{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MU6G4R276Q2ST5FZL3CLR22F2Z","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":"ab37cd6e1d084423dfbd1bc9c934f5c121b983a283890bb24ab53da3c1ecc467","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-15T17:50:18Z","title_canon_sha256":"fcc369989bd11c363084c6a3f4fae42b24e1f6ca73d1c52f5548fcad7948895a"},"schema_version":"1.0","source":{"id":"2312.09983","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.09983","created_at":"2026-07-05T07:25:27Z"},{"alias_kind":"arxiv_version","alias_value":"2312.09983v2","created_at":"2026-07-05T07:25:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.09983","created_at":"2026-07-05T07:25:27Z"},{"alias_kind":"pith_short_12","alias_value":"MU6G4R276Q2S","created_at":"2026-07-05T07:25:27Z"},{"alias_kind":"pith_short_16","alias_value":"MU6G4R276Q2ST5FZ","created_at":"2026-07-05T07:25:27Z"},{"alias_kind":"pith_short_8","alias_value":"MU6G4R27","created_at":"2026-07-05T07:25:27Z"}],"graph_snapshots":[{"event_id":"sha256:de4c0ed391dd080423e4fd06eaf51cceb37fe201f57392b2c5713cf78c120b65","target":"graph","created_at":"2026-07-05T07:25:27Z","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/2312.09983/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inverse reinforcement learning (IRL) is computationally challenging, with common approaches requiring the solution of multiple reinforcement learning (RL) sub-problems. This work motivates the use of potential-based reward shaping to reduce the computational burden of each RL sub-problem. This work serves as a proof-of-concept and we hope will inspire future developments towards computationally efficient IRL.","authors_text":"Cassidy Laidlaw, Edwin Zhang, Finale Doshi-Velez, Harvey Klyne, Lauren H. Cooke, Milind Tambe","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-15T17:50:18Z","title":"Toward Computationally Efficient Inverse Reinforcement Learning via Reward Shaping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.09983","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":"sha256:0f612c95495a9085c19bdeb1968b4d73fb2398c8f58efa83acde90d53a4706bf","target":"record","created_at":"2026-07-05T07:25:27Z","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":"ab37cd6e1d084423dfbd1bc9c934f5c121b983a283890bb24ab53da3c1ecc467","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-15T17:50:18Z","title_canon_sha256":"fcc369989bd11c363084c6a3f4fae42b24e1f6ca73d1c52f5548fcad7948895a"},"schema_version":"1.0","source":{"id":"2312.09983","kind":"arxiv","version":2}},"canonical_sha256":"653c6e475ff43529f4b95ec4b8eb45d644c4967d33c25dcc9036ae7ccf44dfe3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"653c6e475ff43529f4b95ec4b8eb45d644c4967d33c25dcc9036ae7ccf44dfe3","first_computed_at":"2026-07-05T07:25:27.166780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:27.166780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N0o/8sCC0WsUEk5CI5D0OgfMuY6/uLVWt7O1zfOaKrbZki6l/7DEYMknPskZE3CQkRNPWPC3X70KklvgLv/FDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:27.167258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.09983","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f612c95495a9085c19bdeb1968b4d73fb2398c8f58efa83acde90d53a4706bf","sha256:de4c0ed391dd080423e4fd06eaf51cceb37fe201f57392b2c5713cf78c120b65"],"state_sha256":"19bd5b35a76e8baab4381b4d8f3478f810b7bba2f12c6e569a2b5e3157163172"}