{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YGYQ42DQF2HSUD4VJGVPII7DA5","short_pith_number":"pith:YGYQ42DQ","canonical_record":{"source":{"id":"2102.03261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-05T16:09:07Z","cross_cats_sorted":[],"title_canon_sha256":"a8a87fbd1e2aaf66d960fcd7e4831bed67c77da00797f137e0437bfa434291d1","abstract_canon_sha256":"221d1854c3ad68dbd2ef3d9f8ef7825b3ca0c8f812dda81cfbc07499922ec2bc"},"schema_version":"1.0"},"canonical_sha256":"c1b10e68702e8f2a0f9549aaf423e3076a5488f45b4463cba7559b3ac7424905","source":{"kind":"arxiv","id":"2102.03261","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.03261","created_at":"2026-07-05T02:13:07Z"},{"alias_kind":"arxiv_version","alias_value":"2102.03261v1","created_at":"2026-07-05T02:13:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.03261","created_at":"2026-07-05T02:13:07Z"},{"alias_kind":"pith_short_12","alias_value":"YGYQ42DQF2HS","created_at":"2026-07-05T02:13:07Z"},{"alias_kind":"pith_short_16","alias_value":"YGYQ42DQF2HSUD4V","created_at":"2026-07-05T02:13:07Z"},{"alias_kind":"pith_short_8","alias_value":"YGYQ42DQ","created_at":"2026-07-05T02:13:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YGYQ42DQF2HSUD4VJGVPII7DA5","target":"record","payload":{"canonical_record":{"source":{"id":"2102.03261","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-05T16:09:07Z","cross_cats_sorted":[],"title_canon_sha256":"a8a87fbd1e2aaf66d960fcd7e4831bed67c77da00797f137e0437bfa434291d1","abstract_canon_sha256":"221d1854c3ad68dbd2ef3d9f8ef7825b3ca0c8f812dda81cfbc07499922ec2bc"},"schema_version":"1.0"},"canonical_sha256":"c1b10e68702e8f2a0f9549aaf423e3076a5488f45b4463cba7559b3ac7424905","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:13:07.589828Z","signature_b64":"FCjogAkQw4Wa3Ssd02UejmFyTgmenZ3YT2T6bTQjgpFT63Nmdie7pN9yR40KphX32xBPwkjZrGoEQp9VnF6IDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1b10e68702e8f2a0f9549aaf423e3076a5488f45b4463cba7559b3ac7424905","last_reissued_at":"2026-07-05T02:13:07.589457Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:13:07.589457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.03261","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":"2026-07-05T02:13:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6y8WXOxp6Dg9f7j3V61Tk/mWCKSJsbXYp7H8Lx8aksuXRe3e4A6A9CjP69jFxb3pDItVD/QkRwCqmff0LhuTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:44:56.594016Z"},"content_sha256":"7d67bb7c683a8a1b9960623c52390beefd83f55f8efa50fce5e5e8773c53f41a","schema_version":"1.0","event_id":"sha256:7d67bb7c683a8a1b9960623c52390beefd83f55f8efa50fce5e5e8773c53f41a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YGYQ42DQF2HSUD4VJGVPII7DA5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting Prioritized Experience Replay: A Value Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ang A. Li, Chenglin Miao, Zongqing Lu","submitted_at":"2021-02-05T16:09:07Z","abstract_excerpt":"Experience replay enables off-policy reinforcement learning (RL) agents to utilize past experiences to maximize the cumulative reward. Prioritized experience replay that weighs experiences by the magnitude of their temporal-difference error ($|\\text{TD}|$) significantly improves the learning efficiency. But how $|\\text{TD}|$ is related to the importance of experience is not well understood. We address this problem from an economic perspective, by linking $|\\text{TD}|$ to value of experience, which is defined as the value added to the cumulative reward by accessing the experience. We theoretica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.03261","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2102.03261/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":"2026-07-05T02:13:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DbNyKSETuLZCZJnkdwTDHFQHLKhufr77rTW7t/RpxwrFB6NvB343WssQcWFP9087joMY2em33T2h6tYB94KyAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:44:56.594536Z"},"content_sha256":"f008778b14a642e4ac3ab17dfc0cc393fcc002951ddb66fd0b22be726d98d0f8","schema_version":"1.0","event_id":"sha256:f008778b14a642e4ac3ab17dfc0cc393fcc002951ddb66fd0b22be726d98d0f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YGYQ42DQF2HSUD4VJGVPII7DA5/bundle.json","state_url":"https://pith.science