{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AIT2U22CLM5TGF7SLLFFPIY6SE","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":"066b3709245bfd92a7940845fa966068b322d5d4d42657b3da4e47c6578e963c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T04:30:30Z","title_canon_sha256":"031a9af8f04b7dd64d25d5ad2c70a9380d7cd3144b774cf5a6d83128f46d257c"},"schema_version":"1.0","source":{"id":"2605.15603","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15603","created_at":"2026-05-20T00:01:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15603v1","created_at":"2026-05-20T00:01:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15603","created_at":"2026-05-20T00:01:07Z"},{"alias_kind":"pith_short_12","alias_value":"AIT2U22CLM5T","created_at":"2026-05-20T00:01:07Z"},{"alias_kind":"pith_short_16","alias_value":"AIT2U22CLM5TGF7S","created_at":"2026-05-20T00:01:07Z"},{"alias_kind":"pith_short_8","alias_value":"AIT2U22C","created_at":"2026-05-20T00:01:07Z"}],"graph_snapshots":[{"event_id":"sha256:421ae1f321db30669ed16114a65eb3ba4fb90e00aea448a700a30d41989e2b1b","target":"graph","created_at":"2026-05-20T00:01:07Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:34.894944Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.052786Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.15603/integrity.json","findings":[],"snapshot_sha256":"ed997616e8fd7ddcb5f5e3dce9e5a64c8d6b4a2d2310c658f5b19f5b33ae47be","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model-based reinforcement learning (RL) offers a compelling approach to offline RL by enabling value learning on imagined on-policy trajectories. However, it often suffers from compounding errors due to repeated model inference on self-generated states. While geometric horizon models (GHM) alleviate this issue through direct prediction over a discounted infinite-horizon future, they remain challenged in accurately modeling distant future states. To this end, we introduce universal horizon models (UHM), a generalization of GHM that directly predicts future states under arbitrary horizons. Lever","authors_text":"Hojun Chung, Junseo Lee, Songhwai Oh","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T04:30:30Z","title":"Offline Reinforcement Learning with Universal Horizon Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15603","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":"sha256:28b4f268682a250d91a87db8c4629151a7186c36efb99361d1d77ff6a743cd97","target":"record","created_at":"2026-05-20T00:01:07Z","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":"066b3709245bfd92a7940845fa966068b322d5d4d42657b3da4e47c6578e963c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T04:30:30Z","title_canon_sha256":"031a9af8f04b7dd64d25d5ad2c70a9380d7cd3144b774cf5a6d83128f46d257c"},"schema_version":"1.0","source":{"id":"2605.15603","kind":"arxiv","version":1}},"canonical_sha256":"0227aa6b425b3b3317f25aca57a31e9117b8bc9e58017000ac369410190564e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0227aa6b425b3b3317f25aca57a31e9117b8bc9e58017000ac369410190564e5","first_computed_at":"2026-05-20T00:01:07.615561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:07.615561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mGKH3ASew7SKQVN1iw8HUCSLsj1KZnQ5gXiR3GuA+ih5HCbs92TE8lRBGjBQGU69JiEvrqGqC+4w3oF+BBahBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:07.616538Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15603","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28b4f268682a250d91a87db8c4629151a7186c36efb99361d1d77ff6a743cd97","sha256:421ae1f321db30669ed16114a65eb3ba4fb90e00aea448a700a30d41989e2b1b"],"state_sha256":"6f2fb73886cda9d9622665e26b1c18c05c61586d62fa57521f3fb307f0c7e727"}