{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Z2QWRHGL6Y4TZTXQCCWPB3R6SA","short_pith_number":"pith:Z2QWRHGL","canonical_record":{"source":{"id":"2407.19902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-29T11:26:17Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"title_canon_sha256":"39033d31a36a2b63c83c849efac5282ad364b87ccf414bc83586546b86f391c3","abstract_canon_sha256":"2dc7e54a4178809f56ee737c75e407788136600de461401e97048c81e41a3d21"},"schema_version":"1.0"},"canonical_sha256":"cea1689ccbf6393ccef010acf0ee3e9006d4648f4335d24a1730829973f67585","source":{"kind":"arxiv","id":"2407.19902","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.19902","created_at":"2026-07-05T08:49:46Z"},{"alias_kind":"arxiv_version","alias_value":"2407.19902v1","created_at":"2026-07-05T08:49:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19902","created_at":"2026-07-05T08:49:46Z"},{"alias_kind":"pith_short_12","alias_value":"Z2QWRHGL6Y4T","created_at":"2026-07-05T08:49:46Z"},{"alias_kind":"pith_short_16","alias_value":"Z2QWRHGL6Y4TZTXQ","created_at":"2026-07-05T08:49:46Z"},{"alias_kind":"pith_short_8","alias_value":"Z2QWRHGL","created_at":"2026-07-05T08:49:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Z2QWRHGL6Y4TZTXQCCWPB3R6SA","target":"record","payload":{"canonical_record":{"source":{"id":"2407.19902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-29T11:26:17Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"title_canon_sha256":"39033d31a36a2b63c83c849efac5282ad364b87ccf414bc83586546b86f391c3","abstract_canon_sha256":"2dc7e54a4178809f56ee737c75e407788136600de461401e97048c81e41a3d21"},"schema_version":"1.0"},"canonical_sha256":"cea1689ccbf6393ccef010acf0ee3e9006d4648f4335d24a1730829973f67585","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:49:46.277385Z","signature_b64":"dcss2ghrNQxckTgOfjy2OmcBRvGHycjnkxT9MKbzF3bsiz4jVQlOBV2gqxHPwOcvN8+qSTYfzPg1MiyEsFkcBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cea1689ccbf6393ccef010acf0ee3e9006d4648f4335d24a1730829973f67585","last_reissued_at":"2026-07-05T08:49:46.276958Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:49:46.276958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.19902","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:49:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1W8hcu+iD5gAFs06Kqtp1H0LknT1lBo2gUM6DcAl3Y7mvO7cykZkG3VEPkPh5LeiXfFRkPehIF85A6hV8dq/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:55:00.227499Z"},"content_sha256":"cc540e6aa91f1f8297ae3bf30a2323fe82ac221faf721c5589d7e2024322577d","schema_version":"1.0","event_id":"sha256:cc540e6aa91f1f8297ae3bf30a2323fe82ac221faf721c5589d7e2024322577d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Z2QWRHGL6Y4TZTXQCCWPB3R6SA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Differential Dynamic Programming Framework for Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.RO","authors_text":"Karl H. Johansson, Kun Cao, Lihua Xie, Wanxin Jin, Xinhang Xu","submitted_at":"2024-07-29T11:26:17Z","abstract_excerpt":"A differential dynamic programming (DDP)-based framework for inverse reinforcement learning (IRL) is introduced to recover the parameters in the cost function, system dynamics, and constraints from demonstrations. Different from existing work, where DDP was used for the inner forward problem with inequality constraints, our proposed framework uses it for efficient computation of the gradient required in the outer inverse problem with equality and inequality constraints. The equivalence between the proposed method and existing methods based on Pontryagin's Maximum Principle (PMP) is established"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19902","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/2407.19902/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":"2026-07-05T08:49:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"varGyAsw2YQzljSmNSrlncAwBDQsDwzx/Y/Bw13u+OvmZW6yoSCGifvt0C7eoIENu/kXFk+U7XWXBgxqMZYmDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:55:00.228030Z"},"content_sha256":"b70a3b0c8aade6fe418e1f6d2d67ec47c231a777a305c8ac6f263eb0fac7053b","schema_version":"1.0","event_id":"sha256:b70a3b0c8aade6fe418e1f6d2d67ec47c231a777a305c8ac6f263eb0fac7053b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z2QWRHGL6Y4TZTXQCCWPB3R6SA/bundle.json","state_url":"https