{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GUJHENTELP6SJZBXS5SZQN5A4W","short_pith_number":"pith:GUJHENTE","schema_version":"1.0","canonical_sha256":"35127236645bfd24e43797659837a0e58e108e9f77025032fea2a556774ddda0","source":{"kind":"arxiv","id":"2605.24405","version":1},"attestation_state":"computed","paper":{"title":"Generative OOD-regularized Model-based Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aysin Tumay, Elise Jortberg, Jiahe Huang, Rose Yu","submitted_at":"2026-05-23T05:29:02Z","abstract_excerpt":"We study sequential decision-making with offline reinforcement learning (RL). Traditional offline RL policies may result in out-of-distribution (OOD) actions when training relies only on sparse offline representations. To ensure safe offline policies in a sparse state-action space, we explore how density estimation models can be integrated into model-based RL methods to avoid the OOD regions. Generative models are capable of explicitly modeling the density in sparse state-action spaces. Building on this, we introduce Generative OOD-regularized Model-based Policy Optimization (GORMPO), a densit"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.24405","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T05:29:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c13b1f1f28ae0c72957eb4f94f7727264b0d32e74333a811c277612656b214a0","abstract_canon_sha256":"36e8dd62ad8fb59816213f20bb4a7e0d3ef2369caac4ea3276fdd8685aaf6ed4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:37.792808Z","signature_b64":"apT7Htj958ZaopGiaKA8QFL0MSwUTFNBdXiVKQsMRng09Aq6nxVGFg4ZckMmfi28sjWlNzFJufyw4I5jm/lqDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35127236645bfd24e43797659837a0e58e108e9f77025032fea2a556774ddda0","last_reissued_at":"2026-05-26T01:03:37.792021Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:37.792021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative OOD-regularized Model-based Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Aysin Tumay, Elise Jortberg, Jiahe Huang, Rose Yu","submitted_at":"2026-05-23T05:29:02Z","abstract_excerpt":"We study sequential decision-making with offline reinforcement learning (RL). Traditional offline RL policies may result in out-of-distribution (OOD) actions when training relies only on sparse offline representations. To ensure safe offline policies in a sparse state-action space, we explore how density estimation models can be integrated into model-based RL methods to avoid the OOD regions. Generative models are capable of explicitly modeling the density in sparse state-action spaces. Building on this, we introduce Generative OOD-regularized Model-based Policy Optimization (GORMPO), a densit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24405","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.24405/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.24405","created_at":"2026-05-26T01:03:37.792144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24405v1","created_at":"2026-05-26T01:03:37.792144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24405","created_at":"2026-05-26T01:03:37.792144+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUJHENTELP6S","created_at":"2026-05-26T01:03:37.792144+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUJHENTELP6SJZBX","created_at":"2026-05-26T01:03:37.792144+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUJHENTE","created_at":"2026-05-26T01:03:37.792144+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GUJHENTELP6SJZBXS5SZQN5A4W","json":"https://pith.science/pith/GUJHENTELP6SJZBXS5SZQN5A4W.json","graph_json":"https://pith.science/api/pith-number/GUJHENTELP6SJZBXS5SZQN5A4W/graph.json","events_json":"https://pith.science/api/pith-number/GUJHENTELP6SJZBXS5SZQN5A4W/events.json","paper":"https://pith.science/paper/GUJHENTE"},"agent_actions":{"view_html":"https://pith.science/pith/GUJHENTELP6SJZBXS5SZQN5A4W","download_json":"https://pith.science/pith/GUJHENTELP6SJZBXS5SZQN5A4W.json","view_paper":"https://pith.science/paper/GUJHENTE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24405&json=true","fetch_graph":"https://pith.science/api/pith-number/GUJHENTELP6SJZBXS5SZQN5A4W/graph.json","fetch_events":"https://pith.science/api/pith-number/GUJHENTELP6SJZBXS5SZQN5A4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUJHENTELP6SJZBXS5SZQN5A4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUJHENTELP6SJZBXS5SZQN5A4W/action/storage_attestation","attest_author":"https://pith.science/pith/GUJHENTELP6SJZBXS5SZQN5A4W/action/author_attestation","sign_citation":"https://pith.science/pith/GUJHENTELP6SJZBXS5SZQN5A4W/action/citation_signature","submit_replication":"https://pith.science/pith/GUJHENTELP6SJZBXS5SZQN5A4W/action/replication_record"}},"created_at":"2026-05-26T01:03:37.792144+00:00","updated_at":"2026-05-26T01:03:37.792144+00:00"}