{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DTUPU4YPWBVOSXHAUETU2SFEGN","short_pith_number":"pith:DTUPU4YP","canonical_record":{"source":{"id":"2605.10236","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T09:11:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c552ff302da0820dc38cc0a64a17100907ea6d70298f50f5faaf1c656cedb6a3","abstract_canon_sha256":"620bf1ffe50dbaacaa7a9d4a62ea8c89e696204990ecc4b3b8aa6e570113787f"},"schema_version":"1.0"},"canonical_sha256":"1ce8fa730fb06ae95ce0a1274d48a43342064e3026b1f2dac2fc69a8a17b28f2","source":{"kind":"arxiv","id":"2605.10236","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10236","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10236v3","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10236","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"DTUPU4YPWBVO","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"DTUPU4YPWBVOSXHA","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"DTUPU4YP","created_at":"2026-05-20T00:04:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DTUPU4YPWBVOSXHAUETU2SFEGN","target":"record","payload":{"canonical_record":{"source":{"id":"2605.10236","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T09:11:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c552ff302da0820dc38cc0a64a17100907ea6d70298f50f5faaf1c656cedb6a3","abstract_canon_sha256":"620bf1ffe50dbaacaa7a9d4a62ea8c89e696204990ecc4b3b8aa6e570113787f"},"schema_version":"1.0"},"canonical_sha256":"1ce8fa730fb06ae95ce0a1274d48a43342064e3026b1f2dac2fc69a8a17b28f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:35.666398Z","signature_b64":"qzaHc4gXZVKgOLcwqMGaKl1ZEUqF6VdkviiQmR6/S1dOOwJxs/f2TEQRZMVeHWLkBhTX6S/qJaHzZQuBzEk5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ce8fa730fb06ae95ce0a1274d48a43342064e3026b1f2dac2fc69a8a17b28f2","last_reissued_at":"2026-05-20T00:04:35.665186Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:35.665186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.10236","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7pesKzS4A6VEsHcN05l39EBfzQwTrCawBfAXt8ezIaohM0VsCdAIP3xyKQ4Vl3yH0WTBYmkOSAKWxihykMz+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T12:18:43.188054Z"},"content_sha256":"0293627d4f91f9308a190e81f841c71caa175bd8aed7d54e7aaa128bce0925d2","schema_version":"1.0","event_id":"sha256:0293627d4f91f9308a190e81f841c71caa175bd8aed7d54e7aaa128bce0925d2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DTUPU4YPWBVOSXHAUETU2SFEGN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Does Non-Uniform Replay Matter in Reinforcement Learning?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Non-uniform replay improves reinforcement learning sample efficiency mainly when replay volume is low, provided sampling entropy stays high.","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Michal Korniak, Michal Nauman, Miko{\\l}aj Czarnecki, Pieter Abbeel, Piotr Mi{\\l}o\\'s, Yarden As","submitted_at":"2026-05-11T09:11:05Z","abstract_excerpt":"Modern off-policy reinforcement learning algorithms often rely on simple uniform replay sampling and it remains unclear when and why non-uniform replay improves over this strong baseline. Across diverse RL settings, we show that the effectiveness of non-uniform replay is governed by three factors: replay volume, the number of replayed transitions per environment step; expected recency, how recent sampled transitions are; and the entropy of the replay sampling distribution. Our main contribution is clarifying when non-uniform replay is beneficial and providing practical guidance for replay desi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"the effectiveness of non-uniform replay is governed by three factors: replay volume, the number of replayed transitions per environment step; expected recency, how recent sampled transitions are; and the entropy of the replay sampling distribution. ... non-uniform replay is most beneficial when replay volume is low, and that high-entropy sampling is important even at comparable expected recency.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the three identified factors comprehensively govern non-uniform replay effectiveness and that the observed benefits will generalize beyond the specific algorithms, benchmarks, and parallel-simulation regimes tested.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Non-uniform replay improves RL sample efficiency mainly in low replay-volume regimes, with high-entropy sampling being key even at comparable recency.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Non-uniform replay improves reinforcement learning sample efficiency mainly when replay volume is low, provided sampling entropy stays high.