{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:P7MKJ3IJR2BSJQRUGGLXJSNECH","short_pith_number":"pith:P7MKJ3IJ","canonical_record":{"source":{"id":"2105.14127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-28T22:22:03Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"44014f7e490319019a10a543ae8fd5ea2d4c58bb93e7c32080da981e7f8d0850","abstract_canon_sha256":"7d0294bd33a3996bff3e02bab2fc990366fab355789f9ba687c783d50c2e2af3"},"schema_version":"1.0"},"canonical_sha256":"7fd8a4ed098e8324c234319774c9a411cae3ab000e59868b0122561151e4f1ad","source":{"kind":"arxiv","id":"2105.14127","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.14127","created_at":"2026-07-05T02:44:20Z"},{"alias_kind":"arxiv_version","alias_value":"2105.14127v1","created_at":"2026-07-05T02:44:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14127","created_at":"2026-07-05T02:44:20Z"},{"alias_kind":"pith_short_12","alias_value":"P7MKJ3IJR2BS","created_at":"2026-07-05T02:44:20Z"},{"alias_kind":"pith_short_16","alias_value":"P7MKJ3IJR2BSJQRU","created_at":"2026-07-05T02:44:20Z"},{"alias_kind":"pith_short_8","alias_value":"P7MKJ3IJ","created_at":"2026-07-05T02:44:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:P7MKJ3IJR2BSJQRUGGLXJSNECH","target":"record","payload":{"canonical_record":{"source":{"id":"2105.14127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-28T22:22:03Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"44014f7e490319019a10a543ae8fd5ea2d4c58bb93e7c32080da981e7f8d0850","abstract_canon_sha256":"7d0294bd33a3996bff3e02bab2fc990366fab355789f9ba687c783d50c2e2af3"},"schema_version":"1.0"},"canonical_sha256":"7fd8a4ed098e8324c234319774c9a411cae3ab000e59868b0122561151e4f1ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:20.554624Z","signature_b64":"2tthOWzSKd5ODjnZVOoFJ3rNN6yIplRpPE/KYZNxHcpxeqRVvsNroLt0bKVx7UapH1ooxkl/Cf+M4OdSV0upDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fd8a4ed098e8324c234319774c9a411cae3ab000e59868b0122561151e4f1ad","last_reissued_at":"2026-07-05T02:44:20.554218Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:20.554218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.14127","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:44:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wsJx5kNqejJM0xhTSnxm3143t5/UFe/jkCZC62ikliWzVrewdctfj5lQ9IrXlCq1tbIi8pcazProaCPFsRhyCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T05:54:52.628262Z"},"content_sha256":"b50463bea85911f884995204deb5c6a0402ec3d2ce7093f250948b762807f673","schema_version":"1.0","event_id":"sha256:b50463bea85911f884995204deb5c6a0402ec3d2ce7093f250948b762807f673"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:P7MKJ3IJR2BSJQRUGGLXJSNECH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Risk-Aware Transfer in Reinforcement Learning using Successor Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Andr\\'e Barreto, Chi-Guhn Lee, Michael Gimelfarb, Scott Sanner","submitted_at":"2021-05-28T22:22:03Z","abstract_excerpt":"Sample efficiency and risk-awareness are central to the development of practical reinforcement learning (RL) for complex decision-making. The former can be addressed by transfer learning and the latter by optimizing some utility function of the return. However, the problem of transferring skills in a risk-aware manner is not well-understood. In this paper, we address the problem of risk-aware policy transfer between tasks in a common domain that differ only in their reward functions, in which risk is measured by the variance of reward streams. Our approach begins by extending the idea of gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14127","kind":"arxiv","version":1},"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/2105.14127/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":"2026-07-05T02:44:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WfAyuhOPz9rsuS+fWZyZnnJv9xn+BL/kvCm3zc4++rLXX85QUwz/A0JrenN1F61TrIkx2vI3B27grBsUy7TkAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-22T05:54:52.628656Z"},"content_sha256":"fd3d8d4fe2f2b17ec9dfd1e71a90f0ef72e4544796bf3aaa0ae12541649b8c37","schema_version":"1.0","event_id":"sha256:fd3d8d4fe2f2b17ec9dfd1e71a90f0ef72e4544796bf3aaa0ae12541649b8c37"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P7MKJ3IJR2BSJQRUGGLXJSNECH/bundle.json","state_url":"https://pith.science/pith/P7MKJ3IJR2BSJQRUGGLXJSNECH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P7MKJ3IJR2BSJQRUGGLXJSNECH/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":"2026-07-22T05:54:52Z","links":{"resolver":"https://pith.science/pith/P7MKJ3IJR2BSJQRUGGLXJSNECH","bundle":"https://pith.science/pith/P7MKJ3IJR2BSJQRUGGLXJSNECH/bundle.json","state":"https://pith.science/pith/P7MKJ3IJR2BSJQRUGGLXJSNECH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P7MKJ3IJR2BSJQRUGGLXJSNECH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:P7MKJ3IJR2BSJQRUGGLXJSNECH","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":"7d0294bd33a3996bff3e02bab2fc990366fab355789f9ba687c783d50c2e2af3","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-28T22:22:03Z","title_canon_sha256":"44014f7e490319019a10a543ae8fd5ea2d4c58bb93e7c32080da981e7f8d0850"},"schema_version":"1.0","source":{"id":"2105.14127","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.14127","created_at":"2026-07-05T02:44:20Z"},{"alias_kind":"arxiv_version","alias_value":"2105.14127v1","created_at":"2026-07-05T02:44:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14127","created_at":"2026-07-05T02:44:20Z"},{"alias_kind":"pith_short_12","alias_value":"P7MKJ3IJR2BS","created_at":"2026-07-05T02:44:20Z"},{"alias_kind":"pith_short_16","alias_value":"P7MKJ3IJR2BSJQRU","created_at":"2026-07-05T02:44:20Z"},{"alias_kind":"pith_short_8","alias_value":"P7MKJ3IJ","created_at":"2026-07-05T02:44:20Z"}],"graph_snapshots":[{"event_id":"sha256:fd3d8d4fe2f2b17ec9dfd1e71a90f0ef72e4544796bf3aaa0ae12541649b8c37","target":"graph","created_at":"2026-07-05T02:44:20Z","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/2105.14127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sample efficiency and risk-awareness are central to the development of practical reinforcement learning (RL) for complex decision-making. The former can be addressed by transfer learning and the latter by optimizing some utility function of the return. However, the problem of transferring skills in a risk-aware manner is not well-understood. In this paper, we address the problem of risk-aware policy transfer between tasks in a common domain that differ only in their reward functions, in which risk is measured by the variance of reward streams. Our approach begins by extending the idea of gener","authors_text":"Andr\\'e Barreto, Chi-Guhn Lee, Michael Gimelfarb, Scott Sanner","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-28T22:22:03Z","title":"Risk-Aware Transfer in Reinforcement Learning using Successor Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14127","kind":"arxiv","version":1},"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:b50463bea85911f884995204deb5c6a0402ec3d2ce7093f250948b762807f673","target":"record","created_at":"2026-07-05T02:44:20Z","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":"7d0294bd33a3996bff3e02bab2fc990366fab355789f9ba687c783d50c2e2af3","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-05-28T22:22:03Z","title_canon_sha256":"44014f7e490319019a10a543ae8fd5ea2d4c58bb93e7c32080da981e7f8d0850"},"schema_version":"1.0","source":{"id":"2105.14127","kind":"arxiv","version":1}},"canonical_sha256":"7fd8a4ed098e8324c234319774c9a411cae3ab000e59868b0122561151e4f1ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7fd8a4ed098e8324c234319774c9a411cae3ab000e59868b0122561151e4f1ad","first_computed_at":"2026-07-05T02:44:20.554218Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:44:20.554218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2tthOWzSKd5ODjnZVOoFJ3rNN6yIplRpPE/KYZNxHcpxeqRVvsNroLt0bKVx7UapH1ooxkl/Cf+M4OdSV0upDw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:44:20.554624Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.14127","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b50463bea85911f884995204deb5c6a0402ec3d2ce7093f250948b762807f673","sha256:fd3d8d4fe2f2b17ec9dfd1e71a90f0ef72e4544796bf3aaa0ae12541649b8c37"],"state_sha256":"b55e1fe9acfeaba6a805bfc12d8742177dda6cc9e17708356918def2a4899c22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j6V9bFkVVMPBDtPZCLSbmaR2gtEmAvX3QXUlk8seX3TAt1P4m2ZsNrG/gjcUhZfysqaV/Kmp9vmu2JOyBrPXAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-22T05:54:52.630831Z","bundle_sha256":"de63949f3baa396cb22b912b15cb5e537d98d969101a091b2d892e8ec45079e0"}}