{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GUJHENTELP6SJZBXS5SZQN5A4W","short_pith_number":"pith:GUJHENTE","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"},"canonical_sha256":"35127236645bfd24e43797659837a0e58e108e9f77025032fea2a556774ddda0","source":{"kind":"arxiv","id":"2605.24405","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24405","created_at":"2026-05-26T01:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24405v1","created_at":"2026-05-26T01:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24405","created_at":"2026-05-26T01:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"GUJHENTELP6S","created_at":"2026-05-26T01:03:37Z"},{"alias_kind":"pith_short_16","alias_value":"GUJHENTELP6SJZBX","created_at":"2026-05-26T01:03:37Z"},{"alias_kind":"pith_short_8","alias_value":"GUJHENTE","created_at":"2026-05-26T01:03:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GUJHENTELP6SJZBXS5SZQN5A4W","target":"record","payload":{"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"},"canonical_sha256":"35127236645bfd24e43797659837a0e58e108e9f77025032fea2a556774ddda0","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"},"source_kind":"arxiv","source_id":"2605.24405","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NHGQXH1OkTzHZUCXIMoL5USEuAsgey0Bh9pjMTMB8+h2TlWmS2Wn3PD1hT0P0/mkIjQR4sP5ScgbOBaiq/0+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T02:57:21.722203Z"},"content_sha256":"b30d0c5f82708acc169a6ef88e6aaa4f7142ce6df4aa58d925938e474fb1ead7","schema_version":"1.0","event_id":"sha256:b30d0c5f82708acc169a6ef88e6aaa4f7142ce6df4aa58d925938e474fb1ead7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GUJHENTELP6SJZBXS5SZQN5A4W","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-26T01:03:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EaS+iwScRrqHLQfmCVwYEAc4KCukzWKSuhn03DPOeemr+9HvoyaQSdTAH63ybqcqXaFNFCm9ytAK4ScWOxGJDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T02:57:21.722590Z"},"content_sha256":"fb563322c3f802e988b4e9fa27f3acc2b8e4fb211ccd62134ce591f729414dde","schema_version":"1.0","event_id":"sha256:fb563322c3f802e988b4e9fa27f3acc2b8e4fb211ccd62134ce591f729414dde"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GUJHENTELP6SJZBXS5SZQN5A4W/bundle.json","state_url":"https://pith.science/pith/GUJHENTELP6SJZBXS5SZQN5A4W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GUJHENTELP6SJZBXS5SZQN5A4W/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-02T02:57:21Z","links":{"resolver":"https://pith.science/pith/GUJHENTELP6SJZBXS5SZQN5A4W","bundle":"https://pith.science/pith/GUJHENTELP6SJZBXS5SZQN5A4W/bundle.json","state":"https://pith.science/pith/GUJHENTELP6SJZBXS5SZQN5A4W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GUJHENTELP6SJZBXS5SZQN5A4W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GUJHENTELP6SJZBXS5SZQN5A4W","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":"36e8dd62ad8fb59816213f20bb4a7e0d3ef2369caac4ea3276fdd8685aaf6ed4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T05:29:02Z","title_canon_sha256":"c13b1f1f28ae0c72957eb4f94f7727264b0d32e74333a811c277612656b214a0"},"schema_version":"1.0","source":{"id":"2605.24405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.24405","created_at":"2026-05-26T01:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"2605.24405v1","created_at":"2026-05-26T01:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24405","created_at":"2026-05-26T01:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"GUJHENTELP6S","created_at":"2026-05-26T01:03:37Z"},{"alias_kind":"pith_short_16","alias_value":"GUJHENTELP6SJZBX","created_at":"2026-05-26T01:03:37Z"},{"alias_kind":"pith_short_8","alias_value":"GUJHENTE","created_at":"2026-05-26T01:03:37Z"}],"graph_snapshots":[{"event_id":"sha256:fb563322c3f802e988b4e9fa27f3acc2b8e4fb211ccd62134ce591f729414dde","target":"graph","created_at":"2026-05-26T01:03:37Z","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/2605.24405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aysin Tumay, Elise Jortberg, Jiahe Huang, Rose Yu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T05:29:02Z","title":"Generative OOD-regularized Model-based Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24405","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:b30d0c5f82708acc169a6ef88e6aaa4f7142ce6df4aa58d925938e474fb1ead7","target":"record","created_at":"2026-05-26T01:03:37Z","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":"36e8dd62ad8fb59816213f20bb4a7e0d3ef2369caac4ea3276fdd8685aaf6ed4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T05:29:02Z","title_canon_sha256":"c13b1f1f28ae0c72957eb4f94f7727264b0d32e74333a811c277612656b214a0"},"schema_version":"1.0","source":{"id":"2605.24405","kind":"arxiv","version":1}},"canonical_sha256":"35127236645bfd24e43797659837a0e58e108e9f77025032fea2a556774ddda0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35127236645bfd24e43797659837a0e58e108e9f77025032fea2a556774ddda0","first_computed_at":"2026-05-26T01:03:37.792021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:37.792021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"apT7Htj958ZaopGiaKA8QFL0MSwUTFNBdXiVKQsMRng09Aq6nxVGFg4ZckMmfi28sjWlNzFJufyw4I5jm/lqDQ==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:37.792808Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.24405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b30d0c5f82708acc169a6ef88e6aaa4f7142ce6df4aa58d925938e474fb1ead7","sha256:fb563322c3f802e988b4e9fa27f3acc2b8e4fb211ccd62134ce591f729414dde"],"state_sha256":"0326a0f8070f0da983d9ccbc0c7547a9b740a23bd55b40b3170e0a9bc33e53d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w2SP8IF6Kr+nC4yAJz6abV/R/x/fu1aSUl6Hmg87arpqL8mKok+7BVBqEjV6amG3mXnZILllDzu89GIzscpODA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T02:57:21.724613Z","bundle_sha256":"12e256990a28cb49420b40fb681c943440277e3f4ab927bcc7e8ba15302499fc"}}