{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BN5RAQZBKTMKXEFDPZ6RZKHGTV","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":"05df09fe226cebad8a5a0e6e59c4db0be7acf5702557fe5b903c05e2b8e96960","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T19:04:09Z","title_canon_sha256":"6a1e1c402ba49bda8f503d992ca971884b8f8fa1d58948555c425e033c48af3d"},"schema_version":"1.0","source":{"id":"2006.10810","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.10810","created_at":"2026-07-05T01:11:25Z"},{"alias_kind":"arxiv_version","alias_value":"2006.10810v1","created_at":"2026-07-05T01:11:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.10810","created_at":"2026-07-05T01:11:25Z"},{"alias_kind":"pith_short_12","alias_value":"BN5RAQZBKTMK","created_at":"2026-07-05T01:11:25Z"},{"alias_kind":"pith_short_16","alias_value":"BN5RAQZBKTMKXEFD","created_at":"2026-07-05T01:11:25Z"},{"alias_kind":"pith_short_8","alias_value":"BN5RAQZB","created_at":"2026-07-05T01:11:25Z"}],"graph_snapshots":[{"event_id":"sha256:9737c3c32e408b894bed8e04c8e96817a5d7925a99b5e145897665abc5f29ea3","target":"graph","created_at":"2026-07-05T01:11:25Z","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/2006.10810/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While recent state-of-the-art results for adversarial imitation-learning algorithms are encouraging, recent works exploring the imitation learning from observation (ILO) setting, where trajectories \\textit{only} contain expert observations, have not been met with the same success. Inspired by recent investigations of $f$-divergence manipulation for the standard imitation learning setting(Ke et al., 2019; Ghasemipour et al., 2019), we here examine the extent to which variations in the choice of probabilistic divergence may yield more performant ILO algorithms. We unfortunately find that $f$-div","authors_text":"Alekh Agarwal, Asli Celikyilmaz, Bill Dolan, Debadeepta Dey, Dilip Arumugam, Elnaz Nouri","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T19:04:09Z","title":"Reparameterized Variational Divergence Minimization for Stable Imitation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.10810","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:ce86b20c09f107318c6915b10ec3bffec7e8b6d146b7240584c836a1da62316a","target":"record","created_at":"2026-07-05T01:11:25Z","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":"05df09fe226cebad8a5a0e6e59c4db0be7acf5702557fe5b903c05e2b8e96960","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-18T19:04:09Z","title_canon_sha256":"6a1e1c402ba49bda8f503d992ca971884b8f8fa1d58948555c425e033c48af3d"},"schema_version":"1.0","source":{"id":"2006.10810","kind":"arxiv","version":1}},"canonical_sha256":"0b7b10432154d8ab90a37e7d1ca8e69d655aeea25c30f38776ff92da356e6564","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b7b10432154d8ab90a37e7d1ca8e69d655aeea25c30f38776ff92da356e6564","first_computed_at":"2026-07-05T01:11:25.615807Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:11:25.615807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UaQ7yATwJnUM5M5nEQFDNS+mZ4mDK9kJlnMW7nwRCY5AZoI3rKjYPQdD8L4zosOPL77F/XKrWMjDUIYVcJinAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:11:25.616270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.10810","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce86b20c09f107318c6915b10ec3bffec7e8b6d146b7240584c836a1da62316a","sha256:9737c3c32e408b894bed8e04c8e96817a5d7925a99b5e145897665abc5f29ea3"],"state_sha256":"5cb783fed29115a9b5f49815a652516ccbeace4ec9ec9807e2a17af1e6552313"}