{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DAZ6TTNIOINLTVPZU7SSAEYSNR","short_pith_number":"pith:DAZ6TTNI","schema_version":"1.0","canonical_sha256":"1833e9cda8721ab9d5f9a7e52013126c4f95de3238066603f7ec5199febff45f","source":{"kind":"arxiv","id":"2606.27448","version":1},"attestation_state":"computed","paper":{"title":"Learning in Markovian bandits with non-observable states and constrained decision epochs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ina Maria Verloop, Thomas Hira, Urtzi Ayesta, Victor Boone","submitted_at":"2026-06-25T18:18:15Z","abstract_excerpt":"This paper studies the problem of regret minimization in Markovian bandits with \\emph{non-observable states} and possibly \\emph{constrained} decision epochs. The focus is restricted to a ``pure'' regret benchmark, that compares the performance of the learning algorithm to the best \\emph{pure policy} which -- akin to optimal policies of stochastic bandits -- picks the optimal arm from start to finish without ever switching. We introduce a generalization of rested Markovian bandits, \\emph{self-degrading Markovian bandits}, for which pure policies are always asymptotically optimal.We show that wi"},"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":"2606.27448","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T18:18:15Z","cross_cats_sorted":[],"title_canon_sha256":"4e65c9ddb410f76e5c5feeaac2b6a2148aedd1c529dd63364720cd871baa12a6","abstract_canon_sha256":"912a2b495384a777f116f36f25d1c7b4244546733c4f884dfb903a78437607a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T00:14:06.615034Z","signature_b64":"+zDBmkIyMzJcan6vNb0JkkxgAEoEkQbWzw8f2KY6NJhxTTK2+xT2htGt0OtNXun1vrPZn9IPtbyAG1+eh+CvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1833e9cda8721ab9d5f9a7e52013126c4f95de3238066603f7ec5199febff45f","last_reissued_at":"2026-06-29T00:14:06.614589Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T00:14:06.614589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning in Markovian bandits with non-observable states and constrained decision epochs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ina Maria Verloop, Thomas Hira, Urtzi Ayesta, Victor Boone","submitted_at":"2026-06-25T18:18:15Z","abstract_excerpt":"This paper studies the problem of regret minimization in Markovian bandits with \\emph{non-observable states} and possibly \\emph{constrained} decision epochs. The focus is restricted to a ``pure'' regret benchmark, that compares the performance of the learning algorithm to the best \\emph{pure policy} which -- akin to optimal policies of stochastic bandits -- picks the optimal arm from start to finish without ever switching. We introduce a generalization of rested Markovian bandits, \\emph{self-degrading Markovian bandits}, for which pure policies are always asymptotically optimal.We show that wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27448","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/2606.27448/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":"2606.27448","created_at":"2026-06-29T00:14:06.614657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27448v1","created_at":"2026-06-29T00:14:06.614657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27448","created_at":"2026-06-29T00:14:06.614657+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAZ6TTNIOINL","created_at":"2026-06-29T00:14:06.614657+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAZ6TTNIOINLTVPZ","created_at":"2026-06-29T00:14:06.614657+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAZ6TTNI","created_at":"2026-06-29T00:14:06.614657+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/DAZ6TTNIOINLTVPZU7SSAEYSNR","json":"https://pith.science/pith/DAZ6TTNIOINLTVPZU7SSAEYSNR.json","graph_json":"https://pith.science/api/pith-number/DAZ6TTNIOINLTVPZU7SSAEYSNR/graph.json","events_json":"https://pith.science/api/pith-number/DAZ6TTNIOINLTVPZU7SSAEYSNR/events.json","paper":"https://pith.science/paper/DAZ6TTNI"},"agent_actions":{"view_html":"https://pith.science/pith/DAZ6TTNIOINLTVPZU7SSAEYSNR","download_json":"https://pith.science/pith/DAZ6TTNIOINLTVPZU7SSAEYSNR.json","view_paper":"https://pith.science/paper/DAZ6TTNI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27448&json=true","fetch_graph":"https://pith.science/api/pith-number/DAZ6TTNIOINLTVPZU7SSAEYSNR/graph.json","fetch_events":"https://pith.science/api/pith-number/DAZ6TTNIOINLTVPZU7SSAEYSNR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAZ6TTNIOINLTVPZU7SSAEYSNR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAZ6TTNIOINLTVPZU7SSAEYSNR/action/storage_attestation","attest_author":"https://pith.science/pith/DAZ6TTNIOINLTVPZU7SSAEYSNR/action/author_attestation","sign_citation":"https://pith.science/pith/DAZ6TTNIOINLTVPZU7SSAEYSNR/action/citation_signature","submit_replication":"https://pith.science/pith/DAZ6TTNIOINLTVPZU7SSAEYSNR/action/replication_record"}},"created_at":"2026-06-29T00:14:06.614657+00:00","updated_at":"2026-06-29T00:14:06.614657+00:00"}