{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:MYOCRV3QVT3ZNTR7VUK3TVXJNZ","short_pith_number":"pith:MYOCRV3Q","canonical_record":{"source":{"id":"1910.12639","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-10-25T01:26:04Z","cross_cats_sorted":["cs.AI","cs.MA","cs.RO","cs.SY"],"title_canon_sha256":"9f88ead471618d0777cc99bae67246d00a56fcaba4b595b066309fbe483a5632","abstract_canon_sha256":"f0a0dd2f463ecce61d4bba0e6cd7845eeeb4e52a0c758ca71fa807ff53f8e63b"},"schema_version":"1.0"},"canonical_sha256":"661c28d770acf796ce3fad15b9d6e96e66b142e47e0d4ea77f527adf5585604e","source":{"kind":"arxiv","id":"1910.12639","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.12639","created_at":"2026-07-05T00:28:55Z"},{"alias_kind":"arxiv_version","alias_value":"1910.12639v2","created_at":"2026-07-05T00:28:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.12639","created_at":"2026-07-05T00:28:55Z"},{"alias_kind":"pith_short_12","alias_value":"MYOCRV3QVT3Z","created_at":"2026-07-05T00:28:55Z"},{"alias_kind":"pith_short_16","alias_value":"MYOCRV3QVT3ZNTR7","created_at":"2026-07-05T00:28:55Z"},{"alias_kind":"pith_short_8","alias_value":"MYOCRV3Q","created_at":"2026-07-05T00:28:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:MYOCRV3QVT3ZNTR7VUK3TVXJNZ","target":"record","payload":{"canonical_record":{"source":{"id":"1910.12639","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-10-25T01:26:04Z","cross_cats_sorted":["cs.AI","cs.MA","cs.RO","cs.SY"],"title_canon_sha256":"9f88ead471618d0777cc99bae67246d00a56fcaba4b595b066309fbe483a5632","abstract_canon_sha256":"f0a0dd2f463ecce61d4bba0e6cd7845eeeb4e52a0c758ca71fa807ff53f8e63b"},"schema_version":"1.0"},"canonical_sha256":"661c28d770acf796ce3fad15b9d6e96e66b142e47e0d4ea77f527adf5585604e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:55.762088Z","signature_b64":"giu0GTkEhDiNpP3X8gCKWr6BwZEYOQpMYoLNV8EBwHiOck7S9O0ZbcomUhf1FiQ9Z6WLhrqzxWF2fo+ZInD7BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"661c28d770acf796ce3fad15b9d6e96e66b142e47e0d4ea77f527adf5585604e","last_reissued_at":"2026-07-05T00:28:55.761655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:55.761655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.12639","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:28:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p2pjtFaBhy0TWhCvYPvHR47XUwlKhFqXWxBUx3WdZM6MjFkYg816XV4db/q0EOLKlzhTg+xI0p6ll2KS5K4eBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:03:32.843614Z"},"content_sha256":"d85d73092a816d4986c64e3cf5571605ff91ba01486a848bb3b4f342a7e3ff15","schema_version":"1.0","event_id":"sha256:d85d73092a816d4986c64e3cf5571605ff91ba01486a848bb3b4f342a7e3ff15"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:MYOCRV3QVT3ZNTR7VUK3TVXJNZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shielding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","cs.RO","cs.SY"],"primary_cat":"eess.SY","authors_text":"Osbert Bastani, Vijay Kumar, Wenbo Zhang","submitted_at":"2019-10-25T01:26:04Z","abstract_excerpt":"Reinforcement learning is a promising approach to learning control policies for performing complex multi-agent robotics tasks. However, a policy learned in simulation often fails to guarantee even simple safety properties such as obstacle avoidance. To ensure safety, we propose multi-agent model predictive shielding (MAMPS), an algorithm that provably guarantees safety for an arbitrary learned policy. In particular, it operates by using the learned policy as often as possible, but instead uses a backup policy in cases where it cannot guarantee the safety of the learned policy. Using a multi-ag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.12639","kind":"arxiv","version":2},"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/1910.12639/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":"2026-07-05T00:28:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FeiuyuBuwC6JzLc8t/LKIvNF5X8RCvP+4VYvahG0eKLj9lF2gOLZNHXMvqBiWfKln/bG+XYC6FCqbgwEAWgfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:03:32.844128Z"},"content_sha256":"947096fc443d20e664634631573059960ce0d385a010a7cd04546a27ce38dc9e","schema_version":"1.0","event_id":"sha256:947096fc443d20e664634631573059960ce0d385a010a7cd04546a27ce38dc9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MYOCRV3QVT3ZNTR7VUK3TVXJNZ/bundle.json","state_url":"https://pith.science/pith/MYOCRV3QVT3ZNTR7VUK3TVXJNZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MYOCRV3QVT3ZNTR7VUK3TVXJNZ/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":"2026-08-06T05:03:32Z","links":{"resolver":"https://pith.science/pith/MYOCRV3QVT3ZNTR7VUK3TVXJNZ","bundle":"https://pith.science/pith/MYOCRV3QVT3ZNTR7VUK3TVXJNZ/bundle.json","state":"https://pith.science/pith/MYOCRV3QVT3ZNTR7VUK3TVXJNZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MYOCRV3QVT3ZNTR7VUK3TVXJNZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:MYOCRV3QVT3ZNTR7VUK3TVXJNZ","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":"f0a0dd2f463ecce61d4bba0e6cd7845eeeb4e52a0c758ca71fa807ff53f8e63b","cross_cats_sorted":["cs.AI","cs.MA","cs.RO","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-10-25T01:26:04Z","title_canon_sha256":"9f88ead471618d0777cc99bae67246d00a56fcaba4b595b066309fbe483a5632"},"schema_version":"1.0","source":{"id":"1910.12639","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.12639","created_at":"2026-07-05T00:28:55Z"},{"alias_kind":"arxiv_version","alias_value":"1910.12639v2","created_at":"2026-07-05T00:28:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.12639","created_at":"2026-07-05T00:28:55Z"},{"alias_kind":"pith_short_12","alias_value":"MYOCRV3QVT3Z","created_at":"2026-07-05T00:28:55Z"},{"alias_kind":"pith_short_16","alias_value":"MYOCRV3QVT3ZNTR7","created_at":"2026-07-05T00:28:55Z"},{"alias_kind":"pith_short_8","alias_value":"MYOCRV3Q","created_at":"2026-07-05T00:28:55Z"}],"graph_snapshots":[{"event_id":"sha256:947096fc443d20e664634631573059960ce0d385a010a7cd04546a27ce38dc9e","target":"graph","created_at":"2026-07-05T00:28:55Z","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/1910.12639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning is a promising approach to learning control policies for performing complex multi-agent robotics tasks. However, a policy learned in simulation often fails to guarantee even simple safety properties such as obstacle avoidance. To ensure safety, we propose multi-agent model predictive shielding (MAMPS), an algorithm that provably guarantees safety for an arbitrary learned policy. In particular, it operates by using the learned policy as often as possible, but instead uses a backup policy in cases where it cannot guarantee the safety of the learned policy. Using a multi-ag","authors_text":"Osbert Bastani, Vijay Kumar, Wenbo Zhang","cross_cats":["cs.AI","cs.MA","cs.RO","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-10-25T01:26:04Z","title":"MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shielding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.12639","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:d85d73092a816d4986c64e3cf5571605ff91ba01486a848bb3b4f342a7e3ff15","target":"record","created_at":"2026-07-05T00:28:55Z","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":"f0a0dd2f463ecce61d4bba0e6cd7845eeeb4e52a0c758ca71fa807ff53f8e63b","cross_cats_sorted":["cs.AI","cs.MA","cs.RO","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.SY","submitted_at":"2019-10-25T01:26:04Z","title_canon_sha256":"9f88ead471618d0777cc99bae67246d00a56fcaba4b595b066309fbe483a5632"},"schema_version":"1.0","source":{"id":"1910.12639","kind":"arxiv","version":2}},"canonical_sha256":"661c28d770acf796ce3fad15b9d6e96e66b142e47e0d4ea77f527adf5585604e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"661c28d770acf796ce3fad15b9d6e96e66b142e47e0d4ea77f527adf5585604e","first_computed_at":"2026-07-05T00:28:55.761655Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:28:55.761655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"giu0GTkEhDiNpP3X8gCKWr6BwZEYOQpMYoLNV8EBwHiOck7S9O0ZbcomUhf1FiQ9Z6WLhrqzxWF2fo+ZInD7BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:28:55.762088Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.12639","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d85d73092a816d4986c64e3cf5571605ff91ba01486a848bb3b4f342a7e3ff15","sha256:947096fc443d20e664634631573059960ce0d385a010a7cd04546a27ce38dc9e"],"state_sha256":"7a351fea54218684b59e5d01e98f3431cd9be0ab1fd24e24ab18b622d1f3bd32"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PHZUq4BQGqRF2pFvvc8DQDPNHXFJCkIZ/Al8eQ5aMErdXX+kgV6iWIv5dZpP9MZ0JaC+S5Xkb5qfqztgmCdCBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:03:32.847835Z","bundle_sha256":"b7e38a2e4f2c103de8616bcf5f4035a5b367f107497d539b464ca6bcdce37554"}}