{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6EDVQTZIYG7FFFHQ2MHLGM2RGP","short_pith_number":"pith:6EDVQTZI","canonical_record":{"source":{"id":"2304.13424","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-26T10:12:12Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c5de48fe7c41c47d0b20f8383407876936e36fee0062d81a6aa83f9e4ef72fd9","abstract_canon_sha256":"a45dd9e376cca200fb3404f6404e0ad18a9cc1bff16c4d4fa8097af9f507be31"},"schema_version":"1.0"},"canonical_sha256":"f107584f28c1be5294f0d30eb3335133e7a2493ed1494649a2d2cf8c7e6cb405","source":{"kind":"arxiv","id":"2304.13424","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.13424","created_at":"2026-07-05T06:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2304.13424v1","created_at":"2026-07-05T06:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13424","created_at":"2026-07-05T06:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"6EDVQTZIYG7F","created_at":"2026-07-05T06:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"6EDVQTZIYG7FFFHQ","created_at":"2026-07-05T06:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"6EDVQTZI","created_at":"2026-07-05T06:04:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6EDVQTZIYG7FFFHQ2MHLGM2RGP","target":"record","payload":{"canonical_record":{"source":{"id":"2304.13424","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-26T10:12:12Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"c5de48fe7c41c47d0b20f8383407876936e36fee0062d81a6aa83f9e4ef72fd9","abstract_canon_sha256":"a45dd9e376cca200fb3404f6404e0ad18a9cc1bff16c4d4fa8097af9f507be31"},"schema_version":"1.0"},"canonical_sha256":"f107584f28c1be5294f0d30eb3335133e7a2493ed1494649a2d2cf8c7e6cb405","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:43.856347Z","signature_b64":"EeZaK1ZKjp1QcyzGjMO7RV1nHdgR5SdcEouSQGHsa4d1TsGlgtYJ0VQZN3l17nKGfS8QBcRkc+Dzcr3knYQpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f107584f28c1be5294f0d30eb3335133e7a2493ed1494649a2d2cf8c7e6cb405","last_reissued_at":"2026-07-05T06:04:43.855939Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:43.855939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.13424","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":"2026-07-05T06:04:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/lkS7xk/cpCGUJgVmu+Fpat4Ft3Nx/Q50UeLM5S00VRqxT3BMSNg9Cj3NfknQeHVWs3jYh8HwBh2kxiIwXvECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:27:40.096400Z"},"content_sha256":"ac568fb76a06d6cad1a75bff7c2b9454bd1e3c2e3b8876d71ca992bb2e6e1ca1","schema_version":"1.0","event_id":"sha256:ac568fb76a06d6cad1a75bff7c2b9454bd1e3c2e3b8876d71ca992bb2e6e1ca1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6EDVQTZIYG7FFFHQ2MHLGM2RGP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Cho-Jui Hsieh, Huan Zhang, Li-Cheng Lan","submitted_at":"2023-04-26T10:12:12Z","abstract_excerpt":"In this paper, we define, evaluate, and improve the ``relay-generalization'' performance of reinforcement learning (RL) agents on the out-of-distribution ``controllable'' states. Ideally, an RL agent that generally masters a task should reach its goal starting from any controllable state of the environment instead of memorizing a small set of trajectories. For example, a self-driving system should be able to take over the control from humans in the middle of driving and must continue to drive the car safely. To practically evaluate this type of generalization, we start the test agent from the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13424","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/2304.13424/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":"2026-07-05T06:04:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sOwfPIWSVNYIJ3RiqTBOeyaqWW0iUHXNML5NTbgc/Z3dKFZkSlTJ1EYs2SDYvZfr0ZNYBL+n8S9rTZEm210EDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T09:27:40.096931Z"},"content_sha256":"0f92b97f89dff78058e782845b7899d319c0f05771e98ed81e4c1d16902c0421","schema_version":"1.0","event_id":"sha256:0f92b97f89dff78058e782845b7899d319c0f05771e98ed81e4c1d16902c0421"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6EDVQTZIYG7FFFHQ2MHLGM2RGP/bundle.json","state_url":"https://pith.science/pith/6EDVQTZIYG7FFFHQ2MHLGM2RGP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6EDVQTZIYG7FFFHQ2MHLGM2RGP/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":"2026-08-18T09:27:40Z","links":{"resolver":"https://pith.science/pith/6EDVQTZIYG7FFFHQ2MHLGM2RGP","bundle":"https://pith.science/pith/6EDVQTZIYG7FFFHQ2MHLGM2RGP/bundle.json","state":"https://pith.science/pith/6EDVQTZIYG7FFFHQ2MHLGM2RGP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6EDVQTZIYG7FFFHQ2MHLGM2RGP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6EDVQTZIYG7FFFHQ2MHLGM2RGP","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":"a45dd9e376cca200fb3404f6404e0ad18a9cc1bff16c4d4fa8097af9f507be31","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-26T10:12:12Z","title_canon_sha256":"c5de48fe7c41c47d0b20f8383407876936e36fee0062d81a6aa83f9e4ef72fd9"},"schema_version":"1.0","source":{"id":"2304.13424","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.13424","created_at":"2026-07-05T06:04:43Z"},{"alias_kind":"arxiv_version","alias_value":"2304.13424v1","created_at":"2026-07-05T06:04:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13424","created_at":"2026-07-05T06:04:43Z"},{"alias_kind":"pith_short_12","alias_value":"6EDVQTZIYG7F","created_at":"2026-07-05T06:04:43Z"},{"alias_kind":"pith_short_16","alias_value":"6EDVQTZIYG7FFFHQ","created_at":"2026-07-05T06:04:43Z"},{"alias_kind":"pith_short_8","alias_value":"6EDVQTZI","created_at":"2026-07-05T06:04:43Z"}],"graph_snapshots":[{"event_id":"sha256:0f92b97f89dff78058e782845b7899d319c0f05771e98ed81e4c1d16902c0421","target":"graph","created_at":"2026-07-05T06:04:43Z","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/2304.13424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we define, evaluate, and improve the ``relay-generalization'' performance of reinforcement learning (RL) agents on the out-of-distribution ``controllable'' states. Ideally, an RL agent that generally masters a task should reach its goal starting from any controllable state of the environment instead of memorizing a small set of trajectories. For example, a self-driving system should be able to take over the control from humans in the middle of driving and must continue to drive the car safely. To practically evaluate this type of generalization, we start the test agent from the ","authors_text":"Cho-Jui Hsieh, Huan Zhang, Li-Cheng Lan","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-26T10:12:12Z","title":"Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13424","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:ac568fb76a06d6cad1a75bff7c2b9454bd1e3c2e3b8876d71ca992bb2e6e1ca1","target":"record","created_at":"2026-07-05T06:04:43Z","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":"a45dd9e376cca200fb3404f6404e0ad18a9cc1bff16c4d4fa8097af9f507be31","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-26T10:12:12Z","title_canon_sha256":"c5de48fe7c41c47d0b20f8383407876936e36fee0062d81a6aa83f9e4ef72fd9"},"schema_version":"1.0","source":{"id":"2304.13424","kind":"arxiv","version":1}},"canonical_sha256":"f107584f28c1be5294f0d30eb3335133e7a2493ed1494649a2d2cf8c7e6cb405","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f107584f28c1be5294f0d30eb3335133e7a2493ed1494649a2d2cf8c7e6cb405","first_computed_at":"2026-07-05T06:04:43.855939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:04:43.855939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EeZaK1ZKjp1QcyzGjMO7RV1nHdgR5SdcEouSQGHsa4d1TsGlgtYJ0VQZN3l17nKGfS8QBcRkc+Dzcr3knYQpAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:04:43.856347Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.13424","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac568fb76a06d6cad1a75bff7c2b9454bd1e3c2e3b8876d71ca992bb2e6e1ca1","sha256:0f92b97f89dff78058e782845b7899d319c0f05771e98ed81e4c1d16902c0421"],"state_sha256":"12fc261f373a1e9cf51647b9b7360a48f8bbf394f5cc3e70d829b9f2b06e2b0f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NnqTQlFn5s9B5M+g64Tgoj1zQJ5O2PbBr4paCd/Uf/eeKfLs0WRfQDdXujEY35QX2o9pFvnqofE2dtVCzJXTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T09:27:40.100643Z","bundle_sha256":"144cef5e9a3e1e2837e779a90f2c041695aa905c3d45235c7f6351047d29254e"}}