{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:P2XGDRTNSSISXR7I4EFUFHU4U7","short_pith_number":"pith:P2XGDRTN","canonical_record":{"source":{"id":"2402.09075","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-02-14T10:35:26Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"81abccb423abfeaf3b001df4f361c90f6579afefc557470efd01490e97d5c8f6","abstract_canon_sha256":"72371efb713a9e436dcd28f1196cbe70cd81c481b7077b14b5456d51513ca402"},"schema_version":"1.0"},"canonical_sha256":"7eae61c66d94912bc7e8e10b429e9ca7ebf088884c4af48eb74a03b0535c6a15","source":{"kind":"arxiv","id":"2402.09075","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09075","created_at":"2026-07-05T08:02:51Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09075v2","created_at":"2026-07-05T08:02:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09075","created_at":"2026-07-05T08:02:51Z"},{"alias_kind":"pith_short_12","alias_value":"P2XGDRTNSSIS","created_at":"2026-07-05T08:02:51Z"},{"alias_kind":"pith_short_16","alias_value":"P2XGDRTNSSISXR7I","created_at":"2026-07-05T08:02:51Z"},{"alias_kind":"pith_short_8","alias_value":"P2XGDRTN","created_at":"2026-07-05T08:02:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:P2XGDRTNSSISXR7I4EFUFHU4U7","target":"record","payload":{"canonical_record":{"source":{"id":"2402.09075","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-02-14T10:35:26Z","cross_cats_sorted":["cs.LG","cs.SY"],"title_canon_sha256":"81abccb423abfeaf3b001df4f361c90f6579afefc557470efd01490e97d5c8f6","abstract_canon_sha256":"72371efb713a9e436dcd28f1196cbe70cd81c481b7077b14b5456d51513ca402"},"schema_version":"1.0"},"canonical_sha256":"7eae61c66d94912bc7e8e10b429e9ca7ebf088884c4af48eb74a03b0535c6a15","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:51.002108Z","signature_b64":"S6l0xOv/3MJ11d56m5EAq8J+xHLwmt6WgfNscZC1ID/jCZoo1eAE79QYgXtVS0SIEVxuzxn8ow5biv8not6GAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eae61c66d94912bc7e8e10b429e9ca7ebf088884c4af48eb74a03b0535c6a15","last_reissued_at":"2026-07-05T08:02:51.001619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:51.001619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.09075","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":"2026-07-05T08:02:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/AaPVWsxqT09OKCWhlmbLp0YxIVFgTIwoPJ6eRMAk1xiCs/fDFOHpt2YE9azSB+NDqorED4QedQe/3fBq8W7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:09:25.905938Z"},"content_sha256":"30596a08b849f921fdf4ffacf74de88e97615fcd4255d17430e7178bc712de12","schema_version":"1.0","event_id":"sha256:30596a08b849f921fdf4ffacf74de88e97615fcd4255d17430e7178bc712de12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:P2XGDRTNSSISXR7I4EFUFHU4U7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Steady-State Error Compensation for Reinforcement Learning with Quadratic Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SY"],"primary_cat":"eess.SY","authors_text":"Liyao Wang, Yuan Lin, Zishun Zheng","submitted_at":"2024-02-14T10:35:26Z","abstract_excerpt":"The selection of a reward function in Reinforcement Learning (RL) has garnered significant attention because of its impact on system performance. Issues of significant steady-state errors often manifest when quadratic reward functions are employed. Although absolute-value-type reward functions alleviate this problem, they tend to induce substantial fluctuations in specific system states, leading to abrupt changes. In response to this challenge, this study proposes an approach that introduces an integral term. By integrating this integral term into quadratic-type reward functions, the RL algori"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09075","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/2402.09075/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":"2026-07-05T08:02:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E8b39MtynFWCRrCtwqzo4RGbAywc6kCOQBGOG7XxgaV1F8WmszpyprvTxVcHOLuWRFpUmOkMizvJ9ASW1yWDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:09:25.907662Z"},"content_sha256":"921eccce02f7492d091848848fda9094bc0b4579121f559919b049ebe622fff6","schema_version":"1.0","event_id":"sha256:921eccce02f7492d091848848fda9094bc0b4579121f559919b049ebe622fff6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P2XGDRTNSSISXR7I4EFUFHU4U7/bundle.json","state_url":"https://pith.science