{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:K7J65GQMJZDG6DI6CMNNGR5EMA","short_pith_number":"pith:K7J65GQM","schema_version":"1.0","canonical_sha256":"57d3ee9a0c4e466f0d1e131ad347a46002b14e4089ee22283fb2199a50728f2d","source":{"kind":"arxiv","id":"2506.00818","version":1},"attestation_state":"computed","paper":{"title":"Generalized Linear Markov Decision Process","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Doudou Zhou, Kaicheng Zhang, Sinian Zhang, Tianxi Cai, Ziping Xu","submitted_at":"2025-06-01T03:50:41Z","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"},"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":"2506.00818","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-06-01T03:50:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bdfd1bdf274aaebb7980f54107a2008171c829d698ad540d771726eebe394f5e","abstract_canon_sha256":"6d5e89ceb4430bd61b52c8b25afa39fbd0fa513ec706dec19d38554955a8c8e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:41.027388Z","signature_b64":"K3aKLIlkoUyHYcfqi6RkPmUEWQBjs0pFEURLcYqDPPBlYA3tO8c8WlW9UEho5SsSE9hXPhOAVWpMeWxHHniUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57d3ee9a0c4e466f0d1e131ad347a46002b14e4089ee22283fb2199a50728f2d","last_reissued_at":"2026-07-05T11:13:41.026779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:41.026779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalized Linear Markov Decision Process","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Doudou Zhou, Kaicheng Zhang, Sinian Zhang, Tianxi Cai, Ziping Xu","submitted_at":"2025-06-01T03:50:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00818","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/2506.00818/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":"2506.00818","created_at":"2026-07-05T11:13:41.026845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00818v1","created_at":"2026-07-05T11:13:41.026845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00818","created_at":"2026-07-05T11:13:41.026845+00:00"},{"alias_kind":"pith_short_12","alias_value":"K7J65GQMJZDG","created_at":"2026-07-05T11:13:41.026845+00:00"},{"alias_kind":"pith_short_16","alias_value":"K7J65GQMJZDG6DI6","created_at":"2026-07-05T11:13:41.026845+00:00"},{"alias_kind":"pith_short_8","alias_value":"K7J65GQM","created_at":"2026-07-05T11:13:41.026845+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/K7J65GQMJZDG6DI6CMNNGR5EMA","json":"https://pith.science/pith/K7J65GQMJZDG6DI6CMNNGR5EMA.json","graph_json":"https://pith.science/api/pith-number/K7J65GQMJZDG6DI6CMNNGR5EMA/graph.json","events_json":"https://pith.science/api/pith-number/K7J65GQMJZDG6DI6CMNNGR5EMA/events.json","paper":"https://pith.science/paper/K7J65GQM"},"agent_actions":{"view_html":"https://pith.science/pith/K7J65GQMJZDG6DI6CMNNGR5EMA","download_json":"https://pith.science/pith/K7J65GQMJZDG6DI6CMNNGR5EMA.json","view_paper":"https://pith.science/paper/K7J65GQM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00818&json=true","fetch_graph":"https://pith.science/api/pith-number/K7J65GQMJZDG6DI6CMNNGR5EMA/graph.json","fetch_events":"https://pith.science/api/pith-number/K7J65GQMJZDG6DI6CMNNGR5EMA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K7J65GQMJZDG6DI6CMNNGR5EMA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K7J65GQMJZDG6DI6CMNNGR5EMA/action/storage_attestation","attest_author":"https://pith.science/pith/K7J65GQMJZDG6DI6CMNNGR5EMA/action/author_attestation","sign_citation":"https://pith.science/pith/K7J65GQMJZDG6DI6CMNNGR5EMA/action/citation_signature","submit_replication":"https://pith.science/pith/K7J65GQMJZDG6DI6CMNNGR5EMA/action/replication_record"}},"created_at":"2026-07-05T11:13:41.026845+00:00","updated_at":"2026-07-05T11:13:41.026845+00:00"}