{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7DGB6UFK5WCMAJHPT7BEP3WTFI","short_pith_number":"pith:7DGB6UFK","canonical_record":{"source":{"id":"2407.09702","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-12T21:56:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7758d25925d7d20f79283bba6ac06ac98e5c9e857b50e39c53f4562856253bd2","abstract_canon_sha256":"a4e836240e32b20996a4b9b426a8d62f5dfb250f7de2cbee9f1615714870fe9b"},"schema_version":"1.0"},"canonical_sha256":"f8cc1f50aaed84c024ef9fc247eed32a0f848f90f57d7e2daed17c91873b45c9","source":{"kind":"arxiv","id":"2407.09702","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09702","created_at":"2026-07-05T09:22:41Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09702v2","created_at":"2026-07-05T09:22:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09702","created_at":"2026-07-05T09:22:41Z"},{"alias_kind":"pith_short_12","alias_value":"7DGB6UFK5WCM","created_at":"2026-07-05T09:22:41Z"},{"alias_kind":"pith_short_16","alias_value":"7DGB6UFK5WCMAJHP","created_at":"2026-07-05T09:22:41Z"},{"alias_kind":"pith_short_8","alias_value":"7DGB6UFK","created_at":"2026-07-05T09:22:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7DGB6UFK5WCMAJHPT7BEP3WTFI","target":"record","payload":{"canonical_record":{"source":{"id":"2407.09702","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-12T21:56:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7758d25925d7d20f79283bba6ac06ac98e5c9e857b50e39c53f4562856253bd2","abstract_canon_sha256":"a4e836240e32b20996a4b9b426a8d62f5dfb250f7de2cbee9f1615714870fe9b"},"schema_version":"1.0"},"canonical_sha256":"f8cc1f50aaed84c024ef9fc247eed32a0f848f90f57d7e2daed17c91873b45c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:41.229204Z","signature_b64":"zYo1HvmWdRmdcftYkoohrWmJ9XpQW4DjWSC0UQoTxiofW2aZrqeweGkD1EQyxrgUm0HTj5yvgAiFHSir8aN1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8cc1f50aaed84c024ef9fc247eed32a0f848f90f57d7e2daed17c91873b45c9","last_reissued_at":"2026-07-05T09:22:41.228734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:41.228734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.09702","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":"2026-07-05T09:22:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3Q5ejbpGeqnpPTDbocy8XknHac3jpSxqbkFm1inN6oMk9t5UFUXSySyl4zpuXUQLxvTC/p7HLGc3ZMBmGuNtAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:24:11.617436Z"},"content_sha256":"92019c1726f0b7f7bbcb83b8e0ff3b6ccbc98209357c540372e6f7f6a8b19235","schema_version":"1.0","event_id":"sha256:92019c1726f0b7f7bbcb83b8e0ff3b6ccbc98209357c540372e6f7f6a8b19235"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7DGB6UFK5WCMAJHPT7BEP3WTFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating the Interplay of Prioritized Replay and Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adam White, Andrew Patterson, Martha White, Parham Mohammad Panahi","submitted_at":"2024-07-12T21:56:24Z","abstract_excerpt":"Experience replay, the reuse of past data to improve sample efficiency, is ubiquitous in reinforcement learning. Though a variety of smart sampling schemes have been introduced to improve performance, uniform sampling by far remains the most common approach. One exception is Prioritized Experience Replay (PER), where sampling is done proportionally to TD errors, inspired by the success of prioritized sweeping in dynamic programming. The original work on PER showed improvements in Atari, but follow-up results were mixed. In this paper, we investigate several variations on PER, to attempt to und"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09702","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/2407.09702/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":"2026-07-05T09:22:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SiroTZhRPfM1XPYE+fiY6MEE6nqU8Jq9CNRktr5jHXmBc+9sF0MvXhmYIAb330VUCQn2LQSkmbha3z6PWpx2Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:24:11.617934Z"},"content_sha256":"a97a57c6bdd5973a28842bfe4968efd04e7222523e3c27860abbf3bcc3e69abd","schema_version":"1.0","event_id":"sha256:a97a57c6bdd5973a28842bfe4968efd04e7222523e3c27860abbf3bcc3e69abd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7DGB6UFK5WCMAJHPT7BEP3WTFI/bundle.json","state_url":"https://pith.science