{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:S5OT6ZHOX67MSX3Z65MAYJYG4G","short_pith_number":"pith:S5OT6ZHO","schema_version":"1.0","canonical_sha256":"975d3f64eebfbec95f79f7580c2706e1abceaa29e4c5bd94c68fe4aae572f1fe","source":{"kind":"arxiv","id":"2210.13600","version":1},"attestation_state":"computed","paper":{"title":"LANS: Large-scale Arabic News Summarization Corpus","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdulaziz Alhamadani, Chang-Tien Lu, Jianfeng He, Xuchao Zhang","submitted_at":"2022-10-24T20:54:01Z","abstract_excerpt":"Text summarization has been intensively studied in many languages, and some languages have reached advanced stages. Yet, Arabic Text Summarization (ATS) is still in its developing stages. Existing ATS datasets are either small or lack diversity. We build, LANS, a large-scale and diverse dataset for Arabic Text Summarization task. LANS offers 8.4 million articles and their summaries extracted from newspapers websites metadata between 1999 and 2019. The high-quality and diverse summaries are written by journalists from 22 major Arab newspapers, and include an eclectic mix of at least more than 7"},"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":"2210.13600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-24T20:54:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"396e1644ed16a376ff759a6619b3bf8da37244eb5872a927c6d7cc7505b00ca2","abstract_canon_sha256":"e59eba8f8eee1aaba8baa44a19fb5d931b1988a6e5ec7d2861c7aca367daf52d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:19.864937Z","signature_b64":"sbo4jJidLzs3uRx133MDIA8EpLaIo4vNOrpRH+QmJhI0zc67KRCl26KwUGXXs5eGq4X+l9Uksg13Vab9aNELCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"975d3f64eebfbec95f79f7580c2706e1abceaa29e4c5bd94c68fe4aae572f1fe","last_reissued_at":"2026-07-05T05:10:19.864603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:19.864603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LANS: Large-scale Arabic News Summarization Corpus","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdulaziz Alhamadani, Chang-Tien Lu, Jianfeng He, Xuchao Zhang","submitted_at":"2022-10-24T20:54:01Z","abstract_excerpt":"Text summarization has been intensively studied in many languages, and some languages have reached advanced stages. Yet, Arabic Text Summarization (ATS) is still in its developing stages. Existing ATS datasets are either small or lack diversity. We build, LANS, a large-scale and diverse dataset for Arabic Text Summarization task. LANS offers 8.4 million articles and their summaries extracted from newspapers websites metadata between 1999 and 2019. The high-quality and diverse summaries are written by journalists from 22 major Arab newspapers, and include an eclectic mix of at least more than 7"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13600","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/2210.13600/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":"2210.13600","created_at":"2026-07-05T05:10:19.864659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.13600v1","created_at":"2026-07-05T05:10:19.864659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13600","created_at":"2026-07-05T05:10:19.864659+00:00"},{"alias_kind":"pith_short_12","alias_value":"S5OT6ZHOX67M","created_at":"2026-07-05T05:10:19.864659+00:00"},{"alias_kind":"pith_short_16","alias_value":"S5OT6ZHOX67MSX3Z","created_at":"2026-07-05T05:10:19.864659+00:00"},{"alias_kind":"pith_short_8","alias_value":"S5OT6ZHO","created_at":"2026-07-05T05:10:19.864659+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":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S5OT6ZHOX67MSX3Z65MAYJYG4G","json":"https://pith.science/pith/S5OT6ZHOX67MSX3Z65MAYJYG4G.json","graph_json":"https://pith.science/api/pith-number/S5OT6ZHOX67MSX3Z65MAYJYG4G/graph.json","events_json":"https://pith.science/api/pith-number/S5OT6ZHOX67MSX3Z65MAYJYG4G/events.json","paper":"https://pith.science/paper/S5OT6ZHO"},"agent_actions":{"view_html":"https://pith.science/pith/S5OT6ZHOX67MSX3Z65MAYJYG4G","download_json":"https://pith.science/pith/S5OT6ZHOX67MSX3Z65MAYJYG4G.json","view_paper":"https://pith.science/paper/S5OT6ZHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.13600&json=true","fetch_graph":"https://pith.science/api/pith-number/S5OT6ZHOX67MSX3Z65MAYJYG4G/graph.json","fetch_events":"https://pith.science/api/pith-number/S5OT6ZHOX67MSX3Z65MAYJYG4G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S5OT6ZHOX67MSX3Z65MAYJYG4G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S5OT6ZHOX67MSX3Z65MAYJYG4G/action/storage_attestation","attest_author":"https://pith.science/pith/S5OT6ZHOX67MSX3Z65MAYJYG4G/action/author_attestation","sign_citation":"https://pith.science/pith/S5OT6ZHOX67MSX3Z65MAYJYG4G/action/citation_signature","submit_replication":"https://pith.science/pith/S5OT6ZHOX67MSX3Z65MAYJYG4G/action/replication_record"}},"created_at":"2026-07-05T05:10:19.864659+00:00","updated_at":"2026-07-05T05:10:19.864659+00:00"}