{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:TI3NK364C3PETPRVUR3Q5INJ22","short_pith_number":"pith:TI3NK364","canonical_record":{"source":{"id":"2303.06614","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-12T09:10:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"421d57ff832057f231da131a929b492ce8e152fac6164a02d76d360ef0e5864e","abstract_canon_sha256":"7cb64fcf33e463613200846b714627d5144420bc6dea0a6f95f38136a73f5c43"},"schema_version":"1.0"},"canonical_sha256":"9a36d56fdc16de49be35a4770ea1a9d680ceefc8c17ade617bd2c618132f8273","source":{"kind":"arxiv","id":"2303.06614","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.06614","created_at":"2026-07-05T07:05:41Z"},{"alias_kind":"arxiv_version","alias_value":"2303.06614v4","created_at":"2026-07-05T07:05:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06614","created_at":"2026-07-05T07:05:41Z"},{"alias_kind":"pith_short_12","alias_value":"TI3NK364C3PE","created_at":"2026-07-05T07:05:41Z"},{"alias_kind":"pith_short_16","alias_value":"TI3NK364C3PETPRV","created_at":"2026-07-05T07:05:41Z"},{"alias_kind":"pith_short_8","alias_value":"TI3NK364","created_at":"2026-07-05T07:05:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:TI3NK364C3PETPRVUR3Q5INJ22","target":"record","payload":{"canonical_record":{"source":{"id":"2303.06614","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-12T09:10:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"421d57ff832057f231da131a929b492ce8e152fac6164a02d76d360ef0e5864e","abstract_canon_sha256":"7cb64fcf33e463613200846b714627d5144420bc6dea0a6f95f38136a73f5c43"},"schema_version":"1.0"},"canonical_sha256":"9a36d56fdc16de49be35a4770ea1a9d680ceefc8c17ade617bd2c618132f8273","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:41.744505Z","signature_b64":"7zE4fJpGr7PQKiSehvx1Dz7hbC+PZON+M1tIVCK70P61WnNeWgvlAvpsTLhzMe9NTZPChIqcjPIYxAbSe/4WCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a36d56fdc16de49be35a4770ea1a9d680ceefc8c17ade617bd2c618132f8273","last_reissued_at":"2026-07-05T07:05:41.743998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:41.743998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.06614","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":"2026-07-05T07:05:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jPm2ih8yVCABeogcbDiQLXPSuArliWTln5JJ2q3+uNUOM4FABtAZ5lR672kd0BROKknSkVLVhshNBkA8jXK8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T15:00:59.795677Z"},"content_sha256":"7b59939f0451ff0005cc490064a1036ab077fd06ede1917d9974e6b527e4fa63","schema_version":"1.0","event_id":"sha256:7b59939f0451ff0005cc490064a1036ab077fd06ede1917d9974e6b527e4fa63"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:TI3NK364C3PETPRVUR3Q5INJ22","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synthetic Experience Replay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cong Lu, Jack Parker-Holder, Philip J. Ball, Yee Whye Teh","submitted_at":"2023-03-12T09:10:45Z","abstract_excerpt":"A key theme in the past decade has been that when large neural networks and large datasets combine they can produce remarkable results. In deep reinforcement learning (RL), this paradigm is commonly made possible through experience replay, whereby a dataset of past experiences is used to train a policy or value function. However, unlike in supervised or self-supervised learning, an RL agent has to collect its own data, which is often limited. Thus, it is challenging to reap the benefits of deep learning, and even small neural networks can overfit at the start of training. In this work, we leve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06614","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2303.06614/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":"2026-07-05T07:05:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3vS/PXpGSbRi4MAjffTsmiamGeZCH6rdHtG2JakNJRzrEviYV2bcyZaMQgvFE07OS08tq9D+MBDdQU4HNkHQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T15:00:59.796023Z"},"content_sha256":"ac33ba70c1e0d6b4427c9a7d0bafd17ad8191104833fa300be1ef341d206b5b5","schema_version":"1.0","event_id":"sha256:ac33ba70c1e0d6b4427c9a7d0bafd17ad8191104833fa300be1ef341d206b5b5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TI3NK364C3PETPRVUR3Q5INJ22/bundle.json","state_url":"https://pith.science/pith/TI3NK364C3PETPRVUR3Q5INJ22/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TI3NK364C3PETPRVUR3Q5INJ22/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":"2026-07-31T15:00:59Z","links":{"resolver":"https://pith.science/pith/TI3NK364C3PETPRVUR3Q5INJ22","bundle":"https://pith.science/pith/TI3NK364C3PETPRVUR3Q5INJ22/bundle.json","state":"https://pith.science/pith/TI3NK364C3PETPRVUR3Q5INJ22/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TI3NK364C3PETPRVUR3Q5INJ22/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TI3NK364C3PETPRVUR3Q5INJ22","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":"7cb64fcf33e463613200846b714627d5144420bc6dea0a6f95f38136a73f5c43","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-12T09:10:45Z","title_canon_sha256":"421d57ff832057f231da131a929b492ce8e152fac6164a02d76d360ef0e5864e"},"schema_version":"1.0","source":{"id":"2303.06614","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.06614","created_at":"2026-07-05T07:05:41Z"},{"alias_kind":"arxiv_version","alias_value":"2303.06614v4","created_at":"2026-07-05T07:05:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06614","created_at":"2026-07-05T07:05:41Z"},{"alias_kind":"pith_short_12","alias_value":"TI3NK364C3PE","created_at":"2026-07-05T07:05:41Z"},{"alias_kind":"pith_short_16","alias_value":"TI3NK364C3PETPRV","created_at":"2026-07-05T07:05:41Z"},{"alias_kind":"pith_short_8","alias_value":"TI3NK364","created_at":"2026-07-05T07:05:41Z"}],"graph_snapshots":[{"event_id":"sha256:ac33ba70c1e0d6b4427c9a7d0bafd17ad8191104833fa300be1ef341d206b5b5","target":"graph","created_at":"2026-07-05T07:05:41Z","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/2303.06614/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A key theme in the past decade has been that when large neural networks and large datasets combine they can produce remarkable results. In deep reinforcement learning (RL), this paradigm is commonly made possible through experience replay, whereby a dataset of past experiences is used to train a policy or value function. However, unlike in supervised or self-supervised learning, an RL agent has to collect its own data, which is often limited. Thus, it is challenging to reap the benefits of deep learning, and even small neural networks can overfit at the start of training. In this work, we leve","authors_text":"Cong Lu, Jack Parker-Holder, Philip J. Ball, Yee Whye Teh","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-12T09:10:45Z","title":"Synthetic Experience Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06614","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":"sha256:7b59939f0451ff0005cc490064a1036ab077fd06ede1917d9974e6b527e4fa63","target":"record","created_at":"2026-07-05T07:05:41Z","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":"7cb64fcf33e463613200846b714627d5144420bc6dea0a6f95f38136a73f5c43","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-12T09:10:45Z","title_canon_sha256":"421d57ff832057f231da131a929b492ce8e152fac6164a02d76d360ef0e5864e"},"schema_version":"1.0","source":{"id":"2303.06614","kind":"arxiv","version":4}},"canonical_sha256":"9a36d56fdc16de49be35a4770ea1a9d680ceefc8c17ade617bd2c618132f8273","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a36d56fdc16de49be35a4770ea1a9d680ceefc8c17ade617bd2c618132f8273","first_computed_at":"2026-07-05T07:05:41.743998Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:41.743998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7zE4fJpGr7PQKiSehvx1Dz7hbC+PZON+M1tIVCK70P61WnNeWgvlAvpsTLhzMe9NTZPChIqcjPIYxAbSe/4WCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:41.744505Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.06614","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7b59939f0451ff0005cc490064a1036ab077fd06ede1917d9974e6b527e4fa63","sha256:ac33ba70c1e0d6b4427c9a7d0bafd17ad8191104833fa300be1ef341d206b5b5"],"state_sha256":"3b0c7f350fd02b0ab342ebbc8fd5d1e1a013377d500f620b5bbf1e87a9b6cb76"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GbO7huP1eE7tJopFg5GbHnD1HrwgiJpIZGuynyIgzHvB+bBLaa3Ltd3PnGm4yLWlgTwOfuGWp4MB0xwGU0OPDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T15:00:59.801156Z","bundle_sha256":"b9547ff6a838d14c2610fe33846ac8a7459eb4b4aed424a93c98d4ac653f7d31"}}