{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NMAOYGL765BUOQCMNNTFEOTJMT","short_pith_number":"pith:NMAOYGL7","schema_version":"1.0","canonical_sha256":"6b00ec197ff74347404c6b66523a6964efc18fcdcbc029118c2ee7434b721581","source":{"kind":"arxiv","id":"2106.13822","version":1},"attestation_state":"computed","paper":{"title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhik Bhattacharjee, Kazi Samin, Md Saiful Islam, M. Sohel Rahman, Rifat Shahriyar, Tahmid Hasan, Yong-Bin Kang, Yuan-Fang Li","submitted_at":"2021-06-25T18:00:24Z","abstract_excerpt":"Contemporary works on abstractive text summarization have focused primarily on high-resource languages like English, mostly due to the limited availability of datasets for low/mid-resource ones. In this work, we present XL-Sum, a comprehensive and diverse dataset comprising 1 million professionally annotated article-summary pairs from BBC, extracted using a set of carefully designed heuristics. The dataset covers 44 languages ranging from low to high-resource, for many of which no public dataset is currently available. XL-Sum is highly abstractive, concise, and of high quality, as indicated by"},"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":"2106.13822","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-25T18:00:24Z","cross_cats_sorted":[],"title_canon_sha256":"80699194a0db2188d560dad5b61a8b5a2e5eae03566283b5ecf653b5a95288c2","abstract_canon_sha256":"27772921a67ae0abbe09c4bbe9b952ba937b3f947574f5c4feea43749a31f69c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:28.967222Z","signature_b64":"HoixbRGz0dCgQPVwpXGF5mR+bNs9VzcV4iOFrijwYqoBVPikC9dqc4sdtZifwzd42VSQv03DXyRym5pYhBc4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b00ec197ff74347404c6b66523a6964efc18fcdcbc029118c2ee7434b721581","last_reissued_at":"2026-07-05T02:52:28.966774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:28.966774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abhik Bhattacharjee, Kazi Samin, Md Saiful Islam, M. Sohel Rahman, Rifat Shahriyar, Tahmid Hasan, Yong-Bin Kang, Yuan-Fang Li","submitted_at":"2021-06-25T18:00:24Z","abstract_excerpt":"Contemporary works on abstractive text summarization have focused primarily on high-resource languages like English, mostly due to the limited availability of datasets for low/mid-resource ones. In this work, we present XL-Sum, a comprehensive and diverse dataset comprising 1 million professionally annotated article-summary pairs from BBC, extracted using a set of carefully designed heuristics. The dataset covers 44 languages ranging from low to high-resource, for many of which no public dataset is currently available. XL-Sum is highly abstractive, concise, and of high quality, as indicated by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13822","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/2106.13822/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":"2106.13822","created_at":"2026-07-05T02:52:28.966830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13822v1","created_at":"2026-07-05T02:52:28.966830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13822","created_at":"2026-07-05T02:52:28.966830+00:00"},{"alias_kind":"pith_short_12","alias_value":"NMAOYGL765BU","created_at":"2026-07-05T02:52:28.966830+00:00"},{"alias_kind":"pith_short_16","alias_value":"NMAOYGL765BUOQCM","created_at":"2026-07-05T02:52:28.966830+00:00"},{"alias_kind":"pith_short_8","alias_value":"NMAOYGL7","created_at":"2026-07-05T02:52:28.966830+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":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NMAOYGL765BUOQCMNNTFEOTJMT","json":"https://pith.science/pith/NMAOYGL765BUOQCMNNTFEOTJMT.json","graph_json":"https://pith.science/api/pith-number/NMAOYGL765BUOQCMNNTFEOTJMT/graph.json","events_json":"https://pith.science/api/pith-number/NMAOYGL765BUOQCMNNTFEOTJMT/events.json","paper":"https://pith.science/paper/NMAOYGL7"},"agent_actions":{"view_html":"https://pith.science/pith/NMAOYGL765BUOQCMNNTFEOTJMT","download_json":"https://pith.science/pith/NMAOYGL765BUOQCMNNTFEOTJMT.json","view_paper":"https://pith.science/paper/NMAOYGL7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13822&json=true","fetch_graph":"https://pith.science/api/pith-number/NMAOYGL765BUOQCMNNTFEOTJMT/graph.json","fetch_events":"https://pith.science/api/pith-number/NMAOYGL765BUOQCMNNTFEOTJMT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NMAOYGL765BUOQCMNNTFEOTJMT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NMAOYGL765BUOQCMNNTFEOTJMT/action/storage_attestation","attest_author":"https://pith.science/pith/NMAOYGL765BUOQCMNNTFEOTJMT/action/author_attestation","sign_citation":"https://pith.science/pith/NMAOYGL765BUOQCMNNTFEOTJMT/action/citation_signature","submit_replication":"https://pith.science/pith/NMAOYGL765BUOQCMNNTFEOTJMT/action/replication_record"}},"created_at":"2026-07-05T02:52:28.966830+00:00","updated_at":"2026-07-05T02:52:28.966830+00:00"}