/pith/YGYQ42DQF2HSUD4VJGVPII7DA5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YGYQ42DQF2HSUD4VJGVPII7DA5/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":"2026-08-07T22:44:56Z","links":{"resolver":"https://pith.science/pith/YGYQ42DQF2HSUD4VJGVPII7DA5","bundle":"https://pith.science/pith/YGYQ42DQF2HSUD4VJGVPII7DA5/bundle.json","state":"https://pith.science/pith/YGYQ42DQF2HSUD4VJGVPII7DA5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YGYQ42DQF2HSUD4VJGVPII7DA5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YGYQ42DQF2HSUD4VJGVPII7DA5","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":"221d1854c3ad68dbd2ef3d9f8ef7825b3ca0c8f812dda81cfbc07499922ec2bc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-05T16:09:07Z","title_canon_sha256":"a8a87fbd1e2aaf66d960fcd7e4831bed67c77da00797f137e0437bfa434291d1"},"schema_version":"1.0","source":{"id":"2102.03261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.03261","created_at":"2026-07-05T02:13:07Z"},{"alias_kind":"arxiv_version","alias_value":"2102.03261v1","created_at":"2026-07-05T02:13:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.03261","created_at":"2026-07-05T02:13:07Z"},{"alias_kind":"pith_short_12","alias_value":"YGYQ42DQF2HS","created_at":"2026-07-05T02:13:07Z"},{"alias_kind":"pith_short_16","alias_value":"YGYQ42DQF2HSUD4V","created_at":"2026-07-05T02:13:07Z"},{"alias_kind":"pith_short_8","alias_value":"YGYQ42DQ","created_at":"2026-07-05T02:13:07Z"}],"graph_snapshots":[{"event_id":"sha256:f008778b14a642e4ac3ab17dfc0cc393fcc002951ddb66fd0b22be726d98d0f8","target":"graph","created_at":"2026-07-05T02:13:07Z","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/2102.03261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Experience replay enables off-policy reinforcement learning (RL) agents to utilize past experiences to maximize the cumulative reward. Prioritized experience replay that weighs experiences by the magnitude of their temporal-difference error ($|\\text{TD}|$) significantly improves the learning efficiency. But how $|\\text{TD}|$ is related to the importance of experience is not well understood. We address this problem from an economic perspective, by linking $|\\text{TD}|$ to value of experience, which is defined as the value added to the cumulative reward by accessing the experience. We theoretica","authors_text":"Ang A. Li, Chenglin Miao, Zongqing Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-05T16:09:07Z","title":"Revisiting Prioritized Experience Replay: A Value Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.03261","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":"sha256:7d67bb7c683a8a1b9960623c52390beefd83f55f8efa50fce5e5e8773c53f41a","target":"record","created_at":"2026-07-05T02:13:07Z","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":"221d1854c3ad68dbd2ef3d9f8ef7825b3ca0c8f812dda81cfbc07499922ec2bc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-05T16:09:07Z","title_canon_sha256":"a8a87fbd1e2aaf66d960fcd7e4831bed67c77da00797f137e0437bfa434291d1"},"schema_version":"1.0","source":{"id":"2102.03261","kind":"arxiv","version":1}},"canonical_sha256":"c1b10e68702e8f2a0f9549aaf423e3076a5488f45b4463cba7559b3ac7424905","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1b10e68702e8f2a0f9549aaf423e3076a5488f45b4463cba7559b3ac7424905","first_computed_at":"2026-07-05T02:13:07.589457Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:13:07.589457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FCjogAkQw4Wa3Ssd02UejmFyTgmenZ3YT2T6bTQjgpFT63Nmdie7pN9yR40KphX32xBPwkjZrGoEQp9VnF6IDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:13:07.589828Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.03261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d67bb7c683a8a1b9960623c52390beefd83f55f8efa50fce5e5e8773c53f41a","sha256:f008778b14a642e4ac3ab17dfc0cc393fcc002951ddb66fd0b22be726d98d0f8"],"state_sha256":"183a9557893aab5b9fa4ff63dfcbb326c1aa86a1c9f60d63874ec0a1b7448146"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"baC5eJauAAHwwwPVvg1TOg+UXYb042ZQB/80b1qCO+DoB1mWt1o7uXlVReaKSUBLK0WZoCcsqsu3V0LTDMdIDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:44:56.599626Z","bundle_sha256":"93df25614a0ede11eac9573765e0c68e29d7f0701e325b28539f640faf72a57b"}}