{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UTFOKYJFZEU2HVLBUSRBT3XKX6","short_pith_number":"pith:UTFOKYJF","schema_version":"1.0","canonical_sha256":"a4cae56125c929a3d561a4a219eeeabfbd760bde09513597a48fcaf091300eaa","source":{"kind":"arxiv","id":"2310.18122","version":2},"attestation_state":"computed","paper":{"title":"OpinSummEval: Revisiting Automated Evaluation for Opinion Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Xiaojun Wan, Yuchen Shen","submitted_at":"2023-10-27T13:09:54Z","abstract_excerpt":"Opinion summarization sets itself apart from other types of summarization tasks due to its distinctive focus on aspects and sentiments. Although certain automated evaluation methods like ROUGE have gained popularity, we have found them to be unreliable measures for assessing the quality of opinion summaries. In this paper, we present OpinSummEval, a dataset comprising human judgments and outputs from 14 opinion summarization models. We further explore the correlation between 24 automatic metrics and human ratings across four dimensions. Our findings indicate that metrics based on neural networ"},"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":"2310.18122","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T13:09:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"84a674c9545b84b7e71e6100529e447985037b6808ef7ea64fcb5761c6f7d431","abstract_canon_sha256":"e15057c1f267d1bae65935d52bf41e9eb6f6ebdbee57c0f3f092b5e875a0a5d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:37.107078Z","signature_b64":"qoXMAEntqC99h4s/XBF0vDO6wmPXV7Og59ZR8TiD/DxSxrwKylhk5f0jxSlTaz40HAL6wKvFdaEYUtN0c1BdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4cae56125c929a3d561a4a219eeeabfbd760bde09513597a48fcaf091300eaa","last_reissued_at":"2026-07-05T07:11:37.106569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:37.106569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpinSummEval: Revisiting Automated Evaluation for Opinion Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Xiaojun Wan, Yuchen Shen","submitted_at":"2023-10-27T13:09:54Z","abstract_excerpt":"Opinion summarization sets itself apart from other types of summarization tasks due to its distinctive focus on aspects and sentiments. Although certain automated evaluation methods like ROUGE have gained popularity, we have found them to be unreliable measures for assessing the quality of opinion summaries. In this paper, we present OpinSummEval, a dataset comprising human judgments and outputs from 14 opinion summarization models. We further explore the correlation between 24 automatic metrics and human ratings across four dimensions. Our findings indicate that metrics based on neural networ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18122","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/2310.18122/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":"2310.18122","created_at":"2026-07-05T07:11:37.106631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18122v2","created_at":"2026-07-05T07:11:37.106631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18122","created_at":"2026-07-05T07:11:37.106631+00:00"},{"alias_kind":"pith_short_12","alias_value":"UTFOKYJFZEU2","created_at":"2026-07-05T07:11:37.106631+00:00"},{"alias_kind":"pith_short_16","alias_value":"UTFOKYJFZEU2HVLB","created_at":"2026-07-05T07:11:37.106631+00:00"},{"alias_kind":"pith_short_8","alias_value":"UTFOKYJF","created_at":"2026-07-05T07:11:37.106631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09564","citing_title":"ACE-Bench: A Lightweight Benchmark for Evaluating Azure SDK Usage Correctness","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05579","citing_title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","ref_index":200,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UTFOKYJFZEU2HVLBUSRBT3XKX6","json":"https://pith.science/pith/UTFOKYJFZEU2HVLBUSRBT3XKX6.json","graph_json":"https://pith.science/api/pith-number/UTFOKYJFZEU2HVLBUSRBT3XKX6/graph.json","events_json":"https://pith.science/api/pith-number/UTFOKYJFZEU2HVLBUSRBT3XKX6/events.json","paper":"https://pith.science/paper/UTFOKYJF"},"agent_actions":{"view_html":"https://pith.science/pith/UTFOKYJFZEU2HVLBUSRBT3XKX6","download_json":"https://pith.science/pith/UTFOKYJFZEU2HVLBUSRBT3XKX6.json","view_paper":"https://pith.science/paper/UTFOKYJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18122&json=true","fetch_graph":"https://pith.science/api/pith-number/UTFOKYJFZEU2HVLBUSRBT3XKX6/graph.json","fetch_events":"https://pith.science/api/pith-number/UTFOKYJFZEU2HVLBUSRBT3XKX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UTFOKYJFZEU2HVLBUSRBT3XKX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UTFOKYJFZEU2HVLBUSRBT3XKX6/action/storage_attestation","attest_author":"https://pith.science/pith/UTFOKYJFZEU2HVLBUSRBT3XKX6/action/author_attestation","sign_citation":"https://pith.science/pith/UTFOKYJFZEU2HVLBUSRBT3XKX6/action/citation_signature","submit_replication":"https://pith.science/pith/UTFOKYJFZEU2HVLBUSRBT3XKX6/action/replication_record"}},"created_at":"2026-07-05T07:11:37.106631+00:00","updated_at":"2026-07-05T07:11:37.106631+00:00"}