{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:D4VBVAWPSJTTJAZLK7WIKRUZNA","short_pith_number":"pith:D4VBVAWP","schema_version":"1.0","canonical_sha256":"1f2a1a82cf926734832b57ec854699681c8a892d8c919ca5ff21602fea69057a","source":{"kind":"arxiv","id":"2004.14900","version":1},"attestation_state":"computed","paper":{"title":"MLSUM: The Multilingual Summarization Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Piwowarski, Jacopo Staiano, Paul-Alexis Dray, Sylvain Lamprier, Thomas Scialom","submitted_at":"2020-04-30T15:58:34Z","abstract_excerpt":"We present MLSUM, the first large-scale MultiLingual SUMmarization dataset. Obtained from online newspapers, it contains 1.5M+ article/summary pairs in five different languages -- namely, French, German, Spanish, Russian, Turkish. Together with English newspapers from the popular CNN/Daily mail dataset, the collected data form a large scale multilingual dataset which can enable new research directions for the text summarization community. We report cross-lingual comparative analyses based on state-of-the-art systems. These highlight existing biases which motivate the use of a multi-lingual dat"},"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":"2004.14900","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T15:58:34Z","cross_cats_sorted":[],"title_canon_sha256":"9686c9ae94479d4ac2b8cec7289ecea79980c148fb5b290344ffaf6ac37db755","abstract_canon_sha256":"6a875c49f70f65d6c9fd795917ffc1faa3a0ac7bbe786d325f8ae7f120d40efb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:30.853629Z","signature_b64":"ATqhql5Nd2hhk4ChTR6IJYt6bKdUxeHx2eW6DHsqt0k4MWYrttprziJtYUk5qZL6kI+OTN8F3x1aWA8D4lR5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f2a1a82cf926734832b57ec854699681c8a892d8c919ca5ff21602fea69057a","last_reissued_at":"2026-07-05T00:59:30.853129Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:30.853129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MLSUM: The Multilingual Summarization Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Piwowarski, Jacopo Staiano, Paul-Alexis Dray, Sylvain Lamprier, Thomas Scialom","submitted_at":"2020-04-30T15:58:34Z","abstract_excerpt":"We present MLSUM, the first large-scale MultiLingual SUMmarization dataset. Obtained from online newspapers, it contains 1.5M+ article/summary pairs in five different languages -- namely, French, German, Spanish, Russian, Turkish. Together with English newspapers from the popular CNN/Daily mail dataset, the collected data form a large scale multilingual dataset which can enable new research directions for the text summarization community. We report cross-lingual comparative analyses based on state-of-the-art systems. These highlight existing biases which motivate the use of a multi-lingual dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14900","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/2004.14900/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":"2004.14900","created_at":"2026-07-05T00:59:30.853193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.14900v1","created_at":"2026-07-05T00:59:30.853193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14900","created_at":"2026-07-05T00:59:30.853193+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4VBVAWPSJTT","created_at":"2026-07-05T00:59:30.853193+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4VBVAWPSJTTJAZL","created_at":"2026-07-05T00:59:30.853193+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4VBVAWP","created_at":"2026-07-05T00:59:30.853193+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.14867","citing_title":"Graph-Convolutional Networks: Named Entity Recognition and Large Language Model Embedding in Document Clustering","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4VBVAWPSJTTJAZLK7WIKRUZNA","json":"https://pith.science/pith/D4VBVAWPSJTTJAZLK7WIKRUZNA.json","graph_json":"https://pith.science/api/pith-number/D4VBVAWPSJTTJAZLK7WIKRUZNA/graph.json","events_json":"https://pith.science/api/pith-number/D4VBVAWPSJTTJAZLK7WIKRUZNA/events.json","paper":"https://pith.science/paper/D4VBVAWP"},"agent_actions":{"view_html":"https://pith.science/pith/D4VBVAWPSJTTJAZLK7WIKRUZNA","download_json":"https://pith.science/pith/D4VBVAWPSJTTJAZLK7WIKRUZNA.json","view_paper":"https://pith.science/paper/D4VBVAWP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.14900&json=true","fetch_graph":"https://pith.science/api/pith-number/D4VBVAWPSJTTJAZLK7WIKRUZNA/graph.json","fetch_events":"https://pith.science/api/pith-number/D4VBVAWPSJTTJAZLK7WIKRUZNA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4VBVAWPSJTTJAZLK7WIKRUZNA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4VBVAWPSJTTJAZLK7WIKRUZNA/action/storage_attestation","attest_author":"https://pith.science/pith/D4VBVAWPSJTTJAZLK7WIKRUZNA/action/author_attestation","sign_citation":"https://pith.science/pith/D4VBVAWPSJTTJAZLK7WIKRUZNA/action/citation_signature","submit_replication":"https://pith.science/pith/D4VBVAWPSJTTJAZLK7WIKRUZNA/action/replication_record"}},"created_at":"2026-07-05T00:59:30.853193+00:00","updated_at":"2026-07-05T00:59:30.853193+00:00"}