{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GZFK36SI2CWFMAJHQCGIV3FQAH","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":"285ba886833abdd58a1a5dcaaf6cd528803a662203fc06a5c0dab98b421dab76","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T01:50:48Z","title_canon_sha256":"58e28f19fdf7931a67cd5607e0f1aeed0210c0c1110c31ee542937f572296215"},"schema_version":"1.0","source":{"id":"2505.12611","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12611","created_at":"2026-07-05T11:05:06Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12611v1","created_at":"2026-07-05T11:05:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12611","created_at":"2026-07-05T11:05:06Z"},{"alias_kind":"pith_short_12","alias_value":"GZFK36SI2CWF","created_at":"2026-07-05T11:05:06Z"},{"alias_kind":"pith_short_16","alias_value":"GZFK36SI2CWFMAJH","created_at":"2026-07-05T11:05:06Z"},{"alias_kind":"pith_short_8","alias_value":"GZFK36SI","created_at":"2026-07-05T11:05:06Z"}],"graph_snapshots":[{"event_id":"sha256:2f5e4ab60d1435fa0ee62295a215d47898886c2e46ddaed654ef1ac72eee0a32","target":"graph","created_at":"2026-07-05T11:05:06Z","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/2505.12611/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent RL research has utilized reward shaping--particularly complex shaping rewards such as intrinsic motivation (IM)--to encourage agent exploration in sparse-reward environments. While often effective, ``reward hacking'' can lead to the shaping reward being optimized at the expense of the extrinsic reward, resulting in a suboptimal policy. Potential-Based Reward Shaping (PBRS) techniques such as Generalized Reward Matching (GRM) and Policy-Invariant Explicit Shaping (PIES) have mitigated this. These methods allow for implementing IM without altering optimal policies. In this work we show th","authors_text":"Arnav Jhala, David L. Roberts, Grant C. Forbes, Jianxun Wang, Leonardo Villalobos-Arias","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T01:50:48Z","title":"Action-Dependent Optimality-Preserving Reward Shaping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12611","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":"sha256:04ca23eafb9524e789901a8fdc85c1d8305b3d3e896e6193b7ddc2f23ba65095","target":"record","created_at":"2026-07-05T11:05:06Z","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":"285ba886833abdd58a1a5dcaaf6cd528803a662203fc06a5c0dab98b421dab76","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T01:50:48Z","title_canon_sha256":"58e28f19fdf7931a67cd5607e0f1aeed0210c0c1110c31ee542937f572296215"},"schema_version":"1.0","source":{"id":"2505.12611","kind":"arxiv","version":1}},"canonical_sha256":"364aadfa48d0ac560127808c8aecb001c9b7dfe1f575c5cf33d2f9ceb36635cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"364aadfa48d0ac560127808c8aecb001c9b7dfe1f575c5cf33d2f9ceb36635cc","first_computed_at":"2026-07-05T11:05:06.916187Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:06.916187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YAOe2aynJS47Cuv07Ahi6xE1gMstuwoqa6VZo9WLKguzWz5eMf5n8CGEwy+bYOILCDBVA2pTy0I3zOZkYJVMBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:06.916706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12611","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04ca23eafb9524e789901a8fdc85c1d8305b3d3e896e6193b7ddc2f23ba65095","sha256:2f5e4ab60d1435fa0ee62295a215d47898886c2e46ddaed654ef1ac72eee0a32"],"state_sha256":"30d1a22164375519443ba8ef10b08bce87fe4ae9e4342435dc5d52fe87aa7d08"}