{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SEB6WWBGQSVOGLF6QWH6AXDQLV","short_pith_number":"pith:SEB6WWBG","schema_version":"1.0","canonical_sha256":"9103eb582684aae32cbe858fe05c705d52bd240a6d612a0597bc014d2bb75420","source":{"kind":"arxiv","id":"2505.21438","version":1},"attestation_state":"computed","paper":{"title":"Measuring Fine-Grained Relatedness in Multitask Learning via Data Attribution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaqi W. Ma, Weijing Tang, Yiwen Tu, Ziqi Liu","submitted_at":"2025-05-27T17:13:31Z","abstract_excerpt":"Measuring task relatedness and mitigating negative transfer remain a critical open challenge in Multitask Learning (MTL). This work extends data attribution -- which quantifies the influence of individual training data points on model predictions -- to MTL setting for measuring task relatedness. We propose the MultiTask Influence Function (MTIF), a method that adapts influence functions to MTL models with hard or soft parameter sharing. Compared to conventional task relatedness measurements, MTIF provides a fine-grained, instance-level relatedness measure beyond the entire-task level. This fin"},"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":"2505.21438","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T17:13:31Z","cross_cats_sorted":[],"title_canon_sha256":"b83b1087a9e4b5580baac3974fec9d1d7f9905a1a9b21deda36dbbee9e2047eb","abstract_canon_sha256":"965e83557491ad755bf415aa6182d31a8adcfdd59eae0bad38d529f6edf95fe3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:41.888000Z","signature_b64":"TiSv8iSsaSwuk7TQO5rnb5+0YONP1zIj6P/zC8gxL3nDQ2lhY0GuVJPJTq0uRTlLg2VPnuM73RLF9QFwjYCxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9103eb582684aae32cbe858fe05c705d52bd240a6d612a0597bc014d2bb75420","last_reissued_at":"2026-07-05T11:10:41.887269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:41.887269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring Fine-Grained Relatedness in Multitask Learning via Data Attribution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jiaqi W. Ma, Weijing Tang, Yiwen Tu, Ziqi Liu","submitted_at":"2025-05-27T17:13:31Z","abstract_excerpt":"Measuring task relatedness and mitigating negative transfer remain a critical open challenge in Multitask Learning (MTL). This work extends data attribution -- which quantifies the influence of individual training data points on model predictions -- to MTL setting for measuring task relatedness. We propose the MultiTask Influence Function (MTIF), a method that adapts influence functions to MTL models with hard or soft parameter sharing. Compared to conventional task relatedness measurements, MTIF provides a fine-grained, instance-level relatedness measure beyond the entire-task level. This fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21438","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/2505.21438/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":"2505.21438","created_at":"2026-07-05T11:10:41.887588+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21438v1","created_at":"2026-07-05T11:10:41.887588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21438","created_at":"2026-07-05T11:10:41.887588+00:00"},{"alias_kind":"pith_short_12","alias_value":"SEB6WWBGQSVO","created_at":"2026-07-05T11:10:41.887588+00:00"},{"alias_kind":"pith_short_16","alias_value":"SEB6WWBGQSVOGLF6","created_at":"2026-07-05T11:10:41.887588+00:00"},{"alias_kind":"pith_short_8","alias_value":"SEB6WWBG","created_at":"2026-07-05T11:10:41.887588+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/SEB6WWBGQSVOGLF6QWH6AXDQLV","json":"https://pith.science/pith/SEB6WWBGQSVOGLF6QWH6AXDQLV.json","graph_json":"https://pith.science/api/pith-number/SEB6WWBGQSVOGLF6QWH6AXDQLV/graph.json","events_json":"https://pith.science/api/pith-number/SEB6WWBGQSVOGLF6QWH6AXDQLV/events.json","paper":"https://pith.science/paper/SEB6WWBG"},"agent_actions":{"view_html":"https://pith.science/pith/SEB6WWBGQSVOGLF6QWH6AXDQLV","download_json":"https://pith.science/pith/SEB6WWBGQSVOGLF6QWH6AXDQLV.json","view_paper":"https://pith.science/paper/SEB6WWBG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21438&json=true","fetch_graph":"https://pith.science/api/pith-number/SEB6WWBGQSVOGLF6QWH6AXDQLV/graph.json","fetch_events":"https://pith.science/api/pith-number/SEB6WWBGQSVOGLF6QWH6AXDQLV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SEB6WWBGQSVOGLF6QWH6AXDQLV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SEB6WWBGQSVOGLF6QWH6AXDQLV/action/storage_attestation","attest_author":"https://pith.science/pith/SEB6WWBGQSVOGLF6QWH6AXDQLV/action/author_attestation","sign_citation":"https://pith.science/pith/SEB6WWBGQSVOGLF6QWH6AXDQLV/action/citation_signature","submit_replication":"https://pith.science/pith/SEB6WWBGQSVOGLF6QWH6AXDQLV/action/replication_record"}},"created_at":"2026-07-05T11:10:41.887588+00:00","updated_at":"2026-07-05T11:10:41.887588+00:00"}