{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PD7MDGOQVJSFOZRNNYYWBAFMUQ","short_pith_number":"pith:PD7MDGOQ","canonical_record":{"source":{"id":"2404.12273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-18T15:46:26Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"c931551fe6d69beae79fc118a9a22450b3bd0c134e86af3034418b3ec9d1c478","abstract_canon_sha256":"be4ee70aa62ea69274659e8d3fe3010a3a2e16ea62620c52460f01ae1fe5466c"},"schema_version":"1.0"},"canonical_sha256":"78fec199d0aa6457662d6e316080aca40fe9bdf3ff2343c0d7bdf09171f5ff12","source":{"kind":"arxiv","id":"2404.12273","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12273","created_at":"2026-07-05T08:09:37Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12273v1","created_at":"2026-07-05T08:09:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12273","created_at":"2026-07-05T08:09:37Z"},{"alias_kind":"pith_short_12","alias_value":"PD7MDGOQVJSF","created_at":"2026-07-05T08:09:37Z"},{"alias_kind":"pith_short_16","alias_value":"PD7MDGOQVJSFOZRN","created_at":"2026-07-05T08:09:37Z"},{"alias_kind":"pith_short_8","alias_value":"PD7MDGOQ","created_at":"2026-07-05T08:09:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PD7MDGOQVJSFOZRNNYYWBAFMUQ","target":"record","payload":{"canonical_record":{"source":{"id":"2404.12273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-18T15:46:26Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"c931551fe6d69beae79fc118a9a22450b3bd0c134e86af3034418b3ec9d1c478","abstract_canon_sha256":"be4ee70aa62ea69274659e8d3fe3010a3a2e16ea62620c52460f01ae1fe5466c"},"schema_version":"1.0"},"canonical_sha256":"78fec199d0aa6457662d6e316080aca40fe9bdf3ff2343c0d7bdf09171f5ff12","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:37.848270Z","signature_b64":"dws6UTqsLGZa9jSIkN2eBnji+obrGkRH6hRutn45OffNSjm03XQmK+4Uj4SFIdVndMDz5VjKaMC40HQmmfCeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78fec199d0aa6457662d6e316080aca40fe9bdf3ff2343c0d7bdf09171f5ff12","last_reissued_at":"2026-07-05T08:09:37.847782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:37.847782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.12273","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:09:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q889u3807rH6afUhTVO5in+9jY8aig1eucp3osekVDB+p0RuzmgrADt2CmRSgvnKyY2516XwY4Ml75IYd0SgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:06:41.570120Z"},"content_sha256":"e03ddbd60ffa1fd83511a02d3716e9517916cf735ab8c4d209a29f732b0c3b5e","schema_version":"1.0","event_id":"sha256:e03ddbd60ffa1fd83511a02d3716e9517916cf735ab8c4d209a29f732b0c3b5e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PD7MDGOQVJSFOZRNNYYWBAFMUQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FedEval-LLM: Federated Evaluation of Large Language Models on Downstream Tasks with Collective Wisdom","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Lixin Fan, Qiang Yang, Yan Kang, Yuanqin He","submitted_at":"2024-04-18T15:46:26Z","abstract_excerpt":"Federated Learning (FL) has emerged as a promising solution for collaborative training of large language models (LLMs). However, the integration of LLMs into FL introduces new challenges, particularly concerning the evaluation of LLMs. Traditional evaluation methods that rely on labeled test sets and similarity-based metrics cover only a subset of the acceptable answers, thereby failing to accurately reflect the performance of LLMs on generative tasks. Meanwhile, although automatic evaluation methods that leverage advanced LLMs present potential, they face critical risks of data leakage due to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12273","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/2404.12273/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":"2026-07-05T08:09:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"49VB18tpzQuXYFNHzYrKBIXdvHPB3BeidudwSYOTYCXkegp5QUxGg4sSQB6EHMdwuMqA9mWa8sZmZaQ11hPwBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:06:41.571014Z"},"content_sha256":"aee1a7764821bb595810c5c3d11ae733ab7207a4dd11c0c927af793ce447d774","schema_version":"1.0","event_id":"sha256:aee1a7764821bb595810c5c3d11ae733ab7207a4dd11c0c927af793ce447d774"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PD7MDGOQVJSFOZRNNYYWBAFMUQ/bundle.json","state_url":"https://pith.science/pith/PD7MDGOQVJSFOZRNNYYWBAFMUQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PD7MDGOQVJSFOZRNNYYWBAFMUQ/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":"2026-08-07T12:06:41Z","links":{"resolver":"https://pith.science/pith/PD7MDGOQVJSFOZRNNYYWBAFMUQ","bundle":"https://pith.science/pith/PD7MDGOQVJSFOZRNNYYWBAFMUQ/bundle.json","state":"https://pith.science/pith/PD7MDGOQVJSFOZRNNYYWBAFMUQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PD7MDGOQVJSFOZRNNYYWBAFMUQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PD7MDGOQVJSFOZRNNYYWBAFMUQ","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":"be4ee70aa62ea69274659e8d3fe3010a3a2e16ea62620c52460f01ae1fe5466c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-18T15:46:26Z","title_canon_sha256":"c931551fe6d69beae79fc118a9a22450b3bd0c134e86af3034418b3ec9d1c478"},"schema_version":"1.0","source":{"id":"2404.12273","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.12273","created_at":"2026-07-05T08:09:37Z"},{"alias_kind":"arxiv_version","alias_value":"2404.12273v1","created_at":"2026-07-05T08:09:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12273","created_at":"2026-07-05T08:09:37Z"},{"alias_kind":"pith_short_12","alias_value":"PD7MDGOQVJSF","created_at":"2026-07-05T08:09:37Z"},{"alias_kind":"pith_short_16","alias_value":"PD7MDGOQVJSFOZRN","created_at":"2026-07-05T08:09:37Z"},{"alias_kind":"pith_short_8","alias_value":"PD7MDGOQ","created_at":"2026-07-05T08:09:37Z"}],"graph_snapshots":[{"event_id":"sha256:aee1a7764821bb595810c5c3d11ae733ab7207a4dd11c0c927af793ce447d774","target":"graph","created_at":"2026-07-05T08:09:37Z","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/2404.12273/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated Learning (FL) has emerged as a promising solution for collaborative training of large language models (LLMs). However, the integration of LLMs into FL introduces new challenges, particularly concerning the evaluation of LLMs. Traditional evaluation methods that rely on labeled test sets and similarity-based metrics cover only a subset of the acceptable answers, thereby failing to accurately reflect the performance of LLMs on generative tasks. Meanwhile, although automatic evaluation methods that leverage advanced LLMs present potential, they face critical risks of data leakage due to","authors_text":"Lixin Fan, Qiang Yang, Yan Kang, Yuanqin He","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-18T15:46:26Z","title":"FedEval-LLM: Federated Evaluation of Large Language Models on Downstream Tasks with Collective Wisdom"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12273","kind":"arxiv","version":1},"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:e03ddbd60ffa1fd83511a02d3716e9517916cf735ab8c4d209a29f732b0c3b5e","target":"record","created_at":"2026-07-05T08:09:37Z","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":"be4ee70aa62ea69274659e8d3fe3010a3a2e16ea62620c52460f01ae1fe5466c","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-18T15:46:26Z","title_canon_sha256":"c931551fe6d69beae79fc118a9a22450b3bd0c134e86af3034418b3ec9d1c478"},"schema_version":"1.0","source":{"id":"2404.12273","kind":"arxiv","version":1}},"canonical_sha256":"78fec199d0aa6457662d6e316080aca40fe9bdf3ff2343c0d7bdf09171f5ff12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78fec199d0aa6457662d6e316080aca40fe9bdf3ff2343c0d7bdf09171f5ff12","first_computed_at":"2026-07-05T08:09:37.847782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:09:37.847782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dws6UTqsLGZa9jSIkN2eBnji+obrGkRH6hRutn45OffNSjm03XQmK+4Uj4SFIdVndMDz5VjKaMC40HQmmfCeDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:09:37.848270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.12273","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e03ddbd60ffa1fd83511a02d3716e9517916cf735ab8c4d209a29f732b0c3b5e","sha256:aee1a7764821bb595810c5c3d11ae733ab7207a4dd11c0c927af793ce447d774"],"state_sha256":"ec2b1c8d47fd5831bc46213a7346917e7ab8e06e0ccde95399f67a933d7e9f68"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7aSlX7wM0fX6opOiN3aEmR6fd+a2+kcNxqw6Nf0q5Rq2i05b7lej3rYBkjydVjS2PJpbsfrte4IOGZeaoEx3Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:06:41.576770Z","bundle_sha256":"dbbb47b3a51eb308e08b2078fcf84efb26cefdc56a1b30af2f4e964c3bd201b2"}}