{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BWR27SCWVSRVAZD5QUNICHWCMU","short_pith_number":"pith:BWR27SCW","canonical_record":{"source":{"id":"2506.15421","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T12:46:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8795543cac56b8cff78a3c1f2c82c2ddd19f82cfce4018a22dda2fa3c8e372d8","abstract_canon_sha256":"a62adc370da5746205d7070053ddeceacb2eb5a33d38068d8c777313cbc553e1"},"schema_version":"1.0"},"canonical_sha256":"0da3afc856aca350647d851a811ec26505974112f129f1bf1d305b9d9587d4e2","source":{"kind":"arxiv","id":"2506.15421","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15421","created_at":"2026-07-05T11:23:42Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15421v1","created_at":"2026-07-05T11:23:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15421","created_at":"2026-07-05T11:23:42Z"},{"alias_kind":"pith_short_12","alias_value":"BWR27SCWVSRV","created_at":"2026-07-05T11:23:42Z"},{"alias_kind":"pith_short_16","alias_value":"BWR27SCWVSRVAZD5","created_at":"2026-07-05T11:23:42Z"},{"alias_kind":"pith_short_8","alias_value":"BWR27SCW","created_at":"2026-07-05T11:23:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BWR27SCWVSRVAZD5QUNICHWCMU","target":"record","payload":{"canonical_record":{"source":{"id":"2506.15421","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T12:46:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8795543cac56b8cff78a3c1f2c82c2ddd19f82cfce4018a22dda2fa3c8e372d8","abstract_canon_sha256":"a62adc370da5746205d7070053ddeceacb2eb5a33d38068d8c777313cbc553e1"},"schema_version":"1.0"},"canonical_sha256":"0da3afc856aca350647d851a811ec26505974112f129f1bf1d305b9d9587d4e2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:42.967030Z","signature_b64":"WupEhwzL0fvSMa5r820hJrkCUfDPF8h5mx+s78WHCCV47AV2lZ2zoE7Yx1w443cRTHA38VDCKO52hte+1b8ABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0da3afc856aca350647d851a811ec26505974112f129f1bf1d305b9d9587d4e2","last_reissued_at":"2026-07-05T11:23:42.966540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:42.966540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.15421","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":"2026-07-05T11:23:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FOXcjEP20u71lV3RgKBFr3EkNpT1ON3b4lgx08C6LZX36dIq8VYGMqQRCk+5EA3yJTu1pBsseb8DkcSI+q1LCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:41:58.350650Z"},"content_sha256":"8b15c03a955140457ba58123ece519c1bf1248803a19238eae3096b2898c17fd","schema_version":"1.0","event_id":"sha256:8b15c03a955140457ba58123ece519c1bf1248803a19238eae3096b2898c17fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BWR27SCWVSRVAZD5QUNICHWCMU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward Models in Deep Reinforcement Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chen-Xiao Gao, De-Chuan Zhan, Le Gan, Rui Yu, ShengHua Wan, Yucen Wang, Zongzhang Zhang","submitted_at":"2025-06-18T12:46:39Z","abstract_excerpt":"In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are introduced as proxies of the desired objectives, such that when the agent maximizes the accumulated reward, it also fulfills the task designer's intentions. Recently, significant attention from both academic and industrial researchers has focused on developing reward models that not only align closely with the true objectives but also facilitate policy optimization. In this survey, we provide a comprehensive review of re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15421","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/2506.15421/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":"2026-07-05T11:23:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E7UHCTHdRq/DocOL+BJJ+X/2sd01YZM22oNP49uMqluBha8kGYieFD4Khb6ILvllFtAm4hxb8T4WEkfRaXvJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T15:41:58.351267Z"},"content_sha256":"33487cb61b8f2ede43aa2d344843bfa8739b718e06980df6435eca6a7d4bf23e","schema_version":"1.0","event_id":"sha256:33487cb61b8f2ede43aa2d344843bfa8739b718e06980df6435eca6a7d4bf23e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BWR27SCWVSRVAZD5QUNICHWCMU/bundle.json