/pith/P2XGDRTNSSISXR7I4EFUFHU4U7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P2XGDRTNSSISXR7I4EFUFHU4U7/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":"2026-08-11T11:09:25Z","links":{"resolver":"https://pith.science/pith/P2XGDRTNSSISXR7I4EFUFHU4U7","bundle":"https://pith.science/pith/P2XGDRTNSSISXR7I4EFUFHU4U7/bundle.json","state":"https://pith.science/pith/P2XGDRTNSSISXR7I4EFUFHU4U7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P2XGDRTNSSISXR7I4EFUFHU4U7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:P2XGDRTNSSISXR7I4EFUFHU4U7","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":"72371efb713a9e436dcd28f1196cbe70cd81c481b7077b14b5456d51513ca402","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-02-14T10:35:26Z","title_canon_sha256":"81abccb423abfeaf3b001df4f361c90f6579afefc557470efd01490e97d5c8f6"},"schema_version":"1.0","source":{"id":"2402.09075","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.09075","created_at":"2026-07-05T08:02:51Z"},{"alias_kind":"arxiv_version","alias_value":"2402.09075v2","created_at":"2026-07-05T08:02:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09075","created_at":"2026-07-05T08:02:51Z"},{"alias_kind":"pith_short_12","alias_value":"P2XGDRTNSSIS","created_at":"2026-07-05T08:02:51Z"},{"alias_kind":"pith_short_16","alias_value":"P2XGDRTNSSISXR7I","created_at":"2026-07-05T08:02:51Z"},{"alias_kind":"pith_short_8","alias_value":"P2XGDRTN","created_at":"2026-07-05T08:02:51Z"}],"graph_snapshots":[{"event_id":"sha256:921eccce02f7492d091848848fda9094bc0b4579121f559919b049ebe622fff6","target":"graph","created_at":"2026-07-05T08:02:51Z","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/2402.09075/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The selection of a reward function in Reinforcement Learning (RL) has garnered significant attention because of its impact on system performance. Issues of significant steady-state errors often manifest when quadratic reward functions are employed. Although absolute-value-type reward functions alleviate this problem, they tend to induce substantial fluctuations in specific system states, leading to abrupt changes. In response to this challenge, this study proposes an approach that introduces an integral term. By integrating this integral term into quadratic-type reward functions, the RL algori","authors_text":"Liyao Wang, Yuan Lin, Zishun Zheng","cross_cats":["cs.LG","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-02-14T10:35:26Z","title":"Steady-State Error Compensation for Reinforcement Learning with Quadratic Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09075","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":"sha256:30596a08b849f921fdf4ffacf74de88e97615fcd4255d17430e7178bc712de12","target":"record","created_at":"2026-07-05T08:02:51Z","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":"72371efb713a9e436dcd28f1196cbe70cd81c481b7077b14b5456d51513ca402","cross_cats_sorted":["cs.LG","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2024-02-14T10:35:26Z","title_canon_sha256":"81abccb423abfeaf3b001df4f361c90f6579afefc557470efd01490e97d5c8f6"},"schema_version":"1.0","source":{"id":"2402.09075","kind":"arxiv","version":2}},"canonical_sha256":"7eae61c66d94912bc7e8e10b429e9ca7ebf088884c4af48eb74a03b0535c6a15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7eae61c66d94912bc7e8e10b429e9ca7ebf088884c4af48eb74a03b0535c6a15","first_computed_at":"2026-07-05T08:02:51.001619Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:02:51.001619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S6l0xOv/3MJ11d56m5EAq8J+xHLwmt6WgfNscZC1ID/jCZoo1eAE79QYgXtVS0SIEVxuzxn8ow5biv8not6GAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:02:51.002108Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.09075","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:30596a08b849f921fdf4ffacf74de88e97615fcd4255d17430e7178bc712de12","sha256:921eccce02f7492d091848848fda9094bc0b4579121f559919b049ebe622fff6"],"state_sha256":"43d75057231d44e40b29234a7638c3fc3b2a0193d621f90eb996e6602d610793"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I6NLdj4bmpOityDDCdpgj8erO0WBzrCNrBXFhOOMu0RGOgOkYhQE4RHUBlbGNRpmpv057Hssgwhm66PkT2cTAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T11:09:25.915683Z","bundle_sha256":"e159eb7a772e4456379b3a20a153d376204341e62826834704d0c794c8e4d321"}}