cde1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c8e21f1721d13619589f6375499d69e39a29fc76abe7d3c86e92f55e1713cde1","first_computed_at":"2026-05-18T00:00:39.519360Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:39.519360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4fJY5Wwnxfw/vLxLLuPdhHOOix87eEmXAxJ8XUCQLu8pvs+ZLBPa4DOgb5+1kKjtcPrh1CyO22gv3j0pjTNNAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:39.519828Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.03335","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:356c78ba621cb15fac70f7c1c609d1adcb899b42f15b776c3152ae04392ecc44","sha256:b531842e1a5634453ff7a2d9c12adf5f380294353b742b34bf19576dead482d4"],"state_sha256":"958f0df5e0f123fde67ef93e80b34e76761d31f959b800a5049c664ccb8dec65"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iFLmr67JBhw6Mi+lTWkijh+wgNes+CQE3Rd65w9D1yow08W0Pi8bEa31N69jdlP/mqWGDDR7PNo+cvdCUdQcAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T17:39:58.232741Z","bundle_sha256":"6fd92a3f137a4e5894b9bb5c72ad67435811ed2a9db2246882f117984153ba86"}}