{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AZH73VZVLPMLSXVC3H7GUWQDMK","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":"654d5dbe190d7bf537331863783b465d7877f8ba37adaf6b7b66459ea510e645","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-16T15:39:51Z","title_canon_sha256":"0fd902a970f62c6f296c22c91ac855b26f56a89b9816800cbb8b97fe29484dc2"},"schema_version":"1.0","source":{"id":"2402.10765","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.10765","created_at":"2026-07-05T07:46:00Z"},{"alias_kind":"arxiv_version","alias_value":"2402.10765v1","created_at":"2026-07-05T07:46:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10765","created_at":"2026-07-05T07:46:00Z"},{"alias_kind":"pith_short_12","alias_value":"AZH73VZVLPML","created_at":"2026-07-05T07:46:00Z"},{"alias_kind":"pith_short_16","alias_value":"AZH73VZVLPMLSXVC","created_at":"2026-07-05T07:46:00Z"},{"alias_kind":"pith_short_8","alias_value":"AZH73VZV","created_at":"2026-07-05T07:46:00Z"}],"graph_snapshots":[{"event_id":"sha256:ef9fabd1135063e1d608673e3aeef27fe340b61a2de72208d3fe93e8f92a7180","target":"graph","created_at":"2026-07-05T07:46:00Z","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/2402.10765/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) can effectively learn complex policies. However, learning these policies often demands extensive trial-and-error interactions with the environment. In many real-world scenarios, this approach is not practical due to the high costs of data collection and safety concerns. As a result, a common strategy is to transfer a policy trained in a low-cost, rapid source simulator to a real-world target environment. However, this process poses challenges. Simulators, no matter how advanced, cannot perfectly replicate the intricacies of the real world, leading to dynamics discre","authors_text":"Hung The Tran, Linh Le Pham Van, Sunil Gupta","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-16T15:39:51Z","title":"Policy Learning for Off-Dynamics RL with Deficient Support"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10765","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":"sha256:8aeea52e26f1f3a8be5bdfb066a0571bb4b61d27dd4da7f5b3dae3692274e9c9","target":"record","created_at":"2026-07-05T07:46:00Z","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":"654d5dbe190d7bf537331863783b465d7877f8ba37adaf6b7b66459ea510e645","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-16T15:39:51Z","title_canon_sha256":"0fd902a970f62c6f296c22c91ac855b26f56a89b9816800cbb8b97fe29484dc2"},"schema_version":"1.0","source":{"id":"2402.10765","kind":"arxiv","version":1}},"canonical_sha256":"064ffdd7355bd8b95ea2d9fe6a5a0362bc287111a676eebc02d5853378c29a36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"064ffdd7355bd8b95ea2d9fe6a5a0362bc287111a676eebc02d5853378c29a36","first_computed_at":"2026-07-05T07:46:00.288474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:00.288474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B3Lj6y6Uv+17I7qkG2T7LT/WZjqYYc/FwMu1gRsZ4fvQSjBWUp/YZRE48PpPlDAw+idMaPlQG/fTZJ8oTj22DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:00.288877Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.10765","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8aeea52e26f1f3a8be5bdfb066a0571bb4b61d27dd4da7f5b3dae3692274e9c9","sha256:ef9fabd1135063e1d608673e3aeef27fe340b61a2de72208d3fe93e8f92a7180"],"state_sha256":"2ea31a0dc4fe3404ead0a10c2375700a8b8f1e3db3847fb157a7e3dd9b6c886c"}