{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:R4IUSEYKERQQLHIHBAWJHWUAXF","short_pith_number":"pith:R4IUSEYK","canonical_record":{"source":{"id":"1705.08118","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-23T08:24:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"53c83740d9464865471c8782badfb818de4fc2f46ba95f4832c3f534acabae61","abstract_canon_sha256":"eaf8ef8f95a255a185ae78a56568e53b1530f1c0c61162ed3c29fea30761bfcf"},"schema_version":"1.0"},"canonical_sha256":"8f1149130a2461059d07082c93da80b94e705950c28bb6c2a8218e72aee72e86","source":{"kind":"arxiv","id":"1705.08118","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08118","created_at":"2026-05-18T00:38:17Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08118v2","created_at":"2026-05-18T00:38:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08118","created_at":"2026-05-18T00:38:17Z"},{"alias_kind":"pith_short_12","alias_value":"R4IUSEYKERQQ","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"R4IUSEYKERQQLHIH","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"R4IUSEYK","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:R4IUSEYKERQQLHIHBAWJHWUAXF","target":"record","payload":{"canonical_record":{"source":{"id":"1705.08118","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-23T08:24:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"53c83740d9464865471c8782badfb818de4fc2f46ba95f4832c3f534acabae61","abstract_canon_sha256":"eaf8ef8f95a255a185ae78a56568e53b1530f1c0c61162ed3c29fea30761bfcf"},"schema_version":"1.0"},"canonical_sha256":"8f1149130a2461059d07082c93da80b94e705950c28bb6c2a8218e72aee72e86","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:17.934361Z","signature_b64":"EICwkFAXkb79iFVqsxmcQ+meSbIdwlBYlYmdgUzbXXWbjok+pr295BGihMTcvxHtbpQLy+o2xDE+2ObIJzIhCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f1149130a2461059d07082c93da80b94e705950c28bb6c2a8218e72aee72e86","last_reissued_at":"2026-05-18T00:38:17.933544Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:17.933544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.08118","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":"2026-05-18T00:38:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zt0h9k5UJR1LrRoI/E1K2Gdz+dkCeJxlzLnvAo5BYX6NSFBopO6mXTHLhgcsLDvPCen9I2Iq4PmN4jofwFPADA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:57:11.689135Z"},"content_sha256":"1aa5e8616d571798f2aa491c8e7057265641e43333871e20ee3ef9ef52b53eff","schema_version":"1.0","event_id":"sha256:1aa5e8616d571798f2aa491c8e7057265641e43333871e20ee3ef9ef52b53eff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:R4IUSEYKERQQLHIHBAWJHWUAXF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Consistent Multitask Learning with Nonlinear Output Relations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Rudi, Carlo Ciliberto, Lorenzo Rosasco, Massimiliano Pontil","submitted_at":"2017-05-23T08:24:06Z","abstract_excerpt":"Key to multitask learning is exploiting relationships between different tasks to improve prediction performance. If the relations are linear, regularization approaches can be used successfully. However, in practice assuming the tasks to be linearly related might be restrictive, and allowing for nonlinear structures is a challenge. In this paper, we tackle this issue by casting the problem within the framework of structured prediction. Our main contribution is a novel algorithm for learning multiple tasks which are related by a system of nonlinear equations that their joint outputs need to sati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08118","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":"2026-05-18T00:38:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pXBteCwLrodnrz17L2B1xKTHcLtttTZQTrJ8VO/8FCTK1Qsb41Uv+9xEha6BVtYnFFxa+yTGzMrdwZBxQXTOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T06:57:11.689833Z"},"content_sha256":"ee2271b962c307a96b904e632dd14f768993078058d37eeff2e9413322cb85f5","schema_version":"1.0","event_id":"sha256:ee2271b962c307a96b904e632dd14f768993078058d37eeff2e9413322cb85f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R4IUSEYKERQQLHIHBAWJHWUAXF/bundle.json","state_url":"https://pith.science/pith