{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5ZWFGDO6NAQF6PYCBP3NZAWDRW","short_pith_number":"pith:5ZWFGDO6","canonical_record":{"source":{"id":"1912.05500","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-12-11T18:00:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9d85cb7a27437c796618be3f070a3d5d3e6b01534f5ed7d29cdf634bb216961e","abstract_canon_sha256":"cd08c209207267491f50cf543e6b8cff8d7c616fa465f4adff77329261459f81"},"schema_version":"1.0"},"canonical_sha256":"ee6c530dde68205f3f020bf6dc82c38d90acdd1e18be001a1788ffc0d502446b","source":{"kind":"arxiv","id":"1912.05500","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.05500","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"1912.05500v3","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05500","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"5ZWFGDO6NAQF","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"5ZWFGDO6NAQF6PYC","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"5ZWFGDO6","created_at":"2026-07-05T01:29:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5ZWFGDO6NAQF6PYCBP3NZAWDRW","target":"record","payload":{"canonical_record":{"source":{"id":"1912.05500","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-12-11T18:00:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9d85cb7a27437c796618be3f070a3d5d3e6b01534f5ed7d29cdf634bb216961e","abstract_canon_sha256":"cd08c209207267491f50cf543e6b8cff8d7c616fa465f4adff77329261459f81"},"schema_version":"1.0"},"canonical_sha256":"ee6c530dde68205f3f020bf6dc82c38d90acdd1e18be001a1788ffc0d502446b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:29:01.816165Z","signature_b64":"550Qh0Z0o2xHEQupu9zQob3g2eY5O8PO02ceO+vIzGGlkfhp+n40k1WjhJ0GKKDqiWKBBkvP5g+0qlx1z9cfBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee6c530dde68205f3f020bf6dc82c38d90acdd1e18be001a1788ffc0d502446b","last_reissued_at":"2026-07-05T01:29:01.815657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:29:01.815657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.05500","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":"2026-07-05T01:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fwpEVEpTORtN3yRn7n6xaDmGtlBvuVBO9pajkHKMrmNnKhq1nZF8ze6RqaEmMHnt32uOW5YoySAcwVhosQyEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:57:20.961334Z"},"content_sha256":"ea8a87db2837ec8fd1c15e35b55c4ac2cb8a07420165c3672c57887566c88e36","schema_version":"1.0","event_id":"sha256:ea8a87db2837ec8fd1c15e35b55c4ac2cb8a07420165c3672c57887566c88e36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5ZWFGDO6NAQF6PYCBP3NZAWDRW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"What Can Learned Intrinsic Rewards Capture?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"David Silver, Hado van Hasselt, Junhyuk Oh, Manuel Kroiss, Matteo Hessel, Satinder Singh, Zeyu Zheng, Zhongwen Xu","submitted_at":"2019-12-11T18:00:05Z","abstract_excerpt":"The objective of a reinforcement learning agent is to behave so as to maximise the sum of a suitable scalar function of state: the reward. These rewards are typically given and immutable. In this paper, we instead consider the proposition that the reward function itself can be a good locus of learned knowledge. To investigate this, we propose a scalable meta-gradient framework for learning useful intrinsic reward functions across multiple lifetimes of experience. Through several proof-of-concept experiments, we show that it is feasible to learn and capture knowledge about long-term exploration"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05500","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/1912.05500/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":"2026-07-05T01:29:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xsPs4u76vUzRmTUnmMTQBv2fYekINMbQdIWvKFkg/iIlyexJO/9L8Vf5CKuUb3Z0mOsHR1HjPaL0p2pDf/vCCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:57:20.961866Z"},"content_sha256":"5af3ee6184c790a471e2b5ce37d12e8fdfad378286cde98e00c935ff37750142","schema_version":"1.0","event_id":"sha256:5af3ee6184c790a471e2b5ce37d12e8fdfad378286cde98e00c935ff37750142"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5ZWFGDO6NAQF6PYCBP3NZAWDRW/bundle.json","state_url":"https://pith.science/pith/5ZWFGDO6NAQF6PYCBP3NZAWDRW