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"43df73cedae58c20bca3de2933d49bbd268b878f2e44eb1c7fa06e009cb362a9"},"source":{"id":"2605.10236","kind":"arxiv","version":3},"verdict":{"id":"7d7639d2-4b3a-4ee5-a83f-d74534203b2e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T06:22:47.019414Z","strongest_claim":"the effectiveness of non-uniform replay is governed by three factors: replay volume, the number of replayed transitions per environment step; expected recency, how recent sampled transitions are; and the entropy of the replay sampling distribution. ... non-uniform replay is most beneficial when replay volume is low, and that high-entropy sampling is important even at comparable expected recency.","one_line_summary":"Non-uniform replay improves RL sample efficiency mainly in low replay-volume regimes, with high-entropy sampling being key even at comparable recency.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the three identified factors comprehensively govern non-uniform replay effectiveness and that the observed benefits will generalize beyond the specific algorithms, benchmarks, and parallel-simulation regimes tested.","pith_extraction_headline":"Non-uniform replay improves reinforcement learning sample efficiency mainly when replay volume is low, provided sampling entropy stays high."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10236/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T15:38:10.202722Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T11:31:19.746771Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:33:47.881786Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9ad6adbe4ce54f729447c63461f7ce37017431aba2fc990d1fa3e8848f8c5734"},"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":"7d7639d2-4b3a-4ee5-a83f-d74534203b2e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rJyXHxaepBjY2zXNPwkXJxVimOFSa2mdl53jO4FJfOFkvasJyQO+57kgVxHWqLMHtSCA62EQCRefWdq7WbjsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T12:18:43.188633Z"},"content_sha256":"a4147cc1e6b87e8d4d9f787ff03c5387aef062cc0e91e17a57869cabac1936da","schema_version":"1.0","event_id":"sha256:a4147cc1e6b87e8d4d9f787ff03c5387aef062cc0e91e17a57869cabac1936da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DTUPU4YPWBVOSXHAUETU2SFEGN/bundle.json","state_url":"https://pith.science/pith/DTUPU4YPWBVOSXHAUETU2SFEGN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DTUPU4YPWBVOSXHAUETU2SFEGN/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":"2026-05-31T12:18:43Z","links":{"resolver":"https://pith.science/pith/DTUPU4YPWBVOSXHAUETU2SFEGN","bundle":"https://pith.science/pith/DTUPU4YPWBVOSXHAUETU2SFEGN/bundle.json","state":"https://pith.science/pith/DTUPU4YPWBVOSXHAUETU2SFEGN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DTUPU4YPWBVOSXHAUETU2SFEGN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DTUPU4YPWBVOSXHAUETU2SFEGN","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":"620bf1ffe50dbaacaa7a9d4a62ea8c89e696204990ecc4b3b8aa6e570113787f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T09:11:05Z","title_canon_sha256":"c552ff302da0820dc38cc0a64a17100907ea6d70298f50f5faaf1c656cedb6a3"},"schema_version":"1.0","source":{"id":"2605.10236","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10236","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10236v3","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10236","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"DTUPU4YPWBVO","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"DTUPU4YPWBVOSXHA","created_at":"2026-05-20T00:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"DTUPU4YP","created_at":"2026-05-20T00:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:a4147cc1e6b87e8d4d9f787ff03c5387aef062cc0e91e17a57869cabac1936da","target":"graph","created_at":"2026-05-20T00:04:35Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"the effectiveness of non-uniform replay is governed by three factors: replay volume, the number of replayed transitions per environment step; expected recency, how recent sampled transitions are; and the entropy of the replay sampling distribution. ... non-uniform replay is most beneficial when replay volume is low, and that high-entropy sampling is important even at comparable expected recency."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the three identified factors comprehensively govern non-uniform replay effectiveness and that the observed benefits will generalize beyond the specific algorithms, benchmarks, and parallel-simulation regimes tested."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Non-uniform replay improves RL sample efficiency mainly in low replay-volume regimes, with high-entropy sampling being key even at comparable recency."