{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HUIPOIMNU66ARTQCPVYTMRC3PV","short_pith_number":"pith:HUIPOIMN","schema_version":"1.0","canonical_sha256":"3d10f7218da7bc08ce027d7136445b7d493e3d76534ee933f5b5bea4a5256610","source":{"kind":"arxiv","id":"2403.19305","version":2},"attestation_state":"computed","paper":{"title":"MATEval: A Multi-Agent Discussion Framework for Advancing Open-Ended Text Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dehai Min, Guilin Qi, Rui Wu, Shenyu Zhang, Wenhao Xu, Xiutian Huang, Yongrui Chen, Yu Li","submitted_at":"2024-03-28T10:41:47Z","abstract_excerpt":"Recent advancements in generative Large Language Models(LLMs) have been remarkable, however, the quality of the text generated by these models often reveals persistent issues. Evaluating the quality of text generated by these models, especially in open-ended text, has consistently presented a significant challenge. Addressing this, recent work has explored the possibility of using LLMs as evaluators. While using a single LLM as an evaluation agent shows potential, it is filled with significant uncertainty and instability. To address these issues, we propose the MATEval: A \"Multi-Agent Text Eva"},"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":"2403.19305","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T10:41:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8de5ed0662155fd4c4351f6a36ad696b42094713b43a8fe9dcdda89da4f268bd","abstract_canon_sha256":"5cfa5985d59211e12807ee4c111f9a37c25b2c600e108ae12e816b27e888614b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:03.052481Z","signature_b64":"9NbjfdRQv0ixZXSyC85UwaZqjPSOwMcSdN88LmcOHBMs9FAL1bpl0RxJk7UPqgm0igPdS32Q/cHduVn0DJTYCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d10f7218da7bc08ce027d7136445b7d493e3d76534ee933f5b5bea4a5256610","last_reissued_at":"2026-07-05T08:08:03.051994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:03.051994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MATEval: A Multi-Agent Discussion Framework for Advancing Open-Ended Text Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dehai Min, Guilin Qi, Rui Wu, Shenyu Zhang, Wenhao Xu, Xiutian Huang, Yongrui Chen, Yu Li","submitted_at":"2024-03-28T10:41:47Z","abstract_excerpt":"Recent advancements in generative Large Language Models(LLMs) have been remarkable, however, the quality of the text generated by these models often reveals persistent issues. Evaluating the quality of text generated by these models, especially in open-ended text, has consistently presented a significant challenge. Addressing this, recent work has explored the possibility of using LLMs as evaluators. While using a single LLM as an evaluation agent shows potential, it is filled with significant uncertainty and instability. To address these issues, we propose the MATEval: A \"Multi-Agent Text Eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19305","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/2403.19305/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":"2403.19305","created_at":"2026-07-05T08:08:03.052051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19305v2","created_at":"2026-07-05T08:08:03.052051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19305","created_at":"2026-07-05T08:08:03.052051+00:00"},{"alias_kind":"pith_short_12","alias_value":"HUIPOIMNU66A","created_at":"2026-07-05T08:08:03.052051+00:00"},{"alias_kind":"pith_short_16","alias_value":"HUIPOIMNU66ARTQC","created_at":"2026-07-05T08:08:03.052051+00:00"},{"alias_kind":"pith_short_8","alias_value":"HUIPOIMN","created_at":"2026-07-05T08:08:03.052051+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/HUIPOIMNU66ARTQCPVYTMRC3PV","json":"https://pith.science/pith/HUIPOIMNU66ARTQCPVYTMRC3PV.json","graph_json":"https://pith.science/api/pith-number/HUIPOIMNU66ARTQCPVYTMRC3PV/graph.json","events_json":"https://pith.science/api/pith-number/HUIPOIMNU66ARTQCPVYTMRC3PV/events.json","paper":"https://pith.science/paper/HUIPOIMN"},"agent_actions":{"view_html":"https://pith.science/pith/HUIPOIMNU66ARTQCPVYTMRC3PV","download_json":"https://pith.science/pith/HUIPOIMNU66ARTQCPVYTMRC3PV.json","view_paper":"https://pith.science/paper/HUIPOIMN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19305&json=true","fetch_graph":"https://pith.science/api/pith-number/HUIPOIMNU66ARTQCPVYTMRC3PV/graph.json","fetch_events":"https://pith.science/api/pith-number/HUIPOIMNU66ARTQCPVYTMRC3PV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HUIPOIMNU66ARTQCPVYTMRC3PV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HUIPOIMNU66ARTQCPVYTMRC3PV/action/storage_attestation","attest_author":"https://pith.science/pith/HUIPOIMNU66ARTQCPVYTMRC3PV/action/author_attestation","sign_citation":"https://pith.science/pith/HUIPOIMNU66ARTQCPVYTMRC3PV/action/citation_signature","submit_replication":"https://pith.science/pith/HUIPOIMNU66ARTQCPVYTMRC3PV/action/replication_record"}},"created_at":"2026-07-05T08:08:03.052051+00:00","updated_at":"2026-07-05T08:08:03.052051+00:00"}