{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ZIVLCEJIHJVIALJ4UHESR3WHFY","short_pith_number":"pith:ZIVLCEJI","canonical_record":{"source":{"id":"1707.08114","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-25T04:43:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"28447570034d788356a7b15eb845c03a6c74bc7dcffd19e98a510dde4bf14495","abstract_canon_sha256":"a4e67f59c066dbb2f2bd2a3f259644d81f58c9360214316ae72daf4fab280f55"},"schema_version":"1.0"},"canonical_sha256":"ca2ab111283a6a802d3ca1c928eec72e1fce2ac77a44f669a7033ae7b0c2426d","source":{"kind":"arxiv","id":"1707.08114","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.08114","created_at":"2026-07-05T02:26:44Z"},{"alias_kind":"arxiv_version","alias_value":"1707.08114v3","created_at":"2026-07-05T02:26:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.08114","created_at":"2026-07-05T02:26:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZIVLCEJIHJVI","created_at":"2026-07-05T02:26:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZIVLCEJIHJVIALJ4","created_at":"2026-07-05T02:26:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZIVLCEJI","created_at":"2026-07-05T02:26:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ZIVLCEJIHJVIALJ4UHESR3WHFY","target":"record","payload":{"canonical_record":{"source":{"id":"1707.08114","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-25T04:43:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"28447570034d788356a7b15eb845c03a6c74bc7dcffd19e98a510dde4bf14495","abstract_canon_sha256":"a4e67f59c066dbb2f2bd2a3f259644d81f58c9360214316ae72daf4fab280f55"},"schema_version":"1.0"},"canonical_sha256":"ca2ab111283a6a802d3ca1c928eec72e1fce2ac77a44f669a7033ae7b0c2426d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:26:44.174964Z","signature_b64":"pR3/Cx45QZwOkkfRoCnomdzB0DsunL+r2MysPxCZyhSG5MVmz7Dk43gTmW2Nn7Tdek01C6PlVjsEVMhygfk+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca2ab111283a6a802d3ca1c928eec72e1fce2ac77a44f669a7033ae7b0c2426d","last_reissued_at":"2026-07-05T02:26:44.174373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:26:44.174373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.08114","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:26:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AuQ5yqdQBWEnqWOezx6wCQfNI1d1vPIySxkJI9ocBBpj9esvtRLVtIQx9tmg7cGOGLlSlMUZiY3LipROw3JpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:10:19.184317Z"},"content_sha256":"4bab35f10c0e7ca9bc9be097bec226b73a90b6ab657a6738f7c208e46b01ba2e","schema_version":"1.0","event_id":"sha256:4bab35f10c0e7ca9bc9be097bec226b73a90b6ab657a6738f7c208e46b01ba2e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ZIVLCEJIHJVIALJ4UHESR3WHFY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey on Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Qiang Yang, Yu Zhang","submitted_at":"2017-07-25T04:43:47Z","abstract_excerpt":"Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks. In this paper, we give a survey for MTL from the perspective of algorithmic modeling, applications and theoretical analyses. For algorithmic modeling, we give a definition of MTL and then classify different MTL algorithms into five categories, including feature learning approach, low-rank approach, task clustering approach, task relation learning approach and decomposition approach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.08114","kind":"arxiv","version":3},"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/1707.08114/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:26:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ur5g9HsgJy7EVMg0pe63L7D7QJE8y+mT1v4EhjbMyRIoFGciESmJgC6K42au8leS0Bnmcmc2KhhjYuZNP55iAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:10:19.184968Z"},"content_sha256":"5384ed0894a96a57dd3d83334a552ac27dc518a1024f48766c1ce311e492569c","schema_version":"1.0","event_id":"sha256:5384ed0894a96a57dd3d83334a552ac27dc518a1024f48766c1ce311e492569c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZIVLCEJIHJVIALJ4UHESR3WHFY/bundle.json","state_url":"https