{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YX2RRSKOGXEZGOUNEZF6EJMHWE","short_pith_number":"pith:YX2RRSKO","canonical_record":{"source":{"id":"2410.18082","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T17:59:52Z","cross_cats_sorted":[],"title_canon_sha256":"ec0c122c36a4a7daf17fa8aeca279b71f2bcfbb12f9167ea2fa1bb9a8fdfa1c0","abstract_canon_sha256":"30c3c93ddf63fbb134475792f4a05ae3dc93017bded846759c2a6f839c432174"},"schema_version":"1.0"},"canonical_sha256":"c5f518c94e35c9933a8d264be22587b1027241cce83994203dc5201944eacb82","source":{"kind":"arxiv","id":"2410.18082","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18082","created_at":"2026-07-05T11:00:39Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18082v2","created_at":"2026-07-05T11:00:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18082","created_at":"2026-07-05T11:00:39Z"},{"alias_kind":"pith_short_12","alias_value":"YX2RRSKOGXEZ","created_at":"2026-07-05T11:00:39Z"},{"alias_kind":"pith_short_16","alias_value":"YX2RRSKOGXEZGOUN","created_at":"2026-07-05T11:00:39Z"},{"alias_kind":"pith_short_8","alias_value":"YX2RRSKO","created_at":"2026-07-05T11:00:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YX2RRSKOGXEZGOUNEZF6EJMHWE","target":"record","payload":{"canonical_record":{"source":{"id":"2410.18082","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T17:59:52Z","cross_cats_sorted":[],"title_canon_sha256":"ec0c122c36a4a7daf17fa8aeca279b71f2bcfbb12f9167ea2fa1bb9a8fdfa1c0","abstract_canon_sha256":"30c3c93ddf63fbb134475792f4a05ae3dc93017bded846759c2a6f839c432174"},"schema_version":"1.0"},"canonical_sha256":"c5f518c94e35c9933a8d264be22587b1027241cce83994203dc5201944eacb82","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:00:39.821271Z","signature_b64":"2PWeJ8D1m/KduwwZaqaqZ+/x43jqyUlBEkK7tKsIQNuNHa7W5O0GOrakIRzY/so+JgiHm10TQIumHigQU1U8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5f518c94e35c9933a8d264be22587b1027241cce83994203dc5201944eacb82","last_reissued_at":"2026-07-05T11:00:39.820798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:00:39.820798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.18082","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:00:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uTUCC76XbY9rB8ZG6ch8nwYTUapJ7jM8vhkmOK7MFSKw5ECOllyIus5JG9/yvYAK/rnHb/5+sq5fAak7K0OYDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T15:23:03.135173Z"},"content_sha256":"72c6d3c79e4db8c64c72c4a73af86f8a7a3818ad99eadb1ea04f6031f81e3733","schema_version":"1.0","event_id":"sha256:72c6d3c79e4db8c64c72c4a73af86f8a7a3818ad99eadb1ea04f6031f81e3733"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YX2RRSKOGXEZGOUNEZF6EJMHWE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prioritized Generative Replay","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexei A. Efros, Kevin Frans, Pieter Abbeel, Renhao Wang, Sergey Levine","submitted_at":"2024-10-23T17:59:52Z","abstract_excerpt":"Sample-efficient online reinforcement learning often uses replay buffers to store experience for reuse when updating the value function. However, uniform replay is inefficient, since certain classes of transitions can be more relevant to learning. While prioritization of more useful samples is helpful, this strategy can also lead to overfitting, as useful samples are likely to be more rare. In this work, we instead propose a prioritized, parametric version of an agent's memory, using generative models to capture online experience. This paradigm enables (1) densification of past experience, wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18082","kind":"arxiv","version":2},"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/2410.18082/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":"2026-07-05T11:00:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PBgA85FtUyQAFtiZJ9+3kaQtalqtOgCdUgFHYbzq5SEyaWFj5ZzEAqIEyjNOAIP2JIKkbvw9UxpQpbV4vk5aBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T15:23:03.135480Z"},"content_sha256":"30707bb4aa322dd45c1196c221e28bb7669abac1bc868318c978994838fcc521","schema_version":"1.0","event_id":"sha256:30707bb4aa322dd45c1196c221e28bb7669abac1bc868318c978994838fcc521"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YX2RRSKOGXEZGOUNEZF6EJMHWE/bundle.json","state_url":"https://pith.science