{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:64XG6Q3API26J7VSJKI2GFY6JV","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":"bfe46756dd950768e74b99455a188b7944514a5a09d05caa8ce644a447a15429","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-23T03:43:10Z","title_canon_sha256":"fe1a0a4b37ae87ea6754bd2a17d8d3b1b6ee6842188d9ee0a59580b4dfeb3973"},"schema_version":"1.0","source":{"id":"2106.12142","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.12142","created_at":"2026-07-05T05:12:48Z"},{"alias_kind":"arxiv_version","alias_value":"2106.12142v4","created_at":"2026-07-05T05:12:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.12142","created_at":"2026-07-05T05:12:48Z"},{"alias_kind":"pith_short_12","alias_value":"64XG6Q3API26","created_at":"2026-07-05T05:12:48Z"},{"alias_kind":"pith_short_16","alias_value":"64XG6Q3API26J7VS","created_at":"2026-07-05T05:12:48Z"},{"alias_kind":"pith_short_8","alias_value":"64XG6Q3A","created_at":"2026-07-05T05:12:48Z"}],"graph_snapshots":[{"event_id":"sha256:07b4de96aa4be96621c2efc6e04b4b142cb1a00f4c5274f020c1ccd7100cbd7c","target":"graph","created_at":"2026-07-05T05:12:48Z","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/2106.12142/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many sequential decision-making problems (e.g., robotics control, game playing, sequential prediction), human or expert data is available containing useful information about the task. However, imitation learning (IL) from a small amount of expert data can be challenging in high-dimensional environments with complex dynamics. Behavioral cloning is a simple method that is widely used due to its simplicity of implementation and stable convergence but doesn't utilize any information involving the environment's dynamics. Many existing methods that exploit dynamics information are difficult to tr","authors_text":"Chris Cundy, Divyansh Garg, Jiaming Song, Matthieu Geist, Shuvam Chakraborty, Stefano Ermon","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-23T03:43:10Z","title":"IQ-Learn: Inverse soft-Q Learning for Imitation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.12142","kind":"arxiv","version":4},"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:ecda7a46344da09bfd0c92550d257a1f3deee4df7cc243ae53c43baab5aa3dae","target":"record","created_at":"2026-07-05T05:12:48Z","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":"bfe46756dd950768e74b99455a188b7944514a5a09d05caa8ce644a447a15429","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-23T03:43:10Z","title_canon_sha256":"fe1a0a4b37ae87ea6754bd2a17d8d3b1b6ee6842188d9ee0a59580b4dfeb3973"},"schema_version":"1.0","source":{"id":"2106.12142","kind":"arxiv","version":4}},"canonical_sha256":"f72e6f43607a35e4feb24a91a3171e4d7437c6133d585041d2e92a08c83eb2e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f72e6f43607a35e4feb24a91a3171e4d7437c6133d585041d2e92a08c83eb2e7","first_computed_at":"2026-07-05T05:12:48.727448Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:12:48.727448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"89tK/Y+fPO+VNagKNzSAs1+3UHDZGy7DHwJEbh1T+9SzkO0SI4PcpY2IqiBngFyvbic1wa+jkFw2NEwA2iuiCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:12:48.727914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.12142","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ecda7a46344da09bfd0c92550d257a1f3deee4df7cc243ae53c43baab5aa3dae","sha256:07b4de96aa4be96621c2efc6e04b4b142cb1a00f4c5274f020c1ccd7100cbd7c"],"state_sha256":"fe079b7a9417cc086a8a1e919a474edb977499b219c4889f1ba6341f6c51c0c5"}