{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7JVWOJEIGI5G6667K5GKA3724Q","short_pith_number":"pith:7JVWOJEI","canonical_record":{"source":{"id":"2410.11540","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T12:14:57Z","cross_cats_sorted":[],"title_canon_sha256":"b28d86f6d7f6a0ad478d3378062e426dbaf53765cbe8a22c975da56837f7390c","abstract_canon_sha256":"3740e6a7d1247cccbe78ccab321bc971abba0b44a9130b20e91ec55177df0c40"},"schema_version":"1.0"},"canonical_sha256":"fa6b672488323a6f7bdf574ca06ffae4191141300de17b75097ff1cd3f80501d","source":{"kind":"arxiv","id":"2410.11540","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11540","created_at":"2026-07-05T10:21:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11540v2","created_at":"2026-07-05T10:21:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11540","created_at":"2026-07-05T10:21:24Z"},{"alias_kind":"pith_short_12","alias_value":"7JVWOJEIGI5G","created_at":"2026-07-05T10:21:24Z"},{"alias_kind":"pith_short_16","alias_value":"7JVWOJEIGI5G6667","created_at":"2026-07-05T10:21:24Z"},{"alias_kind":"pith_short_8","alias_value":"7JVWOJEI","created_at":"2026-07-05T10:21:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7JVWOJEIGI5G6667K5GKA3724Q","target":"record","payload":{"canonical_record":{"source":{"id":"2410.11540","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T12:14:57Z","cross_cats_sorted":[],"title_canon_sha256":"b28d86f6d7f6a0ad478d3378062e426dbaf53765cbe8a22c975da56837f7390c","abstract_canon_sha256":"3740e6a7d1247cccbe78ccab321bc971abba0b44a9130b20e91ec55177df0c40"},"schema_version":"1.0"},"canonical_sha256":"fa6b672488323a6f7bdf574ca06ffae4191141300de17b75097ff1cd3f80501d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:21:24.649161Z","signature_b64":"GTUeA9w/GIlybsyYla6kS3YjnqRKpeWP2DaNmMSTaH6jBM5+npIMuXai2BGdyQSJl8Kg+lDYNR7R+UkHHNvUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa6b672488323a6f7bdf574ca06ffae4191141300de17b75097ff1cd3f80501d","last_reissued_at":"2026-07-05T10:21:24.648276Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:21:24.648276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.11540","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:21:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kj1CZJnWvW8/nhkgwy61OSTEsVWH/TFNB6GpsIfiRgcDeuHGqUg+PXIaqViinKKfSucW8t8VRJKwomu//KC6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:50:53.706668Z"},"content_sha256":"b03ebe84e85bf4d21afbdb88e6d31116868f0bb9c636c467eca8fc261d3de65a","schema_version":"1.0","event_id":"sha256:b03ebe84e85bf4d21afbdb88e6d31116868f0bb9c636c467eca8fc261d3de65a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7JVWOJEIGI5G6667K5GKA3724Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Quality Control in Federated Instruction-tuning of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fengting Yuchi, Jingjing Qu, Rui Ye, Siheng Chen, Wanru Zhao, Yanfeng Wang, Yaxin Du","submitted_at":"2024-10-15T12:14:57Z","abstract_excerpt":"Federated Learning (FL) enables privacy-preserving collaborative instruction tuning of large language models (LLMs) by leveraging massively distributed data. However, the decentralized nature of FL exacerbates data quality challenges, as local clients lack global visibility to filter noisy or low-quality samples before training. To resolve this issue, we propose FedDQC, a novel federated instruction tuning framework with dynamic data quality control. Our approach introduces two key innovations. First, we propose instruction-response alignment (IRA), an efficient client-side metric for quality "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11540","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/2410.11540/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:21:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O3a0eKJJ0fUplV6TRXoZjdMB8EqTclwUxTtUEgYRMW4qAESGhxwJuHgUKtLFFrrzI+b/sqL5bWQQwhiKFek0DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:50:53.707163Z"},"content_sha256":"4db5205781550249b6408e4da22b98dc8e183b3c7e873f2ac6b7271ed56f94d1","schema_version":"1.0","event_id":"sha256:4db5205781550249b6408e4da22b98dc8e183b3c7e873f2ac6b7271ed56f94d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7JVWOJEIGI5G6667K5GKA3724Q/bundle.json","state_url":"https://pith.science/pith/7JVWOJEIGI5G6667K5GKA3724Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7JVWOJEIGI5G6667K5GKA3724Q/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T12:50:53Z","links":{"resolver":"https://pith.science/pith/7JVWOJEIGI5G6667K5GKA3724Q","bundle":"https://pith.science/pith/7JVWOJEIGI5G6667K5GKA3724Q/bundle.json","state":"https://pith.science/pith/7JVWOJEIGI5G6667K5GKA3724Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7JVWOJEIGI5G6667K5GKA3724Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7JVWOJEIGI5G6667K5GKA3724Q","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3740e6a7d1247cccbe78ccab321bc971abba0b44a9130b20e91ec55177df0c40","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T12:14:57Z","title_canon_sha256":"b28d86f6d7f6a0ad478d3378062e426dbaf53765cbe8a22c975da56837f7390c"},"schema_version":"1.0","source":{"id":"2410.11540","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.11540","created_at":"2026-07-05T10:21:24Z"},{"alias_kind":"arxiv_version","alias_value":"2410.11540v2","created_at":"2026-07-05T10:21:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11540","created_at":"2026-07-05T10:21:24Z"},{"alias_kind":"pith_short_12","alias_value":"7JVWOJEIGI5G","created_at":"2026-07-05T10:21:24Z"},{"alias_kind":"pith_short_16","alias_value":"7JVWOJEIGI5G6667","created_at":"2026-07-05T10:21:24Z"},{"alias_kind":"pith_short_8","alias_value":"7JVWOJEI","created_at":"2026-07-05T10:21:24Z"}],"graph_snapshots":[{"event_id":"sha256:4db5205781550249b6408e4da22b98dc8e183b3c7e873f2ac6b7271ed56f94d1","target":"graph","created_at":"2026-07-05T10:21:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.11540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated Learning (FL) enables privacy-preserving collaborative instruction tuning of large language models (LLMs) by leveraging massively distributed data. However, the decentralized nature of FL exacerbates data quality challenges, as local clients lack global visibility to filter noisy or low-quality samples before training. To resolve this issue, we propose FedDQC, a novel federated instruction tuning framework with dynamic data quality control. Our approach introduces two key innovations. First, we propose instruction-response alignment (IRA), an efficient client-side metric for quality ","authors_text":"Fengting Yuchi, Jingjing Qu, Rui Ye, Siheng Chen, Wanru Zhao, Yanfeng Wang, Yaxin Du","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T12:14:57Z","title":"Data Quality Control in Federated Instruction-tuning of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11540","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b03ebe84e85bf4d21afbdb88e6d31116868f0bb9c636c467eca8fc261d3de65a","target":"record","created_at":"2026-07-05T10:21:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3740e6a7d1247cccbe78ccab321bc971abba0b44a9130b20e91ec55177df0c40","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-15T12:14:57Z","title_canon_sha256":"b28d86f6d7f6a0ad478d3378062e426dbaf53765cbe8a22c975da56837f7390c"},"schema_version":"1.0","source":{"id":"2410.11540","kind":"arxiv","version":2}},"canonical_sha256":"fa6b672488323a6f7bdf574ca06ffae4191141300de17b75097ff1cd3f80501d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa6b672488323a6f7bdf574ca06ffae4191141300de17b75097ff1cd3f80501d","first_computed_at":"2026-07-05T10:21:24.648276Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:24.648276Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GTUeA9w/GIlybsyYla6kS3YjnqRKpeWP2DaNmMSTaH6jBM5+npIMuXai2BGdyQSJl8Kg+lDYNR7R+UkHHNvUAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:24.649161Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.11540","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b03ebe84e85bf4d21afbdb88e6d31116868f0bb9c636c467eca8fc261d3de65a","sha256:4db5205781550249b6408e4da22b98dc8e183b3c7e873f2ac6b7271ed56f94d1"],"state_sha256":"53b5eb1161f9c79d1ec08f6b54afdadd22e9940834b27dc8770db1398f21ba3e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lAtnX0Qsvi0x5cmfHEjkvZS+jmwDs+W+V10IbRI/Xm0DuyiNIA13hpf+Bsviwa3+jehht/EFMKRFuY/E0b+bDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T12:50:53.711283Z","bundle_sha256":"a6c49443ee41ea86a1ba63c5740d2912b2b914b6d1482e2a4ead2bb249f8d8c2"}}