://pith.science/pith/ZIVLCEJIHJVIALJ4UHESR3WHFY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZIVLCEJIHJVIALJ4UHESR3WHFY/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":"2026-08-07T00:10:19Z","links":{"resolver":"https://pith.science/pith/ZIVLCEJIHJVIALJ4UHESR3WHFY","bundle":"https://pith.science/pith/ZIVLCEJIHJVIALJ4UHESR3WHFY/bundle.json","state":"https://pith.science/pith/ZIVLCEJIHJVIALJ4UHESR3WHFY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZIVLCEJIHJVIALJ4UHESR3WHFY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ZIVLCEJIHJVIALJ4UHESR3WHFY","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":"a4e67f59c066dbb2f2bd2a3f259644d81f58c9360214316ae72daf4fab280f55","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-25T04:43:47Z","title_canon_sha256":"28447570034d788356a7b15eb845c03a6c74bc7dcffd19e98a510dde4bf14495"},"schema_version":"1.0","source":{"id":"1707.08114","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.08114","created_at":"2026-07-05T02:26:44Z"},{"alias_kind":"arxiv_version","alias_value":"1707.08114v3","created_at":"2026-07-05T02:26:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.08114","created_at":"2026-07-05T02:26:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZIVLCEJIHJVI","created_at":"2026-07-05T02:26:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZIVLCEJIHJVIALJ4","created_at":"2026-07-05T02:26:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZIVLCEJI","created_at":"2026-07-05T02:26:44Z"}],"graph_snapshots":[{"event_id":"sha256:5384ed0894a96a57dd3d83334a552ac27dc518a1024f48766c1ce311e492569c","target":"graph","created_at":"2026-07-05T02:26:44Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1707.08114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks. In this paper, we give a survey for MTL from the perspective of algorithmic modeling, applications and theoretical analyses. For algorithmic modeling, we give a definition of MTL and then classify different MTL algorithms into five categories, including feature learning approach, low-rank approach, task clustering approach, task relation learning approach and decomposition approach","authors_text":"Qiang Yang, Yu Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-25T04:43:47Z","title":"A Survey on Multi-Task Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.08114","kind":"arxiv","version":3},"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":"sha256:4bab35f10c0e7ca9bc9be097bec226b73a90b6ab657a6738f7c208e46b01ba2e","target":"record","created_at":"2026-07-05T02:26:44Z","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":"a4e67f59c066dbb2f2bd2a3f259644d81f58c9360214316ae72daf4fab280f55","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-07-25T04:43:47Z","title_canon_sha256":"28447570034d788356a7b15eb845c03a6c74bc7dcffd19e98a510dde4bf14495"},"schema_version":"1.0","source":{"id":"1707.08114","kind":"arxiv","version":3}},"canonical_sha256":"ca2ab111283a6a802d3ca1c928eec72e1fce2ac77a44f669a7033ae7b0c2426d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca2ab111283a6a802d3ca1c928eec72e1fce2ac77a44f669a7033ae7b0c2426d","first_computed_at":"2026-07-05T02:26:44.174373Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:44.174373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pR3/Cx45QZwOkkfRoCnomdzB0DsunL+r2MysPxCZyhSG5MVmz7Dk43gTmW2Nn7Tdek01C6PlVjsEVMhygfk+AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:44.174964Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.08114","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4bab35f10c0e7ca9bc9be097bec226b73a90b6ab657a6738f7c208e46b01ba2e","sha256:5384ed0894a96a57dd3d83334a552ac27dc518a1024f48766c1ce311e492569c"],"state_sha256":"5596176b894eb8b729bc8cb847e47da45c9d65f3afd6e0099c720a7496c1d72f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4BteBWE/7HhL8CwxbbYnj09175xKGM5nwjV6frvMbmDza6kA7kl/HEvo/M8bBJX/QMdNtRe5JSmMK8kFBk11Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:10:19.190140Z","bundle_sha256":"7225869f9a047fa8966a80e2833defbc8ff74d48da4b8093eed63e32e3e3e2ae"}}