{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MXAYXHHZPE6IY7XD7C3JPZM6XP","short_pith_number":"pith:MXAYXHHZ","canonical_record":{"source":{"id":"2605.14779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T12:48:44Z","cross_cats_sorted":[],"title_canon_sha256":"ec524ec31ae6e9e2d3f6519f371fe7a482f5a17a5185ed03ca53b88c776a5695","abstract_canon_sha256":"3cbc5602807dcded4501c93b8ced0a4a2d5520d187ca77665a38566aa243b505"},"schema_version":"1.0"},"canonical_sha256":"65c18b9cf9793c8c7ee3f8b697e59ebbdd0ff53da67c4a451b639d708f15c126","source":{"kind":"arxiv","id":"2605.14779","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14779","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14779v1","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14779","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"pith_short_12","alias_value":"MXAYXHHZPE6I","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"MXAYXHHZPE6IY7XD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"MXAYXHHZ","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MXAYXHHZPE6IY7XD7C3JPZM6XP","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T12:48:44Z","cross_cats_sorted":[],"title_canon_sha256":"ec524ec31ae6e9e2d3f6519f371fe7a482f5a17a5185ed03ca53b88c776a5695","abstract_canon_sha256":"3cbc5602807dcded4501c93b8ced0a4a2d5520d187ca77665a38566aa243b505"},"schema_version":"1.0"},"canonical_sha256":"65c18b9cf9793c8c7ee3f8b697e59ebbdd0ff53da67c4a451b639d708f15c126","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:58.572362Z","signature_b64":"u4qi02OKLv5BtfJidnLIOdnNuk0ssYrttdQrueo2NRti9SAaVse2XrAOnIPigi7Ek3LPbOflC3iF+il3n+esAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65c18b9cf9793c8c7ee3f8b697e59ebbdd0ff53da67c4a451b639d708f15c126","last_reissued_at":"2026-05-17T23:38:58.571640Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:58.571640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14779","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":"2026-05-17T23:38:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6abPrDRJUoNy+8C1ZgmO8sRXHiOv1QSCrQsXohWD2NYRFqyzuPY5H+ckXLe0yReXT4cdmmI6YoTahCdyBi7NAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T23:40:30.318901Z"},"content_sha256":"ce81d8a772b829f1203f85b27324733534cbc7002d7a9934bea444a3d2420eda","schema_version":"1.0","event_id":"sha256:ce81d8a772b829f1203f85b27324733534cbc7002d7a9934bea444a3d2420eda"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MXAYXHHZPE6IY7XD7C3JPZM6XP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Peng's Q($\\lambda$) for Conservative Value Estimation in Offline Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Byeongchan Kim, Min-hwan Oh","submitted_at":"2026-05-14T12:48:44Z","abstract_excerpt":"We propose a model-free offline multi-step reinforcement learning (RL) algorithm, Conservative Peng's Q($\\lambda$) (CPQL). Our algorithm adapts the Peng's Q($\\lambda$) (PQL) operator for conservative value estimation as an alternative to the Bellman operator. To the best of our knowledge, this is the first work in offline RL to theoretically and empirically demonstrate the effectiveness of conservative value estimation with a \\textit{multi-step} operator by fully leveraging offline trajectories. The fixed point of the PQL operator in offline RL lies closer to the value function of the behavior"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14779","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":""},"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":"2026-05-17T23:38:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"daFeZDBIcdCHMWcTACaamDo8xPr1YSZjzrXjVTsdurjoSZJz7FUirttRfZGnBZpgrHYN6KqKXQ0dJ3jqkDIjCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T23:40:30.319234Z"},"content_sha256":"ee48b677c2747ca8a359dd505f25865ec88d35ea7ec34867e38308132d938b47","schema_version":"1.0","event_id":"sha256:ee48b677c2747ca8a359dd505f25865ec88d35ea7ec34867e38308132d938b47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MXAYXHHZPE6IY7XD7C3JPZM6XP/bundle.json","state_url":"https://pith.science/pith/MXAYXHHZPE6IY7XD7C3JPZM6XP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MXAYXHHZPE6IY7XD7C3JPZM6XP/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":"2026-06-01T23:40:30Z","links":{"resolver":"https://pith.science/pith/MXAYXHHZPE6IY7XD7C3JPZM6XP","bundle":"https://pith.science/pith/MXAYXHHZPE6IY7XD7C3JPZM6XP/bundle.json","state":"https://pith.science/pith/MXAYXHHZPE6IY7XD7C3JPZM6XP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MXAYXHHZPE6IY7XD7C3JPZM6XP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MXAYXHHZPE6IY7XD7C3JPZM6XP","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":"3cbc5602807dcded4501c93b8ced0a4a2d5520d187ca77665a38566aa243b505","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T12:48:44Z","title_canon_sha256":"ec524ec31ae6e9e2d3f6519f371fe7a482f5a17a5185ed03ca53b88c776a5695"},"schema_version":"1.0","source":{"id":"2605.14779","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14779","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14779v1","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14779","created_at":"2026-05-17T23:38:58Z"},{"alias_kind":"pith_short_12","alias_value":"MXAYXHHZPE6I","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"MXAYXHHZPE6IY7XD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"MXAYXHHZ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:ee48b677c2747ca8a359dd505f25865ec88d35ea7ec34867e38308132d938b47","target":"graph","created_at":"2026-05-17T23:38:58Z","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"},"paper":{"abstract_excerpt":"We propose a model-free offline multi-step reinforcement learning (RL) algorithm, Conservative Peng's Q($\\lambda$) (CPQL). Our algorithm adapts the Peng's Q($\\lambda$) (PQL) operator for conservative value estimation as an alternative to the Bellman operator. To the best of our knowledge, this is the first work in offline RL to theoretically and empirically demonstrate the effectiveness of conservative value estimation with a \\textit{multi-step} operator by fully leveraging offline trajectories. The fixed point of the PQL operator in offline RL lies closer to the value function of the behavior","authors_text":"Byeongchan Kim, Min-hwan Oh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T12:48:44Z","title":"Peng's Q($\\lambda$) for Conservative Value Estimation in Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14779","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:ce81d8a772b829f1203f85b27324733534cbc7002d7a9934bea444a3d2420eda","target":"record","created_at":"2026-05-17T23:38:58Z","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":"3cbc5602807dcded4501c93b8ced0a4a2d5520d187ca77665a38566aa243b505","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T12:48:44Z","title_canon_sha256":"ec524ec31ae6e9e2d3f6519f371fe7a482f5a17a5185ed03ca53b88c776a5695"},"schema_version":"1.0","source":{"id":"2605.14779","kind":"arxiv","version":1}},"canonical_sha256":"65c18b9cf9793c8c7ee3f8b697e59ebbdd0ff53da67c4a451b639d708f15c126","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65c18b9cf9793c8c7ee3f8b697e59ebbdd0ff53da67c4a451b639d708f15c126","first_computed_at":"2026-05-17T23:38:58.571640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:58.571640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u4qi02OKLv5BtfJidnLIOdnNuk0ssYrttdQrueo2NRti9SAaVse2XrAOnIPigi7Ek3LPbOflC3iF+il3n+esAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:58.572362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14779","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce81d8a772b829f1203f85b27324733534cbc7002d7a9934bea444a3d2420eda","sha256:ee48b677c2747ca8a359dd505f25865ec88d35ea7ec34867e38308132d938b47"],"state_sha256":"21fa19af374c42f196f257e44f8b986a53a68a68d4a0fbc2dcc26e9230b0e53a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hKGKzA1U2/b2WOVWQO+66UQcd1lJHqi8daGxHKHehfv5H6iX/nRvSzbHnPQFOBJD9UEWvUOlCdOKoEPGLnbkAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T23:40:30.321130Z","bundle_sha256":"39bcbae7d140f5ab055eb72db35d59bbc4a2baba625cf1a8cb4c5133d8542a48"}}