{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DLBMWF53RK5QVN2YSZ36HECWA4","short_pith_number":"pith:DLBMWF53","canonical_record":{"source":{"id":"2405.09999","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-16T11:33:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8bb3409356ffc1706e973be7e3c9aee0572c650093b9df20efcc6887356763f1","abstract_canon_sha256":"e2ae4638c34d622df660cdc352a2813de791132e8cc787cdbedebeb4e5b901ac"},"schema_version":"1.0"},"canonical_sha256":"1ac2cb17bb8abb0ab7589677e39056070c0c1f90f5b58ef244e595256b455725","source":{"kind":"arxiv","id":"2405.09999","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.09999","created_at":"2026-07-05T09:28:30Z"},{"alias_kind":"arxiv_version","alias_value":"2405.09999v2","created_at":"2026-07-05T09:28:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.09999","created_at":"2026-07-05T09:28:30Z"},{"alias_kind":"pith_short_12","alias_value":"DLBMWF53RK5Q","created_at":"2026-07-05T09:28:30Z"},{"alias_kind":"pith_short_16","alias_value":"DLBMWF53RK5QVN2Y","created_at":"2026-07-05T09:28:30Z"},{"alias_kind":"pith_short_8","alias_value":"DLBMWF53","created_at":"2026-07-05T09:28:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DLBMWF53RK5QVN2YSZ36HECWA4","target":"record","payload":{"canonical_record":{"source":{"id":"2405.09999","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-16T11:33:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8bb3409356ffc1706e973be7e3c9aee0572c650093b9df20efcc6887356763f1","abstract_canon_sha256":"e2ae4638c34d622df660cdc352a2813de791132e8cc787cdbedebeb4e5b901ac"},"schema_version":"1.0"},"canonical_sha256":"1ac2cb17bb8abb0ab7589677e39056070c0c1f90f5b58ef244e595256b455725","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:30.877397Z","signature_b64":"9naRqBDUuq37SRL3CWjLDjCq8LeE9Jsx5TMQHTLEpvayldDUOaxEp4W6I7VtdnK99WFkMm82Fht/2PHfvoXUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ac2cb17bb8abb0ab7589677e39056070c0c1f90f5b58ef244e595256b455725","last_reissued_at":"2026-07-05T09:28:30.876914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:30.876914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.09999","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":"2026-07-05T09:28:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vehgcW/r0mkPPEJqcJvpwm2EQIT07EqJU7k2GU/urKoUfdK5JfD9NkCKIsieAyG8PGgb+ALPKPhSNDfFxYL1Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:25:04.965706Z"},"content_sha256":"62cc05cea975baf438ff793373e4548c016d2b54f02441898bf6d99e1d5a8b4a","schema_version":"1.0","event_id":"sha256:62cc05cea975baf438ff793373e4548c016d2b54f02441898bf6d99e1d5a8b4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DLBMWF53RK5QVN2YSZ36HECWA4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward Centering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abhishek Naik, Manan Tomar, Richard S. Sutton, Yi Wan","submitted_at":"2024-05-16T11:33:49Z","abstract_excerpt":"We show that discounted methods for solving continuing reinforcement learning problems can perform significantly better if they center their rewards by subtracting out the rewards' empirical average. The improvement is substantial at commonly used discount factors and increases further as the discount factor approaches one. In addition, we show that if a problem's rewards are shifted by a constant, then standard methods perform much worse, whereas methods with reward centering are unaffected. Estimating the average reward is straightforward in the on-policy setting; we propose a slightly more "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.09999","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/2405.09999/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":"2026-07-05T09:28:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ywVsdl4LomuchG4dU4y9UzUpzbEjHWZ75griGYJZ1KHucWmzMFVE8HqKA91eWC2dzpg/ZPsyF/lAKzZHS15OCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:25:04.966344Z"},"content_sha256":"ed6103a8214f39dab9edb446f8ee925aadc70d3fc01e3c610fdf1e2aeb490a82","schema_version":"1.0","event_id":"sha256:ed6103a8214f39dab9edb446f8ee925aadc70d3fc01e3c610fdf1e2aeb490a82"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DLBMWF53RK5QVN2YSZ36HECWA4/bundle.json","state_url":"https://pith.