{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LGMKK75W7MLNBQRHBRCGGWTAGC","short_pith_number":"pith:LGMKK75W","schema_version":"1.0","canonical_sha256":"5998a57fb6fb16d0c2270c44635a603083b12bed9dc5bdece6e7f6c795a540e9","source":{"kind":"arxiv","id":"2403.04529","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Data Quality in Federated Fine-Tuning of Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Nicholas Donald Lane, Siheng Chen, Wanru Zhao, Yanfeng Wang, Yaxin Du","submitted_at":"2024-03-07T14:28:04Z","abstract_excerpt":"In the current landscape of foundation model training, there is a significant reliance on public domain data, which is nearing exhaustion according to recent research. To further scale up, it is crucial to incorporate collaboration among multiple specialized and high-quality private domain data sources. However, the challenge of training models locally without sharing private data presents numerous obstacles in data quality control. To tackle this issue, we propose a data quality control pipeline for federated fine-tuning of foundation models. This pipeline computes scores reflecting the quali"},"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":"2403.04529","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-07T14:28:04Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"0c353c928f12892f67cb3c06c226f59c60f384819a900e908cca52bec54cd455","abstract_canon_sha256":"356213c529a3189d7c6e9ca875ae27bbfc8d0d97e36df4c1b80888e99733cc6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:24.652324Z","signature_b64":"D03NfvqGwYnJ8DSUhtxjIGFbPLANi5+RVoMK/f7xOU+wIFC81t7aipKnd+K9Y0znb8JY3w0mvd9pgOw3/AtNDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5998a57fb6fb16d0c2270c44635a603083b12bed9dc5bdece6e7f6c795a540e9","last_reissued_at":"2026-07-05T07:53:24.651819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:24.651819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Data Quality in Federated Fine-Tuning of Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Nicholas Donald Lane, Siheng Chen, Wanru Zhao, Yanfeng Wang, Yaxin Du","submitted_at":"2024-03-07T14:28:04Z","abstract_excerpt":"In the current landscape of foundation model training, there is a significant reliance on public domain data, which is nearing exhaustion according to recent research. To further scale up, it is crucial to incorporate collaboration among multiple specialized and high-quality private domain data sources. However, the challenge of training models locally without sharing private data presents numerous obstacles in data quality control. To tackle this issue, we propose a data quality control pipeline for federated fine-tuning of foundation models. This pipeline computes scores reflecting the quali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.04529","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/2403.04529/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":"2403.04529","created_at":"2026-07-05T07:53:24.651876+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.04529v1","created_at":"2026-07-05T07:53:24.651876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.04529","created_at":"2026-07-05T07:53:24.651876+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGMKK75W7MLN","created_at":"2026-07-05T07:53:24.651876+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGMKK75W7MLNBQRH","created_at":"2026-07-05T07:53:24.651876+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGMKK75W","created_at":"2026-07-05T07:53:24.651876+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30288","citing_title":"MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGMKK75W7MLNBQRHBRCGGWTAGC","json":"https://pith.science/pith/LGMKK75W7MLNBQRHBRCGGWTAGC.json","graph_json":"https://pith.science/api/pith-number/LGMKK75W7MLNBQRHBRCGGWTAGC/graph.json","events_json":"https://pith.science/api/pith-number/LGMKK75W7MLNBQRHBRCGGWTAGC/events.json","paper":"https://pith.science/paper/LGMKK75W"},"agent_actions":{"view_html":"https://pith.science/pith/LGMKK75W7MLNBQRHBRCGGWTAGC","download_json":"https://pith.science/pith/LGMKK75W7MLNBQRHBRCGGWTAGC.json","view_paper":"https://pith.science/paper/LGMKK75W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.04529&json=true","fetch_graph":"https://pith.science/api/pith-number/LGMKK75W7MLNBQRHBRCGGWTAGC/graph.json","fetch_events":"https://pith.science/api/pith-number/LGMKK75W7MLNBQRHBRCGGWTAGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGMKK75W7MLNBQRHBRCGGWTAGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGMKK75W7MLNBQRHBRCGGWTAGC/action/storage_attestation","attest_author":"https://pith.science/pith/LGMKK75W7MLNBQRHBRCGGWTAGC/action/author_attestation","sign_citation":"https://pith.science/pith/LGMKK75W7MLNBQRHBRCGGWTAGC/action/citation_signature","submit_replication":"https://pith.science/pith/LGMKK75W7MLNBQRHBRCGGWTAGC/action/replication_record"}},"created_at":"2026-07-05T07:53:24.651876+00:00","updated_at":"2026-07-05T07:53:24.651876+00:00"}