/pith/7DGB6UFK5WCMAJHPT7BEP3WTFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7DGB6UFK5WCMAJHPT7BEP3WTFI/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":"2026-08-15T18:24:11Z","links":{"resolver":"https://pith.science/pith/7DGB6UFK5WCMAJHPT7BEP3WTFI","bundle":"https://pith.science/pith/7DGB6UFK5WCMAJHPT7BEP3WTFI/bundle.json","state":"https://pith.science/pith/7DGB6UFK5WCMAJHPT7BEP3WTFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7DGB6UFK5WCMAJHPT7BEP3WTFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7DGB6UFK5WCMAJHPT7BEP3WTFI","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":"a4e836240e32b20996a4b9b426a8d62f5dfb250f7de2cbee9f1615714870fe9b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-12T21:56:24Z","title_canon_sha256":"7758d25925d7d20f79283bba6ac06ac98e5c9e857b50e39c53f4562856253bd2"},"schema_version":"1.0","source":{"id":"2407.09702","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09702","created_at":"2026-07-05T09:22:41Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09702v2","created_at":"2026-07-05T09:22:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09702","created_at":"2026-07-05T09:22:41Z"},{"alias_kind":"pith_short_12","alias_value":"7DGB6UFK5WCM","created_at":"2026-07-05T09:22:41Z"},{"alias_kind":"pith_short_16","alias_value":"7DGB6UFK5WCMAJHP","created_at":"2026-07-05T09:22:41Z"},{"alias_kind":"pith_short_8","alias_value":"7DGB6UFK","created_at":"2026-07-05T09:22:41Z"}],"graph_snapshots":[{"event_id":"sha256:a97a57c6bdd5973a28842bfe4968efd04e7222523e3c27860abbf3bcc3e69abd","target":"graph","created_at":"2026-07-05T09:22:41Z","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/2407.09702/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Experience replay, the reuse of past data to improve sample efficiency, is ubiquitous in reinforcement learning. Though a variety of smart sampling schemes have been introduced to improve performance, uniform sampling by far remains the most common approach. One exception is Prioritized Experience Replay (PER), where sampling is done proportionally to TD errors, inspired by the success of prioritized sweeping in dynamic programming. The original work on PER showed improvements in Atari, but follow-up results were mixed. In this paper, we investigate several variations on PER, to attempt to und","authors_text":"Adam White, Andrew Patterson, Martha White, Parham Mohammad Panahi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-12T21:56:24Z","title":"Investigating the Interplay of Prioritized Replay and Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09702","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":"sha256:92019c1726f0b7f7bbcb83b8e0ff3b6ccbc98209357c540372e6f7f6a8b19235","target":"record","created_at":"2026-07-05T09:22:41Z","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":"a4e836240e32b20996a4b9b426a8d62f5dfb250f7de2cbee9f1615714870fe9b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-12T21:56:24Z","title_canon_sha256":"7758d25925d7d20f79283bba6ac06ac98e5c9e857b50e39c53f4562856253bd2"},"schema_version":"1.0","source":{"id":"2407.09702","kind":"arxiv","version":2}},"canonical_sha256":"f8cc1f50aaed84c024ef9fc247eed32a0f848f90f57d7e2daed17c91873b45c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8cc1f50aaed84c024ef9fc247eed32a0f848f90f57d7e2daed17c91873b45c9","first_computed_at":"2026-07-05T09:22:41.228734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:41.228734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zYo1HvmWdRmdcftYkoohrWmJ9XpQW4DjWSC0UQoTxiofW2aZrqeweGkD1EQyxrgUm0HTj5yvgAiFHSir8aN1CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:41.229204Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.09702","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92019c1726f0b7f7bbcb83b8e0ff3b6ccbc98209357c540372e6f7f6a8b19235","sha256:a97a57c6bdd5973a28842bfe4968efd04e7222523e3c27860abbf3bcc3e69abd"],"state_sha256":"9f43748311aff1f7987649b4a0e7c7b7027e1a1973742d488165c7dc6d6795f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dt8O9wViollksRWf23FLc7s4uZCVeVswTEmzNUhdhayNXw4pOIocrcnwQ0HqztZbXJ3kKTej/OJfZfWGvfwmBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T18:24:11.623189Z","bundle_sha256":"27c320ac92ed42819bbc847c1d9f0968228ac4f9cd9b03b0fe02414878c4eed7"}}