{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:SOXDMFFRLT57TJXDNM7CSE3VRB","short_pith_number":"pith:SOXDMFFR","canonical_record":{"source":{"id":"1801.07292","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-22T19:47:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a07f998a035eaa861e7ede9d15aec11daf99a2e3df1ae03fcde08b3339b418eb","abstract_canon_sha256":"9aa4672d948fe5af2503bcc3cbd270dd9587e213f303566043b8d65b8ad4a30d"},"schema_version":"1.0"},"canonical_sha256":"93ae3614b15cfbf9a6e36b3e291375884fa0641a8fa137151f6c5e7c02d5ba3e","source":{"kind":"arxiv","id":"1801.07292","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.07292","created_at":"2026-05-18T00:25:14Z"},{"alias_kind":"arxiv_version","alias_value":"1801.07292v1","created_at":"2026-05-18T00:25:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07292","created_at":"2026-05-18T00:25:14Z"},{"alias_kind":"pith_short_12","alias_value":"SOXDMFFRLT57","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SOXDMFFRLT57TJXD","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SOXDMFFR","created_at":"2026-05-18T12:32:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:SOXDMFFRLT57TJXDNM7CSE3VRB","target":"record","payload":{"canonical_record":{"source":{"id":"1801.07292","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-22T19:47:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a07f998a035eaa861e7ede9d15aec11daf99a2e3df1ae03fcde08b3339b418eb","abstract_canon_sha256":"9aa4672d948fe5af2503bcc3cbd270dd9587e213f303566043b8d65b8ad4a30d"},"schema_version":"1.0"},"canonical_sha256":"93ae3614b15cfbf9a6e36b3e291375884fa0641a8fa137151f6c5e7c02d5ba3e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:25:14.956874Z","signature_b64":"9p23xA0e6Hp2AZ1irJmiQGFavvB6qwPDWS/YMle0abH5PNkPP/FYX0OUefELgl1Rr0ZH75T4XWKVp1ITgkXzBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93ae3614b15cfbf9a6e36b3e291375884fa0641a8fa137151f6c5e7c02d5ba3e","last_reissued_at":"2026-05-18T00:25:14.956209Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:25:14.956209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.07292","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":"2026-05-18T00:25:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LMwMQes48YFQdJYhakSV3zicTxXuRSJmbAu6FyrjPu14Xzg8vU52w1V6arYXFR94I86KclBROo0K2+SiqCxnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:21:25.317699Z"},"content_sha256":"6d69ff8336de7bfb72b875267409b7cafcaece0e8ddfd48a63472eb3b846a4fe","schema_version":"1.0","event_id":"sha256:6d69ff8336de7bfb72b875267409b7cafcaece0e8ddfd48a63472eb3b846a4fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:SOXDMFFRLT57TJXDNM7CSE3VRB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convergence of Value Aggregation for Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Byron Boots, Ching-An Cheng","submitted_at":"2018-01-22T19:47:34Z","abstract_excerpt":"Value aggregation is a general framework for solving imitation learning problems. Based on the idea of data aggregation, it generates a policy sequence by iteratively interleaving policy optimization and evaluation in an online learning setting. While the existence of a good policy in the policy sequence can be guaranteed non-asymptotically, little is known about the convergence of the sequence or the performance of the last policy. In this paper, we debunk the common belief that value aggregation always produces a convergent policy sequence with improving performance. Moreover, we identify a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07292","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":"2026-05-18T00:25:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CmBYttxdwlNC2K3pSuMEWbegL1VdlKvY3s2V8HNjof5Tc3lYwGonuoQnBN8T6WqZCSQe3IYJIQaq0N+v899EBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:21:25.318052Z"},"content_sha256":"80ba174356bc9a003e66b8a9d99c2a7e96399e6137bea7e6931413393e781028","schema_version":"1.0","event_id":"sha256:80ba174356bc9a003e66b8a9d99c2a7e96399e6137bea7e6931413393e781028"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SOXDMFFRLT57TJXDNM7CSE3VRB/bundle.json","state_url":"https://pith.science/pith/SOXDMFFRLT57TJXDNM7CSE3VRB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SOXDMFFRLT57TJXDNM7CSE3VRB/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":"2026-05-26T17:21:25Z","links":{"resolver":"https://pith.science/pith/SOXDMFFRLT57TJXDNM7CSE3VRB","bundle":"https://pith.science/pith/SOXDMFFRLT57TJXDNM7CSE3VRB/bundle.json","state":"https://pith.science/pith/SOXDMFFRLT57TJXDNM7CSE3VRB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SOXDMFFRLT57TJXDNM7CSE3VRB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:SOXDMFFRLT57TJXDNM7CSE3VRB","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":"9aa4672d948fe5af2503bcc3cbd270dd9587e213f303566043b8d65b8ad4a30d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-22T19:47:34Z","title_canon_sha256":"a07f998a035eaa861e7ede9d15aec11daf99a2e3df1ae03fcde08b3339b418eb"},"schema_version":"1.0","source":{"id":"1801.07292","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.07292","created_at":"2026-05-18T00:25:14Z"},{"alias_kind":"arxiv_version","alias_value":"1801.07292v1","created_at":"2026-05-18T00:25:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.07292","created_at":"2026-05-18T00:25:14Z"},{"alias_kind":"pith_short_12","alias_value":"SOXDMFFRLT57","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"SOXDMFFRLT57TJXD","created_at":"2026-05-18T12:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"SOXDMFFR","created_at":"2026-05-18T12:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:80ba174356bc9a003e66b8a9d99c2a7e96399e6137bea7e6931413393e781028","target":"graph","created_at":"2026-05-18T00:25:14Z","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":"Value aggregation is a general framework for solving imitation learning problems. Based on the idea of data aggregation, it generates a policy sequence by iteratively interleaving policy optimization and evaluation in an online learning setting. While the existence of a good policy in the policy sequence can be guaranteed non-asymptotically, little is known about the convergence of the sequence or the performance of the last policy. In this paper, we debunk the common belief that value aggregation always produces a convergent policy sequence with improving performance. Moreover, we identify a ","authors_text":"Byron Boots, Ching-An Cheng","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-22T19:47:34Z","title":"Convergence of Value Aggregation for Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.07292","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":"sha256:6d69ff8336de7bfb72b875267409b7cafcaece0e8ddfd48a63472eb3b846a4fe","target":"record","created_at":"2026-05-18T00:25:14Z","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":"9aa4672d948fe5af2503bcc3cbd270dd9587e213f303566043b8d65b8ad4a30d","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-01-22T19:47:34Z","title_canon_sha256":"a07f998a035eaa861e7ede9d15aec11daf99a2e3df1ae03fcde08b3339b418eb"},"schema_version":"1.0","source":{"id":"1801.07292","kind":"arxiv","version":1}},"canonical_sha256":"93ae3614b15cfbf9a6e36b3e291375884fa0641a8fa137151f6c5e7c02d5ba3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93ae3614b15cfbf9a6e36b3e291375884fa0641a8fa137151f6c5e7c02d5ba3e","first_computed_at":"2026-05-18T00:25:14.956209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:25:14.956209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9p23xA0e6Hp2AZ1irJmiQGFavvB6qwPDWS/YMle0abH5PNkPP/FYX0OUefELgl1Rr0ZH75T4XWKVp1ITgkXzBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:25:14.956874Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.07292","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d69ff8336de7bfb72b875267409b7cafcaece0e8ddfd48a63472eb3b846a4fe","sha256:80ba174356bc9a003e66b8a9d99c2a7e96399e6137bea7e6931413393e781028"],"state_sha256":"3168c6924213def52266f20e44b28ca7179a9efce408be41eed4006591901f18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/0ZznpizcOM2jPCVZIhOCoiXtw1hmf9yMKqx2s+a2vihg7LCrdsAD/psiXBmfDYQqqggct2D79IYuWLlhozICQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T17:21:25.320839Z","bundle_sha256":"2fccbd8d5cebf51df877f003dff0ddeac5bf2fa3f732ac2ee418654f4d127ece"}}