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5ZWFGDO6NAQF6PYCBP3NZAWDRW/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":"2026-08-08T13:57:20Z","links":{"resolver":"https://pith.science/pith/5ZWFGDO6NAQF6PYCBP3NZAWDRW","bundle":"https://pith.science/pith/5ZWFGDO6NAQF6PYCBP3NZAWDRW/bundle.json","state":"https://pith.science/pith/5ZWFGDO6NAQF6PYCBP3NZAWDRW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5ZWFGDO6NAQF6PYCBP3NZAWDRW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5ZWFGDO6NAQF6PYCBP3NZAWDRW","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":"cd08c209207267491f50cf543e6b8cff8d7c616fa465f4adff77329261459f81","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-12-11T18:00:05Z","title_canon_sha256":"9d85cb7a27437c796618be3f070a3d5d3e6b01534f5ed7d29cdf634bb216961e"},"schema_version":"1.0","source":{"id":"1912.05500","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.05500","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"arxiv_version","alias_value":"1912.05500v3","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.05500","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"pith_short_12","alias_value":"5ZWFGDO6NAQF","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"pith_short_16","alias_value":"5ZWFGDO6NAQF6PYC","created_at":"2026-07-05T01:29:01Z"},{"alias_kind":"pith_short_8","alias_value":"5ZWFGDO6","created_at":"2026-07-05T01:29:01Z"}],"graph_snapshots":[{"event_id":"sha256:5af3ee6184c790a471e2b5ce37d12e8fdfad378286cde98e00c935ff37750142","target":"graph","created_at":"2026-07-05T01:29:01Z","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/1912.05500/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The objective of a reinforcement learning agent is to behave so as to maximise the sum of a suitable scalar function of state: the reward. These rewards are typically given and immutable. In this paper, we instead consider the proposition that the reward function itself can be a good locus of learned knowledge. To investigate this, we propose a scalable meta-gradient framework for learning useful intrinsic reward functions across multiple lifetimes of experience. Through several proof-of-concept experiments, we show that it is feasible to learn and capture knowledge about long-term exploration","authors_text":"David Silver, Hado van Hasselt, Junhyuk Oh, Manuel Kroiss, Matteo Hessel, Satinder Singh, Zeyu Zheng, Zhongwen Xu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-12-11T18:00:05Z","title":"What Can Learned Intrinsic Rewards Capture?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.05500","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:ea8a87db2837ec8fd1c15e35b55c4ac2cb8a07420165c3672c57887566c88e36","target":"record","created_at":"2026-07-05T01:29:01Z","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":"cd08c209207267491f50cf543e6b8cff8d7c616fa465f4adff77329261459f81","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-12-11T18:00:05Z","title_canon_sha256":"9d85cb7a27437c796618be3f070a3d5d3e6b01534f5ed7d29cdf634bb216961e"},"schema_version":"1.0","source":{"id":"1912.05500","kind":"arxiv","version":3}},"canonical_sha256":"ee6c530dde68205f3f020bf6dc82c38d90acdd1e18be001a1788ffc0d502446b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee6c530dde68205f3f020bf6dc82c38d90acdd1e18be001a1788ffc0d502446b","first_computed_at":"2026-07-05T01:29:01.815657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:29:01.815657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"550Qh0Z0o2xHEQupu9zQob3g2eY5O8PO02ceO+vIzGGlkfhp+n40k1WjhJ0GKKDqiWKBBkvP5g+0qlx1z9cfBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:29:01.816165Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.05500","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea8a87db2837ec8fd1c15e35b55c4ac2cb8a07420165c3672c57887566c88e36","sha256:5af3ee6184c790a471e2b5ce37d12e8fdfad378286cde98e00c935ff37750142"],"state_sha256":"2050e8b1397a93f2d937b3e22bbbccd4fa3c4e7314bf199cafe0d183cbeee8f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gvE10IUDIRRbJ//mi7LSJQs1czC5n6Gdsn3SOXNGhbPJRAaFz3g63Xp2nhgywXIqpXwOZuuy/nLwO3q4Sy1IDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:57:20.967719Z","bundle_sha256":"1ce919a9b977e6f0dd9d3f105e89b3283f0d5885d3cab3470868d80c5c13b8d6"}}