{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PIJNTQN6PSKMOTM2AQQDBN4XLH","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":"ca693f6ffac9ff22902a0ac9e728114b6a84eeca35c08479dd463572d755550c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-06T18:31:08Z","title_canon_sha256":"1aed49b339be8a8a8b55ad6b41bc2aac847300a0173a9474d5a5dec4c0c7edf0"},"schema_version":"1.0","source":{"id":"2106.03207","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03207","created_at":"2026-07-05T03:52:49Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03207v3","created_at":"2026-07-05T03:52:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03207","created_at":"2026-07-05T03:52:49Z"},{"alias_kind":"pith_short_12","alias_value":"PIJNTQN6PSKM","created_at":"2026-07-05T03:52:49Z"},{"alias_kind":"pith_short_16","alias_value":"PIJNTQN6PSKMOTM2","created_at":"2026-07-05T03:52:49Z"},{"alias_kind":"pith_short_8","alias_value":"PIJNTQN6","created_at":"2026-07-05T03:52:49Z"}],"graph_snapshots":[{"event_id":"sha256:f5d1ff8980512f0927def8fdc5b0dc849601923bf397080f81200a3d8360586d","target":"graph","created_at":"2026-07-05T03:52:49Z","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/2106.03207/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies offline Imitation Learning (IL) where an agent learns to imitate an expert demonstrator without additional online environment interactions. Instead, the learner is presented with a static offline dataset of state-action-next state transition triples from a potentially less proficient behavior policy. We introduce Model-based IL from Offline data (MILO): an algorithmic framework that utilizes the static dataset to solve the offline IL problem efficiently both in theory and in practice. In theory, even if the behavior policy is highly sub-optimal compared to the expert, we sho","authors_text":"Dhruv Sreenivas, Jonathan D. Chang, Masatoshi Uehara, Rahul Kidambi, Wen Sun","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-06T18:31:08Z","title":"Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03207","kind":"arxiv","version":3},"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:ab330189faffd1fb4ac47ec9dd5968656e1b58772d33e24be4b0fa71ddf84ef5","target":"record","created_at":"2026-07-05T03:52:49Z","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":"ca693f6ffac9ff22902a0ac9e728114b6a84eeca35c08479dd463572d755550c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-06T18:31:08Z","title_canon_sha256":"1aed49b339be8a8a8b55ad6b41bc2aac847300a0173a9474d5a5dec4c0c7edf0"},"schema_version":"1.0","source":{"id":"2106.03207","kind":"arxiv","version":3}},"canonical_sha256":"7a12d9c1be7c94c74d9a042030b79759cfde5ce10b9d0247d527798e55ddde8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a12d9c1be7c94c74d9a042030b79759cfde5ce10b9d0247d527798e55ddde8c","first_computed_at":"2026-07-05T03:52:49.650779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:52:49.650779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tfZfnYi2wC6pFGdANln8KR1Hv/3KY/pdOi3jsuvvLXiaYikJPIBeQBd+MrWFhwkasujz6izpwmaUrbiwPc0HAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:52:49.651239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.03207","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab330189faffd1fb4ac47ec9dd5968656e1b58772d33e24be4b0fa71ddf84ef5","sha256:f5d1ff8980512f0927def8fdc5b0dc849601923bf397080f81200a3d8360586d"],"state_sha256":"9415287dd8a3d5415ee8bb0017e3e83a4e923b3425a2ce99dad21174fc00dcaa"}