{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:3YL3P2TZTGDLNKYTZSVWH5FAG5","short_pith_number":"pith:3YL3P2TZ","schema_version":"1.0","canonical_sha256":"de17b7ea799986b6ab13ccab63f4a0377ecc5fa155c3470a8c5ea830343bfcee","source":{"kind":"arxiv","id":"1211.0439","version":1},"attestation_state":"computed","paper":{"title":"Learning curves for multi-task Gaussian process regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","stat.ML"],"primary_cat":"cs.LG","authors_text":"Peter Sollich, Simon R. F. Ashton","submitted_at":"2012-11-02T12:46:24Z","abstract_excerpt":"We study the average case performance of multi-task Gaussian process (GP) regression as captured in the learning curve, i.e. the average Bayes error for a chosen task versus the total number of examples $n$ for all tasks. For GP covariances that are the product of an input-dependent covariance function and a free-form inter-task covariance matrix, we show that accurate approximations for the learning curve can be obtained for an arbitrary number of tasks $T$. We use these to study the asymptotic learning behaviour for large $n$. Surprisingly, multi-task learning can be asymptotically essential"},"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":"1211.0439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-11-02T12:46:24Z","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"title_canon_sha256":"70b21632238173586fc97651c2f64aaecaf5ac89705c33cb8cc6e269850117b8","abstract_canon_sha256":"dbd2cef26a22e830d8d652bd6341491d34ba22e2d98f67370896aca29e5ea264"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:41:40.993656Z","signature_b64":"MbCmVbXVrHOtFW1CUe0KsZzQ+vjQUe9/7VhiNhi9ot0h9aKBy1OXR2J9dsWHfuAfjyRbORRDNMqCQYnP3VuxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de17b7ea799986b6ab13ccab63f4a0377ecc5fa155c3470a8c5ea830343bfcee","last_reissued_at":"2026-05-18T03:41:40.992640Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:41:40.992640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning curves for multi-task Gaussian process regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","stat.ML"],"primary_cat":"cs.LG","authors_text":"Peter Sollich, Simon R. F. Ashton","submitted_at":"2012-11-02T12:46:24Z","abstract_excerpt":"We study the average case performance of multi-task Gaussian process (GP) regression as captured in the learning curve, i.e. the average Bayes error for a chosen task versus the total number of examples $n$ for all tasks. For GP covariances that are the product of an input-dependent covariance function and a free-form inter-task covariance matrix, we show that accurate approximations for the learning curve can be obtained for an arbitrary number of tasks $T$. We use these to study the asymptotic learning behaviour for large $n$. Surprisingly, multi-task learning can be asymptotically essential"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1211.0439","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":"1211.0439","created_at":"2026-05-18T03:41:40.992841+00:00"},{"alias_kind":"arxiv_version","alias_value":"1211.0439v1","created_at":"2026-05-18T03:41:40.992841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1211.0439","created_at":"2026-05-18T03:41:40.992841+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YL3P2TZTGDL","created_at":"2026-05-18T12:26:53.410803+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YL3P2TZTGDLNKYT","created_at":"2026-05-18T12:26:53.410803+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YL3P2TZ","created_at":"2026-05-18T12:26:53.410803+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/3YL3P2TZTGDLNKYTZSVWH5FAG5","json":"https://pith.science/pith/3YL3P2TZTGDLNKYTZSVWH5FAG5.json","graph_json":"https://pith.science/api/pith-number/3YL3P2TZTGDLNKYTZSVWH5FAG5/graph.json","events_json":"https://pith.science/api/pith-number/3YL3P2TZTGDLNKYTZSVWH5FAG5/events.json","paper":"https://pith.science/paper/3YL3P2TZ"},"agent_actions":{"view_html":"https://pith.science/pith/3YL3P2TZTGDLNKYTZSVWH5FAG5","download_json":"https://pith.science/pith/3YL3P2TZTGDLNKYTZSVWH5FAG5.json","view_paper":"https://pith.science/paper/3YL3P2TZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1211.0439&json=true","fetch_graph":"https://pith.science/api/pith-number/3YL3P2TZTGDLNKYTZSVWH5FAG5/graph.json","fetch_events":"https://pith.science/api/pith-number/3YL3P2TZTGDLNKYTZSVWH5FAG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YL3P2TZTGDLNKYTZSVWH5FAG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YL3P2TZTGDLNKYTZSVWH5FAG5/action/storage_attestation","attest_author":"https://pith.science/pith/3YL3P2TZTGDLNKYTZSVWH5FAG5/action/author_attestation","sign_citation":"https://pith.science/pith/3YL3P2TZTGDLNKYTZSVWH5FAG5/action/citation_signature","submit_replication":"https://pith.science/pith/3YL3P2TZTGDLNKYTZSVWH5FAG5/action/replication_record"}},"created_at":"2026-05-18T03:41:40.992841+00:00","updated_at":"2026-05-18T03:41:40.992841+00:00"}