{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CZ63ESKXNPZI5D4U2BRXRNIE47","short_pith_number":"pith:CZ63ESKX","schema_version":"1.0","canonical_sha256":"167db249576bf28e8f94d06378b504e7d5d69bb0ff1f5f44b01fc0dead212acb","source":{"kind":"arxiv","id":"2301.12618","version":3},"attestation_state":"computed","paper":{"title":"ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baixu Chen, Jie Jiang, Junguang Jiang, Junwei Pan, Liu Dapeng, Mingsheng Long, Ximei Wang","submitted_at":"2023-01-30T02:27:02Z","abstract_excerpt":"Auxiliary-Task Learning (ATL) aims to improve the performance of the target task by leveraging the knowledge obtained from related tasks. Occasionally, learning multiple tasks simultaneously results in lower accuracy than learning only the target task, which is known as negative transfer. This problem is often attributed to the gradient conflicts among tasks, and is frequently tackled by coordinating the task gradients in previous works. However, these optimization-based methods largely overlook the auxiliary-target generalization capability. To better understand the root cause of negative tra"},"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":"2301.12618","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-01-30T02:27:02Z","cross_cats_sorted":[],"title_canon_sha256":"eedf8df9dcbec253039414d84bc9d17a761d65620036210a0fb2d58150d58e67","abstract_canon_sha256":"9f7f102c9feba7e35bd1ab5ee66f29e60af6f42b773b4c9eb86bf2fd9a413426"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:21.108836Z","signature_b64":"et2Jym99nixavCRYbwrK7apmk149goB90vCjr1CteSbjOCpyBHk4TzRSnoSWThXxLjye8mh7vOIEok5h2FBzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"167db249576bf28e8f94d06378b504e7d5d69bb0ff1f5f44b01fc0dead212acb","last_reissued_at":"2026-07-05T07:13:21.108307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:21.108307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baixu Chen, Jie Jiang, Junguang Jiang, Junwei Pan, Liu Dapeng, Mingsheng Long, Ximei Wang","submitted_at":"2023-01-30T02:27:02Z","abstract_excerpt":"Auxiliary-Task Learning (ATL) aims to improve the performance of the target task by leveraging the knowledge obtained from related tasks. Occasionally, learning multiple tasks simultaneously results in lower accuracy than learning only the target task, which is known as negative transfer. This problem is often attributed to the gradient conflicts among tasks, and is frequently tackled by coordinating the task gradients in previous works. However, these optimization-based methods largely overlook the auxiliary-target generalization capability. To better understand the root cause of negative tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12618","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/2301.12618/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":"2301.12618","created_at":"2026-07-05T07:13:21.108391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12618v3","created_at":"2026-07-05T07:13:21.108391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12618","created_at":"2026-07-05T07:13:21.108391+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZ63ESKXNPZI","created_at":"2026-07-05T07:13:21.108391+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZ63ESKXNPZI5D4U","created_at":"2026-07-05T07:13:21.108391+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZ63ESKX","created_at":"2026-07-05T07:13:21.108391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00061","citing_title":"Smooth-Distill: A Self-distillation Framework for Multitask Learning with Wearable Sensor Data","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CZ63ESKXNPZI5D4U2BRXRNIE47","json":"https://pith.science/pith/CZ63ESKXNPZI5D4U2BRXRNIE47.json","graph_json":"https://pith.science/api/pith-number/CZ63ESKXNPZI5D4U2BRXRNIE47/graph.json","events_json":"https://pith.science/api/pith-number/CZ63ESKXNPZI5D4U2BRXRNIE47/events.json","paper":"https://pith.science/paper/CZ63ESKX"},"agent_actions":{"view_html":"https://pith.science/pith/CZ63ESKXNPZI5D4U2BRXRNIE47","download_json":"https://pith.science/pith/CZ63ESKXNPZI5D4U2BRXRNIE47.json","view_paper":"https://pith.science/paper/CZ63ESKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12618&json=true","fetch_graph":"https://pith.science/api/pith-number/CZ63ESKXNPZI5D4U2BRXRNIE47/graph.json","fetch_events":"https://pith.science/api/pith-number/CZ63ESKXNPZI5D4U2BRXRNIE47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZ63ESKXNPZI5D4U2BRXRNIE47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZ63ESKXNPZI5D4U2BRXRNIE47/action/storage_attestation","attest_author":"https://pith.science/pith/CZ63ESKXNPZI5D4U2BRXRNIE47/action/author_attestation","sign_citation":"https://pith.science/pith/CZ63ESKXNPZI5D4U2BRXRNIE47/action/citation_signature","submit_replication":"https://pith.science/pith/CZ63ESKXNPZI5D4U2BRXRNIE47/action/replication_record"}},"created_at":"2026-07-05T07:13:21.108391+00:00","updated_at":"2026-07-05T07:13:21.108391+00:00"}