{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:QI3Z2DFHWK6B4NGTQM46FUKZJN","short_pith_number":"pith:QI3Z2DFH","canonical_record":{"source":{"id":"1702.08584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-02-28T00:21:26Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"e80ace691928eff0b7786f60bc64c0acf6cf41cc25444238a361366b6614e71b","abstract_canon_sha256":"131954ccad685bb12adbef061d666fb4c331d622ede024f5a12bb9697fa7d92e"},"schema_version":"1.0"},"canonical_sha256":"82379d0ca7b2bc1e34d38339e2d1594b5d71ffd72260b1c281117591fb8904ec","source":{"kind":"arxiv","id":"1702.08584","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.08584","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"arxiv_version","alias_value":"1702.08584v1","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08584","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"pith_short_12","alias_value":"QI3Z2DFHWK6B","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"QI3Z2DFHWK6B4NGT","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"QI3Z2DFH","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:QI3Z2DFHWK6B4NGTQM46FUKZJN","target":"record","payload":{"canonical_record":{"source":{"id":"1702.08584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-02-28T00:21:26Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"e80ace691928eff0b7786f60bc64c0acf6cf41cc25444238a361366b6614e71b","abstract_canon_sha256":"131954ccad685bb12adbef061d666fb4c331d622ede024f5a12bb9697fa7d92e"},"schema_version":"1.0"},"canonical_sha256":"82379d0ca7b2bc1e34d38339e2d1594b5d71ffd72260b1c281117591fb8904ec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:46.759537Z","signature_b64":"eKdHShMgUJKqistU0iIerZmpZ6ZbghtxwTOiOHLp7HzF7PBzho2yA/edR6AYhm9N15ni5bt6TsTvH0TJiRj3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82379d0ca7b2bc1e34d38339e2d1594b5d71ffd72260b1c281117591fb8904ec","last_reissued_at":"2026-05-18T00:39:46.758777Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:46.758777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.08584","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":"2026-05-18T00:39:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VSPtL5t7WY21d8a3OkVjufVCwDtbq5N9ssPY2bWxRxYYthN7nSQs+zOPChXDxDORQ96P8FvIa8FaKjOw6PRPAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T17:22:11.976652Z"},"content_sha256":"d449c3aad97eda92185bbc31ef90f05f62c56d2b6db8fc4d25fc79755260bd84","schema_version":"1.0","event_id":"sha256:d449c3aad97eda92185bbc31ef90f05f62c56d2b6db8fc4d25fc79755260bd84"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:QI3Z2DFHWK6B4NGTQM46FUKZJN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Model-based reinforcement learning in differential graphical games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.SY","authors_text":"Justin R. Klotz, Patrick Walters, Rushikesh Kamalapurkar, Warren E. Dixon","submitted_at":"2017-02-28T00:21:26Z","abstract_excerpt":"This paper seeks to combine differential game theory with the actor-critic-identifier architecture to determine forward-in-time, approximate optimal controllers for formation tracking in multi-agent systems, where the agents have uncertain heterogeneous nonlinear dynamics. A continuous control strategy is proposed, using communication feedback from extended neighbors on a communication topology that has a spanning tree. A model-based reinforcement learning technique is developed to cooperatively control a group of agents to track a trajectory in a desired formation. Simulation results are pres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08584","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":"2026-05-18T00:39:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"olZAQKOJuygZX5XhL/HoxolvpQL7inSGHubwvb6ufyNy5BJKBpps2aU30SK7H2VmgKb8F0C9cFApY+G51tc/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T17:22:11.977451Z"},"content_sha256":"5a67b3d3de017bb36258090a43f0a587763298bcf3c77a0e62e7fc8f1d624c8f","schema_version":"1.0","event_id":"sha256:5a67b3d3de017bb36258090a43f0a587763298bcf3c77a0e62e7fc8f1d624c8f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QI3Z2DFHWK6B4NGTQM46FUKZJN/bundle.json","state_url":"https://pith.science/pith