{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:X32CPSY2QBFZ422QCSCUPPEM3T","short_pith_number":"pith:X32CPSY2","canonical_record":{"source":{"id":"1906.05253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-06-12T17:24:03Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"95a6aeaca0825363dbf266cc4e8742689e953c0b515b2a809f98ae042b103d1a","abstract_canon_sha256":"b9ae168c12d0d17d8c5931bba9c3ca97614a3fdd49033058cfec153479aceb70"},"schema_version":"1.0"},"canonical_sha256":"bef427cb1a804b9e6b50148547bc8cdcca5e1b5381c81711c74455c5b9e88e15","source":{"kind":"arxiv","id":"1906.05253","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05253","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05253v1","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05253","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"X32CPSY2QBFZ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"X32CPSY2QBFZ422Q","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"X32CPSY2","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:X32CPSY2QBFZ422QCSCUPPEM3T","target":"record","payload":{"canonical_record":{"source":{"id":"1906.05253","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-06-12T17:24:03Z","cross_cats_sorted":["cs.LG","cs.RO"],"title_canon_sha256":"95a6aeaca0825363dbf266cc4e8742689e953c0b515b2a809f98ae042b103d1a","abstract_canon_sha256":"b9ae168c12d0d17d8c5931bba9c3ca97614a3fdd49033058cfec153479aceb70"},"schema_version":"1.0"},"canonical_sha256":"bef427cb1a804b9e6b50148547bc8cdcca5e1b5381c81711c74455c5b9e88e15","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:29.050225Z","signature_b64":"VaE2+rR8zuucSOkCohCa/p/Y1uh+hobyHSxaCX6jdA3pS3A71ZgtxbmlCSYfodjeGMjdywFOGbj0aRbYWW7WAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bef427cb1a804b9e6b50148547bc8cdcca5e1b5381c81711c74455c5b9e88e15","last_reissued_at":"2026-05-17T23:43:29.049521Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:29.049521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.05253","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":"2026-05-17T23:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nlDD/5pU8MdKGUgcONwjyW4oZlnECcely9wkQ86Iw5JqrviN6hSUuLw50s85OZjER76tmD9GNzsstXiPSqjIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:34:23.489596Z"},"content_sha256":"ac9e1980ddceca70b6f3682a5421f749cd6cb37d54478eafb06d5a9eb3ed1125","schema_version":"1.0","event_id":"sha256:ac9e1980ddceca70b6f3682a5421f749cd6cb37d54478eafb06d5a9eb3ed1125"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:X32CPSY2QBFZ422QCSCUPPEM3T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.RO"],"primary_cat":"cs.AI","authors_text":"Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine","submitted_at":"2019-06-12T17:24:03Z","abstract_excerpt":"The history of learning for control has been an exciting back and forth between two broad classes of algorithms: planning and reinforcement learning. Planning algorithms effectively reason over long horizons, but assume access to a local policy and distance metric over collision-free paths. Reinforcement learning excels at learning policies and the relative values of states, but fails to plan over long horizons. Despite the successes of each method in various domains, tasks that require reasoning over long horizons with limited feedback and high-dimensional observations remain exceedingly chal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05253","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":""},"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":"2026-05-17T23:43:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vfvrHA8OkAcPqRnn9V0v5zKHeVLC52oQR7xs3OT7XUg2QQAWF8wm3pM9E7meUOVBZE8M9Cg68nmVm481fGnBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T07:34:23.490196Z"},"content_sha256":"0ce4f6df527e1d40400cdf7966e660ac001a77fb625e83f0e15415bda36b448b","schema_version":"1.0","event_id":"sha256:0ce4f6df527e1d40400cdf7966e660ac001a77fb625e83f0e15415bda36b448b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X32CPSY2QBFZ422QCSCUPPEM3T/bundle.json","state_url":"https://pith.science/pith/X32CPSY2QBFZ422QCSCUPPEM3T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X32CPSY2QBFZ422QCSCUPPEM3T/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":"2026-05-27T07:34:23Z","links":{"resolver":"https://pith.science/pith/X32CPSY2QBFZ422QCSCUPPEM3T","bundle":"https://pith.science/pith/X32CPSY2QBFZ422QCSCUPPEM3T/bundle.json","state":"https://pith.science/pith/X32CPSY2QBFZ422QCSCUPPEM3T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X32CPSY2QBFZ422QCSCUPPEM3T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:X32CPSY2QBFZ422QCSCUPPEM3T","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":"b9ae168c12d0d17d8c5931bba9c3ca97614a3fdd49033058cfec153479aceb70","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-06-12T17:24:03Z","title_canon_sha256":"95a6aeaca0825363dbf266cc4e8742689e953c0b515b2a809f98ae042b103d1a"},"schema_version":"1.0","source":{"id":"1906.05253","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05253","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05253v1","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05253","created_at":"2026-05-17T23:43:29Z"},{"alias_kind":"pith_short_12","alias_value":"X32CPSY2QBFZ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"X32CPSY2QBFZ422Q","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"X32CPSY2","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:0ce4f6df527e1d40400cdf7966e660ac001a77fb625e83f0e15415bda36b448b","target":"graph","created_at":"2026-05-17T23:43:29Z","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":"The history of learning for control has been an exciting back and forth between two broad classes of algorithms: planning and reinforcement learning. Planning algorithms effectively reason over long horizons, but assume access to a local policy and distance metric over collision-free paths. Reinforcement learning excels at learning policies and the relative values of states, but fails to plan over long horizons. Despite the successes of each method in various domains, tasks that require reasoning over long horizons with limited feedback and high-dimensional observations remain exceedingly chal","authors_text":"Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-06-12T17:24:03Z","title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05253","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:ac9e1980ddceca70b6f3682a5421f749cd6cb37d54478eafb06d5a9eb3ed1125","target":"record","created_at":"2026-05-17T23:43:29Z","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":"b9ae168c12d0d17d8c5931bba9c3ca97614a3fdd49033058cfec153479aceb70","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-06-12T17:24:03Z","title_canon_sha256":"95a6aeaca0825363dbf266cc4e8742689e953c0b515b2a809f98ae042b103d1a"},"schema_version":"1.0","source":{"id":"1906.05253","kind":"arxiv","version":1}},"canonical_sha256":"bef427cb1a804b9e6b50148547bc8cdcca5e1b5381c81711c74455c5b9e88e15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bef427cb1a804b9e6b50148547bc8cdcca5e1b5381c81711c74455c5b9e88e15","first_computed_at":"2026-05-17T23:43:29.049521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:29.049521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VaE2+rR8zuucSOkCohCa/p/Y1uh+hobyHSxaCX6jdA3pS3A71ZgtxbmlCSYfodjeGMjdywFOGbj0aRbYWW7WAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:29.050225Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.05253","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac9e1980ddceca70b6f3682a5421f749cd6cb37d54478eafb06d5a9eb3ed1125","sha256:0ce4f6df527e1d40400cdf7966e660ac001a77fb625e83f0e15415bda36b448b"],"state_sha256":"b2654b9633e7b997adba697da59618667f95057a5ce083c254ffd89fca767e69"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3/5Mb+NPvOiz0h6VzL7+cwtHjRbdcLr2zytIdDdM9v2za8FggnzLbWbVAwQ8anloQiT057cjeXv0GDu3JLdCAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T07:34:23.493454Z","bundle_sha256":"19f450238d4e38c4e4549c63d761b39d9bfbce6f68540d94fbe1319432164b30"}}