{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:GJZ3OHFZ4RQRD3SREB7Q6LMD7S","short_pith_number":"pith:GJZ3OHFZ","canonical_record":{"source":{"id":"1810.11505","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2018-10-26T18:57:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bd5c1a13b0b60f39f1129e660941f1d0631d57e54f4dfad238403f3468a03636","abstract_canon_sha256":"6e2c14dae74d3eb32fe11d51d2ecc82da3dc4a5dc2d7c5e0976e05dcde3ddfc9"},"schema_version":"1.0"},"canonical_sha256":"3273b71cb9e46111ee51207f0f2d83fc8ca2a9a08d149b2411a5cda756b5147f","source":{"kind":"arxiv","id":"1810.11505","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11505","created_at":"2026-05-18T00:02:08Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11505v1","created_at":"2026-05-18T00:02:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11505","created_at":"2026-05-18T00:02:08Z"},{"alias_kind":"pith_short_12","alias_value":"GJZ3OHFZ4RQR","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GJZ3OHFZ4RQRD3SR","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GJZ3OHFZ","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:GJZ3OHFZ4RQRD3SREB7Q6LMD7S","target":"record","payload":{"canonical_record":{"source":{"id":"1810.11505","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2018-10-26T18:57:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bd5c1a13b0b60f39f1129e660941f1d0631d57e54f4dfad238403f3468a03636","abstract_canon_sha256":"6e2c14dae74d3eb32fe11d51d2ecc82da3dc4a5dc2d7c5e0976e05dcde3ddfc9"},"schema_version":"1.0"},"canonical_sha256":"3273b71cb9e46111ee51207f0f2d83fc8ca2a9a08d149b2411a5cda756b5147f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:08.472907Z","signature_b64":"P4FTWuUXZiHVIh3KCcG0S3wZ1Hpl1YInF/ke46bjIuw2WkMOwsKWhaLRx+oQmD158drDrgM/Zcuit2k82E0qCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3273b71cb9e46111ee51207f0f2d83fc8ca2a9a08d149b2411a5cda756b5147f","last_reissued_at":"2026-05-18T00:02:08.472063Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:08.472063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.11505","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":"2026-05-18T00:02:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VAsPxHmIvSIFTtjAzgswFyyoftrJZST9LcuSHOjUcAqBe9241xdm/204Xy00qDl6QGyaDf4xbr1X1FCDZlczDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T15:12:43.768394Z"},"content_sha256":"81cc5faa07f62e0880fe3791f32ad98ac6eaf058c0eaf01a60764446e38db1d8","schema_version":"1.0","event_id":"sha256:81cc5faa07f62e0880fe3791f32ad98ac6eaf058c0eaf01a60764446e38db1d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:GJZ3OHFZ4RQRD3SREB7Q6LMD7S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stability-certified reinforcement learning: A control-theoretic perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SY","authors_text":"Javad Lavaei, Ming Jin","submitted_at":"2018-10-26T18:57:35Z","abstract_excerpt":"We investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems. We show that by regulating the input-output gradients of policies, strong guarantees of robust stability can be obtained based on a proposed semidefinite programming feasibility problem. The method is able to certify a large set of stabilizing controllers by exploiting problem-specific structures; furthermore, we analyze and establish its (non)conservatism. Empirical evaluations on two decentralized control tasks, namely multi-flight formation an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11505","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":"2026-05-18T00:02:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q0ZhaMXI/Iw5mP4sSRjyFn+TtLHrpmT7bTJGP8w5sxptAYZIyWbZw14A7G5reSHDqkT58Fjn3h6ke+7XZANUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T15:12:43.768894Z"},"content_sha256":"bc0c8f33e44684a3308443cdb1ad78315bdcc8e37232e3c1eb56c5eacace8045","schema_version":"1.0","event_id":"sha256:bc0c8f33e44684a3308443cdb1ad78315bdcc8e37232e3c1eb56c5eacace8045"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GJZ3OHFZ4RQRD3SREB7Q6LMD7S/bundle.json","state_url":"https://pith.science/pith/GJZ3OHFZ4RQRD3SREB7Q6