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Non-uniform replay improves reinforcement learning sample efficiency mainly when replay volume is low, provided sampling entropy stays high."}],"snapshot_sha256":"43df73cedae58c20bca3de2933d49bbd268b878f2e44eb1c7fa06e009cb362a9"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T15:38:10.202722Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T11:31:19.746771Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T09:33:47.881786Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.10236/integrity.json","findings":[],"snapshot_sha256":"9ad6adbe4ce54f729447c63461f7ce37017431aba2fc990d1fa3e8848f8c5734","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern off-policy reinforcement learning algorithms often rely on simple uniform replay sampling and it remains unclear when and why non-uniform replay improves over this strong baseline. Across diverse RL settings, we show that the effectiveness of non-uniform replay is governed by three factors: replay volume, the number of replayed transitions per environment step; expected recency, how recent sampled transitions are; and the entropy of the replay sampling distribution. Our main contribution is clarifying when non-uniform replay is beneficial and providing practical guidance for replay desi","authors_text":"Michal Korniak, Michal Nauman, Miko{\\l}aj Czarnecki, Pieter Abbeel, Piotr Mi{\\l}o\\'s, Yarden As","cross_cats":["cs.AI"],"headline":"Non-uniform replay improves reinforcement learning sample efficiency mainly when replay volume is low, provided sampling entropy stays high.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T09:11:05Z","title":"When Does Non-Uniform Replay Matter in Reinforcement Learning?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.10236","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-13T06:22:47.019414Z","id":"7d7639d2-4b3a-4ee5-a83f-d74534203b2e","model_set":{"reader":"grok-4.3"},"one_line_summary":"Non-uniform replay improves RL sample efficiency mainly in low replay-volume regimes, with high-entropy sampling being key even at comparable recency.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Non-uniform replay improves reinforcement learning sample efficiency mainly when replay volume is low, provided sampling entropy stays high.","strongest_claim":"the effectiveness of non-uniform replay is governed by three factors: replay volume, the number of replayed transitions per environment step; expected recency, how recent sampled transitions are; and the entropy of the replay sampling distribution. ... non-uniform replay is most beneficial when replay volume is low, and that high-entropy sampling is important even at comparable expected recency.","weakest_assumption":"That the three identified factors comprehensively govern non-uniform replay effectiveness and that the observed benefits will generalize beyond the specific algorithms, benchmarks, and parallel-simulation regimes tested."}},"verdict_id":"7d7639d2-4b3a-4ee5-a83f-d74534203b2e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0293627d4f91f9308a190e81f841c71caa175bd8aed7d54e7aaa128bce0925d2","target":"record","created_at":"2026-05-20T00:04:35Z","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":"620bf1ffe50dbaacaa7a9d4a62ea8c89e696204990ecc4b3b8aa6e570113787f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-11T09:11:05Z","title_canon_sha256":"c552ff302da0820dc38cc0a64a17100907ea6d70298f50f5faaf1c656cedb6a3"},"schema_version":"1.0","source":{"id":"2605.10236","kind":"arxiv","version":3}},"canonical_sha256":"1ce8fa730fb06ae95ce0a1274d48a43342064e3026b1f2dac2fc69a8a17b28f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ce8fa730fb06ae95ce0a1274d48a43342064e3026b1f2dac2fc69a8a17b28f2","first_computed_at":"2026-05-20T00:04:35.665186Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:35.665186Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qzaHc4gXZVKgOLcwqMGaKl1ZEUqF6VdkviiQmR6/S1dOOwJxs/f2TEQRZMVeHWLkBhTX6S/qJaHzZQuBzEk5Cg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:35.666398Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.10236","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0293627d4f91f9308a190e81f841c71caa175bd8aed7d54e7aaa128bce0925d2","sha256:a4147cc1e6b87e8d4d9f787ff03c5387aef062cc0e91e17a57869cabac1936da"],"state_sha256":"907fa88471bb3ad868e5a52f7d41a08f3775c6406ceaae12e071283425b3b0f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3abB92kcqFmJ1iEVDcZI8pjDbzjJqcwq3/tSXyYvGnLmqGTABP2eeFIEEuGt9CWWjGidMFwtDBQVzywAyh61Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T12:18:43.192308Z","bundle_sha256":"f8b9f634c0f96ed6ef2115b87f23c573fb94964b4dfb28312ace8300da59edc9"}}