://pith.science/pith/Z2QWRHGL6Y4TZTXQCCWPB3R6SA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z2QWRHGL6Y4TZTXQCCWPB3R6SA/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":"2026-08-09T13:55:00Z","links":{"resolver":"https://pith.science/pith/Z2QWRHGL6Y4TZTXQCCWPB3R6SA","bundle":"https://pith.science/pith/Z2QWRHGL6Y4TZTXQCCWPB3R6SA/bundle.json","state":"https://pith.science/pith/Z2QWRHGL6Y4TZTXQCCWPB3R6SA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z2QWRHGL6Y4TZTXQCCWPB3R6SA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z2QWRHGL6Y4TZTXQCCWPB3R6SA","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":"2dc7e54a4178809f56ee737c75e407788136600de461401e97048c81e41a3d21","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-29T11:26:17Z","title_canon_sha256":"39033d31a36a2b63c83c849efac5282ad364b87ccf414bc83586546b86f391c3"},"schema_version":"1.0","source":{"id":"2407.19902","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.19902","created_at":"2026-07-05T08:49:46Z"},{"alias_kind":"arxiv_version","alias_value":"2407.19902v1","created_at":"2026-07-05T08:49:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19902","created_at":"2026-07-05T08:49:46Z"},{"alias_kind":"pith_short_12","alias_value":"Z2QWRHGL6Y4T","created_at":"2026-07-05T08:49:46Z"},{"alias_kind":"pith_short_16","alias_value":"Z2QWRHGL6Y4TZTXQ","created_at":"2026-07-05T08:49:46Z"},{"alias_kind":"pith_short_8","alias_value":"Z2QWRHGL","created_at":"2026-07-05T08:49:46Z"}],"graph_snapshots":[{"event_id":"sha256:b70a3b0c8aade6fe418e1f6d2d67ec47c231a777a305c8ac6f263eb0fac7053b","target":"graph","created_at":"2026-07-05T08:49:46Z","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/2407.19902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A differential dynamic programming (DDP)-based framework for inverse reinforcement learning (IRL) is introduced to recover the parameters in the cost function, system dynamics, and constraints from demonstrations. Different from existing work, where DDP was used for the inner forward problem with inequality constraints, our proposed framework uses it for efficient computation of the gradient required in the outer inverse problem with equality and inequality constraints. The equivalence between the proposed method and existing methods based on Pontryagin's Maximum Principle (PMP) is established","authors_text":"Karl H. Johansson, Kun Cao, Lihua Xie, Wanxin Jin, Xinhang Xu","cross_cats":["cs.SY","eess.SY","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-29T11:26:17Z","title":"A Differential Dynamic Programming Framework for Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19902","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:cc540e6aa91f1f8297ae3bf30a2323fe82ac221faf721c5589d7e2024322577d","target":"record","created_at":"2026-07-05T08:49:46Z","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":"2dc7e54a4178809f56ee737c75e407788136600de461401e97048c81e41a3d21","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-07-29T11:26:17Z","title_canon_sha256":"39033d31a36a2b63c83c849efac5282ad364b87ccf414bc83586546b86f391c3"},"schema_version":"1.0","source":{"id":"2407.19902","kind":"arxiv","version":1}},"canonical_sha256":"cea1689ccbf6393ccef010acf0ee3e9006d4648f4335d24a1730829973f67585","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cea1689ccbf6393ccef010acf0ee3e9006d4648f4335d24a1730829973f67585","first_computed_at":"2026-07-05T08:49:46.276958Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:49:46.276958Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dcss2ghrNQxckTgOfjy2OmcBRvGHycjnkxT9MKbzF3bsiz4jVQlOBV2gqxHPwOcvN8+qSTYfzPg1MiyEsFkcBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:49:46.277385Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.19902","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc540e6aa91f1f8297ae3bf30a2323fe82ac221faf721c5589d7e2024322577d","sha256:b70a3b0c8aade6fe418e1f6d2d67ec47c231a777a305c8ac6f263eb0fac7053b"],"state_sha256":"7052c001121ae90773cd6cd85f164e18925d36b923728096b69ce083fe872f3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jf8jQ/akNOzSgtFjWD8t79FaZ+bkg7/gYskiaFMF2BeYwr6tOTu6iABlAXds2FPxdDtFvCcNUO+lf6rGx4TmBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:55:00.233322Z","bundle_sha256":"03fd49f431ccc6c96683c2883dc20738e764bcb99b6081e4a3aece7a2d9e9f63"}}