","state_url":"https://pith.science/pith/BWR27SCWVSRVAZD5QUNICHWCMU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BWR27SCWVSRVAZD5QUNICHWCMU/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":"2026-08-07T15:41:58Z","links":{"resolver":"https://pith.science/pith/BWR27SCWVSRVAZD5QUNICHWCMU","bundle":"https://pith.science/pith/BWR27SCWVSRVAZD5QUNICHWCMU/bundle.json","state":"https://pith.science/pith/BWR27SCWVSRVAZD5QUNICHWCMU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BWR27SCWVSRVAZD5QUNICHWCMU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BWR27SCWVSRVAZD5QUNICHWCMU","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":"a62adc370da5746205d7070053ddeceacb2eb5a33d38068d8c777313cbc553e1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T12:46:39Z","title_canon_sha256":"8795543cac56b8cff78a3c1f2c82c2ddd19f82cfce4018a22dda2fa3c8e372d8"},"schema_version":"1.0","source":{"id":"2506.15421","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15421","created_at":"2026-07-05T11:23:42Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15421v1","created_at":"2026-07-05T11:23:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15421","created_at":"2026-07-05T11:23:42Z"},{"alias_kind":"pith_short_12","alias_value":"BWR27SCWVSRV","created_at":"2026-07-05T11:23:42Z"},{"alias_kind":"pith_short_16","alias_value":"BWR27SCWVSRVAZD5","created_at":"2026-07-05T11:23:42Z"},{"alias_kind":"pith_short_8","alias_value":"BWR27SCW","created_at":"2026-07-05T11:23:42Z"}],"graph_snapshots":[{"event_id":"sha256:33487cb61b8f2ede43aa2d344843bfa8739b718e06980df6435eca6a7d4bf23e","target":"graph","created_at":"2026-07-05T11:23:42Z","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/2506.15421/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are introduced as proxies of the desired objectives, such that when the agent maximizes the accumulated reward, it also fulfills the task designer's intentions. Recently, significant attention from both academic and industrial researchers has focused on developing reward models that not only align closely with the true objectives but also facilitate policy optimization. In this survey, we provide a comprehensive review of re","authors_text":"Chen-Xiao Gao, De-Chuan Zhan, Le Gan, Rui Yu, ShengHua Wan, Yucen Wang, Zongzhang Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T12:46:39Z","title":"Reward Models in Deep Reinforcement Learning: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15421","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":"sha256:8b15c03a955140457ba58123ece519c1bf1248803a19238eae3096b2898c17fd","target":"record","created_at":"2026-07-05T11:23:42Z","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":"a62adc370da5746205d7070053ddeceacb2eb5a33d38068d8c777313cbc553e1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T12:46:39Z","title_canon_sha256":"8795543cac56b8cff78a3c1f2c82c2ddd19f82cfce4018a22dda2fa3c8e372d8"},"schema_version":"1.0","source":{"id":"2506.15421","kind":"arxiv","version":1}},"canonical_sha256":"0da3afc856aca350647d851a811ec26505974112f129f1bf1d305b9d9587d4e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0da3afc856aca350647d851a811ec26505974112f129f1bf1d305b9d9587d4e2","first_computed_at":"2026-07-05T11:23:42.966540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:42.966540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WupEhwzL0fvSMa5r820hJrkCUfDPF8h5mx+s78WHCCV47AV2lZ2zoE7Yx1w443cRTHA38VDCKO52hte+1b8ABg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:42.967030Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.15421","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b15c03a955140457ba58123ece519c1bf1248803a19238eae3096b2898c17fd","sha256:33487cb61b8f2ede43aa2d344843bfa8739b718e06980df6435eca6a7d4bf23e"],"state_sha256":"c4b1040d9666dddb4d89f7efec692684b8ac18111287ca5daecb488af98ff105"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCckvzv4Y+QMMLrixhkTfFM6MNg8Vht5bwVrLN9XyoBc15wcQiq77+8Xz8RRv6hHHh1dpJZYJ05CAooRL3PCCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T15:41:58.355456Z","bundle_sha256":"eaa4ca7a052fd0833d4c085e8a11c65648c7f51b1c00c7c49ebc3cbc724be129"}}