{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:HSPFOFLQ5WRPDPSFZYLASMGAVV","short_pith_number":"pith:HSPFOFLQ","canonical_record":{"source":{"id":"1805.08395","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-22T05:11:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9072fccbbeb824cdd23ca98d61b2dcb4480b19261e3d44608255cccdecf5bf3f","abstract_canon_sha256":"ae27471648da3a8350d130aa094de0fab2685f7d97ae2cd35b294319f00a9358"},"schema_version":"1.0"},"canonical_sha256":"3c9e571570eda2f1be45ce160930c0ad62e50b3d47ded5efc20e5a0fc9b00ddc","source":{"kind":"arxiv","id":"1805.08395","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08395","created_at":"2026-05-18T00:15:26Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08395v1","created_at":"2026-05-18T00:15:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08395","created_at":"2026-05-18T00:15:26Z"},{"alias_kind":"pith_short_12","alias_value":"HSPFOFLQ5WRP","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HSPFOFLQ5WRPDPSF","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HSPFOFLQ","created_at":"2026-05-18T12:32:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:HSPFOFLQ5WRPDPSFZYLASMGAVV","target":"record","payload":{"canonical_record":{"source":{"id":"1805.08395","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-22T05:11:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9072fccbbeb824cdd23ca98d61b2dcb4480b19261e3d44608255cccdecf5bf3f","abstract_canon_sha256":"ae27471648da3a8350d130aa094de0fab2685f7d97ae2cd35b294319f00a9358"},"schema_version":"1.0"},"canonical_sha256":"3c9e571570eda2f1be45ce160930c0ad62e50b3d47ded5efc20e5a0fc9b00ddc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:26.665522Z","signature_b64":"HdS6B91Q0cTs5+GtDg9We6Fza4dxNfLv02t3+ln7CAx2PvzhqJfDiAqpMzCCIwxHninyqTAz5fJeY9yCSEzqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c9e571570eda2f1be45ce160930c0ad62e50b3d47ded5efc20e5a0fc9b00ddc","last_reissued_at":"2026-05-18T00:15:26.664797Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:26.664797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.08395","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":"2026-05-18T00:15:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SQ4IFXy8LuhSfa6JUBRg8DIDVesGBNbhtr0pypzE5DuAHorp79yLTALipoPfRwjrsj36Hy3PN4pZ20anK51OAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T10:11:29.203126Z"},"content_sha256":"f590aa69b7586df045c5cdc19d341ed09f8b934d865a7d60aa1cda363809c400","schema_version":"1.0","event_id":"sha256:f590aa69b7586df045c5cdc19d341ed09f8b934d865a7d60aa1cda363809c400"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:HSPFOFLQ5WRPDPSFZYLASMGAVV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Optimize via Wasserstein Deep Inverse Optimal Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongyuan Zha, Le Song, Yichen Wang","submitted_at":"2018-05-22T05:11:59Z","abstract_excerpt":"We study the inverse optimal control problem in social sciences: we aim at learning a user's true cost function from the observed temporal behavior. In contrast to traditional phenomenological works that aim to learn a generative model to fit the behavioral data, we propose a novel variational principle and treat user as a reinforcement learning algorithm, which acts by optimizing his cost function. We first propose a unified KL framework that generalizes existing maximum entropy inverse optimal control methods. We further propose a two-step Wasserstein inverse optimal control framework. In th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08395","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":""},"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":"2026-05-18T00:15:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zN+5IFM6DvayNEUn1HHFL8BkvtaUxKCYkMm3u+igGABfTx3nbykBzB4RO2vU2F4INyNVBjPrC17rwaQRbWOOCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T10:11:29.203805Z"},"content_sha256":"a17a8c9b9fb91c27ccf73b2244df4e1b4b2b37dd4193f4b8261170012cfc601c","schema_version":"1.0","event_id":"sha256:a17a8c9b9fb91c27ccf73b2244df4e1b4b2b37dd4193f4b8261170012cfc601c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HSPFOFLQ5WRPDPSFZYLASMGAVV/bundle.json","state