{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4ZXCXFJLOAZTZHV3QBY4WTVAFB","short_pith_number":"pith:4ZXCXFJL","schema_version":"1.0","canonical_sha256":"e66e2b952b70333c9ebb8071cb4ea0285d0276d5817ec9ba91c31d87d12132d8","source":{"kind":"arxiv","id":"2509.06575","version":1},"attestation_state":"computed","paper":{"title":"Robust and Adaptive Spectral Method for Representation Multi-Task Learning with Contamination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Yang Feng, Yian Huang, Zhiliang Ying","submitted_at":"2025-09-08T11:41:30Z","abstract_excerpt":"Representation-based multi-task learning (MTL) improves efficiency by learning a shared structure across tasks, but its practical application is often hindered by contamination, outliers, or adversarial tasks. Most existing methods and theories assume a clean or near-clean setting, failing when contamination is significant. This paper tackles representation MTL with an unknown and potentially large contamination proportion, while also allowing for heterogeneity among inlier tasks. We introduce a Robust and Adaptive Spectral method (RAS) that can distill the shared inlier representation effecti"},"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":"2509.06575","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-09-08T11:41:30Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"a38edd78651c98b66089785139b8406ecdefb21f379f4274099e459d2722a38b","abstract_canon_sha256":"a0fa549fd57b25ee345adddcce00df7f0cdbf5ecfd1d7d56d470a3330d09fc9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:38.491790Z","signature_b64":"cd9evdQbyIqCxrkV4vn8nhp5CKwR9Qi4x10lG2CEmDIZInqa3K5yiF8E7B6xz1uwxgXlahzOeR31RYUERh21Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e66e2b952b70333c9ebb8071cb4ea0285d0276d5817ec9ba91c31d87d12132d8","last_reissued_at":"2026-07-05T12:06:38.491267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:38.491267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust and Adaptive Spectral Method for Representation Multi-Task Learning with Contamination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Yang Feng, Yian Huang, Zhiliang Ying","submitted_at":"2025-09-08T11:41:30Z","abstract_excerpt":"Representation-based multi-task learning (MTL) improves efficiency by learning a shared structure across tasks, but its practical application is often hindered by contamination, outliers, or adversarial tasks. Most existing methods and theories assume a clean or near-clean setting, failing when contamination is significant. This paper tackles representation MTL with an unknown and potentially large contamination proportion, while also allowing for heterogeneity among inlier tasks. We introduce a Robust and Adaptive Spectral method (RAS) that can distill the shared inlier representation effecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06575","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/2509.06575/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":"2509.06575","created_at":"2026-07-05T12:06:38.491324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06575v1","created_at":"2026-07-05T12:06:38.491324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06575","created_at":"2026-07-05T12:06:38.491324+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZXCXFJLOAZT","created_at":"2026-07-05T12:06:38.491324+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZXCXFJLOAZTZHV3","created_at":"2026-07-05T12:06:38.491324+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZXCXFJL","created_at":"2026-07-05T12:06:38.491324+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/4ZXCXFJLOAZTZHV3QBY4WTVAFB","json":"https://pith.science/pith/4ZXCXFJLOAZTZHV3QBY4WTVAFB.json","graph_json":"https://pith.science/api/pith-number/4ZXCXFJLOAZTZHV3QBY4WTVAFB/graph.json","events_json":"https://pith.science/api/pith-number/4ZXCXFJLOAZTZHV3QBY4WTVAFB/events.json","paper":"https://pith.science/paper/4ZXCXFJL"},"agent_actions":{"view_html":"https://pith.science/pith/4ZXCXFJLOAZTZHV3QBY4WTVAFB","download_json":"https://pith.science/pith/4ZXCXFJLOAZTZHV3QBY4WTVAFB.json","view_paper":"https://pith.science/paper/4ZXCXFJL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06575&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZXCXFJLOAZTZHV3QBY4WTVAFB/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZXCXFJLOAZTZHV3QBY4WTVAFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZXCXFJLOAZTZHV3QBY4WTVAFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZXCXFJLOAZTZHV3QBY4WTVAFB/action/storage_attestation","attest_author":"https://pith.science/pith/4ZXCXFJLOAZTZHV3QBY4WTVAFB/action/author_attestation","sign_citation":"https://pith.science/pith/4ZXCXFJLOAZTZHV3QBY4WTVAFB/action/citation_signature","submit_replication":"https://pith.science/pith/4ZXCXFJLOAZTZHV3QBY4WTVAFB/action/replication_record"}},"created_at":"2026-07-05T12:06:38.491324+00:00","updated_at":"2026-07-05T12:06:38.491324+00:00"}