{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:HC2OFER5UZISRTR7LRPV7BCNNZ","short_pith_number":"pith:HC2OFER5","canonical_record":{"source":{"id":"1610.01283","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-05T06:51:58Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"ef6754fbd12236831f5fd993989d02e4ecd0cc5f2a7bd9df742d9e41545b8946","abstract_canon_sha256":"698a9923894aed98a468670270840cd4355488f0a0a12ecf16207f98a3785e21"},"schema_version":"1.0"},"canonical_sha256":"38b4e2923da65128ce3f5c5f5f844d6e4f88982b3488ac9fd2c5f4e59d431d7a","source":{"kind":"arxiv","id":"1610.01283","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.01283","created_at":"2026-05-18T00:49:32Z"},{"alias_kind":"arxiv_version","alias_value":"1610.01283v4","created_at":"2026-05-18T00:49:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.01283","created_at":"2026-05-18T00:49:32Z"},{"alias_kind":"pith_short_12","alias_value":"HC2OFER5UZIS","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"HC2OFER5UZISRTR7","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"HC2OFER5","created_at":"2026-05-18T12:30:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:HC2OFER5UZISRTR7LRPV7BCNNZ","target":"record","payload":{"canonical_record":{"source":{"id":"1610.01283","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-05T06:51:58Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"ef6754fbd12236831f5fd993989d02e4ecd0cc5f2a7bd9df742d9e41545b8946","abstract_canon_sha256":"698a9923894aed98a468670270840cd4355488f0a0a12ecf16207f98a3785e21"},"schema_version":"1.0"},"canonical_sha256":"38b4e2923da65128ce3f5c5f5f844d6e4f88982b3488ac9fd2c5f4e59d431d7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:32.017263Z","signature_b64":"BvMXcDFSOBj18j2or6Ut/WpukuphqgEBD8f6HkJ2YT0rxfv3P4jzWDX1maUStptHmUIRWUyDvu7exTA0531mCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38b4e2923da65128ce3f5c5f5f844d6e4f88982b3488ac9fd2c5f4e59d431d7a","last_reissued_at":"2026-05-18T00:49:32.016714Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:32.016714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.01283","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:49:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xkL6oK87ctMZkJnj/oNRmi4XRwLwGMNtS2Hf6Nv75LmCSFnMF1KaEZuZGwXjsZ4kRdfVtdHlOuttbUsexHwsCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T19:05:03.096335Z"},"content_sha256":"296655ef7e444ee552c6adc0b32079aab8bb1d7b62ec135c35f0fc6dd307d18d","schema_version":"1.0","event_id":"sha256:296655ef7e444ee552c6adc0b32079aab8bb1d7b62ec135c35f0fc6dd307d18d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:HC2OFER5UZISRTR7LRPV7BCNNZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EPOpt: Learning Robust Neural Network Policies Using Model Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Aravind Rajeswaran, Balaraman Ravindran, Sarvjeet Ghotra, Sergey Levine","submitted_at":"2016-10-05T06:51:58Z","abstract_excerpt":"Sample complexity and safety are major challenges when learning policies with reinforcement learning for real-world tasks, especially when the policies are represented using rich function approximators like deep neural networks. Model-based methods where the real-world target domain is approximated using a simulated source domain provide an avenue to tackle the above challenges by augmenting real data with simulated data. However, discrepancies between the simulated source domain and the target domain pose a challenge for simulated training. We introduce the EPOpt algorithm, which uses an ense"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.01283","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:49:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5pQrIQs7sqhNyxsmk6yeqTYb2WiKYm3pjf9WDwWjp14CcWKENGpBAaiep5UjwkIYdk2zo6X8p7yc4TBcuTN7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T19:05:03.096995Z"},"content_sha256":"9733470d1d44ccd526bd6bec34683272404a2e9f8f0e875f2239414f1e8e717a","schema_version":"1.0","event_id":"sha256:9733470d1d44ccd526bd6bec34683272404a2e9f8f0e875f2239414f1e8e717a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HC2OFER5UZISRTR7LRPV7BCNNZ/bundle.json","state_url":"https://pith.science/pith/HC2OFER5UZISRTR7LRPV7BCNNZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