{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GMZN322AMHHLP4VTKLLOTMRHUN","short_pith_number":"pith:GMZN322A","canonical_record":{"source":{"id":"2106.00669","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-06-01T17:56:13Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f4eba4b52b9c422b11c205f960a1ba888d4823c4f3ffdaf454bf05a99d00e518","abstract_canon_sha256":"1b8909ff610623b92ebf624991a6091e2c6832b167e48187aa8097fb996ccafa"},"schema_version":"1.0"},"canonical_sha256":"3332ddeb4061ceb7f2b352d6e9b227a362af006c755ec54d4518dea0ba302b08","source":{"kind":"arxiv","id":"2106.00669","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00669","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00669v2","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00669","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"pith_short_12","alias_value":"GMZN322AMHHL","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"pith_short_16","alias_value":"GMZN322AMHHLP4VT","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"pith_short_8","alias_value":"GMZN322A","created_at":"2026-07-05T03:45:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GMZN322AMHHLP4VTKLLOTMRHUN","target":"record","payload":{"canonical_record":{"source":{"id":"2106.00669","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-06-01T17:56:13Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f4eba4b52b9c422b11c205f960a1ba888d4823c4f3ffdaf454bf05a99d00e518","abstract_canon_sha256":"1b8909ff610623b92ebf624991a6091e2c6832b167e48187aa8097fb996ccafa"},"schema_version":"1.0"},"canonical_sha256":"3332ddeb4061ceb7f2b352d6e9b227a362af006c755ec54d4518dea0ba302b08","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:45:09.321615Z","signature_b64":"EwX4UkkB3+Dmmho4n59+v47ZFeXhO/mpxmLZ7S3SVQuHT7DFvmk3+j1QAdEI1DLr5snxuNqhkkPOlzZKlG2aAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3332ddeb4061ceb7f2b352d6e9b227a362af006c755ec54d4518dea0ba302b08","last_reissued_at":"2026-07-05T03:45:09.321176Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:45:09.321176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.00669","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":"2026-07-05T03:45:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zgxKho/tlwwiGwCBmjnEVIa+wwFlKhVtyTHPJmGj/6c2NSuFayuazFVyFB0QvIL8f5uD+FwFEalLOqN8ElTGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:47:08.626343Z"},"content_sha256":"d603e0286aa98f9dc21d769d7247676ca6f04ab1504d710ab970f4eb7da72743","schema_version":"1.0","event_id":"sha256:d603e0286aa98f9dc21d769d7247676ca6f04ab1504d710ab970f4eb7da72743"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GMZN322AMHHLP4VTKLLOTMRHUN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discovering Diverse Nearly Optimal Policies with Successor Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Andre Barreto, Brendan O'Donoghue, Satinder Singh, Sebastian Flennerhag, Tom Zahavy, Volodymyr Mnih","submitted_at":"2021-06-01T17:56:13Z","abstract_excerpt":"Finding different solutions to the same problem is a key aspect of intelligence associated with creativity and adaptation to novel situations. In reinforcement learning, a set of diverse policies can be useful for exploration, transfer, hierarchy, and robustness. We propose Diverse Successive Policies, a method for discovering policies that are diverse in the space of Successor Features, while assuring that they are near optimal. We formalize the problem as a Constrained Markov Decision Process (CMDP) where the goal is to find policies that maximize diversity, characterized by an intrinsic div"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00669","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.00669/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":"2026-07-05T03:45:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vqjEcKftoBacZPBZzuzirqf+E014DfAzUUaaZxUtFxjyTbq6xshB0nl0gGlZZCMg8LmIg9JrwjZGUjM+MjJuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:47:08.626858Z"},"content_sha256":"be20d0b6b1369730cdcd57e03dd09d8b17329aaf3e595647847e5e5d7c0a64c3","schema_version":"1.0","event_id":"sha256:be20d0b6b1369730cdcd57e03dd09d8b17329aaf3e595647847e5e5d7c0a64c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GMZN322AMHHLP4VTKLLOTMRHUN/bundle.json","state_url":"https://pith