{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TMOQE6XVRFZGPYSPYAUI6TSMFL","short_pith_number":"pith:TMOQE6XV","schema_version":"1.0","canonical_sha256":"9b1d027af5897267e24fc0288f4e4c2ad8f3d0c076e3ae564e2dd4aceb16246c","source":{"kind":"arxiv","id":"1904.01747","version":1},"attestation_state":"computed","paper":{"title":"On Better Exploring and Exploiting Task Relationships in Multi-Task Learning: Joint Model and Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Tongliang Liu, Xinmei Tian, Ya Li","submitted_at":"2019-04-03T03:14:20Z","abstract_excerpt":"Multitask learning (MTL) aims to learn multiple tasks simultaneously through the interdependence between different tasks. The way to measure the relatedness between tasks is always a popular issue. There are mainly two ways to measure relatedness between tasks: common parameters sharing and common features sharing across different tasks. However, these two types of relatedness are mainly learned independently, leading to a loss of information. In this paper, we propose a new strategy to measure the relatedness that jointly learns shared parameters and shared feature representations. The object"},"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":"1904.01747","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-03T03:14:20Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0b7e20ca922f0cef92ada1bcfaad3e8f3e585a89fd824c2ccf7736d65f10afe7","abstract_canon_sha256":"b252cc464f1710244a92955800ec5405e1d247e5b9f116e505fb7a5847d88be7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:29.815623Z","signature_b64":"j+SZR3Xwp2AajhoALGndsTX8CAvMwb+u2k+SJePdSnpPeLUJKTA4Zr8zon5CsaXuCLQEJ3lFkQegqyE2imVCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b1d027af5897267e24fc0288f4e4c2ad8f3d0c076e3ae564e2dd4aceb16246c","last_reissued_at":"2026-05-17T23:49:29.814894Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:29.814894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Better Exploring and Exploiting Task Relationships in Multi-Task Learning: Joint Model and Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dacheng Tao, Tongliang Liu, Xinmei Tian, Ya Li","submitted_at":"2019-04-03T03:14:20Z","abstract_excerpt":"Multitask learning (MTL) aims to learn multiple tasks simultaneously through the interdependence between different tasks. The way to measure the relatedness between tasks is always a popular issue. There are mainly two ways to measure relatedness between tasks: common parameters sharing and common features sharing across different tasks. However, these two types of relatedness are mainly learned independently, leading to a loss of information. In this paper, we propose a new strategy to measure the relatedness that jointly learns shared parameters and shared feature representations. The object"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01747","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":"1904.01747","created_at":"2026-05-17T23:49:29.815013+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.01747v1","created_at":"2026-05-17T23:49:29.815013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01747","created_at":"2026-05-17T23:49:29.815013+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMOQE6XVRFZG","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMOQE6XVRFZGPYSP","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMOQE6XV","created_at":"2026-05-18T12:33:30.264802+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/TMOQE6XVRFZGPYSPYAUI6TSMFL","json":"https://pith.science/pith/TMOQE6XVRFZGPYSPYAUI6TSMFL.json","graph_json":"https://pith.science/api/pith-number/TMOQE6XVRFZGPYSPYAUI6TSMFL/graph.json","events_json":"https://pith.science/api/pith-number/TMOQE6XVRFZGPYSPYAUI6TSMFL/events.json","paper":"https://pith.science/paper/TMOQE6XV"},"agent_actions":{"view_html":"https://pith.science/pith/TMOQE6XVRFZGPYSPYAUI6TSMFL","download_json":"https://pith.science/pith/TMOQE6XVRFZGPYSPYAUI6TSMFL.json","view_paper":"https://pith.science/paper/TMOQE6XV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.01747&json=true","fetch_graph":"https://pith.science/api/pith-number/TMOQE6XVRFZGPYSPYAUI6TSMFL/graph.json","fetch_events":"https://pith.science/api/pith-number/TMOQE6XVRFZGPYSPYAUI6TSMFL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMOQE6XVRFZGPYSPYAUI6TSMFL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMOQE6XVRFZGPYSPYAUI6TSMFL/action/storage_attestation","attest_author":"https://pith.science/pith/TMOQE6XVRFZGPYSPYAUI6TSMFL/action/author_attestation","sign_citation":"https://pith.science/pith/TMOQE6XVRFZGPYSPYAUI6TSMFL/action/citation_signature","submit_replication":"https://pith.science/pith/TMOQE6XVRFZGPYSPYAUI6TSMFL/action/replication_record"}},"created_at":"2026-05-17T23:49:29.815013+00:00","updated_at":"2026-05-17T23:49:29.815013+00:00"}