{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YRGJTN6Q57DZH6P6RGTABF44DJ","short_pith_number":"pith:YRGJTN6Q","schema_version":"1.0","canonical_sha256":"c44c99b7d0efc793f9fe89a600979c1a5f8e8d15c21f427aca6a74a57ccb269d","source":{"kind":"arxiv","id":"2206.09403","version":1},"attestation_state":"computed","paper":{"title":"MME-CRS: Multi-Metric Evaluation Based on Correlation Re-Scaling for Evaluating Open-Domain Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cao Liu, Chunyang Yuan, Jian Wang, Kaidong Yu, Pengfei Zhang, Song Han, Xiaohui Hu","submitted_at":"2022-06-19T13:43:59Z","abstract_excerpt":"Automatic open-domain dialogue evaluation is a crucial component of dialogue systems. Recently, learning-based evaluation metrics have achieved state-of-the-art performance in open-domain dialogue evaluation. However, these metrics, which only focus on a few qualities, are hard to evaluate dialogue comprehensively. Furthermore, these metrics lack an effective score composition approach for diverse evaluation qualities. To address the above problems, we propose a Multi-Metric Evaluation based on Correlation Re-Scaling (MME-CRS) for evaluating open-domain dialogue. Firstly, we build an evaluatio"},"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":"2206.09403","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-19T13:43:59Z","cross_cats_sorted":[],"title_canon_sha256":"9553fe8eb50a5484d569058f5683a251750dd408128abf16a2e2452ebae74135","abstract_canon_sha256":"dcdf5f2b0e97b1dc48d039c640b81424997ae6120e8d8951b014ff6177d16f38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:07.134553Z","signature_b64":"HlozgGYXbITHMC0Nj94w+YOkAKb0Vpt8FfO1XgXZub7SLHnb/aMwFccSc8hRrNU6ZWJor+axTSeFju9dfXxPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c44c99b7d0efc793f9fe89a600979c1a5f8e8d15c21f427aca6a74a57ccb269d","last_reissued_at":"2026-07-05T04:33:07.134131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:07.134131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MME-CRS: Multi-Metric Evaluation Based on Correlation Re-Scaling for Evaluating Open-Domain Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cao Liu, Chunyang Yuan, Jian Wang, Kaidong Yu, Pengfei Zhang, Song Han, Xiaohui Hu","submitted_at":"2022-06-19T13:43:59Z","abstract_excerpt":"Automatic open-domain dialogue evaluation is a crucial component of dialogue systems. Recently, learning-based evaluation metrics have achieved state-of-the-art performance in open-domain dialogue evaluation. However, these metrics, which only focus on a few qualities, are hard to evaluate dialogue comprehensively. Furthermore, these metrics lack an effective score composition approach for diverse evaluation qualities. To address the above problems, we propose a Multi-Metric Evaluation based on Correlation Re-Scaling (MME-CRS) for evaluating open-domain dialogue. Firstly, we build an evaluatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09403","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/2206.09403/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":"2206.09403","created_at":"2026-07-05T04:33:07.134188+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.09403v1","created_at":"2026-07-05T04:33:07.134188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09403","created_at":"2026-07-05T04:33:07.134188+00:00"},{"alias_kind":"pith_short_12","alias_value":"YRGJTN6Q57DZ","created_at":"2026-07-05T04:33:07.134188+00:00"},{"alias_kind":"pith_short_16","alias_value":"YRGJTN6Q57DZH6P6","created_at":"2026-07-05T04:33:07.134188+00:00"},{"alias_kind":"pith_short_8","alias_value":"YRGJTN6Q","created_at":"2026-07-05T04:33:07.134188+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.17087","citing_title":"Leveraging LLMs as Meta-Judges: A Multi-Agent Framework for Evaluating LLM Judgments","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YRGJTN6Q57DZH6P6RGTABF44DJ","json":"https://pith.science/pith/YRGJTN6Q57DZH6P6RGTABF44DJ.json","graph_json":"https://pith.science/api/pith-number/YRGJTN6Q57DZH6P6RGTABF44DJ/graph.json","events_json":"https://pith.science/api/pith-number/YRGJTN6Q57DZH6P6RGTABF44DJ/events.json","paper":"https://pith.science/paper/YRGJTN6Q"},"agent_actions":{"view_html":"https://pith.science/pith/YRGJTN6Q57DZH6P6RGTABF44DJ","download_json":"https://pith.science/pith/YRGJTN6Q57DZH6P6RGTABF44DJ.json","view_paper":"https://pith.science/paper/YRGJTN6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.09403&json=true","fetch_graph":"https://pith.science/api/pith-number/YRGJTN6Q57DZH6P6RGTABF44DJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YRGJTN6Q57DZH6P6RGTABF44DJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YRGJTN6Q57DZH6P6RGTABF44DJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YRGJTN6Q57DZH6P6RGTABF44DJ/action/storage_attestation","attest_author":"https://pith.science/pith/YRGJTN6Q57DZH6P6RGTABF44DJ/action/author_attestation","sign_citation":"https://pith.science/pith/YRGJTN6Q57DZH6P6RGTABF44DJ/action/citation_signature","submit_replication":"https://pith.science/pith/YRGJTN6Q57DZH6P6RGTABF44DJ/action/replication_record"}},"created_at":"2026-07-05T04:33:07.134188+00:00","updated_at":"2026-07-05T04:33:07.134188+00:00"}