{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:N3FDFQIOHBDDNZVPUR5S5OLU2U","short_pith_number":"pith:N3FDFQIO","schema_version":"1.0","canonical_sha256":"6eca32c10e384636e6afa47b2eb974d52c47a69fb5d7b4cfaee526514ee7877f","source":{"kind":"arxiv","id":"2203.14338","version":1},"attestation_state":"computed","paper":{"title":"LibMTL: A Python Library for Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baijiong Lin, Yu Zhang","submitted_at":"2022-03-27T16:00:48Z","abstract_excerpt":"This paper presents LibMTL, an open-source Python library built on PyTorch, which provides a unified, comprehensive, reproducible, and extensible implementation framework for Multi-Task Learning (MTL). LibMTL considers different settings and approaches in MTL, and it supports a large number of state-of-the-art MTL methods, including 12 loss weighting strategies, 7 architectures, and 84 combinations of different architectures and loss weighting methods. Moreover, the modular design in LibMTL makes it easy-to-use and well extensible, thus users can easily and fast develop new MTL methods, compar"},"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":"2203.14338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-27T16:00:48Z","cross_cats_sorted":[],"title_canon_sha256":"dc3b91a9b1dbc72c552f27b3a10103947d90ac38613f3fe093136cea7baa184a","abstract_canon_sha256":"a341af5d2b23c3b13f39c26866592b60c977ba19dbbda12b55a0fc4f54fe4bb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:03.883099Z","signature_b64":"jpmT+SSqup1RN4z1fn8QtI7Hn2813OGOv6t2mj/+wrHYTLxinIQXnUGdvHxlA0MKu8KVeiY81moVy0j/bedSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6eca32c10e384636e6afa47b2eb974d52c47a69fb5d7b4cfaee526514ee7877f","last_reissued_at":"2026-07-05T04:09:03.882669Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:03.882669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LibMTL: A Python Library for Multi-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baijiong Lin, Yu Zhang","submitted_at":"2022-03-27T16:00:48Z","abstract_excerpt":"This paper presents LibMTL, an open-source Python library built on PyTorch, which provides a unified, comprehensive, reproducible, and extensible implementation framework for Multi-Task Learning (MTL). LibMTL considers different settings and approaches in MTL, and it supports a large number of state-of-the-art MTL methods, including 12 loss weighting strategies, 7 architectures, and 84 combinations of different architectures and loss weighting methods. Moreover, the modular design in LibMTL makes it easy-to-use and well extensible, thus users can easily and fast develop new MTL methods, compar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14338","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.14338/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2203.14338","created_at":"2026-07-05T04:09:03.882733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.14338v1","created_at":"2026-07-05T04:09:03.882733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14338","created_at":"2026-07-05T04:09:03.882733+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3FDFQIOHBDD","created_at":"2026-07-05T04:09:03.882733+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3FDFQIOHBDDNZVP","created_at":"2026-07-05T04:09:03.882733+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3FDFQIO","created_at":"2026-07-05T04:09:03.882733+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25131","citing_title":"Towards Unified Multi-task EEG Analysis with Low-Rank Adaptation","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N3FDFQIOHBDDNZVPUR5S5OLU2U","json":"https://pith.science/pith/N3FDFQIOHBDDNZVPUR5S5OLU2U.json","graph_json":"https://pith.science/api/pith-number/N3FDFQIOHBDDNZVPUR5S5OLU2U/graph.json","events_json":"https://pith.science/api/pith-number/N3FDFQIOHBDDNZVPUR5S5OLU2U/events.json","paper":"https://pith.science/paper/N3FDFQIO"},"agent_actions":{"view_html":"https://pith.science/pith/N3FDFQIOHBDDNZVPUR5S5OLU2U","download_json":"https://pith.science/pith/N3FDFQIOHBDDNZVPUR5S5OLU2U.json","view_paper":"https://pith.science/paper/N3FDFQIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.14338&json=true","fetch_graph":"https://pith.science/api/pith-number/N3FDFQIOHBDDNZVPUR5S5OLU2U/graph.json","fetch_events":"https://pith.science/api/pith-number/N3FDFQIOHBDDNZVPUR5S5OLU2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3FDFQIOHBDDNZVPUR5S5OLU2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3FDFQIOHBDDNZVPUR5S5OLU2U/action/storage_attestation","attest_author":"https://pith.science/pith/N3FDFQIOHBDDNZVPUR5S5OLU2U/action/author_attestation","sign_citation":"https://pith.science/pith/N3FDFQIOHBDDNZVPUR5S5OLU2U/action/citation_signature","submit_replication":"https://pith.science/pith/N3FDFQIOHBDDNZVPUR5S5OLU2U/action/replication_record"}},"created_at":"2026-07-05T04:09:03.882733+00:00","updated_at":"2026-07-05T04:09:03.882733+00:00"}