{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:F4OGEURBSPMBS4L3LUQJ4UV6XF","short_pith_number":"pith:F4OGEURB","canonical_record":{"source":{"id":"1504.03101","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-04-13T09:13:23Z","cross_cats_sorted":[],"title_canon_sha256":"5aa3801bcea22abaaa7b47bb49cd8a963ebab7f760a3370363facaa3b03bc95d","abstract_canon_sha256":"8d911879815d347844b0e79512de5ec5820c3f099a34c46a4ddc8aa3042506d8"},"schema_version":"1.0"},"canonical_sha256":"2f1c62522193d819717b5d209e52beb95760bc3a0ad4baa374385f1b97f0f5a2","source":{"kind":"arxiv","id":"1504.03101","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.03101","created_at":"2026-05-18T02:18:30Z"},{"alias_kind":"arxiv_version","alias_value":"1504.03101v2","created_at":"2026-05-18T02:18:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.03101","created_at":"2026-05-18T02:18:30Z"},{"alias_kind":"pith_short_12","alias_value":"F4OGEURBSPMB","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"F4OGEURBSPMBS4L3","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"F4OGEURB","created_at":"2026-05-18T12:29:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:F4OGEURBSPMBS4L3LUQJ4UV6XF","target":"record","payload":{"canonical_record":{"source":{"id":"1504.03101","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-04-13T09:13:23Z","cross_cats_sorted":[],"title_canon_sha256":"5aa3801bcea22abaaa7b47bb49cd8a963ebab7f760a3370363facaa3b03bc95d","abstract_canon_sha256":"8d911879815d347844b0e79512de5ec5820c3f099a34c46a4ddc8aa3042506d8"},"schema_version":"1.0"},"canonical_sha256":"2f1c62522193d819717b5d209e52beb95760bc3a0ad4baa374385f1b97f0f5a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:18:30.942215Z","signature_b64":"HCqv8my5V1yVIZHrC7f5lWxt9h2hNUKAbYowTTPAaw5a2oaGAd0JtW6TVOBSxL4tjHp6I9deIuq8MFftuhkoDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f1c62522193d819717b5d209e52beb95760bc3a0ad4baa374385f1b97f0f5a2","last_reissued_at":"2026-05-18T02:18:30.941772Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:18:30.941772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1504.03101","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:18:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iBeVNrvVZ1zy8Q57Idl5iqimjghCUqaZlzqzZbB8iktkjUEMMC+qtqWTwmp8OD9vKKZOHR+iWAfgpfkYx1q5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T09:45:30.344259Z"},"content_sha256":"a1269719665c85705f959469ca3e84bc495e9cba00f0b6ac400bacd9375fbcbf","schema_version":"1.0","event_id":"sha256:a1269719665c85705f959469ca3e84bc495e9cba00f0b6ac400bacd9375fbcbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:F4OGEURBSPMBS4L3LUQJ4UV6XF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Convex Learning of Multiple Tasks and their Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Carlo Ciliberto, Lorenzo Rosasco, Tomaso Poggio, Youssef Mroueh","submitted_at":"2015-04-13T09:13:23Z","abstract_excerpt":"Reducing the amount of human supervision is a key problem in machine learning and a natural approach is that of exploiting the relations (structure) among different tasks. This is the idea at the core of multi-task learning. In this context a fundamental question is how to incorporate the tasks structure in the learning problem.We tackle this question by studying a general computational framework that allows to encode a-priori knowledge of the tasks structure in the form of a convex penalty; in this setting a variety of previously proposed methods can be recovered as special cases, including l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.03101","kind":"arxiv","version":2},"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":"2026-05-18T02:18:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mr1R7FGoPjVBU7zNCRxNSIV7JkOVMZUG2+sh/7SwDyparlobOII7rLWk9vK4IDedGvX6vBY69SQfrCnu3mLHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T09:45:30.344971Z"},"content_sha256":"96e0e87a1d19ba9003a59f7ba49106289f5ef283baf94853202ed3ce5652185b","schema_version":"1.0","event_id":"sha256:96e0e87a1d19ba9003a59f7ba49106289f5ef283baf94853202ed3ce5652185b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F4OGEURBSPMBS4L3LUQJ4UV6XF/bundle.json","state_url":"https://pith.science/pith/F4OGEURBSPMBS4L3LUQJ4UV6XF