{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GZFK36SI2CWFMAJHQCGIV3FQAH","short_pith_number":"pith:GZFK36SI","schema_version":"1.0","canonical_sha256":"364aadfa48d0ac560127808c8aecb001c9b7dfe1f575c5cf33d2f9ceb36635cc","source":{"kind":"arxiv","id":"2505.12611","version":1},"attestation_state":"computed","paper":{"title":"Action-Dependent Optimality-Preserving Reward Shaping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arnav Jhala, David L. Roberts, Grant C. Forbes, Jianxun Wang, Leonardo Villalobos-Arias","submitted_at":"2025-05-19T01:50:48Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.12611","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T01:50:48Z","cross_cats_sorted":[],"title_canon_sha256":"58e28f19fdf7931a67cd5607e0f1aeed0210c0c1110c31ee542937f572296215","abstract_canon_sha256":"285ba886833abdd58a1a5dcaaf6cd528803a662203fc06a5c0dab98b421dab76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:06.916706Z","signature_b64":"YAOe2aynJS47Cuv07Ahi6xE1gMstuwoqa6VZo9WLKguzWz5eMf5n8CGEwy+bYOILCDBVA2pTy0I3zOZkYJVMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"364aadfa48d0ac560127808c8aecb001c9b7dfe1f575c5cf33d2f9ceb36635cc","last_reissued_at":"2026-07-05T11:05:06.916187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:06.916187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Action-Dependent Optimality-Preserving Reward Shaping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arnav Jhala, David L. Roberts, Grant C. Forbes, Jianxun Wang, Leonardo Villalobos-Arias","submitted_at":"2025-05-19T01:50:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12611","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/2505.12611/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.12611","created_at":"2026-07-05T11:05:06.916245+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12611v1","created_at":"2026-07-05T11:05:06.916245+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12611","created_at":"2026-07-05T11:05:06.916245+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZFK36SI2CWF","created_at":"2026-07-05T11:05:06.916245+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZFK36SI2CWFMAJH","created_at":"2026-07-05T11:05:06.916245+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZFK36SI","created_at":"2026-07-05T11:05:06.916245+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19725","citing_title":"Minding Motivation: The Effect of Intrinsic Motivation on Agent Behaviors","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZFK36SI2CWFMAJHQCGIV3FQAH","json":"https://pith.science/pith/GZFK36SI2CWFMAJHQCGIV3FQAH.json","graph_json":"https://pith.science/api/pith-number/GZFK36SI2CWFMAJHQCGIV3FQAH/graph.json","events_json":"https://pith.science/api/pith-number/GZFK36SI2CWFMAJHQCGIV3FQAH/events.json","paper":"https://pith.science/paper/GZFK36SI"},"agent_actions":{"view_html":"https://pith.science/pith/GZFK36SI2CWFMAJHQCGIV3FQAH","download_json":"https://pith.science/pith/GZFK36SI2CWFMAJHQCGIV3FQAH.json","view_paper":"https://pith.science/paper/GZFK36SI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12611&json=true","fetch_graph":"https://pith.science/api/pith-number/GZFK36SI2CWFMAJHQCGIV3FQAH/graph.json","fetch_events":"https://pith.science/api/pith-number/GZFK36SI2CWFMAJHQCGIV3FQAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZFK36SI2CWFMAJHQCGIV3FQAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZFK36SI2CWFMAJHQCGIV3FQAH/action/storage_attestation","attest_author":"https://pith.science/pith/GZFK36SI2CWFMAJHQCGIV3FQAH/action/author_attestation","sign_citation":"https://pith.science/pith/GZFK36SI2CWFMAJHQCGIV3FQAH/action/citation_signature","submit_replication":"https://pith.science/pith/GZFK36SI2CWFMAJHQCGIV3FQAH/action/replication_record"}},"created_at":"2026-07-05T11:05:06.916245+00:00","updated_at":"2026-07-05T11:05:06.916245+00:00"}