{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UZ4KI3L2VBITRGHQ6X7RENU7FN","short_pith_number":"pith:UZ4KI3L2","schema_version":"1.0","canonical_sha256":"a678a46d7aa8513898f0f5ff12369f2b4e010570f65e22c324364e5a93d32513","source":{"kind":"arxiv","id":"2409.10883","version":1},"attestation_state":"computed","paper":{"title":"CREAM: Comparison-Based Reference-Free ELO-Ranked Automatic Evaluation for Meeting Summarization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmad Emami, Alexander Johnson, Emmy Phung, Harshsaiprasad Deshpande, Julia Hirschberg, Lin Ai, Zehui Wu, Ziwei Gong","submitted_at":"2024-09-17T04:39:20Z","abstract_excerpt":"Large Language Models (LLMs) have spurred interest in automatic evaluation methods for summarization, offering a faster, more cost-effective alternative to human evaluation. However, existing methods often fall short when applied to complex tasks like long-context summarizations and dialogue-based meeting summarizations. In this paper, we introduce CREAM (Comparison-Based Reference-Free Elo-Ranked Automatic Evaluation for Meeting Summarization), a novel framework that addresses the unique challenges of evaluating meeting summaries. CREAM leverages a combination of chain-of-thought reasoning an"},"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":"2409.10883","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T04:39:20Z","cross_cats_sorted":[],"title_canon_sha256":"17cde0a472de25ef797115323446d1eed2f9111e1a8e46763ecc6d8a3e898007","abstract_canon_sha256":"8ce624d2a6dc3a2fa9805d667a1dac3ce20192119096d87ada37869c5243ae8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:58.436699Z","signature_b64":"gfZo6Gj1OhaBs6FJ+B5TFs/jh1XWZcLkYR6OPqR04+DUlsmSWOjJZD8c2epXL1NPpIvUvbTJEHBCzSYY1GHNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a678a46d7aa8513898f0f5ff12369f2b4e010570f65e22c324364e5a93d32513","last_reissued_at":"2026-07-05T09:07:58.436153Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:58.436153Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CREAM: Comparison-Based Reference-Free ELO-Ranked Automatic Evaluation for Meeting Summarization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ahmad Emami, Alexander Johnson, Emmy Phung, Harshsaiprasad Deshpande, Julia Hirschberg, Lin Ai, Zehui Wu, Ziwei Gong","submitted_at":"2024-09-17T04:39:20Z","abstract_excerpt":"Large Language Models (LLMs) have spurred interest in automatic evaluation methods for summarization, offering a faster, more cost-effective alternative to human evaluation. However, existing methods often fall short when applied to complex tasks like long-context summarizations and dialogue-based meeting summarizations. In this paper, we introduce CREAM (Comparison-Based Reference-Free Elo-Ranked Automatic Evaluation for Meeting Summarization), a novel framework that addresses the unique challenges of evaluating meeting summaries. CREAM leverages a combination of chain-of-thought reasoning an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.10883","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/2409.10883/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":"2409.10883","created_at":"2026-07-05T09:07:58.436228+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.10883v1","created_at":"2026-07-05T09:07:58.436228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.10883","created_at":"2026-07-05T09:07:58.436228+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZ4KI3L2VBIT","created_at":"2026-07-05T09:07:58.436228+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZ4KI3L2VBITRGHQ","created_at":"2026-07-05T09:07:58.436228+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZ4KI3L2","created_at":"2026-07-05T09:07:58.436228+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08342","citing_title":"Beyond N-Grams: Rethinking Evaluation Metrics and Strategies for Multilingual Abstractive Summarization","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UZ4KI3L2VBITRGHQ6X7RENU7FN","json":"https://pith.science/pith/UZ4KI3L2VBITRGHQ6X7RENU7FN.json","graph_json":"https://pith.science/api/pith-number/UZ4KI3L2VBITRGHQ6X7RENU7FN/graph.json","events_json":"https://pith.science/api/pith-number/UZ4KI3L2VBITRGHQ6X7RENU7FN/events.json","paper":"https://pith.science/paper/UZ4KI3L2"},"agent_actions":{"view_html":"https://pith.science/pith/UZ4KI3L2VBITRGHQ6X7RENU7FN","download_json":"https://pith.science/pith/UZ4KI3L2VBITRGHQ6X7RENU7FN.json","view_paper":"https://pith.science/paper/UZ4KI3L2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.10883&json=true","fetch_graph":"https://pith.science/api/pith-number/UZ4KI3L2VBITRGHQ6X7RENU7FN/graph.json","fetch_events":"https://pith.science/api/pith-number/UZ4KI3L2VBITRGHQ6X7RENU7FN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZ4KI3L2VBITRGHQ6X7RENU7FN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZ4KI3L2VBITRGHQ6X7RENU7FN/action/storage_attestation","attest_author":"https://pith.science/pith/UZ4KI3L2VBITRGHQ6X7RENU7FN/action/author_attestation","sign_citation":"https://pith.science/pith/UZ4KI3L2VBITRGHQ6X7RENU7FN/action/citation_signature","submit_replication":"https://pith.science/pith/UZ4KI3L2VBITRGHQ6X7RENU7FN/action/replication_record"}},"created_at":"2026-07-05T09:07:58.436228+00:00","updated_at":"2026-07-05T09:07:58.436228+00:00"}