{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4SH3WVGMFABBS3GG4UIF3J4EDZ","short_pith_number":"pith:4SH3WVGM","canonical_record":{"source":{"id":"1703.01310","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T19:07:53Z","cross_cats_sorted":[],"title_canon_sha256":"e9836eee740407c96bc73456a38ccb344540f8a6930c456d30a4287409afef99","abstract_canon_sha256":"33a6a9a8e24577b94b731aacd67701450d7cb0ef341323f2cdfb9d8330ed0e7b"},"schema_version":"1.0"},"canonical_sha256":"e48fbb54cc2802196cc6e5105da7841e5d0edbb36a2eee316252b63ce060cdc7","source":{"kind":"arxiv","id":"1703.01310","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.01310","created_at":"2026-05-18T00:42:23Z"},{"alias_kind":"arxiv_version","alias_value":"1703.01310v2","created_at":"2026-05-18T00:42:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01310","created_at":"2026-05-18T00:42:23Z"},{"alias_kind":"pith_short_12","alias_value":"4SH3WVGMFABB","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4SH3WVGMFABBS3GG","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4SH3WVGM","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4SH3WVGMFABBS3GG4UIF3J4EDZ","target":"record","payload":{"canonical_record":{"source":{"id":"1703.01310","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T19:07:53Z","cross_cats_sorted":[],"title_canon_sha256":"e9836eee740407c96bc73456a38ccb344540f8a6930c456d30a4287409afef99","abstract_canon_sha256":"33a6a9a8e24577b94b731aacd67701450d7cb0ef341323f2cdfb9d8330ed0e7b"},"schema_version":"1.0"},"canonical_sha256":"e48fbb54cc2802196cc6e5105da7841e5d0edbb36a2eee316252b63ce060cdc7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:23.502003Z","signature_b64":"bvq4y1mqVHMnGy3A/r9h40Vu7UDawLlKmeskqKlpcotGR0LlFth29ITXOtCdscZovHwShrimhvMEZOQmauWkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e48fbb54cc2802196cc6e5105da7841e5d0edbb36a2eee316252b63ce060cdc7","last_reissued_at":"2026-05-18T00:42:23.501622Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:23.501622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.01310","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":"2026-05-18T00:42:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qfrVPx+hPjeK3aXthjPpubDdqSWawFl0CjAfm5QBIZZFqqSPa+ynPLc5BsA7kPKS13afc28YX2MigR0xFXZ2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:53:30.467039Z"},"content_sha256":"a7e1979388b4d9367d58f35c3f65a7087bc6f4ec05de68386eafabd2b8965982","schema_version":"1.0","event_id":"sha256:a7e1979388b4d9367d58f35c3f65a7087bc6f4ec05de68386eafabd2b8965982"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4SH3WVGMFABBS3GG4UIF3J4EDZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Count-Based Exploration with Neural Density Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aaron van den Oord, Georg Ostrovski, Marc G. Bellemare, Remi Munos","submitted_at":"2017-03-03T19:07:53Z","abstract_excerpt":"Bellemare et al. (2016) introduced the notion of a pseudo-count, derived from a density model, to generalize count-based exploration to non-tabular reinforcement learning. This pseudo-count was used to generate an exploration bonus for a DQN agent and combined with a mixed Monte Carlo update was sufficient to achieve state of the art on the Atari 2600 game Montezuma's Revenge. We consider two questions left open by their work: First, how important is the quality of the density model for exploration? Second, what role does the Monte Carlo update play in exploration? We answer the first question"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01310","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":"2026-05-18T00:42:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9VTQVoQKwoGZdZDWR92Gg9UAe6PLWN9S6uw8StiJdW7bvsVjVs6bUxL8CpZqIhVp4KBmRblPoiUGSYAuoULgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:53:30.467709Z"},"content_sha256":"ed040d620e734dc99710c2c4bb4c48198e4281df8ad996d3a9711e0e9198def2","schema_version":"1.0","event_id":"sha256:ed040d620e734dc99710c2c4bb4c48198e4281df8ad996d3a9711e0e9198def2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ/bundle.json","state_url":"https://pith.