{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LDYYSK5HZ7O7GYPSHTJGOICM3Q","short_pith_number":"pith:LDYYSK5H","schema_version":"1.0","canonical_sha256":"58f1892ba7cfddf361f23cd267204cdc113041d06b617817820412ba458c27b7","source":{"kind":"arxiv","id":"2402.11683","version":2},"attestation_state":"computed","paper":{"title":"One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amey Patil, Muthusamy Chelliah, Nikesh Garera, Pushpak Bhattacharyya, Rupasai Rangaraju, Sankara Sri Raghava Ravindra Muddu, Sudhanshu Shekhar Singh, Suman Banerjee, Swaprava Nath, Swaroop Nath, Tejpalsingh Siledar","submitted_at":"2024-02-18T19:13:52Z","abstract_excerpt":"Evaluation of opinion summaries using conventional reference-based metrics rarely provides a holistic evaluation and has been shown to have a relatively low correlation with human judgments. Recent studies suggest using Large Language Models (LLMs) as reference-free metrics for NLG evaluation, however, they remain unexplored for opinion summary evaluation. Moreover, limited opinion summary evaluation datasets inhibit progress. To address this, we release the SUMMEVAL-OP dataset covering 7 dimensions related to the evaluation of opinion summaries: fluency, coherence, relevance, faithfulness, as"},"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":"2402.11683","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T19:13:52Z","cross_cats_sorted":[],"title_canon_sha256":"688ec55c8838add8b2c3c1d0942a868eafadb95213a26096586d4201003a363f","abstract_canon_sha256":"3a7b36e5bb8632fd94b006fabc4a411afc31fdd85097f6641621dc73da9a2df2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:22.487676Z","signature_b64":"0xDymKr5R7KrPqcGbn/ikTKdFXSJJi+h5WMXoLSoHcm0NVzOcw0tK1lBUNoM/Qpj7foiqzgwG6y2m7DXxw56DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58f1892ba7cfddf361f23cd267204cdc113041d06b617817820412ba458c27b7","last_reissued_at":"2026-07-05T08:29:22.486442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:22.486442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amey Patil, Muthusamy Chelliah, Nikesh Garera, Pushpak Bhattacharyya, Rupasai Rangaraju, Sankara Sri Raghava Ravindra Muddu, Sudhanshu Shekhar Singh, Suman Banerjee, Swaprava Nath, Swaroop Nath, Tejpalsingh Siledar","submitted_at":"2024-02-18T19:13:52Z","abstract_excerpt":"Evaluation of opinion summaries using conventional reference-based metrics rarely provides a holistic evaluation and has been shown to have a relatively low correlation with human judgments. Recent studies suggest using Large Language Models (LLMs) as reference-free metrics for NLG evaluation, however, they remain unexplored for opinion summary evaluation. Moreover, limited opinion summary evaluation datasets inhibit progress. To address this, we release the SUMMEVAL-OP dataset covering 7 dimensions related to the evaluation of opinion summaries: fluency, coherence, relevance, faithfulness, as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11683","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/2402.11683/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":"2402.11683","created_at":"2026-07-05T08:29:22.486977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11683v2","created_at":"2026-07-05T08:29:22.486977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11683","created_at":"2026-07-05T08:29:22.486977+00:00"},{"alias_kind":"pith_short_12","alias_value":"LDYYSK5HZ7O7","created_at":"2026-07-05T08:29:22.486977+00:00"},{"alias_kind":"pith_short_16","alias_value":"LDYYSK5HZ7O7GYPS","created_at":"2026-07-05T08:29:22.486977+00:00"},{"alias_kind":"pith_short_8","alias_value":"LDYYSK5H","created_at":"2026-07-05T08:29:22.486977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12049","citing_title":"Leveraging Weighted Syntactic and Semantic Context Assessment Summary (wSSAS) Towards Text Categorization Using LLMs","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15547","citing_title":"Consistency Analysis of Sentiment Predictions using Syntactic & Semantic Context Assessment Summarization (SSAS)","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LDYYSK5HZ7O7GYPSHTJGOICM3Q","json":"https://pith.science/pith/LDYYSK5HZ7O7GYPSHTJGOICM3Q.json","graph_json":"https://pith.science/api/pith-number/LDYYSK5HZ7O7GYPSHTJGOICM3Q/graph.json","events_json":"https://pith.science/api/pith-number/LDYYSK5HZ7O7GYPSHTJGOICM3Q/events.json","paper":"https://pith.science/paper/LDYYSK5H"},"agent_actions":{"view_html":"https://pith.science/pith/LDYYSK5HZ7O7GYPSHTJGOICM3Q","download_json":"https://pith.science/pith/LDYYSK5HZ7O7GYPSHTJGOICM3Q.json","view_paper":"https://pith.science/paper/LDYYSK5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11683&json=true","fetch_graph":"https://pith.science/api/pith-number/LDYYSK5HZ7O7GYPSHTJGOICM3Q/graph.json","fetch_events":"https://pith.science/api/pith-number/LDYYSK5HZ7O7GYPSHTJGOICM3Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LDYYSK5HZ7O7GYPSHTJGOICM3Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LDYYSK5HZ7O7GYPSHTJGOICM3Q/action/storage_attestation","attest_author":"https://pith.science/pith/LDYYSK5HZ7O7GYPSHTJGOICM3Q/action/author_attestation","sign_citation":"https://pith.science/pith/LDYYSK5HZ7O7GYPSHTJGOICM3Q/action/citation_signature","submit_replication":"https://pith.science/pith/LDYYSK5HZ7O7GYPSHTJGOICM3Q/action/replication_record"}},"created_at":"2026-07-05T08:29:22.486977+00:00","updated_at":"2026-07-05T08:29:22.486977+00:00"}