{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:3YL3P2TZTGDLNKYTZSVWH5FAG5","short_pith_number":"pith:3YL3P2TZ","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"},"canonical_sha256":"de17b7ea799986b6ab13ccab63f4a0377ecc5fa155c3470a8c5ea830343bfcee","source":{"kind":"arxiv","id":"1211.0439","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1211.0439","created_at":"2026-05-18T03:41:40Z"},{"alias_kind":"arxiv_version","alias_value":"1211.0439v1","created_at":"2026-05-18T03:41:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1211.0439","created_at":"2026-05-18T03:41:40Z"},{"alias_kind":"pith_short_12","alias_value":"3YL3P2TZTGDL","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"3YL3P2TZTGDLNKYT","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"3YL3P2TZ","created_at":"2026-05-18T12:26:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:3YL3P2TZTGDLNKYTZSVWH5FAG5","target":"record","payload":{"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"},"canonical_sha256":"de17b7ea799986b6ab13ccab63f4a0377ecc5fa155c3470a8c5ea830343bfcee","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"},"source_kind":"arxiv","source_id":"1211.0439","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:41:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vCi3uNSlAb3GVxZnBOJSnIaYCl/5bmFYgo9MaSrbv8Gh2vSD3xP5gnrbCwIwVko4yXtB96CdJuJ2DoIl8seyCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T01:20:27.576163Z"},"content_sha256":"ff3e57953df890ae4485882e4d7e722a7e9a9358681fa390534c0f5f9d0fc6af","schema_version":"1.0","event_id":"sha256:ff3e57953df890ae4485882e4d7e722a7e9a9358681fa390534c0f5f9d0fc6af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:3YL3P2TZTGDLNKYTZSVWH5FAG5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:41:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wvfBvRokgmVbTMeANK+v+Jez0X4DyuZx/urpqxLHB6+W1DBN38ZLRRcJX2tdAURkhS55U9Y9aH0LUqzaCbzVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T01:20:27.576525Z"},"content_sha256":"85a400783534a863b916939d910144dc320da2d6f528fa832b00ed15fc8fd041","schema_version":"1.0","event_id":"sha256:85a400783534a863b916939d910144dc320da2d6f528fa832b00ed15fc8fd041"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3YL3P2TZTGDLNKYTZSVWH5FAG5/bundle.json","state_url":"https://pith.science/pith/3YL3P2TZTGDLNKYTZSVWH5FAG5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3YL3P2TZTGDLNKYTZSVWH5FAG5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T01:20:27Z","links":{"resolver":"https://pith.science/pith/3YL3P2TZTGDLNKYTZSVWH5FAG5","bundle":"https://pith.science/pith/3YL3P2TZTGDLNKYTZSVWH5FAG5/bundle.json","state":"https://pith.science/pith/3YL3P2TZTGDLNKYTZSVWH5FAG5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3YL3P2TZTGDLNKYTZSVWH5FAG5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:3YL3P2TZTGDLNKYTZSVWH5FAG5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"dbd2cef26a22e830d8d652bd6341491d34ba22e2d98f67370896aca29e5ea264","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-11-02T12:46:24Z","title_canon_sha256":"70b21632238173586fc97651c2f64aaecaf5ac89705c33cb8cc6e269850117b8"},"schema_version":"1.0","source":{"id":"1211.0439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1211.0439","created_at":"2026-05-18T03:41:40Z"},{"alias_kind":"arxiv_version","alias_value":"1211.0439v1","created_at":"2026-05-18T03:41:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1211.0439","created_at":"2026-05-18T03:41:40Z"},{"alias_kind":"pith_short_12","alias_value":"3YL3P2TZTGDL","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"3YL3P2TZTGDLNKYT","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"3YL3P2TZ","created_at":"2026-05-18T12:26:53Z"}],"graph_snapshots":[{"event_id":"sha256:85a400783534a863b916939d910144dc320da2d6f528fa832b00ed15fc8fd041","target":"graph","created_at":"2026-05-18T03:41:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Peter Sollich, Simon R. F. Ashton","cross_cats":["cond-mat.dis-nn","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-11-02T12:46:24Z","title":"Learning curves for multi-task Gaussian process regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1211.0439","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ff3e57953df890ae4485882e4d7e722a7e9a9358681fa390534c0f5f9d0fc6af","target":"record","created_at":"2026-05-18T03:41:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"dbd2cef26a22e830d8d652bd6341491d34ba22e2d98f67370896aca29e5ea264","cross_cats_sorted":["cond-mat.dis-nn","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-11-02T12:46:24Z","title_canon_sha256":"70b21632238173586fc97651c2f64aaecaf5ac89705c33cb8cc6e269850117b8"},"schema_version":"1.0","source":{"id":"1211.0439","kind":"arxiv","version":1}},"canonical_sha256":"de17b7ea799986b6ab13ccab63f4a0377ecc5fa155c3470a8c5ea830343bfcee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de17b7ea799986b6ab13ccab63f4a0377ecc5fa155c3470a8c5ea830343bfcee","first_computed_at":"2026-05-18T03:41:40.992640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:41:40.992640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MbCmVbXVrHOtFW1CUe0KsZzQ+vjQUe9/7VhiNhi9ot0h9aKBy1OXR2J9dsWHfuAfjyRbORRDNMqCQYnP3VuxAw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:41:40.993656Z","signed_message":"canonical_sha256_bytes"},"source_id":"1211.0439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff3e57953df890ae4485882e4d7e722a7e9a9358681fa390534c0f5f9d0fc6af","sha256:85a400783534a863b916939d910144dc320da2d6f528fa832b00ed15fc8fd041"],"state_sha256":"b0b48e58e05cc69ba2e45d8a84bf490caff211d3de84d8707ecb4a69a06c43f7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t/qiPRthRyF6glYr0b2bxiPTUTlxExDzLENSzC5LwFDZzqik7ewF7wn77Lj03sufyWd1V64LSGJZWACMZNJYDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T01:20:27.578490Z","bundle_sha256":"88befe88e2504ebf69ec2c7dddd4b8fcc311ae5d06c849b50d5ce50bbfefc58a"}}