{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YFMXA7LKTAXCTZZV2VG2257QBI","short_pith_number":"pith:YFMXA7LK","canonical_record":{"source":{"id":"1906.08189","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T16:06:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"71ee5dcfa611d804e4f29603e181f31659911d89e4a5723b3aaf9f99f0fcdc40","abstract_canon_sha256":"41171ae6b7f52a745ce4f3e8ae39ee08836c16ee01170826c203fa4f1692dc5d"},"schema_version":"1.0"},"canonical_sha256":"c159707d6a982e29e735d54dad77f00a35c0cfba91c2975884ba094ec2b0114a","source":{"kind":"arxiv","id":"1906.08189","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08189","created_at":"2026-07-05T02:06:47Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08189v5","created_at":"2026-07-05T02:06:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08189","created_at":"2026-07-05T02:06:47Z"},{"alias_kind":"pith_short_12","alias_value":"YFMXA7LKTAXC","created_at":"2026-07-05T02:06:47Z"},{"alias_kind":"pith_short_16","alias_value":"YFMXA7LKTAXCTZZV","created_at":"2026-07-05T02:06:47Z"},{"alias_kind":"pith_short_8","alias_value":"YFMXA7LK","created_at":"2026-07-05T02:06:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YFMXA7LKTAXCTZZV2VG2257QBI","target":"record","payload":{"canonical_record":{"source":{"id":"1906.08189","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T16:06:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"71ee5dcfa611d804e4f29603e181f31659911d89e4a5723b3aaf9f99f0fcdc40","abstract_canon_sha256":"41171ae6b7f52a745ce4f3e8ae39ee08836c16ee01170826c203fa4f1692dc5d"},"schema_version":"1.0"},"canonical_sha256":"c159707d6a982e29e735d54dad77f00a35c0cfba91c2975884ba094ec2b0114a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:06:47.514153Z","signature_b64":"f+RJ6JvV9yik+zSvxAxnO1QLhX6FFUnEQRKQthJ2RFOZrZ3sJENgIQS+kQgyPFXhHf4rM8qWn5sABaa1z4AZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c159707d6a982e29e735d54dad77f00a35c0cfba91c2975884ba094ec2b0114a","last_reissued_at":"2026-07-05T02:06:47.513700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:06:47.513700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.08189","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:06:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UAUgVDk7cbT07XxEnFf3UX7Y+lvkYTTr/hzQwWe12NSjyjGZ9yaImT3e5NX3XPCtJOrc3KxGsuCrgerXvyp8DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:38:08.825851Z"},"content_sha256":"6b4b58c5dbee5f760587693c3a5d9ff1440fba84320210c1018b9c2a56127893","schema_version":"1.0","event_id":"sha256:6b4b58c5dbee5f760587693c3a5d9ff1440fba84320210c1018b9c2a56127893"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YFMXA7LKTAXCTZZV2VG2257QBI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward Prediction Error as an Exploration Objective in Deep RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anthony Bisulco, Ben Eisner, Daniel Lee, Daniel Yang, Eric Mitchell, Riley Simmons-Edler, Sebastian Seung","submitted_at":"2019-06-19T16:06:36Z","abstract_excerpt":"A major challenge in reinforcement learning is exploration, when local dithering methods such as epsilon-greedy sampling are insufficient to solve a given task. Many recent methods have proposed to intrinsically motivate an agent to seek novel states, driving the agent to discover improved reward. However, while state-novelty exploration methods are suitable for tasks where novel observations correlate well with improved reward, they may not explore more efficiently than epsilon-greedy approaches in environments where the two are not well-correlated. In this paper, we distinguish between explo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08189","kind":"arxiv","version":5},"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/1906.08189/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":"2026-07-05T02:06:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RceqSRZvd4VFA8CFqpyjrXny4Cr7iVk583T4y+9c+/KyYGc7kY8krReUNmOgE4CT7lZZkG7EuKtfwj7YCeYMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:38:08.826401Z"},"content_sha256":"ca2483996099c765a1cfe5a4008a3a9d9c2874a7d27925cf0c90208b37b62a9e","schema_version":"1.0","event_id":"sha256:ca2483996099c765a1cfe5a4008a3a9d9c2874a7d27925cf0c90208b37b62a9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YFMXA7LKTAXCTZZV2VG2257QBI/bundle.json","state_url":"https://pith.science/pith