{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6W2WU3AIUIBG2F6ENJZA3VVYXK","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":"743f2cc028eb705ad86988d411189bf9154848f80c915f3cb954ad446b7e9491","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-08-06T02:53:55Z","title_canon_sha256":"123a5aa332d4ffe7415311cd2c01272003ae5e82a4e828ad2893becb94c3841c"},"schema_version":"1.0","source":{"id":"2408.02912","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.02912","created_at":"2026-07-05T09:21:47Z"},{"alias_kind":"arxiv_version","alias_value":"2408.02912v3","created_at":"2026-07-05T09:21:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02912","created_at":"2026-07-05T09:21:47Z"},{"alias_kind":"pith_short_12","alias_value":"6W2WU3AIUIBG","created_at":"2026-07-05T09:21:47Z"},{"alias_kind":"pith_short_16","alias_value":"6W2WU3AIUIBG2F6E","created_at":"2026-07-05T09:21:47Z"},{"alias_kind":"pith_short_8","alias_value":"6W2WU3AI","created_at":"2026-07-05T09:21:47Z"}],"graph_snapshots":[{"event_id":"sha256:48f6f18286a5cdad9caf2fa1e961608ba7a4fdb36913284cbb00d9f3713f6ab1","target":"graph","created_at":"2026-07-05T09:21:47Z","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/2408.02912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Online Imitation Learning struggles with the gap between extensive online exploration space and limited expert trajectories, hindering efficient exploration due to inaccurate reward estimation. Inspired by the findings from cognitive neuroscience, we hypothesize that an agent could estimate precise task-aware reward for efficient online exploration, through decomposing the target task into the objectives of \"what to do\" and the mechanisms of \"how to do\". In this work, we introduce the hybrid Key-state guided Online Imitation (KOI) learning method, which leverages the integration of semantic an","authors_text":"Bin Zhao, Di Hu, Dong Wang, Jingxian Lu, Wenke Xia, Xuelong Li, Zhigang Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-08-06T02:53:55Z","title":"KOI: Accelerating Online Imitation Learning via Hybrid Key-state Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02912","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":"sha256:1aa30f4d039fcd8182cf4bbb46762b3cc2f605b78494519b59e8f54eedb80050","target":"record","created_at":"2026-07-05T09:21:47Z","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":"743f2cc028eb705ad86988d411189bf9154848f80c915f3cb954ad446b7e9491","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-08-06T02:53:55Z","title_canon_sha256":"123a5aa332d4ffe7415311cd2c01272003ae5e82a4e828ad2893becb94c3841c"},"schema_version":"1.0","source":{"id":"2408.02912","kind":"arxiv","version":3}},"canonical_sha256":"f5b56a6c08a2026d17c46a720dd6b8ba811eb778b8798eae1aeb8a574958c4d4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5b56a6c08a2026d17c46a720dd6b8ba811eb778b8798eae1aeb8a574958c4d4","first_computed_at":"2026-07-05T09:21:47.586871Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:21:47.586871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jT6SrbQRq/DX7YXwjxzVgyjuveh5+tNNa0oSaecu9gOavWT6QVN3jC2/doSabGUTrMI2ZKJJ693Sao04+mDDCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:21:47.587362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.02912","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1aa30f4d039fcd8182cf4bbb46762b3cc2f605b78494519b59e8f54eedb80050","sha256:48f6f18286a5cdad9caf2fa1e961608ba7a4fdb36913284cbb00d9f3713f6ab1"],"state_sha256":"d53e748e6a534832211060331014b9ed03d30f4aa84766367738e5c6fdd24f24"}