{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6EXCAQJNYVCLNWIKL7L4HUO3DP","short_pith_number":"pith:6EXCAQJN","schema_version":"1.0","canonical_sha256":"f12e20412dc544b6d90a5fd7c3d1db1bcd137e861083f833897214ccc1270414","source":{"kind":"arxiv","id":"2411.18607","version":2},"attestation_state":"computed","paper":{"title":"Task Arithmetic Through The Lens Of One-Shot Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ian Mason, Sanjeev Kulkarni, Xavier Boix, Zhixu Silvia Tao","submitted_at":"2024-11-27T18:53:41Z","abstract_excerpt":"Task Arithmetic is a model merging technique that enables the combination of multiple models' capabilities into a single model through simple arithmetic in the weight space, without the need for additional fine-tuning or access to the original training data. However, the factors that determine the success of Task Arithmetic remain unclear. In this paper, we examine Task Arithmetic for multi-task learning by framing it as a one-shot Federated Learning problem. We demonstrate that Task Arithmetic is mathematically equivalent to the commonly used algorithm in Federated Learning, called Federated "},"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":"2411.18607","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-27T18:53:41Z","cross_cats_sorted":[],"title_canon_sha256":"3ec9e16383d030c736fed9631f6b990326d948a3f00d71e90725943f77c3de5e","abstract_canon_sha256":"93f7d61e7330f6df1865d978b670607310ba0d31d212f8ee8b607e7d4b584427"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:11.258513Z","signature_b64":"7d8LNuCpZXY5IDLaRM+eKR5uTu5qLAx3iSuv8xQuo+ov3j/JyluaFDOlF6EA/1at5jexuYgPqY/7DHyPxeFNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f12e20412dc544b6d90a5fd7c3d1db1bcd137e861083f833897214ccc1270414","last_reissued_at":"2026-07-05T11:35:11.258022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:11.258022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task Arithmetic Through The Lens Of One-Shot Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ian Mason, Sanjeev Kulkarni, Xavier Boix, Zhixu Silvia Tao","submitted_at":"2024-11-27T18:53:41Z","abstract_excerpt":"Task Arithmetic is a model merging technique that enables the combination of multiple models' capabilities into a single model through simple arithmetic in the weight space, without the need for additional fine-tuning or access to the original training data. However, the factors that determine the success of Task Arithmetic remain unclear. In this paper, we examine Task Arithmetic for multi-task learning by framing it as a one-shot Federated Learning problem. We demonstrate that Task Arithmetic is mathematically equivalent to the commonly used algorithm in Federated Learning, called Federated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18607","kind":"arxiv","version":2},"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/2411.18607/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":"2411.18607","created_at":"2026-07-05T11:35:11.258077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18607v2","created_at":"2026-07-05T11:35:11.258077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18607","created_at":"2026-07-05T11:35:11.258077+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EXCAQJNYVCL","created_at":"2026-07-05T11:35:11.258077+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EXCAQJNYVCLNWIK","created_at":"2026-07-05T11:35:11.258077+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EXCAQJN","created_at":"2026-07-05T11:35:11.258077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01194","citing_title":"FedRPCA: Enhancing Federated LoRA Aggregation Using Robust PCA","ref_index":75,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6EXCAQJNYVCLNWIKL7L4HUO3DP","json":"https://pith.science/pith/6EXCAQJNYVCLNWIKL7L4HUO3DP.json","graph_json":"https://pith.science/api/pith-number/6EXCAQJNYVCLNWIKL7L4HUO3DP/graph.json","events_json":"https://pith.science/api/pith-number/6EXCAQJNYVCLNWIKL7L4HUO3DP/events.json","paper":"https://pith.science/paper/6EXCAQJN"},"agent_actions":{"view_html":"https://pith.science/pith/6EXCAQJNYVCLNWIKL7L4HUO3DP","download_json":"https://pith.science/pith/6EXCAQJNYVCLNWIKL7L4HUO3DP.json","view_paper":"https://pith.science/paper/6EXCAQJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18607&json=true","fetch_graph":"https://pith.science/api/pith-number/6EXCAQJNYVCLNWIKL7L4HUO3DP/graph.json","fetch_events":"https://pith.science/api/pith-number/6EXCAQJNYVCLNWIKL7L4HUO3DP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EXCAQJNYVCLNWIKL7L4HUO3DP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EXCAQJNYVCLNWIKL7L4HUO3DP/action/storage_attestation","attest_author":"https://pith.science/pith/6EXCAQJNYVCLNWIKL7L4HUO3DP/action/author_attestation","sign_citation":"https://pith.science/pith/6EXCAQJNYVCLNWIKL7L4HUO3DP/action/citation_signature","submit_replication":"https://pith.science/pith/6EXCAQJNYVCLNWIKL7L4HUO3DP/action/replication_record"}},"created_at":"2026-07-05T11:35:11.258077+00:00","updated_at":"2026-07-05T11:35:11.258077+00:00"}