{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3TBWN7OFQFXUYYZ2KSJXH44R65","short_pith_number":"pith:3TBWN7OF","schema_version":"1.0","canonical_sha256":"dcc366fdc5816f4c633a549373f391f75e85be7c10da70d25a30fbcc996fc614","source":{"kind":"arxiv","id":"2404.06003","version":1},"attestation_state":"computed","paper":{"title":"FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chang Gao, Jindong Wang, Shikun Zhang, Wei Ye, Wenjin Yao, Yidong Wang, Yue Zhang, Zhengran Zeng, Zhuohao Yu","submitted_at":"2024-04-09T04:17:51Z","abstract_excerpt":"The rapid development of large language model (LLM) evaluation methodologies and datasets has led to a profound challenge: integrating state-of-the-art evaluation techniques cost-effectively while ensuring reliability, reproducibility, and efficiency. Currently, there is a notable absence of a unified and adaptable framework that seamlessly integrates various evaluation approaches. Moreover, the reliability of evaluation findings is often questionable due to potential data contamination, with the evaluation efficiency commonly overlooked when facing the substantial costs associated with LLM in"},"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":"2404.06003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-09T04:17:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f68031d54caf763e760a5dcb13ac528dda98448ef16afe2c689fc7d00386a48e","abstract_canon_sha256":"df86415575b69859f81011dcd35b0618a2cde240f01ba3567067a03f6125c922"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:02.184540Z","signature_b64":"gnyCovnpVthJgxGujQDNesrOCNN702YP5ZtcHtgEzbDQyqMzWy+3Fr7zur71KQCizvWqzYHOMeDXl0kocOb3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcc366fdc5816f4c633a549373f391f75e85be7c10da70d25a30fbcc996fc614","last_reissued_at":"2026-07-05T08:06:02.184051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:02.184051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FreeEval: A Modular Framework for Trustworthy and Efficient Evaluation of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chang Gao, Jindong Wang, Shikun Zhang, Wei Ye, Wenjin Yao, Yidong Wang, Yue Zhang, Zhengran Zeng, Zhuohao Yu","submitted_at":"2024-04-09T04:17:51Z","abstract_excerpt":"The rapid development of large language model (LLM) evaluation methodologies and datasets has led to a profound challenge: integrating state-of-the-art evaluation techniques cost-effectively while ensuring reliability, reproducibility, and efficiency. Currently, there is a notable absence of a unified and adaptable framework that seamlessly integrates various evaluation approaches. Moreover, the reliability of evaluation findings is often questionable due to potential data contamination, with the evaluation efficiency commonly overlooked when facing the substantial costs associated with LLM in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06003","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/2404.06003/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":"2404.06003","created_at":"2026-07-05T08:06:02.184108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.06003v1","created_at":"2026-07-05T08:06:02.184108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06003","created_at":"2026-07-05T08:06:02.184108+00:00"},{"alias_kind":"pith_short_12","alias_value":"3TBWN7OFQFXU","created_at":"2026-07-05T08:06:02.184108+00:00"},{"alias_kind":"pith_short_16","alias_value":"3TBWN7OFQFXUYYZ2","created_at":"2026-07-05T08:06:02.184108+00:00"},{"alias_kind":"pith_short_8","alias_value":"3TBWN7OF","created_at":"2026-07-05T08:06:02.184108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.04244","citing_title":"Benchmark Data Contamination of Large Language Models: A Survey","ref_index":175,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3TBWN7OFQFXUYYZ2KSJXH44R65","json":"https://pith.science/pith/3TBWN7OFQFXUYYZ2KSJXH44R65.json","graph_json":"https://pith.science/api/pith-number/3TBWN7OFQFXUYYZ2KSJXH44R65/graph.json","events_json":"https://pith.science/api/pith-number/3TBWN7OFQFXUYYZ2KSJXH44R65/events.json","paper":"https://pith.science/paper/3TBWN7OF"},"agent_actions":{"view_html":"https://pith.science/pith/3TBWN7OFQFXUYYZ2KSJXH44R65","download_json":"https://pith.science/pith/3TBWN7OFQFXUYYZ2KSJXH44R65.json","view_paper":"https://pith.science/paper/3TBWN7OF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.06003&json=true","fetch_graph":"https://pith.science/api/pith-number/3TBWN7OFQFXUYYZ2KSJXH44R65/graph.json","fetch_events":"https://pith.science/api/pith-number/3TBWN7OFQFXUYYZ2KSJXH44R65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3TBWN7OFQFXUYYZ2KSJXH44R65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3TBWN7OFQFXUYYZ2KSJXH44R65/action/storage_attestation","attest_author":"https://pith.science/pith/3TBWN7OFQFXUYYZ2KSJXH44R65/action/author_attestation","sign_citation":"https://pith.science/pith/3TBWN7OFQFXUYYZ2KSJXH44R65/action/citation_signature","submit_replication":"https://pith.science/pith/3TBWN7OFQFXUYYZ2KSJXH44R65/action/replication_record"}},"created_at":"2026-07-05T08:06:02.184108+00:00","updated_at":"2026-07-05T08:06:02.184108+00:00"}