/QI3Z2DFHWK6B4NGTQM46FUKZJN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QI3Z2DFHWK6B4NGTQM46FUKZJN/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":"2026-06-11T17:22:11Z","links":{"resolver":"https://pith.science/pith/QI3Z2DFHWK6B4NGTQM46FUKZJN","bundle":"https://pith.science/pith/QI3Z2DFHWK6B4NGTQM46FUKZJN/bundle.json","state":"https://pith.science/pith/QI3Z2DFHWK6B4NGTQM46FUKZJN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QI3Z2DFHWK6B4NGTQM46FUKZJN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:QI3Z2DFHWK6B4NGTQM46FUKZJN","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":"131954ccad685bb12adbef061d666fb4c331d622ede024f5a12bb9697fa7d92e","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-02-28T00:21:26Z","title_canon_sha256":"e80ace691928eff0b7786f60bc64c0acf6cf41cc25444238a361366b6614e71b"},"schema_version":"1.0","source":{"id":"1702.08584","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.08584","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"arxiv_version","alias_value":"1702.08584v1","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08584","created_at":"2026-05-18T00:39:46Z"},{"alias_kind":"pith_short_12","alias_value":"QI3Z2DFHWK6B","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"QI3Z2DFHWK6B4NGT","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"QI3Z2DFH","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:5a67b3d3de017bb36258090a43f0a587763298bcf3c77a0e62e7fc8f1d624c8f","target":"graph","created_at":"2026-05-18T00:39:46Z","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"},"paper":{"abstract_excerpt":"This paper seeks to combine differential game theory with the actor-critic-identifier architecture to determine forward-in-time, approximate optimal controllers for formation tracking in multi-agent systems, where the agents have uncertain heterogeneous nonlinear dynamics. A continuous control strategy is proposed, using communication feedback from extended neighbors on a communication topology that has a spanning tree. A model-based reinforcement learning technique is developed to cooperatively control a group of agents to track a trajectory in a desired formation. Simulation results are pres","authors_text":"Justin R. Klotz, Patrick Walters, Rushikesh Kamalapurkar, Warren E. Dixon","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-02-28T00:21:26Z","title":"Model-based reinforcement learning in differential graphical games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08584","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:d449c3aad97eda92185bbc31ef90f05f62c56d2b6db8fc4d25fc79755260bd84","target":"record","created_at":"2026-05-18T00:39:46Z","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":"131954ccad685bb12adbef061d666fb4c331d622ede024f5a12bb9697fa7d92e","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2017-02-28T00:21:26Z","title_canon_sha256":"e80ace691928eff0b7786f60bc64c0acf6cf41cc25444238a361366b6614e71b"},"schema_version":"1.0","source":{"id":"1702.08584","kind":"arxiv","version":1}},"canonical_sha256":"82379d0ca7b2bc1e34d38339e2d1594b5d71ffd72260b1c281117591fb8904ec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"82379d0ca7b2bc1e34d38339e2d1594b5d71ffd72260b1c281117591fb8904ec","first_computed_at":"2026-05-18T00:39:46.758777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:39:46.758777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eKdHShMgUJKqistU0iIerZmpZ6ZbghtxwTOiOHLp7HzF7PBzho2yA/edR6AYhm9N15ni5bt6TsTvH0TJiRj3Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:39:46.759537Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.08584","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d449c3aad97eda92185bbc31ef90f05f62c56d2b6db8fc4d25fc79755260bd84","sha256:5a67b3d3de017bb36258090a43f0a587763298bcf3c77a0e62e7fc8f1d624c8f"],"state_sha256":"48d537d3944477a2b4f8b6be861ea75bfc5e3118d984efe47efaf407ab68f955"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lXLlNZ+I44m9AD+aIEyu/WJOMhXEXqrDQQmyn3fkbqI7B8YYiXCv1pwSWUrm66AXqK+5OHmOGdbfbJYA3k/LBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T17:22:11.981630Z","bundle_sha256":"b6b8bf5babb8d3bef502b96193f471341ad3d128e16434acf95ceca6e50b0a20"}}