{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K7J65GQMJZDG6DI6CMNNGR5EMA","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":"6d5e89ceb4430bd61b52c8b25afa39fbd0fa513ec706dec19d38554955a8c8e1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-01T03:50:41Z","title_canon_sha256":"bdfd1bdf274aaebb7980f54107a2008171c829d698ad540d771726eebe394f5e"},"schema_version":"1.0","source":{"id":"2506.00818","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00818","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00818v1","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00818","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"pith_short_12","alias_value":"K7J65GQMJZDG","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"pith_short_16","alias_value":"K7J65GQMJZDG6DI6","created_at":"2026-07-05T11:13:41Z"},{"alias_kind":"pith_short_8","alias_value":"K7J65GQM","created_at":"2026-07-05T11:13:41Z"}],"graph_snapshots":[{"event_id":"sha256:aca15ed430a8002dc68f2b8599fbb1d094f6d1c3ffe2a07f22289b0554abc614","target":"graph","created_at":"2026-07-05T11:13:41Z","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/2506.00818/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The linear Markov Decision Process (MDP) framework offers a principled foundation for reinforcement learning (RL) with strong theoretical guarantees and sample efficiency. However, its restrictive assumption-that both transition dynamics and reward functions are linear in the same feature space-limits its applicability in real-world domains, where rewards often exhibit nonlinear or discrete structures. Motivated by applications such as healthcare and e-commerce, where data is scarce and reward signals can be binary or count-valued, we propose the Generalized Linear MDP (GLMDP) framework-an ext","authors_text":"Doudou Zhou, Kaicheng Zhang, Sinian Zhang, Tianxi Cai, Ziping Xu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-01T03:50:41Z","title":"Generalized Linear Markov Decision Process"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00818","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:c6a1a0b489b6e973102b23db197b126e5a7b5bd089541839e9a637b274b7cf05","target":"record","created_at":"2026-07-05T11:13:41Z","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":"6d5e89ceb4430bd61b52c8b25afa39fbd0fa513ec706dec19d38554955a8c8e1","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-01T03:50:41Z","title_canon_sha256":"bdfd1bdf274aaebb7980f54107a2008171c829d698ad540d771726eebe394f5e"},"schema_version":"1.0","source":{"id":"2506.00818","kind":"arxiv","version":1}},"canonical_sha256":"57d3ee9a0c4e466f0d1e131ad347a46002b14e4089ee22283fb2199a50728f2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"57d3ee9a0c4e466f0d1e131ad347a46002b14e4089ee22283fb2199a50728f2d","first_computed_at":"2026-07-05T11:13:41.026779Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:41.026779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"K3aKLIlkoUyHYcfqi6RkPmUEWQBjs0pFEURLcYqDPPBlYA3tO8c8WlW9UEho5SsSE9hXPhOAVWpMeWxHHniUBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:41.027388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00818","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6a1a0b489b6e973102b23db197b126e5a7b5bd089541839e9a637b274b7cf05","sha256:aca15ed430a8002dc68f2b8599fbb1d094f6d1c3ffe2a07f22289b0554abc614"],"state_sha256":"4a779a3fd4d9e340af1e2d686729beac6b8bc1b25f2f566003c355f780f2d3b7"}