.science/pith/GMZN322AMHHLP4VTKLLOTMRHUN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GMZN322AMHHLP4VTKLLOTMRHUN/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":"2026-08-08T07:47:08Z","links":{"resolver":"https://pith.science/pith/GMZN322AMHHLP4VTKLLOTMRHUN","bundle":"https://pith.science/pith/GMZN322AMHHLP4VTKLLOTMRHUN/bundle.json","state":"https://pith.science/pith/GMZN322AMHHLP4VTKLLOTMRHUN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GMZN322AMHHLP4VTKLLOTMRHUN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GMZN322AMHHLP4VTKLLOTMRHUN","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":"1b8909ff610623b92ebf624991a6091e2c6832b167e48187aa8097fb996ccafa","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-06-01T17:56:13Z","title_canon_sha256":"f4eba4b52b9c422b11c205f960a1ba888d4823c4f3ffdaf454bf05a99d00e518"},"schema_version":"1.0","source":{"id":"2106.00669","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00669","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00669v2","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00669","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"pith_short_12","alias_value":"GMZN322AMHHL","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"pith_short_16","alias_value":"GMZN322AMHHLP4VT","created_at":"2026-07-05T03:45:09Z"},{"alias_kind":"pith_short_8","alias_value":"GMZN322A","created_at":"2026-07-05T03:45:09Z"}],"graph_snapshots":[{"event_id":"sha256:be20d0b6b1369730cdcd57e03dd09d8b17329aaf3e595647847e5e5d7c0a64c3","target":"graph","created_at":"2026-07-05T03:45:09Z","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/2106.00669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Finding different solutions to the same problem is a key aspect of intelligence associated with creativity and adaptation to novel situations. In reinforcement learning, a set of diverse policies can be useful for exploration, transfer, hierarchy, and robustness. We propose Diverse Successive Policies, a method for discovering policies that are diverse in the space of Successor Features, while assuring that they are near optimal. We formalize the problem as a Constrained Markov Decision Process (CMDP) where the goal is to find policies that maximize diversity, characterized by an intrinsic div","authors_text":"Andre Barreto, Brendan O'Donoghue, Satinder Singh, Sebastian Flennerhag, Tom Zahavy, Volodymyr Mnih","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-06-01T17:56:13Z","title":"Discovering Diverse Nearly Optimal Policies with Successor Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00669","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:d603e0286aa98f9dc21d769d7247676ca6f04ab1504d710ab970f4eb7da72743","target":"record","created_at":"2026-07-05T03:45:09Z","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":"1b8909ff610623b92ebf624991a6091e2c6832b167e48187aa8097fb996ccafa","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-06-01T17:56:13Z","title_canon_sha256":"f4eba4b52b9c422b11c205f960a1ba888d4823c4f3ffdaf454bf05a99d00e518"},"schema_version":"1.0","source":{"id":"2106.00669","kind":"arxiv","version":2}},"canonical_sha256":"3332ddeb4061ceb7f2b352d6e9b227a362af006c755ec54d4518dea0ba302b08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3332ddeb4061ceb7f2b352d6e9b227a362af006c755ec54d4518dea0ba302b08","first_computed_at":"2026-07-05T03:45:09.321176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:45:09.321176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EwX4UkkB3+Dmmho4n59+v47ZFeXhO/mpxmLZ7S3SVQuHT7DFvmk3+j1QAdEI1DLr5snxuNqhkkPOlzZKlG2aAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:45:09.321615Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.00669","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d603e0286aa98f9dc21d769d7247676ca6f04ab1504d710ab970f4eb7da72743","sha256:be20d0b6b1369730cdcd57e03dd09d8b17329aaf3e595647847e5e5d7c0a64c3"],"state_sha256":"67b4028500933099d68d74694dc715a0b21287e9cb1838e6434a7fa8e7b5051a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8qi9XIz7J9irBCFexRZYz6SsrhcNPcfVC0AQ1o3YiRchEVEOnFvXDcEBpmCvS/xixFIsDakYrE+FQyibwCn0DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:47:08.631796Z","bundle_sha256":"8f3cea5964b51be476710046612e357e0eeb7b658679009a28e7e273be5151a2"}}