/R4IUSEYKERQQLHIHBAWJHWUAXF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R4IUSEYKERQQLHIHBAWJHWUAXF/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":"2026-05-26T06:57:11Z","links":{"resolver":"https://pith.science/pith/R4IUSEYKERQQLHIHBAWJHWUAXF","bundle":"https://pith.science/pith/R4IUSEYKERQQLHIHBAWJHWUAXF/bundle.json","state":"https://pith.science/pith/R4IUSEYKERQQLHIHBAWJHWUAXF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R4IUSEYKERQQLHIHBAWJHWUAXF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:R4IUSEYKERQQLHIHBAWJHWUAXF","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":"eaf8ef8f95a255a185ae78a56568e53b1530f1c0c61162ed3c29fea30761bfcf","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-23T08:24:06Z","title_canon_sha256":"53c83740d9464865471c8782badfb818de4fc2f46ba95f4832c3f534acabae61"},"schema_version":"1.0","source":{"id":"1705.08118","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.08118","created_at":"2026-05-18T00:38:17Z"},{"alias_kind":"arxiv_version","alias_value":"1705.08118v2","created_at":"2026-05-18T00:38:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.08118","created_at":"2026-05-18T00:38:17Z"},{"alias_kind":"pith_short_12","alias_value":"R4IUSEYKERQQ","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"R4IUSEYKERQQLHIH","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"R4IUSEYK","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:ee2271b962c307a96b904e632dd14f768993078058d37eeff2e9413322cb85f5","target":"graph","created_at":"2026-05-18T00:38:17Z","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":"Key to multitask learning is exploiting relationships between different tasks to improve prediction performance. If the relations are linear, regularization approaches can be used successfully. However, in practice assuming the tasks to be linearly related might be restrictive, and allowing for nonlinear structures is a challenge. In this paper, we tackle this issue by casting the problem within the framework of structured prediction. Our main contribution is a novel algorithm for learning multiple tasks which are related by a system of nonlinear equations that their joint outputs need to sati","authors_text":"Alessandro Rudi, Carlo Ciliberto, Lorenzo Rosasco, Massimiliano Pontil","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-23T08:24:06Z","title":"Consistent Multitask Learning with Nonlinear Output Relations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.08118","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":"sha256:1aa5e8616d571798f2aa491c8e7057265641e43333871e20ee3ef9ef52b53eff","target":"record","created_at":"2026-05-18T00:38:17Z","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":"eaf8ef8f95a255a185ae78a56568e53b1530f1c0c61162ed3c29fea30761bfcf","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-23T08:24:06Z","title_canon_sha256":"53c83740d9464865471c8782badfb818de4fc2f46ba95f4832c3f534acabae61"},"schema_version":"1.0","source":{"id":"1705.08118","kind":"arxiv","version":2}},"canonical_sha256":"8f1149130a2461059d07082c93da80b94e705950c28bb6c2a8218e72aee72e86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f1149130a2461059d07082c93da80b94e705950c28bb6c2a8218e72aee72e86","first_computed_at":"2026-05-18T00:38:17.933544Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:17.933544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EICwkFAXkb79iFVqsxmcQ+meSbIdwlBYlYmdgUzbXXWbjok+pr295BGihMTcvxHtbpQLy+o2xDE+2ObIJzIhCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:17.934361Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.08118","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1aa5e8616d571798f2aa491c8e7057265641e43333871e20ee3ef9ef52b53eff","sha256:ee2271b962c307a96b904e632dd14f768993078058d37eeff2e9413322cb85f5"],"state_sha256":"e055ed9f31676feaaa05a5ac484ef955305dc80706d855b3c61f71b13de69b33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X1bKZs5wnEGnbT/Y+Vfpd11HOU94ftntU9CCmNfFb87dOLVHEpP7ZLPB6CoQfygN2l2ltg38F4Fscu7mAQ2hBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T06:57:11.693205Z","bundle_sha256":"9ee6fdd98951a0426c366c1fc75338de3e6de6e5032c4edd648d56faf1377f3e"}}