{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4GQCVMYLWUGKNL2XNIK7ETISKR","short_pith_number":"pith:4GQCVMYL","schema_version":"1.0","canonical_sha256":"e1a02ab30bb50ca6af576a15f24d12546b6c8dbba471c6ad2c3e19ac4e3b83c2","source":{"kind":"arxiv","id":"2504.16555","version":1},"attestation_state":"computed","paper":{"title":"Confidence Sequences for Generalized Linear Models via Regret Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Eugenio Clerico, Gergely Neu, Hamish Flynn, Wojciech Kot{\\l}owski","submitted_at":"2025-04-23T09:32:40Z","abstract_excerpt":"We develop a methodology for constructing confidence sets for parameters of statistical models via a reduction to sequential prediction. Our key observation is that for any generalized linear model (GLM), one can construct an associated game of sequential probability assignment such that achieving low regret in the game implies a high-probability upper bound on the excess likelihood of the true parameter of the GLM. This allows us to develop a scheme that we call online-to-confidence-set conversions, which effectively reduces the problem of proving the desired statistical claim to an algorithm"},"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":"2504.16555","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.ST","submitted_at":"2025-04-23T09:32:40Z","cross_cats_sorted":["cs.LG","stat.ML","stat.TH"],"title_canon_sha256":"3c9e5e33f0000c84bea20336a9adf0c25ffe6d194bb425e06a4525ec23490644","abstract_canon_sha256":"1a5bf20d6493c1ea91a66c9178e44a851df8580e7712d71f42e8cb9fb3549fd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:01.510144Z","signature_b64":"LCoKFRm2QB0SYN8x9+HhXkT7/oftFeqKRSnJk0uxCpqwgz9DgzdH7A1woJXs/O1KWlyC40ZEYj97XvVpdpWHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1a02ab30bb50ca6af576a15f24d12546b6c8dbba471c6ad2c3e19ac4e3b83c2","last_reissued_at":"2026-07-05T10:53:01.509672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:01.509672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence Sequences for Generalized Linear Models via Regret Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML","stat.TH"],"primary_cat":"math.ST","authors_text":"Eugenio Clerico, Gergely Neu, Hamish Flynn, Wojciech Kot{\\l}owski","submitted_at":"2025-04-23T09:32:40Z","abstract_excerpt":"We develop a methodology for constructing confidence sets for parameters of statistical models via a reduction to sequential prediction. Our key observation is that for any generalized linear model (GLM), one can construct an associated game of sequential probability assignment such that achieving low regret in the game implies a high-probability upper bound on the excess likelihood of the true parameter of the GLM. This allows us to develop a scheme that we call online-to-confidence-set conversions, which effectively reduces the problem of proving the desired statistical claim to an algorithm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16555","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/2504.16555/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":"2504.16555","created_at":"2026-07-05T10:53:01.509729+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16555v1","created_at":"2026-07-05T10:53:01.509729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16555","created_at":"2026-07-05T10:53:01.509729+00:00"},{"alias_kind":"pith_short_12","alias_value":"4GQCVMYLWUGK","created_at":"2026-07-05T10:53:01.509729+00:00"},{"alias_kind":"pith_short_16","alias_value":"4GQCVMYLWUGKNL2X","created_at":"2026-07-05T10:53:01.509729+00:00"},{"alias_kind":"pith_short_8","alias_value":"4GQCVMYL","created_at":"2026-07-05T10:53:01.509729+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.12325","citing_title":"Eventually LIL Regret: Almost Sure $\\ln\\ln T$ Regret for a sub-Gaussian Mixture on Unbounded Data","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05745","citing_title":"Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4GQCVMYLWUGKNL2XNIK7ETISKR","json":"https://pith.science/pith/4GQCVMYLWUGKNL2XNIK7ETISKR.json","graph_json":"https://pith.science/api/pith-number/4GQCVMYLWUGKNL2XNIK7ETISKR/graph.json","events_json":"https://pith.science/api/pith-number/4GQCVMYLWUGKNL2XNIK7ETISKR/events.json","paper":"https://pith.science/paper/4GQCVMYL"},"agent_actions":{"view_html":"https://pith.science/pith/4GQCVMYLWUGKNL2XNIK7ETISKR","download_json":"https://pith.science/pith/4GQCVMYLWUGKNL2XNIK7ETISKR.json","view_paper":"https://pith.science/paper/4GQCVMYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16555&json=true","fetch_graph":"https://pith.science/api/pith-number/4GQCVMYLWUGKNL2XNIK7ETISKR/graph.json","fetch_events":"https://pith.science/api/pith-number/4GQCVMYLWUGKNL2XNIK7ETISKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4GQCVMYLWUGKNL2XNIK7ETISKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4GQCVMYLWUGKNL2XNIK7ETISKR/action/storage_attestation","attest_author":"https://pith.science/pith/4GQCVMYLWUGKNL2XNIK7ETISKR/action/author_attestation","sign_citation":"https://pith.science/pith/4GQCVMYLWUGKNL2XNIK7ETISKR/action/citation_signature","submit_replication":"https://pith.science/pith/4GQCVMYLWUGKNL2XNIK7ETISKR/action/replication_record"}},"created_at":"2026-07-05T10:53:01.509729+00:00","updated_at":"2026-07-05T10:53:01.509729+00:00"}