{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JU76TWW7RRBVNJGWACVUJZFV7D","short_pith_number":"pith:JU76TWW7","schema_version":"1.0","canonical_sha256":"4d3fe9dadf8c4356a4d600ab44e4b5f8e873e91912f63aef35612a17fe1abb0f","source":{"kind":"arxiv","id":"2409.19507","version":1},"attestation_state":"computed","paper":{"title":"A Critical Look at Meta-evaluating Summarisation Evaluation Metrics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Biaoyan Fang, Sarvnaz Karimi, Xiang Dai","submitted_at":"2024-09-29T01:30:13Z","abstract_excerpt":"Effective summarisation evaluation metrics enable researchers and practitioners to compare different summarisation systems efficiently. Estimating the effectiveness of an automatic evaluation metric, termed meta-evaluation, is a critically important research question. In this position paper, we review recent meta-evaluation practices for summarisation evaluation metrics and find that (1) evaluation metrics are primarily meta-evaluated on datasets consisting of examples from news summarisation datasets, and (2) there has been a noticeable shift in research focus towards evaluating the faithfuln"},"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":"2409.19507","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-29T01:30:13Z","cross_cats_sorted":[],"title_canon_sha256":"8cd4be9f509ff80ca5966bfe4513a45c28c03db29f2b7a565ce26237e23a13b8","abstract_canon_sha256":"b36fe3af8e6e15b1a6678925a7323e2a79963c887d7670381cf3480a3cb8a09d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:16.423325Z","signature_b64":"c/fTH+tT/77JMTEckWEfOHtdn573DcrnWAuCe/z1crUmQOWKYYZ6S53w/cClhDquZckJsctUNfP7yEDzZDBZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d3fe9dadf8c4356a4d600ab44e4b5f8e873e91912f63aef35612a17fe1abb0f","last_reissued_at":"2026-07-05T09:13:16.422847Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:16.422847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Critical Look at Meta-evaluating Summarisation Evaluation Metrics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Biaoyan Fang, Sarvnaz Karimi, Xiang Dai","submitted_at":"2024-09-29T01:30:13Z","abstract_excerpt":"Effective summarisation evaluation metrics enable researchers and practitioners to compare different summarisation systems efficiently. Estimating the effectiveness of an automatic evaluation metric, termed meta-evaluation, is a critically important research question. In this position paper, we review recent meta-evaluation practices for summarisation evaluation metrics and find that (1) evaluation metrics are primarily meta-evaluated on datasets consisting of examples from news summarisation datasets, and (2) there has been a noticeable shift in research focus towards evaluating the faithfuln"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19507","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/2409.19507/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":"2409.19507","created_at":"2026-07-05T09:13:16.422906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19507v1","created_at":"2026-07-05T09:13:16.422906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19507","created_at":"2026-07-05T09:13:16.422906+00:00"},{"alias_kind":"pith_short_12","alias_value":"JU76TWW7RRBV","created_at":"2026-07-05T09:13:16.422906+00:00"},{"alias_kind":"pith_short_16","alias_value":"JU76TWW7RRBVNJGW","created_at":"2026-07-05T09:13:16.422906+00:00"},{"alias_kind":"pith_short_8","alias_value":"JU76TWW7","created_at":"2026-07-05T09:13:16.422906+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/JU76TWW7RRBVNJGWACVUJZFV7D","json":"https://pith.science/pith/JU76TWW7RRBVNJGWACVUJZFV7D.json","graph_json":"https://pith.science/api/pith-number/JU76TWW7RRBVNJGWACVUJZFV7D/graph.json","events_json":"https://pith.science/api/pith-number/JU76TWW7RRBVNJGWACVUJZFV7D/events.json","paper":"https://pith.science/paper/JU76TWW7"},"agent_actions":{"view_html":"https://pith.science/pith/JU76TWW7RRBVNJGWACVUJZFV7D","download_json":"https://pith.science/pith/JU76TWW7RRBVNJGWACVUJZFV7D.json","view_paper":"https://pith.science/paper/JU76TWW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19507&json=true","fetch_graph":"https://pith.science/api/pith-number/JU76TWW7RRBVNJGWACVUJZFV7D/graph.json","fetch_events":"https://pith.science/api/pith-number/JU76TWW7RRBVNJGWACVUJZFV7D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JU76TWW7RRBVNJGWACVUJZFV7D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JU76TWW7RRBVNJGWACVUJZFV7D/action/storage_attestation","attest_author":"https://pith.science/pith/JU76TWW7RRBVNJGWACVUJZFV7D/action/author_attestation","sign_citation":"https://pith.science/pith/JU76TWW7RRBVNJGWACVUJZFV7D/action/citation_signature","submit_replication":"https://pith.science/pith/JU76TWW7RRBVNJGWACVUJZFV7D/action/replication_record"}},"created_at":"2026-07-05T09:13:16.422906+00:00","updated_at":"2026-07-05T09:13:16.422906+00:00"}