{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DAZ6TTNIOINLTVPZU7SSAEYSNR","short_pith_number":"pith:DAZ6TTNI","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"},"canonical_sha256":"1833e9cda8721ab9d5f9a7e52013126c4f95de3238066603f7ec5199febff45f","source":{"kind":"arxiv","id":"2606.27448","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27448","created_at":"2026-06-29T00:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27448v1","created_at":"2026-06-29T00:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27448","created_at":"2026-06-29T00:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"DAZ6TTNIOINL","created_at":"2026-06-29T00:14:06Z"},{"alias_kind":"pith_short_16","alias_value":"DAZ6TTNIOINLTVPZ","created_at":"2026-06-29T00:14:06Z"},{"alias_kind":"pith_short_8","alias_value":"DAZ6TTNI","created_at":"2026-06-29T00:14:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DAZ6TTNIOINLTVPZU7SSAEYSNR","target":"record","payload":{"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"},"canonical_sha256":"1833e9cda8721ab9d5f9a7e52013126c4f95de3238066603f7ec5199febff45f","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"},"source_kind":"arxiv","source_id":"2606.27448","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":"2026-06-29T00:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6gRpMvVWQhkL3/MSEN2MTY4NES9w4mzIFmYTjx/S3+t22VliDP5XE58sZHrvNO9aEbtV3kyRS4vpZlaIyc3zCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:19:36.237273Z"},"content_sha256":"58602c25dbf3e98bd8ce8b50cca52f52ffd335cc144afa72d654c4fe7ee633a8","schema_version":"1.0","event_id":"sha256:58602c25dbf3e98bd8ce8b50cca52f52ffd335cc144afa72d654c4fe7ee633a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DAZ6TTNIOINLTVPZU7SSAEYSNR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-29T00:14:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DGmaCHTrxar13G4lWIgV03viGksKpo32u/v3fQFVLLNMI0vCy2xIC1OuL6i12xgUnzMuWjXtgALj2lR56FzwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T02:19:36.237643Z"},"content_sha256":"50c7ffaf96900dee3c5be3605d4dc6d05a7f7fd427f9e566734f92897c173f95","schema_version":"1.0","event_id":"sha256:50c7ffaf96900dee3c5be3605d4dc6d05a7f7fd427f9e566734f92897c173f95"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DAZ6TTNIOINLTVPZU7SSAEYSNR/bundle.json","state_url":"https://pith.science/pith/DAZ6TTNIOINLTVPZU7SSAEYSNR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DAZ6TTNIOINLTVPZU7SSAEYSNR/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":"2026-08-05T02:19:36Z","links":{"resolver":"https://pith.science/pith/DAZ6TTNIOINLTVPZU7SSAEYSNR","bundle":"https://pith.science/pith/DAZ6TTNIOINLTVPZU7SSAEYSNR/bundle.json","state":"https://pith.science/pith/DAZ6TTNIOINLTVPZU7SSAEYSNR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DAZ6TTNIOINLTVPZU7SSAEYSNR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DAZ6TTNIOINLTVPZU7SSAEYSNR","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":"912a2b495384a777f116f36f25d1c7b4244546733c4f884dfb903a78437607a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T18:18:15Z","title_canon_sha256":"4e65c9ddb410f76e5c5feeaac2b6a2148aedd1c529dd63364720cd871baa12a6"},"schema_version":"1.0","source":{"id":"2606.27448","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27448","created_at":"2026-06-29T00:14:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27448v1","created_at":"2026-06-29T00:14:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27448","created_at":"2026-06-29T00:14:06Z"},{"alias_kind":"pith_short_12","alias_value":"DAZ6TTNIOINL","created_at":"2026-06-29T00:14:06Z"},{"alias_kind":"pith_short_16","alias_value":"DAZ6TTNIOINLTVPZ","created_at":"2026-06-29T00:14:06Z"},{"alias_kind":"pith_short_8","alias_value":"DAZ6TTNI","created_at":"2026-06-29T00:14:06Z"}],"graph_snapshots":[{"event_id":"sha256:50c7ffaf96900dee3c5be3605d4dc6d05a7f7fd427f9e566734f92897c173f95","target":"graph","created_at":"2026-06-29T00:14:06Z","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/2606.27448/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ina Maria Verloop, Thomas Hira, Urtzi Ayesta, Victor Boone","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T18:18:15Z","title":"Learning in Markovian bandits with non-observable states and constrained decision epochs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27448","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":"sha256:58602c25dbf3e98bd8ce8b50cca52f52ffd335cc144afa72d654c4fe7ee633a8","target":"record","created_at":"2026-06-29T00:14:06Z","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":"912a2b495384a777f116f36f25d1c7b4244546733c4f884dfb903a78437607a7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-25T18:18:15Z","title_canon_sha256":"4e65c9ddb410f76e5c5feeaac2b6a2148aedd1c529dd63364720cd871baa12a6"},"schema_version":"1.0","source":{"id":"2606.27448","kind":"arxiv","version":1}},"canonical_sha256":"1833e9cda8721ab9d5f9a7e52013126c4f95de3238066603f7ec5199febff45f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1833e9cda8721ab9d5f9a7e52013126c4f95de3238066603f7ec5199febff45f","first_computed_at":"2026-06-29T00:14:06.614589Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T00:14:06.614589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+zDBmkIyMzJcan6vNb0JkkxgAEoEkQbWzw8f2KY6NJhxTTK2+xT2htGt0OtNXun1vrPZn9IPtbyAG1+eh+CvBg==","signature_status":"signed_v1","signed_at":"2026-06-29T00:14:06.615034Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.27448","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:58602c25dbf3e98bd8ce8b50cca52f52ffd335cc144afa72d654c4fe7ee633a8","sha256:50c7ffaf96900dee3c5be3605d4dc6d05a7f7fd427f9e566734f92897c173f95"],"state_sha256":"73c498922fa5d397a9dab61efcc2031a887d88db11eb3bb06107544dd8772564"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"shWGuI4JjGVkaRBjXq6S45F2sxeA2ldyws1QGcaiSg+CYsmR7JeGC41IDxbioJbBNkLb4MdBisdi87iLbESQBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T02:19:36.239855Z","bundle_sha256":"cef6076a432691cbb04894715c4edec15a8e240cbfaac209bd963f1c6a067e8d"}}