HC2OFER5UZISRTR7LRPV7BCNNZ/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":"2026-06-05T19:05:03Z","links":{"resolver":"https://pith.science/pith/HC2OFER5UZISRTR7LRPV7BCNNZ","bundle":"https://pith.science/pith/HC2OFER5UZISRTR7LRPV7BCNNZ/bundle.json","state":"https://pith.science/pith/HC2OFER5UZISRTR7LRPV7BCNNZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HC2OFER5UZISRTR7LRPV7BCNNZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:HC2OFER5UZISRTR7LRPV7BCNNZ","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":"698a9923894aed98a468670270840cd4355488f0a0a12ecf16207f98a3785e21","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-05T06:51:58Z","title_canon_sha256":"ef6754fbd12236831f5fd993989d02e4ecd0cc5f2a7bd9df742d9e41545b8946"},"schema_version":"1.0","source":{"id":"1610.01283","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.01283","created_at":"2026-05-18T00:49:32Z"},{"alias_kind":"arxiv_version","alias_value":"1610.01283v4","created_at":"2026-05-18T00:49:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.01283","created_at":"2026-05-18T00:49:32Z"},{"alias_kind":"pith_short_12","alias_value":"HC2OFER5UZIS","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_16","alias_value":"HC2OFER5UZISRTR7","created_at":"2026-05-18T12:30:19Z"},{"alias_kind":"pith_short_8","alias_value":"HC2OFER5","created_at":"2026-05-18T12:30:19Z"}],"graph_snapshots":[{"event_id":"sha256:9733470d1d44ccd526bd6bec34683272404a2e9f8f0e875f2239414f1e8e717a","target":"graph","created_at":"2026-05-18T00:49:32Z","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"},"paper":{"abstract_excerpt":"Sample complexity and safety are major challenges when learning policies with reinforcement learning for real-world tasks, especially when the policies are represented using rich function approximators like deep neural networks. Model-based methods where the real-world target domain is approximated using a simulated source domain provide an avenue to tackle the above challenges by augmenting real data with simulated data. However, discrepancies between the simulated source domain and the target domain pose a challenge for simulated training. We introduce the EPOpt algorithm, which uses an ense","authors_text":"Aravind Rajeswaran, Balaraman Ravindran, Sarvjeet Ghotra, Sergey Levine","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-05T06:51:58Z","title":"EPOpt: Learning Robust Neural Network Policies Using Model Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.01283","kind":"arxiv","version":4},"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":"sha256:296655ef7e444ee552c6adc0b32079aab8bb1d7b62ec135c35f0fc6dd307d18d","target":"record","created_at":"2026-05-18T00:49:32Z","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":"698a9923894aed98a468670270840cd4355488f0a0a12ecf16207f98a3785e21","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-05T06:51:58Z","title_canon_sha256":"ef6754fbd12236831f5fd993989d02e4ecd0cc5f2a7bd9df742d9e41545b8946"},"schema_version":"1.0","source":{"id":"1610.01283","kind":"arxiv","version":4}},"canonical_sha256":"38b4e2923da65128ce3f5c5f5f844d6e4f88982b3488ac9fd2c5f4e59d431d7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38b4e2923da65128ce3f5c5f5f844d6e4f88982b3488ac9fd2c5f4e59d431d7a","first_computed_at":"2026-05-18T00:49:32.016714Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:49:32.016714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BvMXcDFSOBj18j2or6Ut/WpukuphqgEBD8f6HkJ2YT0rxfv3P4jzWDX1maUStptHmUIRWUyDvu7exTA0531mCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:49:32.017263Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.01283","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:296655ef7e444ee552c6adc0b32079aab8bb1d7b62ec135c35f0fc6dd307d18d","sha256:9733470d1d44ccd526bd6bec34683272404a2e9f8f0e875f2239414f1e8e717a"],"state_sha256":"9606d2814f301cfe172fe6e35faec695de881760cdea3fec6ad7a2d5473938ba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9t/GzQwdLpFt/xPDBQq70Ar6fa+k8TOeHx1xLRpS8vjytV/taRvRGRe/CHcygK3T2hhFuk7/2DwPKwupKOEQDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T19:05:03.100324Z","bundle_sha256":"68b71bb962f8093614c61f63074043e28cadb3eb20b02451d58f49f2bd92b9f8"}}