science/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ/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":"2026-05-25T19:53:30Z","links":{"resolver":"https://pith.science/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ","bundle":"https://pith.science/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ/bundle.json","state":"https://pith.science/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4SH3WVGMFABBS3GG4UIF3J4EDZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4SH3WVGMFABBS3GG4UIF3J4EDZ","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":"33a6a9a8e24577b94b731aacd67701450d7cb0ef341323f2cdfb9d8330ed0e7b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T19:07:53Z","title_canon_sha256":"e9836eee740407c96bc73456a38ccb344540f8a6930c456d30a4287409afef99"},"schema_version":"1.0","source":{"id":"1703.01310","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.01310","created_at":"2026-05-18T00:42:23Z"},{"alias_kind":"arxiv_version","alias_value":"1703.01310v2","created_at":"2026-05-18T00:42:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.01310","created_at":"2026-05-18T00:42:23Z"},{"alias_kind":"pith_short_12","alias_value":"4SH3WVGMFABB","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4SH3WVGMFABBS3GG","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4SH3WVGM","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:ed040d620e734dc99710c2c4bb4c48198e4281df8ad996d3a9711e0e9198def2","target":"graph","created_at":"2026-05-18T00:42:23Z","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":"Bellemare et al. (2016) introduced the notion of a pseudo-count, derived from a density model, to generalize count-based exploration to non-tabular reinforcement learning. This pseudo-count was used to generate an exploration bonus for a DQN agent and combined with a mixed Monte Carlo update was sufficient to achieve state of the art on the Atari 2600 game Montezuma's Revenge. We consider two questions left open by their work: First, how important is the quality of the density model for exploration? Second, what role does the Monte Carlo update play in exploration? We answer the first question","authors_text":"Aaron van den Oord, Georg Ostrovski, Marc G. Bellemare, Remi Munos","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T19:07:53Z","title":"Count-Based Exploration with Neural Density Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.01310","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:a7e1979388b4d9367d58f35c3f65a7087bc6f4ec05de68386eafabd2b8965982","target":"record","created_at":"2026-05-18T00:42:23Z","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":"33a6a9a8e24577b94b731aacd67701450d7cb0ef341323f2cdfb9d8330ed0e7b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-03-03T19:07:53Z","title_canon_sha256":"e9836eee740407c96bc73456a38ccb344540f8a6930c456d30a4287409afef99"},"schema_version":"1.0","source":{"id":"1703.01310","kind":"arxiv","version":2}},"canonical_sha256":"e48fbb54cc2802196cc6e5105da7841e5d0edbb36a2eee316252b63ce060cdc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e48fbb54cc2802196cc6e5105da7841e5d0edbb36a2eee316252b63ce060cdc7","first_computed_at":"2026-05-18T00:42:23.501622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:42:23.501622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bvq4y1mqVHMnGy3A/r9h40Vu7UDawLlKmeskqKlpcotGR0LlFth29ITXOtCdscZovHwShrimhvMEZOQmauWkAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:42:23.502003Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.01310","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a7e1979388b4d9367d58f35c3f65a7087bc6f4ec05de68386eafabd2b8965982","sha256:ed040d620e734dc99710c2c4bb4c48198e4281df8ad996d3a9711e0e9198def2"],"state_sha256":"0f3f9ff3ec3737a87931f53214e3432437156a825d682b16ecaa6186d8cfa37d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cvLP44Z+OjryMb5/d6EttHPSmAPG08//D3TpXiLeeewd9LIhbY+5eKHtVaspb4XA225hFmV0G3QLOXfhHifEBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:53:30.470883Z","bundle_sha256":"bf6587d7d836874be0a014188c23aa2171ec976ce00dc2d090a30510c9b879b2"}}