/pith/YX2RRSKOGXEZGOUNEZF6EJMHWE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YX2RRSKOGXEZGOUNEZF6EJMHWE/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":"2026-07-31T15:23:03Z","links":{"resolver":"https://pith.science/pith/YX2RRSKOGXEZGOUNEZF6EJMHWE","bundle":"https://pith.science/pith/YX2RRSKOGXEZGOUNEZF6EJMHWE/bundle.json","state":"https://pith.science/pith/YX2RRSKOGXEZGOUNEZF6EJMHWE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YX2RRSKOGXEZGOUNEZF6EJMHWE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YX2RRSKOGXEZGOUNEZF6EJMHWE","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":"30c3c93ddf63fbb134475792f4a05ae3dc93017bded846759c2a6f839c432174","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T17:59:52Z","title_canon_sha256":"ec0c122c36a4a7daf17fa8aeca279b71f2bcfbb12f9167ea2fa1bb9a8fdfa1c0"},"schema_version":"1.0","source":{"id":"2410.18082","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18082","created_at":"2026-07-05T11:00:39Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18082v2","created_at":"2026-07-05T11:00:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18082","created_at":"2026-07-05T11:00:39Z"},{"alias_kind":"pith_short_12","alias_value":"YX2RRSKOGXEZ","created_at":"2026-07-05T11:00:39Z"},{"alias_kind":"pith_short_16","alias_value":"YX2RRSKOGXEZGOUN","created_at":"2026-07-05T11:00:39Z"},{"alias_kind":"pith_short_8","alias_value":"YX2RRSKO","created_at":"2026-07-05T11:00:39Z"}],"graph_snapshots":[{"event_id":"sha256:30707bb4aa322dd45c1196c221e28bb7669abac1bc868318c978994838fcc521","target":"graph","created_at":"2026-07-05T11:00:39Z","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/2410.18082/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sample-efficient online reinforcement learning often uses replay buffers to store experience for reuse when updating the value function. However, uniform replay is inefficient, since certain classes of transitions can be more relevant to learning. While prioritization of more useful samples is helpful, this strategy can also lead to overfitting, as useful samples are likely to be more rare. In this work, we instead propose a prioritized, parametric version of an agent's memory, using generative models to capture online experience. This paradigm enables (1) densification of past experience, wit","authors_text":"Alexei A. Efros, Kevin Frans, Pieter Abbeel, Renhao Wang, Sergey Levine","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T17:59:52Z","title":"Prioritized Generative Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18082","kind":"arxiv","version":2},"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":"sha256:72c6d3c79e4db8c64c72c4a73af86f8a7a3818ad99eadb1ea04f6031f81e3733","target":"record","created_at":"2026-07-05T11:00:39Z","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":"30c3c93ddf63fbb134475792f4a05ae3dc93017bded846759c2a6f839c432174","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-23T17:59:52Z","title_canon_sha256":"ec0c122c36a4a7daf17fa8aeca279b71f2bcfbb12f9167ea2fa1bb9a8fdfa1c0"},"schema_version":"1.0","source":{"id":"2410.18082","kind":"arxiv","version":2}},"canonical_sha256":"c5f518c94e35c9933a8d264be22587b1027241cce83994203dc5201944eacb82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5f518c94e35c9933a8d264be22587b1027241cce83994203dc5201944eacb82","first_computed_at":"2026-07-05T11:00:39.820798Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:39.820798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2PWeJ8D1m/KduwwZaqaqZ+/x43jqyUlBEkK7tKsIQNuNHa7W5O0GOrakIRzY/so+JgiHm10TQIumHigQU1U8Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:39.821271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18082","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:72c6d3c79e4db8c64c72c4a73af86f8a7a3818ad99eadb1ea04f6031f81e3733","sha256:30707bb4aa322dd45c1196c221e28bb7669abac1bc868318c978994838fcc521"],"state_sha256":"1e2cdb505c173f4aca55ecca59defb54206e00e14a2836764049345f6f02f375"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nvxccwKq9LAnJjtED1MRCI7PCEOTxFl9Ts0e6rhN3k36zRKyPBU2/s0gimeAEPLRao1ZIxzKVfXaUgW+bdpLAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T15:23:03.138117Z","bundle_sha256":"48e7aac6397f24c0b64c1a7d13a3a7e952d5c8ab23f3b00eeccaeef98f146f06"}}