{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:L3UUFX4HELNJVAMUPCI4IANYOB","short_pith_number":"pith:L3UUFX4H","schema_version":"1.0","canonical_sha256":"5ee942df8722da9a81947891c401b8706c43043e05a1dcc99981b11647e55680","source":{"kind":"arxiv","id":"2412.14424","version":1},"attestation_state":"computed","paper":{"title":"FedPIA -- Permuting and Integrating Adapters leveraging Wasserstein Barycenters for Finetuning Foundation Models in Multi-Modal Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Divyanshu Mishra, Felix Wagner, J. Alison Noble, Konstantinos Kamnitsas, Pramit Saha","submitted_at":"2024-12-19T00:24:00Z","abstract_excerpt":"Large Vision-Language Models typically require large text and image datasets for effective fine-tuning. However, collecting data from various sites, especially in healthcare, is challenging due to strict privacy regulations. An alternative is to fine-tune these models on end-user devices, such as in medical clinics, without sending data to a server. These local clients typically have limited computing power and small datasets, which are not enough for fully fine-tuning large VLMs on their own. A naive solution to these scenarios is to leverage parameter-efficient fine-tuning (PEFT) strategies "},"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":"2412.14424","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-19T00:24:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"74a947e39b06b3d4473933c0fdb4737e2e20fd62d729a22d2d84e48927f0cb7f","abstract_canon_sha256":"75a94448037f0361d6427f2f5e7263304db32625b786bfe1d7df1e96e2b8677f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:46.921638Z","signature_b64":"Dj6bxDNN36bTEHPlk/BOuZeHFHoNCdDI9/HCB1ts4fLcNLvttJZlhjrgQP3rCCQohRcuQJ28qrpmwM2xx0siAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ee942df8722da9a81947891c401b8706c43043e05a1dcc99981b11647e55680","last_reissued_at":"2026-07-05T09:51:46.921164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:46.921164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedPIA -- Permuting and Integrating Adapters leveraging Wasserstein Barycenters for Finetuning Foundation Models in Multi-Modal Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Divyanshu Mishra, Felix Wagner, J. Alison Noble, Konstantinos Kamnitsas, Pramit Saha","submitted_at":"2024-12-19T00:24:00Z","abstract_excerpt":"Large Vision-Language Models typically require large text and image datasets for effective fine-tuning. However, collecting data from various sites, especially in healthcare, is challenging due to strict privacy regulations. An alternative is to fine-tune these models on end-user devices, such as in medical clinics, without sending data to a server. These local clients typically have limited computing power and small datasets, which are not enough for fully fine-tuning large VLMs on their own. A naive solution to these scenarios is to leverage parameter-efficient fine-tuning (PEFT) strategies "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14424","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/2412.14424/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":"2412.14424","created_at":"2026-07-05T09:51:46.921220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14424v1","created_at":"2026-07-05T09:51:46.921220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14424","created_at":"2026-07-05T09:51:46.921220+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3UUFX4HELNJ","created_at":"2026-07-05T09:51:46.921220+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3UUFX4HELNJVAMU","created_at":"2026-07-05T09:51:46.921220+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3UUFX4H","created_at":"2026-07-05T09:51:46.921220+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/L3UUFX4HELNJVAMUPCI4IANYOB","json":"https://pith.science/pith/L3UUFX4HELNJVAMUPCI4IANYOB.json","graph_json":"https://pith.science/api/pith-number/L3UUFX4HELNJVAMUPCI4IANYOB/graph.json","events_json":"https://pith.science/api/pith-number/L3UUFX4HELNJVAMUPCI4IANYOB/events.json","paper":"https://pith.science/paper/L3UUFX4H"},"agent_actions":{"view_html":"https://pith.science/pith/L3UUFX4HELNJVAMUPCI4IANYOB","download_json":"https://pith.science/pith/L3UUFX4HELNJVAMUPCI4IANYOB.json","view_paper":"https://pith.science/paper/L3UUFX4H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14424&json=true","fetch_graph":"https://pith.science/api/pith-number/L3UUFX4HELNJVAMUPCI4IANYOB/graph.json","fetch_events":"https://pith.science/api/pith-number/L3UUFX4HELNJVAMUPCI4IANYOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3UUFX4HELNJVAMUPCI4IANYOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3UUFX4HELNJVAMUPCI4IANYOB/action/storage_attestation","attest_author":"https://pith.science/pith/L3UUFX4HELNJVAMUPCI4IANYOB/action/author_attestation","sign_citation":"https://pith.science/pith/L3UUFX4HELNJVAMUPCI4IANYOB/action/citation_signature","submit_replication":"https://pith.science/pith/L3UUFX4HELNJVAMUPCI4IANYOB/action/replication_record"}},"created_at":"2026-07-05T09:51:46.921220+00:00","updated_at":"2026-07-05T09:51:46.921220+00:00"}