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F4OGEURBSPMBS4L3LUQJ4UV6XF/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":"2026-05-25T09:45:30Z","links":{"resolver":"https://pith.science/pith/F4OGEURBSPMBS4L3LUQJ4UV6XF","bundle":"https://pith.science/pith/F4OGEURBSPMBS4L3LUQJ4UV6XF/bundle.json","state":"https://pith.science/pith/F4OGEURBSPMBS4L3LUQJ4UV6XF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F4OGEURBSPMBS4L3LUQJ4UV6XF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:F4OGEURBSPMBS4L3LUQJ4UV6XF","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":"8d911879815d347844b0e79512de5ec5820c3f099a34c46a4ddc8aa3042506d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-04-13T09:13:23Z","title_canon_sha256":"5aa3801bcea22abaaa7b47bb49cd8a963ebab7f760a3370363facaa3b03bc95d"},"schema_version":"1.0","source":{"id":"1504.03101","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1504.03101","created_at":"2026-05-18T02:18:30Z"},{"alias_kind":"arxiv_version","alias_value":"1504.03101v2","created_at":"2026-05-18T02:18:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1504.03101","created_at":"2026-05-18T02:18:30Z"},{"alias_kind":"pith_short_12","alias_value":"F4OGEURBSPMB","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_16","alias_value":"F4OGEURBSPMBS4L3","created_at":"2026-05-18T12:29:19Z"},{"alias_kind":"pith_short_8","alias_value":"F4OGEURB","created_at":"2026-05-18T12:29:19Z"}],"graph_snapshots":[{"event_id":"sha256:96e0e87a1d19ba9003a59f7ba49106289f5ef283baf94853202ed3ce5652185b","target":"graph","created_at":"2026-05-18T02:18:30Z","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":"Reducing the amount of human supervision is a key problem in machine learning and a natural approach is that of exploiting the relations (structure) among different tasks. This is the idea at the core of multi-task learning. In this context a fundamental question is how to incorporate the tasks structure in the learning problem.We tackle this question by studying a general computational framework that allows to encode a-priori knowledge of the tasks structure in the form of a convex penalty; in this setting a variety of previously proposed methods can be recovered as special cases, including l","authors_text":"Carlo Ciliberto, Lorenzo Rosasco, Tomaso Poggio, Youssef Mroueh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-04-13T09:13:23Z","title":"Convex Learning of Multiple Tasks and their Structure"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1504.03101","kind":"arxiv","version":2},"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:a1269719665c85705f959469ca3e84bc495e9cba00f0b6ac400bacd9375fbcbf","target":"record","created_at":"2026-05-18T02:18:30Z","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":"8d911879815d347844b0e79512de5ec5820c3f099a34c46a4ddc8aa3042506d8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-04-13T09:13:23Z","title_canon_sha256":"5aa3801bcea22abaaa7b47bb49cd8a963ebab7f760a3370363facaa3b03bc95d"},"schema_version":"1.0","source":{"id":"1504.03101","kind":"arxiv","version":2}},"canonical_sha256":"2f1c62522193d819717b5d209e52beb95760bc3a0ad4baa374385f1b97f0f5a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f1c62522193d819717b5d209e52beb95760bc3a0ad4baa374385f1b97f0f5a2","first_computed_at":"2026-05-18T02:18:30.941772Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:18:30.941772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HCqv8my5V1yVIZHrC7f5lWxt9h2hNUKAbYowTTPAaw5a2oaGAd0JtW6TVOBSxL4tjHp6I9deIuq8MFftuhkoDw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:18:30.942215Z","signed_message":"canonical_sha256_bytes"},"source_id":"1504.03101","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1269719665c85705f959469ca3e84bc495e9cba00f0b6ac400bacd9375fbcbf","sha256:96e0e87a1d19ba9003a59f7ba49106289f5ef283baf94853202ed3ce5652185b"],"state_sha256":"ad05c98697e07128936bda739ec7acc9ac7effe898e9f45d703ce34a0ca95065"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g8FnYi1/fmi3nZeqRUeNzIT9jeipw1G+QsUHEgMEC23UZDDEuyjeecCfGhBrKnO0qiYrTfJJlUIjOCRmQeMcBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T09:45:30.348495Z","bundle_sha256":"199ef701495bf57231968d740d2d8bad67adb189dec1cc155c5afc0142acd19f"}}