_url":"https://pith.science/pith/HSPFOFLQ5WRPDPSFZYLASMGAVV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HSPFOFLQ5WRPDPSFZYLASMGAVV/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":"2026-06-09T10:11:29Z","links":{"resolver":"https://pith.science/pith/HSPFOFLQ5WRPDPSFZYLASMGAVV","bundle":"https://pith.science/pith/HSPFOFLQ5WRPDPSFZYLASMGAVV/bundle.json","state":"https://pith.science/pith/HSPFOFLQ5WRPDPSFZYLASMGAVV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HSPFOFLQ5WRPDPSFZYLASMGAVV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:HSPFOFLQ5WRPDPSFZYLASMGAVV","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":"ae27471648da3a8350d130aa094de0fab2685f7d97ae2cd35b294319f00a9358","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-22T05:11:59Z","title_canon_sha256":"9072fccbbeb824cdd23ca98d61b2dcb4480b19261e3d44608255cccdecf5bf3f"},"schema_version":"1.0","source":{"id":"1805.08395","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08395","created_at":"2026-05-18T00:15:26Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08395v1","created_at":"2026-05-18T00:15:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08395","created_at":"2026-05-18T00:15:26Z"},{"alias_kind":"pith_short_12","alias_value":"HSPFOFLQ5WRP","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"HSPFOFLQ5WRPDPSF","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"HSPFOFLQ","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:a17a8c9b9fb91c27ccf73b2244df4e1b4b2b37dd4193f4b8261170012cfc601c","target":"graph","created_at":"2026-05-18T00:15:26Z","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"},"paper":{"abstract_excerpt":"We study the inverse optimal control problem in social sciences: we aim at learning a user's true cost function from the observed temporal behavior. In contrast to traditional phenomenological works that aim to learn a generative model to fit the behavioral data, we propose a novel variational principle and treat user as a reinforcement learning algorithm, which acts by optimizing his cost function. We first propose a unified KL framework that generalizes existing maximum entropy inverse optimal control methods. We further propose a two-step Wasserstein inverse optimal control framework. In th","authors_text":"Hongyuan Zha, Le Song, Yichen Wang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-22T05:11:59Z","title":"Learning to Optimize via Wasserstein Deep Inverse Optimal Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08395","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:f590aa69b7586df045c5cdc19d341ed09f8b934d865a7d60aa1cda363809c400","target":"record","created_at":"2026-05-18T00:15:26Z","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":"ae27471648da3a8350d130aa094de0fab2685f7d97ae2cd35b294319f00a9358","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-22T05:11:59Z","title_canon_sha256":"9072fccbbeb824cdd23ca98d61b2dcb4480b19261e3d44608255cccdecf5bf3f"},"schema_version":"1.0","source":{"id":"1805.08395","kind":"arxiv","version":1}},"canonical_sha256":"3c9e571570eda2f1be45ce160930c0ad62e50b3d47ded5efc20e5a0fc9b00ddc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3c9e571570eda2f1be45ce160930c0ad62e50b3d47ded5efc20e5a0fc9b00ddc","first_computed_at":"2026-05-18T00:15:26.664797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:26.664797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HdS6B91Q0cTs5+GtDg9We6Fza4dxNfLv02t3+ln7CAx2PvzhqJfDiAqpMzCCIwxHninyqTAz5fJeY9yCSEzqCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:26.665522Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08395","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f590aa69b7586df045c5cdc19d341ed09f8b934d865a7d60aa1cda363809c400","sha256:a17a8c9b9fb91c27ccf73b2244df4e1b4b2b37dd4193f4b8261170012cfc601c"],"state_sha256":"e6e7f20a8ac985f30772fba0ba84f40929db4152034287484e12c5e076c7fc6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ci4Y0R9ZLLlWa2UHwmy0C8F+FXZFIt4d4xGVfJZhMj9UaguEBjCySW4pOq0Hr5WKw+v7cqUUjdy6gxXiS4noAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T10:11:29.207608Z","bundle_sha256":"888ea5637bcbac18ac5e04bb841d579faac17fe145e9c2ac06e3670b1db46827"}}