{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7A2TZDAKZNCYS7MZH7KTY3OFGT","short_pith_number":"pith:7A2TZDAK","schema_version":"1.0","canonical_sha256":"f8353c8c0acb45897d993fd53c6dc534e8670ece3914e46d1bc88f94b5cce469","source":{"kind":"arxiv","id":"2605.17126","version":1},"attestation_state":"computed","paper":{"title":"Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness and Safety","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Seok-Jin Kim","submitted_at":"2026-05-16T19:06:54Z","abstract_excerpt":"We study the multi-task linear regression problem in the presence of contaminated tasks. We address the setting where the unknown parameters of a majority of tasks are close in the $\\ell_2$-norm, while a fraction of tasks are arbitrary outliers. Existing theoretical frameworks for this problem rely heavily on the assumption that the empirical second moment of each task has a minimum eigenvalue bounded away from zero (order $\\Omega(1)$). Crucially, this assumption fails in many high-dimensional scenarios, rendering prior guarantees vacuous. To overcome this limitation, we propose an estimator b"},"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":"2605.17126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-16T19:06:54Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"b051757d78ca757f196cee71ea021a8b915f54bfbc6911a164b483309b19ac1a","abstract_canon_sha256":"eeaa9644da16b5b73b0b84cf9609a0552df60173a46e1341e5b58c6157da5b0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:41.241433Z","signature_b64":"M2SJsfUZ4rY71qQI6bUdEU0U3XTbGl2ss1KW/aytqOnkjWw5TQleNP7cBETBRiRf4pUxvCdRwmRovvGd+DQUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8353c8c0acb45897d993fd53c6dc534e8670ece3914e46d1bc88f94b5cce469","last_reissued_at":"2026-05-20T00:03:41.240522Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:41.240522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-task Linear Regression without Eigenvalue Lower Bounds: Adaptivity, Robustness and Safety","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Seok-Jin Kim","submitted_at":"2026-05-16T19:06:54Z","abstract_excerpt":"We study the multi-task linear regression problem in the presence of contaminated tasks. We address the setting where the unknown parameters of a majority of tasks are close in the $\\ell_2$-norm, while a fraction of tasks are arbitrary outliers. Existing theoretical frameworks for this problem rely heavily on the assumption that the empirical second moment of each task has a minimum eigenvalue bounded away from zero (order $\\Omega(1)$). Crucially, this assumption fails in many high-dimensional scenarios, rendering prior guarantees vacuous. To overcome this limitation, we propose an estimator b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17126","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/2605.17126/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:23.780435Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T22:01:58.028124Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"abcc2508d5dc5127a6bc7ee4fd8923cd3dd61bba16b6c2ecda56bc9bd218a1fb"},"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":"2605.17126","created_at":"2026-05-20T00:03:41.240667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17126v1","created_at":"2026-05-20T00:03:41.240667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17126","created_at":"2026-05-20T00:03:41.240667+00:00"},{"alias_kind":"pith_short_12","alias_value":"7A2TZDAKZNCY","created_at":"2026-05-20T00:03:41.240667+00:00"},{"alias_kind":"pith_short_16","alias_value":"7A2TZDAKZNCYS7MZ","created_at":"2026-05-20T00:03:41.240667+00:00"},{"alias_kind":"pith_short_8","alias_value":"7A2TZDAK","created_at":"2026-05-20T00:03:41.240667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16260","citing_title":"The Impact of Process Competition on Energy Consumption: Analysis and Modeling","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7A2TZDAKZNCYS7MZH7KTY3OFGT","json":"https://pith.science/pith/7A2TZDAKZNCYS7MZH7KTY3OFGT.json","graph_json":"https://pith.science/api/pith-number/7A2TZDAKZNCYS7MZH7KTY3OFGT/graph.json","events_json":"https://pith.science/api/pith-number/7A2TZDAKZNCYS7MZH7KTY3OFGT/events.json","paper":"https://pith.science/paper/7A2TZDAK"},"agent_actions":{"view_html":"https://pith.science/pith/7A2TZDAKZNCYS7MZH7KTY3OFGT","download_json":"https://pith.science/pith/7A2TZDAKZNCYS7MZH7KTY3OFGT.json","view_paper":"https://pith.science/paper/7A2TZDAK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17126&json=true","fetch_graph":"https://pith.science/api/pith-number/7A2TZDAKZNCYS7MZH7KTY3OFGT/graph.json","fetch_events":"https://pith.science/api/pith-number/7A2TZDAKZNCYS7MZH7KTY3OFGT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7A2TZDAKZNCYS7MZH7KTY3OFGT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7A2TZDAKZNCYS7MZH7KTY3OFGT/action/storage_attestation","attest_author":"https://pith.science/pith/7A2TZDAKZNCYS7MZH7KTY3OFGT/action/author_attestation","sign_citation":"https://pith.science/pith/7A2TZDAKZNCYS7MZH7KTY3OFGT/action/citation_signature","submit_replication":"https://pith.science/pith/7A2TZDAKZNCYS7MZH7KTY3OFGT/action/replication_record"}},"created_at":"2026-05-20T00:03:41.240667+00:00","updated_at":"2026-05-20T00:03:41.240667+00:00"}