{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:67IKDQ3G5WX2AFCN7FFEMQD3OD","short_pith_number":"pith:67IKDQ3G","schema_version":"1.0","canonical_sha256":"f7d0a1c366edafa0144df94a46407b70dad4c89d45ea84163652d1ecf157fa94","source":{"kind":"arxiv","id":"2307.08074","version":2},"attestation_state":"computed","paper":{"title":"Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Deng Cai, Dian Yu, Donghuai Liu, Haiyun Jiang, Leyang Cui, Longyue Wang, Shuming Shi, Yan Wang, Zefeng Du, Zhaopeng Tu","submitted_at":"2023-07-16T15:18:25Z","abstract_excerpt":"Modeling discourse -- the linguistic phenomena that go beyond individual sentences, is a fundamental yet challenging aspect of natural language processing (NLP). However, existing evaluation benchmarks primarily focus on the evaluation of inter-sentence properties and overlook critical discourse phenomena that cross sentences. To bridge the gap, we propose Disco-Bench, a benchmark that can evaluate intra-sentence discourse properties across a diverse set of NLP tasks, covering understanding, translation, and generation. Disco-Bench consists of 9 document-level testsets in the literature domain"},"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":"2307.08074","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-16T15:18:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ea24e0cb3f3f769b5dc27ad492c728e07cb21736d4abff2d0469a4afd85cb011","abstract_canon_sha256":"429aa6b2a13fbd8539d40c7946824a08d39191c5c1f36834b05d575026e6abd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:33:33.980113Z","signature_b64":"9ATT8ul2dgR/Z+5YgfVyT8C1gKuAGO47exg3g/Eb28e67A975DMoGI/LYlt7GTC/vwqab90rF9sz4y42atD+Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7d0a1c366edafa0144df94a46407b70dad4c89d45ea84163652d1ecf157fa94","last_reissued_at":"2026-07-05T06:33:33.979659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:33:33.979659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Deng Cai, Dian Yu, Donghuai Liu, Haiyun Jiang, Leyang Cui, Longyue Wang, Shuming Shi, Yan Wang, Zefeng Du, Zhaopeng Tu","submitted_at":"2023-07-16T15:18:25Z","abstract_excerpt":"Modeling discourse -- the linguistic phenomena that go beyond individual sentences, is a fundamental yet challenging aspect of natural language processing (NLP). However, existing evaluation benchmarks primarily focus on the evaluation of inter-sentence properties and overlook critical discourse phenomena that cross sentences. To bridge the gap, we propose Disco-Bench, a benchmark that can evaluate intra-sentence discourse properties across a diverse set of NLP tasks, covering understanding, translation, and generation. Disco-Bench consists of 9 document-level testsets in the literature domain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08074","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/2307.08074/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":"2307.08074","created_at":"2026-07-05T06:33:33.979717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.08074v2","created_at":"2026-07-05T06:33:33.979717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08074","created_at":"2026-07-05T06:33:33.979717+00:00"},{"alias_kind":"pith_short_12","alias_value":"67IKDQ3G5WX2","created_at":"2026-07-05T06:33:33.979717+00:00"},{"alias_kind":"pith_short_16","alias_value":"67IKDQ3G5WX2AFCN","created_at":"2026-07-05T06:33:33.979717+00:00"},{"alias_kind":"pith_short_8","alias_value":"67IKDQ3G","created_at":"2026-07-05T06:33:33.979717+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11732","citing_title":"Findings of the WMT 2024 Shared Task on Discourse-Level Literary Translation","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/67IKDQ3G5WX2AFCN7FFEMQD3OD","json":"https://pith.science/pith/67IKDQ3G5WX2AFCN7FFEMQD3OD.json","graph_json":"https://pith.science/api/pith-number/67IKDQ3G5WX2AFCN7FFEMQD3OD/graph.json","events_json":"https://pith.science/api/pith-number/67IKDQ3G5WX2AFCN7FFEMQD3OD/events.json","paper":"https://pith.science/paper/67IKDQ3G"},"agent_actions":{"view_html":"https://pith.science/pith/67IKDQ3G5WX2AFCN7FFEMQD3OD","download_json":"https://pith.science/pith/67IKDQ3G5WX2AFCN7FFEMQD3OD.json","view_paper":"https://pith.science/paper/67IKDQ3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.08074&json=true","fetch_graph":"https://pith.science/api/pith-number/67IKDQ3G5WX2AFCN7FFEMQD3OD/graph.json","fetch_events":"https://pith.science/api/pith-number/67IKDQ3G5WX2AFCN7FFEMQD3OD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67IKDQ3G5WX2AFCN7FFEMQD3OD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67IKDQ3G5WX2AFCN7FFEMQD3OD/action/storage_attestation","attest_author":"https://pith.science/pith/67IKDQ3G5WX2AFCN7FFEMQD3OD/action/author_attestation","sign_citation":"https://pith.science/pith/67IKDQ3G5WX2AFCN7FFEMQD3OD/action/citation_signature","submit_replication":"https://pith.science/pith/67IKDQ3G5WX2AFCN7FFEMQD3OD/action/replication_record"}},"created_at":"2026-07-05T06:33:33.979717+00:00","updated_at":"2026-07-05T06:33:33.979717+00:00"}