{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:I6LSADAYQMOFR5Y2EFJOQSVL3R","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":"c4ad1e70a22898b6d3ad63e6dff5279b762b493bccf32366a7af98a10d1c3a92","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-02T12:11:44Z","title_canon_sha256":"3037b45b0e87aabecb4bab4d1ab0690f50f4e0391691fd0831d628bb4e408231"},"schema_version":"1.0","source":{"id":"2210.00498","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.00498","created_at":"2026-07-05T05:44:25Z"},{"alias_kind":"arxiv_version","alias_value":"2210.00498v2","created_at":"2026-07-05T05:44:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.00498","created_at":"2026-07-05T05:44:25Z"},{"alias_kind":"pith_short_12","alias_value":"I6LSADAYQMOF","created_at":"2026-07-05T05:44:25Z"},{"alias_kind":"pith_short_16","alias_value":"I6LSADAYQMOFR5Y2","created_at":"2026-07-05T05:44:25Z"},{"alias_kind":"pith_short_8","alias_value":"I6LSADAY","created_at":"2026-07-05T05:44:25Z"}],"graph_snapshots":[{"event_id":"sha256:4d24cabbad92635ee12ff571ecd1b20763bc25836379e26276aad481cdf607e6","target":"graph","created_at":"2026-07-05T05:44:25Z","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/2210.00498/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unsupervised reinforcement learning (URL) poses a promising paradigm to learn useful behaviors in a task-agnostic environment without the guidance of extrinsic rewards to facilitate the fast adaptation of various downstream tasks. Previous works focused on the pre-training in a model-free manner while lacking the study of transition dynamics modeling that leaves a large space for the improvement of sample efficiency in downstream tasks. To this end, we propose an Efficient Unsupervised Reinforcement Learning Framework with Multi-choice Dynamics model (EUCLID), which introduces a novel model-fu","authors_text":"Changjie Fan, Fei Ni, Jianye Hao, Jinyi Liu, Yan Zheng, Yao Mu, Yifu Yuan, Yingfeng Chen, Yujing Hu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-02T12:11:44Z","title":"EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.00498","kind":"arxiv","version":2},"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:c2b59204bc326aca1655f85b004501243ffac823fbf7200c85496b6a7677bb2d","target":"record","created_at":"2026-07-05T05:44:25Z","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":"c4ad1e70a22898b6d3ad63e6dff5279b762b493bccf32366a7af98a10d1c3a92","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-02T12:11:44Z","title_canon_sha256":"3037b45b0e87aabecb4bab4d1ab0690f50f4e0391691fd0831d628bb4e408231"},"schema_version":"1.0","source":{"id":"2210.00498","kind":"arxiv","version":2}},"canonical_sha256":"4797200c18831c58f71a2152e84aabdc48d8f9aee3997c6e7dec9e32b16f3ab7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4797200c18831c58f71a2152e84aabdc48d8f9aee3997c6e7dec9e32b16f3ab7","first_computed_at":"2026-07-05T05:44:25.244924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:44:25.244924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kRCrpve4G8anmxA2QL7KrxN5m9DuGqYA98V8RLDXKbtf0sM9w+ZSflL2Di2UrM8+k/fHZ39WX7/UPyqnUykUDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:44:25.245391Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.00498","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2b59204bc326aca1655f85b004501243ffac823fbf7200c85496b6a7677bb2d","sha256:4d24cabbad92635ee12ff571ecd1b20763bc25836379e26276aad481cdf607e6"],"state_sha256":"687c0aef2ec7123f94b2911beaa5d5ba66cf3979b47e140d377c1705a590ab55"}