{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2FQXE3ZJXOOAF3IKTJMNK257SU","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":"39955d79d7c23a3d1a0626c36909b3d0a5d1fbf8230eb80ffe2b3dc6235d0f41","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T19:29:56Z","title_canon_sha256":"951276f4836216697f322554d959f313473c59391dcf64f996c0c728b2f0c88e"},"schema_version":"1.0","source":{"id":"2205.15397","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.15397","created_at":"2026-07-05T05:33:11Z"},{"alias_kind":"arxiv_version","alias_value":"2205.15397v5","created_at":"2026-07-05T05:33:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.15397","created_at":"2026-07-05T05:33:11Z"},{"alias_kind":"pith_short_12","alias_value":"2FQXE3ZJXOOA","created_at":"2026-07-05T05:33:11Z"},{"alias_kind":"pith_short_16","alias_value":"2FQXE3ZJXOOAF3IK","created_at":"2026-07-05T05:33:11Z"},{"alias_kind":"pith_short_8","alias_value":"2FQXE3ZJ","created_at":"2026-07-05T05:33:11Z"}],"graph_snapshots":[{"event_id":"sha256:2e172c6eb51105112d139d2b74f5ef91f62354adb83fa77ebe3ec6ddc7a27320","target":"graph","created_at":"2026-07-05T05:33:11Z","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/2205.15397/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Online imitation learning is the problem of how best to mimic expert demonstrations, given access to the environment or an accurate simulator. Prior work has shown that in the infinite sample regime, exact moment matching achieves value equivalence to the expert policy. However, in the finite sample regime, even if one has no optimization error, empirical variance can lead to a performance gap that scales with $H^2 / N$ for behavioral cloning and $H / \\sqrt{N}$ for online moment matching, where $H$ is the horizon and $N$ is the size of the expert dataset. We introduce the technique of replay e","authors_text":"Gokul Swamy, J. Andrew Bagnell, Jiantao Jiao, Kannan Ramchandran, Matthew Peng, Nived Rajaraman, Sanjiban Choudhury, Zhiwei Steven Wu","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T19:29:56Z","title":"Minimax Optimal Online Imitation Learning via Replay Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.15397","kind":"arxiv","version":5},"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:eccf7357e966a8c6728f7202a35316b4eeb77f15708483f85ce451c3c135b8d1","target":"record","created_at":"2026-07-05T05:33:11Z","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":"39955d79d7c23a3d1a0626c36909b3d0a5d1fbf8230eb80ffe2b3dc6235d0f41","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T19:29:56Z","title_canon_sha256":"951276f4836216697f322554d959f313473c59391dcf64f996c0c728b2f0c88e"},"schema_version":"1.0","source":{"id":"2205.15397","kind":"arxiv","version":5}},"canonical_sha256":"d161726f29bb9c02ed0a9a58d56bbf9537613f3639cbbfd932977c9f626e4f51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d161726f29bb9c02ed0a9a58d56bbf9537613f3639cbbfd932977c9f626e4f51","first_computed_at":"2026-07-05T05:33:11.549504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:33:11.549504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XCz7UA0l0Cawvo0K2cxFl2eOqvXS6s+vwjC/kUz4EApubVyNEh6FDAP2JxiConbfIxZYIn3aEx6jvfgDh/b9BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:33:11.549931Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.15397","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eccf7357e966a8c6728f7202a35316b4eeb77f15708483f85ce451c3c135b8d1","sha256:2e172c6eb51105112d139d2b74f5ef91f62354adb83fa77ebe3ec6ddc7a27320"],"state_sha256":"8b23a4d27b112f9e31641b68b9abe47b4bee57b3e9b4db0309ccdf2955745bc1"}