/YFMXA7LKTAXCTZZV2VG2257QBI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YFMXA7LKTAXCTZZV2VG2257QBI/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":"2026-08-22T13:38:08Z","links":{"resolver":"https://pith.science/pith/YFMXA7LKTAXCTZZV2VG2257QBI","bundle":"https://pith.science/pith/YFMXA7LKTAXCTZZV2VG2257QBI/bundle.json","state":"https://pith.science/pith/YFMXA7LKTAXCTZZV2VG2257QBI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YFMXA7LKTAXCTZZV2VG2257QBI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YFMXA7LKTAXCTZZV2VG2257QBI","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":"41171ae6b7f52a745ce4f3e8ae39ee08836c16ee01170826c203fa4f1692dc5d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T16:06:36Z","title_canon_sha256":"71ee5dcfa611d804e4f29603e181f31659911d89e4a5723b3aaf9f99f0fcdc40"},"schema_version":"1.0","source":{"id":"1906.08189","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.08189","created_at":"2026-07-05T02:06:47Z"},{"alias_kind":"arxiv_version","alias_value":"1906.08189v5","created_at":"2026-07-05T02:06:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08189","created_at":"2026-07-05T02:06:47Z"},{"alias_kind":"pith_short_12","alias_value":"YFMXA7LKTAXC","created_at":"2026-07-05T02:06:47Z"},{"alias_kind":"pith_short_16","alias_value":"YFMXA7LKTAXCTZZV","created_at":"2026-07-05T02:06:47Z"},{"alias_kind":"pith_short_8","alias_value":"YFMXA7LK","created_at":"2026-07-05T02:06:47Z"}],"graph_snapshots":[{"event_id":"sha256:ca2483996099c765a1cfe5a4008a3a9d9c2874a7d27925cf0c90208b37b62a9e","target":"graph","created_at":"2026-07-05T02:06:47Z","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/1906.08189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A major challenge in reinforcement learning is exploration, when local dithering methods such as epsilon-greedy sampling are insufficient to solve a given task. Many recent methods have proposed to intrinsically motivate an agent to seek novel states, driving the agent to discover improved reward. However, while state-novelty exploration methods are suitable for tasks where novel observations correlate well with improved reward, they may not explore more efficiently than epsilon-greedy approaches in environments where the two are not well-correlated. In this paper, we distinguish between explo","authors_text":"Anthony Bisulco, Ben Eisner, Daniel Lee, Daniel Yang, Eric Mitchell, Riley Simmons-Edler, Sebastian Seung","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T16:06:36Z","title":"Reward Prediction Error as an Exploration Objective in Deep RL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08189","kind":"arxiv","version":5},"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":"sha256:6b4b58c5dbee5f760587693c3a5d9ff1440fba84320210c1018b9c2a56127893","target":"record","created_at":"2026-07-05T02:06:47Z","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":"41171ae6b7f52a745ce4f3e8ae39ee08836c16ee01170826c203fa4f1692dc5d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-19T16:06:36Z","title_canon_sha256":"71ee5dcfa611d804e4f29603e181f31659911d89e4a5723b3aaf9f99f0fcdc40"},"schema_version":"1.0","source":{"id":"1906.08189","kind":"arxiv","version":5}},"canonical_sha256":"c159707d6a982e29e735d54dad77f00a35c0cfba91c2975884ba094ec2b0114a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c159707d6a982e29e735d54dad77f00a35c0cfba91c2975884ba094ec2b0114a","first_computed_at":"2026-07-05T02:06:47.513700Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:06:47.513700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f+RJ6JvV9yik+zSvxAxnO1QLhX6FFUnEQRKQthJ2RFOZrZ3sJENgIQS+kQgyPFXhHf4rM8qWn5sABaa1z4AZCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:06:47.514153Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.08189","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b4b58c5dbee5f760587693c3a5d9ff1440fba84320210c1018b9c2a56127893","sha256:ca2483996099c765a1cfe5a4008a3a9d9c2874a7d27925cf0c90208b37b62a9e"],"state_sha256":"281209041061cf802fe11f7215d0daf80caeb8f180a70f583b83283968f60374"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"byOOsAYeXrF9e02G/sHFzIIdrSHNOTrdrLASIVskDm6lMCVoYnovE48lOC24yCLPx+72JQ9JDttufuZu+VPYCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T13:38:08.830279Z","bundle_sha256":"607aa73a61d1916d9d53fc5d2647eda2ab5f9f8efb118495bc8212a0b32dc146"}}