science/pith/DLBMWF53RK5QVN2YSZ36HECWA4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DLBMWF53RK5QVN2YSZ36HECWA4/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":"2026-08-08T06:25:04Z","links":{"resolver":"https://pith.science/pith/DLBMWF53RK5QVN2YSZ36HECWA4","bundle":"https://pith.science/pith/DLBMWF53RK5QVN2YSZ36HECWA4/bundle.json","state":"https://pith.science/pith/DLBMWF53RK5QVN2YSZ36HECWA4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DLBMWF53RK5QVN2YSZ36HECWA4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DLBMWF53RK5QVN2YSZ36HECWA4","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":"e2ae4638c34d622df660cdc352a2813de791132e8cc787cdbedebeb4e5b901ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-16T11:33:49Z","title_canon_sha256":"8bb3409356ffc1706e973be7e3c9aee0572c650093b9df20efcc6887356763f1"},"schema_version":"1.0","source":{"id":"2405.09999","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.09999","created_at":"2026-07-05T09:28:30Z"},{"alias_kind":"arxiv_version","alias_value":"2405.09999v2","created_at":"2026-07-05T09:28:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.09999","created_at":"2026-07-05T09:28:30Z"},{"alias_kind":"pith_short_12","alias_value":"DLBMWF53RK5Q","created_at":"2026-07-05T09:28:30Z"},{"alias_kind":"pith_short_16","alias_value":"DLBMWF53RK5QVN2Y","created_at":"2026-07-05T09:28:30Z"},{"alias_kind":"pith_short_8","alias_value":"DLBMWF53","created_at":"2026-07-05T09:28:30Z"}],"graph_snapshots":[{"event_id":"sha256:ed6103a8214f39dab9edb446f8ee925aadc70d3fc01e3c610fdf1e2aeb490a82","target":"graph","created_at":"2026-07-05T09:28:30Z","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/2405.09999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We show that discounted methods for solving continuing reinforcement learning problems can perform significantly better if they center their rewards by subtracting out the rewards' empirical average. The improvement is substantial at commonly used discount factors and increases further as the discount factor approaches one. In addition, we show that if a problem's rewards are shifted by a constant, then standard methods perform much worse, whereas methods with reward centering are unaffected. Estimating the average reward is straightforward in the on-policy setting; we propose a slightly more ","authors_text":"Abhishek Naik, Manan Tomar, Richard S. Sutton, Yi Wan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-16T11:33:49Z","title":"Reward Centering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.09999","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":"sha256:62cc05cea975baf438ff793373e4548c016d2b54f02441898bf6d99e1d5a8b4a","target":"record","created_at":"2026-07-05T09:28:30Z","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":"e2ae4638c34d622df660cdc352a2813de791132e8cc787cdbedebeb4e5b901ac","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-16T11:33:49Z","title_canon_sha256":"8bb3409356ffc1706e973be7e3c9aee0572c650093b9df20efcc6887356763f1"},"schema_version":"1.0","source":{"id":"2405.09999","kind":"arxiv","version":2}},"canonical_sha256":"1ac2cb17bb8abb0ab7589677e39056070c0c1f90f5b58ef244e595256b455725","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ac2cb17bb8abb0ab7589677e39056070c0c1f90f5b58ef244e595256b455725","first_computed_at":"2026-07-05T09:28:30.876914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:30.876914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9naRqBDUuq37SRL3CWjLDjCq8LeE9Jsx5TMQHTLEpvayldDUOaxEp4W6I7VtdnK99WFkMm82Fht/2PHfvoXUAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:30.877397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.09999","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62cc05cea975baf438ff793373e4548c016d2b54f02441898bf6d99e1d5a8b4a","sha256:ed6103a8214f39dab9edb446f8ee925aadc70d3fc01e3c610fdf1e2aeb490a82"],"state_sha256":"bd800717a33f8b3b383f80440cc82b8b81c92bb2592bbd67272a31fc01d7c533"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fm+SSzfyk/wadV1AH9hopgVtR5FPSJwMrxQBrkeeJe2NHe3uY84wyoeMEpmJh9RrKICuj5O0uEL4PKci8iQcAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:25:04.972006Z","bundle_sha256":"a22f46a47e555a995df988007e67457b6ecb0e81dc13ab12e59a75725b34637f"}}