{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DBVE6DG6OS3TXJ5JTERE7PDW3L","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":"b1fa4b4d2ef4cf0925e9eb18fb86ebee907f524a3acca5cf744988247a6e7027","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T14:35:29Z","title_canon_sha256":"a92e24fb2d7b867c45897793d2aa3dee6d50e8cec7da2d9a6164d790387d3d39"},"schema_version":"1.0","source":{"id":"2608.08158","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08158","created_at":"2026-08-11T01:21:50Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08158v1","created_at":"2026-08-11T01:21:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08158","created_at":"2026-08-11T01:21:50Z"},{"alias_kind":"pith_short_12","alias_value":"DBVE6DG6OS3T","created_at":"2026-08-11T01:21:50Z"},{"alias_kind":"pith_short_16","alias_value":"DBVE6DG6OS3TXJ5J","created_at":"2026-08-11T01:21:50Z"},{"alias_kind":"pith_short_8","alias_value":"DBVE6DG6","created_at":"2026-08-11T01:21:50Z"}],"graph_snapshots":[{"event_id":"sha256:14e8b07c4ca61c1e743a939950add5a874e82c0f6a5f0634a5713ad7ded65e76","target":"graph","created_at":"2026-08-11T01:21:50Z","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/2608.08158/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse, delayed, and weakly informative rewards remain central obstacles to efficient reinforcement learning. Reward shaping addresses these limitations by supplementing the task reward with an auxiliary signal that can accelerate learning while, in the classical setting, the original objective remains the evaluation criterion. Established theory guarantees safety for fixed shaping signals: potential-based reward shaping preserves optimal policies when the auxiliary term is the discounted difference of a time-invariant potential. In contemporary reinforcement learning systems, however, both th","authors_text":"Fouad Bahrpeyma","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T14:35:29Z","title":"A Unified Framework for Dynamic Reward Shaping in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08158","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:aaab9afba65a613dc9b44a8da6ea2ce01722acacec8b0a85393f3f4e6d74b9ce","target":"record","created_at":"2026-08-11T01:21:50Z","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":"b1fa4b4d2ef4cf0925e9eb18fb86ebee907f524a3acca5cf744988247a6e7027","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T14:35:29Z","title_canon_sha256":"a92e24fb2d7b867c45897793d2aa3dee6d50e8cec7da2d9a6164d790387d3d39"},"schema_version":"1.0","source":{"id":"2608.08158","kind":"arxiv","version":1}},"canonical_sha256":"186a4f0cde74b73ba7a999224fbc76dad95ff739718431b925f24d9c8b5ee43b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"186a4f0cde74b73ba7a999224fbc76dad95ff739718431b925f24d9c8b5ee43b","first_computed_at":"2026-08-11T01:21:50.847359Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:21:50.847359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UgT9C1+qXs4dHHc0zZCtO1zKkrmjdxZybkw5ThyvBTVpL68AUt0ePxXaXb3o0alOe8CcLPh9ZZdOXMjfSa1OCw==","signature_status":"signed_v1","signed_at":"2026-08-11T01:21:50.849820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08158","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aaab9afba65a613dc9b44a8da6ea2ce01722acacec8b0a85393f3f4e6d74b9ce","sha256:14e8b07c4ca61c1e743a939950add5a874e82c0f6a5f0634a5713ad7ded65e76"],"state_sha256":"b9d277a0a5822bec7e8743e66e6760bafe82ac0a3734cffbe43150557ffceb49"}