{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:SKTTBCFICZPNIB44XUJIITE7MU","short_pith_number":"pith:SKTTBCFI","schema_version":"1.0","canonical_sha256":"92a73088a8165ed4079cbd12844c9f650c730dfd0f9a708e1b43d84468e17845","source":{"kind":"arxiv","id":"1805.08562","version":1},"attestation_state":"computed","paper":{"title":"Best of many worlds: Robust model selection for online supervised learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anant Sahai, Mitas Ray, Peter L. Bartlett, Vidya Muthukumar","submitted_at":"2018-05-22T13:08:41Z","abstract_excerpt":"We introduce algorithms for online, full-information prediction that are competitive with contextual tree experts of unknown complexity, in both probabilistic and adversarial settings. We show that by incorporating a probabilistic framework of structural risk minimization into existing adaptive algorithms, we can robustly learn not only the presence of stochastic structure when it exists (leading to constant as opposed to $\\mathcal{O}(\\sqrt{T})$ regret), but also the correct model order. We thus obtain regret bounds that are competitive with the regret of an optimal algorithm that possesses st"},"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":"1805.08562","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-22T13:08:41Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"420707273b344d709b52747072bacb8662111c50f435c3f71230c621e5d0ac40","abstract_canon_sha256":"cff44bb2d6eef1bb349a375984347afdd36996f64ddeaaafab0a0123d23dd6bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:26.008224Z","signature_b64":"Gv0nADuImsbfVOZDviSqDW5IWvv8uKnMMBzfJPHkZbwcAbDl2eqOXCoSxIF+ovXpYu+Sfy4obuC+Ba7oSTJRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92a73088a8165ed4079cbd12844c9f650c730dfd0f9a708e1b43d84468e17845","last_reissued_at":"2026-05-18T00:15:26.007283Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:26.007283Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Best of many worlds: Robust model selection for online supervised learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anant Sahai, Mitas Ray, Peter L. Bartlett, Vidya Muthukumar","submitted_at":"2018-05-22T13:08:41Z","abstract_excerpt":"We introduce algorithms for online, full-information prediction that are competitive with contextual tree experts of unknown complexity, in both probabilistic and adversarial settings. We show that by incorporating a probabilistic framework of structural risk minimization into existing adaptive algorithms, we can robustly learn not only the presence of stochastic structure when it exists (leading to constant as opposed to $\\mathcal{O}(\\sqrt{T})$ regret), but also the correct model order. We thus obtain regret bounds that are competitive with the regret of an optimal algorithm that possesses st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08562","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":""},"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":"1805.08562","created_at":"2026-05-18T00:15:26.007447+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08562v1","created_at":"2026-05-18T00:15:26.007447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08562","created_at":"2026-05-18T00:15:26.007447+00:00"},{"alias_kind":"pith_short_12","alias_value":"SKTTBCFICZPN","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"SKTTBCFICZPNIB44","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"SKTTBCFI","created_at":"2026-05-18T12:32:53.628368+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/SKTTBCFICZPNIB44XUJIITE7MU","json":"https://pith.science/pith/SKTTBCFICZPNIB44XUJIITE7MU.json","graph_json":"https://pith.science/api/pith-number/SKTTBCFICZPNIB44XUJIITE7MU/graph.json","events_json":"https://pith.science/api/pith-number/SKTTBCFICZPNIB44XUJIITE7MU/events.json","paper":"https://pith.science/paper/SKTTBCFI"},"agent_actions":{"view_html":"https://pith.science/pith/SKTTBCFICZPNIB44XUJIITE7MU","download_json":"https://pith.science/pith/SKTTBCFICZPNIB44XUJIITE7MU.json","view_paper":"https://pith.science/paper/SKTTBCFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08562&json=true","fetch_graph":"https://pith.science/api/pith-number/SKTTBCFICZPNIB44XUJIITE7MU/graph.json","fetch_events":"https://pith.science/api/pith-number/SKTTBCFICZPNIB44XUJIITE7MU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SKTTBCFICZPNIB44XUJIITE7MU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SKTTBCFICZPNIB44XUJIITE7MU/action/storage_attestation","attest_author":"https://pith.science/pith/SKTTBCFICZPNIB44XUJIITE7MU/action/author_attestation","sign_citation":"https://pith.science/pith/SKTTBCFICZPNIB44XUJIITE7MU/action/citation_signature","submit_replication":"https://pith.science/pith/SKTTBCFICZPNIB44XUJIITE7MU/action/replication_record"}},"created_at":"2026-05-18T00:15:26.007447+00:00","updated_at":"2026-05-18T00:15:26.007447+00:00"}