{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TYYNNOADJWLDADGW4EIN3PFNEX","short_pith_number":"pith:TYYNNOAD","canonical_record":{"source":{"id":"1806.04640","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-12T16:48:52Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5c1a4fcab4346f51c807e72529b8604bd1f6427553ebe9f7a4c70493c1a1ddb3","abstract_canon_sha256":"e481cfaf0ea979994992fa730475fab978e42fa46cac7fbcf00a90de91add545"},"schema_version":"1.0"},"canonical_sha256":"9e30d6b8034d96300cd6e110ddbcad25e9609f3da249b8793cd191e02275be66","source":{"kind":"arxiv","id":"1806.04640","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04640","created_at":"2026-07-05T00:59:20Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04640v3","created_at":"2026-07-05T00:59:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04640","created_at":"2026-07-05T00:59:20Z"},{"alias_kind":"pith_short_12","alias_value":"TYYNNOADJWLD","created_at":"2026-07-05T00:59:20Z"},{"alias_kind":"pith_short_16","alias_value":"TYYNNOADJWLDADGW","created_at":"2026-07-05T00:59:20Z"},{"alias_kind":"pith_short_8","alias_value":"TYYNNOAD","created_at":"2026-07-05T00:59:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TYYNNOADJWLDADGW4EIN3PFNEX","target":"record","payload":{"canonical_record":{"source":{"id":"1806.04640","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-12T16:48:52Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5c1a4fcab4346f51c807e72529b8604bd1f6427553ebe9f7a4c70493c1a1ddb3","abstract_canon_sha256":"e481cfaf0ea979994992fa730475fab978e42fa46cac7fbcf00a90de91add545"},"schema_version":"1.0"},"canonical_sha256":"9e30d6b8034d96300cd6e110ddbcad25e9609f3da249b8793cd191e02275be66","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:20.437359Z","signature_b64":"asjOvXkSHLqB+Hkx+SSVSp0FXXMBcQJH3c1/JEowoaNukASJ6Iq4u4zOSOVnrAQKohgMr805xf9B/C34YVGlCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e30d6b8034d96300cd6e110ddbcad25e9609f3da249b8793cd191e02275be66","last_reissued_at":"2026-07-05T00:59:20.436944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:20.436944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.04640","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":"2026-07-05T00:59:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"twD83nz+CnYh9ghih+P0D4QIFvw/UamUXdxNxiVPwdYwZoa6Pg+rQ9UKAVVEq9KYJ3LKRPEsd78w7urLofjLCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:18:10.765681Z"},"content_sha256":"6fdc92416a4af5725ad594bf16425b1c43634e3d070b02f61401de88845a8ff8","schema_version":"1.0","event_id":"sha256:6fdc92416a4af5725ad594bf16425b1c43634e3d070b02f61401de88845a8ff8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TYYNNOADJWLDADGW4EIN3PFNEX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Meta-Learning for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Gupta, Benjamin Eysenbach, Chelsea Finn, Sergey Levine","submitted_at":"2018-06-12T16:48:52Z","abstract_excerpt":"Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by utilizing experience from prior tasks. The performance of meta-learning algorithms depends on the tasks available for meta-training: in the same way that supervised learning generalizes best to test points drawn from the same distribution as the training points, meta-learning methods generalize best to tasks from the same distribution as the meta-training tasks. In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04640","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/1806.04640/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":"2026-07-05T00:59:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y6OmOXN2GsNbpHsGMaOyUDBNLRtVNE74fS0PYpqa5hw7Wutwh0qDXw3v4e2PAK6kWRmsywXhM7IopwN644oqAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:18:10.766189Z"},"content_sha256":"5a622e0d55edf759d21028f5bac78057870345f5521bdf548526144cd49b9e12","schema_version":"1.0","event_id":"sha256:5a622e0d55edf759d21028f5bac78057870345f5521bdf548526144cd49b9e12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TYYNNOADJWLDADGW4EIN3PFNEX/bundle.json","state_url":"https://pith.science/pith/TYYNNOADJWLDADGW4EIN3PFNEX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TYYNNOADJWLDADGW4EIN3PFNEX/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":"2026-08-09T13:18:10Z","links":{"resolver":"https://pith.science/pith/TYYNNOADJWLDADGW4EIN3PFNEX","bundle":"https://pith.science/pith/TYYNNOADJWLDADGW4EIN3PFNEX/bundle.json","state":"https://pith.science/pith/TYYNNOADJWLDADGW4EIN3PFNEX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TYYNNOADJWLDADGW4EIN3PFNEX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TYYNNOADJWLDADGW4EIN3PFNEX","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":"e481cfaf0ea979994992fa730475fab978e42fa46cac7fbcf00a90de91add545","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-12T16:48:52Z","title_canon_sha256":"5c1a4fcab4346f51c807e72529b8604bd1f6427553ebe9f7a4c70493c1a1ddb3"},"schema_version":"1.0","source":{"id":"1806.04640","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.04640","created_at":"2026-07-05T00:59:20Z"},{"alias_kind":"arxiv_version","alias_value":"1806.04640v3","created_at":"2026-07-05T00:59:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.04640","created_at":"2026-07-05T00:59:20Z"},{"alias_kind":"pith_short_12","alias_value":"TYYNNOADJWLD","created_at":"2026-07-05T00:59:20Z"},{"alias_kind":"pith_short_16","alias_value":"TYYNNOADJWLDADGW","created_at":"2026-07-05T00:59:20Z"},{"alias_kind":"pith_short_8","alias_value":"TYYNNOAD","created_at":"2026-07-05T00:59:20Z"}],"graph_snapshots":[{"event_id":"sha256:5a622e0d55edf759d21028f5bac78057870345f5521bdf548526144cd49b9e12","target":"graph","created_at":"2026-07-05T00:59:20Z","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/1806.04640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meta-learning algorithms use past experience to learn to quickly solve new tasks. In the context of reinforcement learning, meta-learning algorithms acquire reinforcement learning procedures to solve new problems more efficiently by utilizing experience from prior tasks. The performance of meta-learning algorithms depends on the tasks available for meta-training: in the same way that supervised learning generalizes best to test points drawn from the same distribution as the training points, meta-learning methods generalize best to tasks from the same distribution as the meta-training tasks. In","authors_text":"Abhishek Gupta, Benjamin Eysenbach, Chelsea Finn, Sergey Levine","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-12T16:48:52Z","title":"Unsupervised Meta-Learning for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.04640","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":"sha256:6fdc92416a4af5725ad594bf16425b1c43634e3d070b02f61401de88845a8ff8","target":"record","created_at":"2026-07-05T00:59:20Z","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":"e481cfaf0ea979994992fa730475fab978e42fa46cac7fbcf00a90de91add545","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-12T16:48:52Z","title_canon_sha256":"5c1a4fcab4346f51c807e72529b8604bd1f6427553ebe9f7a4c70493c1a1ddb3"},"schema_version":"1.0","source":{"id":"1806.04640","kind":"arxiv","version":3}},"canonical_sha256":"9e30d6b8034d96300cd6e110ddbcad25e9609f3da249b8793cd191e02275be66","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e30d6b8034d96300cd6e110ddbcad25e9609f3da249b8793cd191e02275be66","first_computed_at":"2026-07-05T00:59:20.436944Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:20.436944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"asjOvXkSHLqB+Hkx+SSVSp0FXXMBcQJH3c1/JEowoaNukASJ6Iq4u4zOSOVnrAQKohgMr805xf9B/C34YVGlCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:20.437359Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.04640","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fdc92416a4af5725ad594bf16425b1c43634e3d070b02f61401de88845a8ff8","sha256:5a622e0d55edf759d21028f5bac78057870345f5521bdf548526144cd49b9e12"],"state_sha256":"cec0361f710067ffcc7f86d41717518ce9fb8720a9f9c89c3143d3d93353bc43"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zgq3UgXF5EKvcdJzjm0zgkqa8t7EKwi9xy6yDB3Fxfv8i4QQHQESNtYhF761XMWM6dLW0laScOAOmNT3LXpsCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:18:10.769746Z","bundle_sha256":"b25ce6f0a2c51bf4a3f19e33b975ed547b4b1a2a320eb4e6cc49553c2bfa8b6f"}}