LMD7S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GJZ3OHFZ4RQRD3SREB7Q6LMD7S/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":"2026-08-23T15:12:43Z","links":{"resolver":"https://pith.science/pith/GJZ3OHFZ4RQRD3SREB7Q6LMD7S","bundle":"https://pith.science/pith/GJZ3OHFZ4RQRD3SREB7Q6LMD7S/bundle.json","state":"https://pith.science/pith/GJZ3OHFZ4RQRD3SREB7Q6LMD7S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GJZ3OHFZ4RQRD3SREB7Q6LMD7S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GJZ3OHFZ4RQRD3SREB7Q6LMD7S","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":"6e2c14dae74d3eb32fe11d51d2ecc82da3dc4a5dc2d7c5e0976e05dcde3ddfc9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2018-10-26T18:57:35Z","title_canon_sha256":"bd5c1a13b0b60f39f1129e660941f1d0631d57e54f4dfad238403f3468a03636"},"schema_version":"1.0","source":{"id":"1810.11505","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11505","created_at":"2026-05-18T00:02:08Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11505v1","created_at":"2026-05-18T00:02:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11505","created_at":"2026-05-18T00:02:08Z"},{"alias_kind":"pith_short_12","alias_value":"GJZ3OHFZ4RQR","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GJZ3OHFZ4RQRD3SR","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GJZ3OHFZ","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:bc0c8f33e44684a3308443cdb1ad78315bdcc8e37232e3c1eb56c5eacace8045","target":"graph","created_at":"2026-05-18T00:02:08Z","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 investigate the important problem of certifying stability of reinforcement learning policies when interconnected with nonlinear dynamical systems. We show that by regulating the input-output gradients of policies, strong guarantees of robust stability can be obtained based on a proposed semidefinite programming feasibility problem. The method is able to certify a large set of stabilizing controllers by exploiting problem-specific structures; furthermore, we analyze and establish its (non)conservatism. Empirical evaluations on two decentralized control tasks, namely multi-flight formation an","authors_text":"Javad Lavaei, Ming Jin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2018-10-26T18:57:35Z","title":"Stability-certified reinforcement learning: A control-theoretic perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11505","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":"sha256:81cc5faa07f62e0880fe3791f32ad98ac6eaf058c0eaf01a60764446e38db1d8","target":"record","created_at":"2026-05-18T00:02:08Z","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":"6e2c14dae74d3eb32fe11d51d2ecc82da3dc4a5dc2d7c5e0976e05dcde3ddfc9","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2018-10-26T18:57:35Z","title_canon_sha256":"bd5c1a13b0b60f39f1129e660941f1d0631d57e54f4dfad238403f3468a03636"},"schema_version":"1.0","source":{"id":"1810.11505","kind":"arxiv","version":1}},"canonical_sha256":"3273b71cb9e46111ee51207f0f2d83fc8ca2a9a08d149b2411a5cda756b5147f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3273b71cb9e46111ee51207f0f2d83fc8ca2a9a08d149b2411a5cda756b5147f","first_computed_at":"2026-05-18T00:02:08.472063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:08.472063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P4FTWuUXZiHVIh3KCcG0S3wZ1Hpl1YInF/ke46bjIuw2WkMOwsKWhaLRx+oQmD158drDrgM/Zcuit2k82E0qCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:08.472907Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.11505","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:81cc5faa07f62e0880fe3791f32ad98ac6eaf058c0eaf01a60764446e38db1d8","sha256:bc0c8f33e44684a3308443cdb1ad78315bdcc8e37232e3c1eb56c5eacace8045"],"state_sha256":"c16346cf4d2722c5925113503196719985e8f9585530258b633fc308f0dbe5c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YGUICI9VcLfUWcmNzii7+ZMYBa5ydOuvN7qnPFj0l1wVuHkJ6kByNp7qUSTwqgRCE/qfGvFKYH9S5c6IgYe5Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T15:12:43.773563Z","bundle_sha256":"0c85a20263adf6301cac1b934340d4e3c72dbefda2a70e3ddb8ff570eec639ea"}}