{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JNQVOXIVOW6NARCAOGLGXIOR52","short_pith_number":"pith:JNQVOXIV","schema_version":"1.0","canonical_sha256":"4b61575d1575bcd0444071966ba1d1ee9a45179c7dbc232cfa4b1567616ae24a","source":{"kind":"arxiv","id":"2202.00602","version":3},"attestation_state":"computed","paper":{"title":"Meta-Learning Hypothesis Spaces for Sequential Decision-making","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Jonas Rothfuss, Parnian Kassraie","submitted_at":"2022-02-01T17:46:51Z","abstract_excerpt":"Obtaining reliable, adaptive confidence sets for prediction functions (hypotheses) is a central challenge in sequential decision-making tasks, such as bandits and model-based reinforcement learning. These confidence sets typically rely on prior assumptions on the hypothesis space, e.g., the known kernel of a Reproducing Kernel Hilbert Space (RKHS). Hand-designing such kernels is error prone, and misspecification may lead to poor or unsafe performance. In this work, we propose to meta-learn a kernel from offline data (Meta-KeL). For the case where the unknown kernel is a combination of known ba"},"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":"2202.00602","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2022-02-01T17:46:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fc7675677fef9fcde13aecb188050711c399d5514cc3177f320d476ca6d745bf","abstract_canon_sha256":"4c0bdb1ee5f9fb4fb102d1976c29f92c9d764306e51c28ec2ed4daf24c899a63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:38.880020Z","signature_b64":"jF/qa3gkegbmj5rYCwOtNgTi+aCTdBLJfY6wRFmMx/KjocHGA1lPNHxz3Avy7Y1iqgTRb6swV1rSaTnLuD4IBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b61575d1575bcd0444071966ba1d1ee9a45179c7dbc232cfa4b1567616ae24a","last_reissued_at":"2026-07-05T04:32:38.879553Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:38.879553Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning Hypothesis Spaces for Sequential Decision-making","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Andreas Krause, Jonas Rothfuss, Parnian Kassraie","submitted_at":"2022-02-01T17:46:51Z","abstract_excerpt":"Obtaining reliable, adaptive confidence sets for prediction functions (hypotheses) is a central challenge in sequential decision-making tasks, such as bandits and model-based reinforcement learning. These confidence sets typically rely on prior assumptions on the hypothesis space, e.g., the known kernel of a Reproducing Kernel Hilbert Space (RKHS). Hand-designing such kernels is error prone, and misspecification may lead to poor or unsafe performance. In this work, we propose to meta-learn a kernel from offline data (Meta-KeL). For the case where the unknown kernel is a combination of known ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.00602","kind":"arxiv","version":3},"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/2202.00602/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":"2202.00602","created_at":"2026-07-05T04:32:38.879609+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.00602v3","created_at":"2026-07-05T04:32:38.879609+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.00602","created_at":"2026-07-05T04:32:38.879609+00:00"},{"alias_kind":"pith_short_12","alias_value":"JNQVOXIVOW6N","created_at":"2026-07-05T04:32:38.879609+00:00"},{"alias_kind":"pith_short_16","alias_value":"JNQVOXIVOW6NARCA","created_at":"2026-07-05T04:32:38.879609+00:00"},{"alias_kind":"pith_short_8","alias_value":"JNQVOXIV","created_at":"2026-07-05T04:32:38.879609+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/JNQVOXIVOW6NARCAOGLGXIOR52","json":"https://pith.science/pith/JNQVOXIVOW6NARCAOGLGXIOR52.json","graph_json":"https://pith.science/api/pith-number/JNQVOXIVOW6NARCAOGLGXIOR52/graph.json","events_json":"https://pith.science/api/pith-number/JNQVOXIVOW6NARCAOGLGXIOR52/events.json","paper":"https://pith.science/paper/JNQVOXIV"},"agent_actions":{"view_html":"https://pith.science/pith/JNQVOXIVOW6NARCAOGLGXIOR52","download_json":"https://pith.science/pith/JNQVOXIVOW6NARCAOGLGXIOR52.json","view_paper":"https://pith.science/paper/JNQVOXIV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.00602&json=true","fetch_graph":"https://pith.science/api/pith-number/JNQVOXIVOW6NARCAOGLGXIOR52/graph.json","fetch_events":"https://pith.science/api/pith-number/JNQVOXIVOW6NARCAOGLGXIOR52/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JNQVOXIVOW6NARCAOGLGXIOR52/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JNQVOXIVOW6NARCAOGLGXIOR52/action/storage_attestation","attest_author":"https://pith.science/pith/JNQVOXIVOW6NARCAOGLGXIOR52/action/author_attestation","sign_citation":"https://pith.science/pith/JNQVOXIVOW6NARCAOGLGXIOR52/action/citation_signature","submit_replication":"https://pith.science/pith/JNQVOXIVOW6NARCAOGLGXIOR52/action/replication_record"}},"created_at":"2026-07-05T04:32:38.879609+00:00","updated_at":"2026-07-05T04:32:38.879609+00:00"}