{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WNNRW5ERIKKSZXEUQZ3KTREJI2","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":"aa290f5bc4e7e9f950f193c8ee038aa87b1e07b84d4678fd82ab783126a84ae4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2022-02-25T10:29:05Z","title_canon_sha256":"b1ec7e6899af870a4e19621c37fad5f4a53058c835d9330f8f6c7ebe83fbcd15"},"schema_version":"1.0","source":{"id":"2202.12597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.12597","created_at":"2026-07-05T04:00:06Z"},{"alias_kind":"arxiv_version","alias_value":"2202.12597v1","created_at":"2026-07-05T04:00:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.12597","created_at":"2026-07-05T04:00:06Z"},{"alias_kind":"pith_short_12","alias_value":"WNNRW5ERIKKS","created_at":"2026-07-05T04:00:06Z"},{"alias_kind":"pith_short_16","alias_value":"WNNRW5ERIKKSZXEU","created_at":"2026-07-05T04:00:06Z"},{"alias_kind":"pith_short_8","alias_value":"WNNRW5ER","created_at":"2026-07-05T04:00:06Z"}],"graph_snapshots":[{"event_id":"sha256:8dcd5223406edc1a7279d4ce4b9bd8f66b276871896b7a48ff35cf131f0d3a79","target":"graph","created_at":"2026-07-05T04:00:06Z","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/2202.12597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An inverse reinforcement learning (IRL) agent learns to act intelligently by observing expert demonstrations and learning the expert's underlying reward function. Although learning the reward functions from demonstrations has achieved great success in various tasks, several other challenges are mostly ignored. Firstly, existing IRL methods try to learn the reward function from scratch without relying on any prior knowledge. Secondly, traditional IRL methods assume the reward functions are homogeneous across all the demonstrations. Some existing IRL methods managed to extend to the heterogeneou","authors_text":"David Hsu, Wee Sun Lee, Wei Gao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2022-02-25T10:29:05Z","title":"Context-Hierarchy Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.12597","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":"sha256:913bd7dd2fad7126d1f986478c3c9766b31edcd76a8b5b1ee3610fd0be70617e","target":"record","created_at":"2026-07-05T04:00:06Z","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":"aa290f5bc4e7e9f950f193c8ee038aa87b1e07b84d4678fd82ab783126a84ae4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2022-02-25T10:29:05Z","title_canon_sha256":"b1ec7e6899af870a4e19621c37fad5f4a53058c835d9330f8f6c7ebe83fbcd15"},"schema_version":"1.0","source":{"id":"2202.12597","kind":"arxiv","version":1}},"canonical_sha256":"b35b1b749142952cdc948676a9c4894697f66291c9aa16b9bbbe92d80c60ad1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b35b1b749142952cdc948676a9c4894697f66291c9aa16b9bbbe92d80c60ad1d","first_computed_at":"2026-07-05T04:00:06.131443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:00:06.131443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Djtii8DFZAma8CA/SsD8fcym75Yo1Hp+H++0lgw7OhwzI/ANF/VxAw0Sm3PSqUfro0rMtobViHkSVTiLQ8bAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:00:06.131830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.12597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:913bd7dd2fad7126d1f986478c3c9766b31edcd76a8b5b1ee3610fd0be70617e","sha256:8dcd5223406edc1a7279d4ce4b9bd8f66b276871896b7a48ff35cf131f0d3a79"],"state_sha256":"1c5c3300629c20635692000456e8302099ce434b53391343ebfe6c85671ecd59"}