{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:D4VBVAWPSJTTJAZLK7WIKRUZNA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6a875c49f70f65d6c9fd795917ffc1faa3a0ac7bbe786d325f8ae7f120d40efb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T15:58:34Z","title_canon_sha256":"9686c9ae94479d4ac2b8cec7289ecea79980c148fb5b290344ffaf6ac37db755"},"schema_version":"1.0","source":{"id":"2004.14900","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14900","created_at":"2026-07-05T00:59:30Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14900v1","created_at":"2026-07-05T00:59:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14900","created_at":"2026-07-05T00:59:30Z"},{"alias_kind":"pith_short_12","alias_value":"D4VBVAWPSJTT","created_at":"2026-07-05T00:59:30Z"},{"alias_kind":"pith_short_16","alias_value":"D4VBVAWPSJTTJAZL","created_at":"2026-07-05T00:59:30Z"},{"alias_kind":"pith_short_8","alias_value":"D4VBVAWP","created_at":"2026-07-05T00:59:30Z"}],"graph_snapshots":[{"event_id":"sha256:94425088241896cb723f47a2eaea51a644adbefe2243ebca1cedc3333e62d68d","target":"graph","created_at":"2026-07-05T00:59:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.14900/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Benjamin Piwowarski, Jacopo Staiano, Paul-Alexis Dray, Sylvain Lamprier, Thomas Scialom","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T15:58:34Z","title":"MLSUM: The Multilingual Summarization Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14900","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2e0e043f0305a413f26562902e3854d3a18f8d4d206d63ff3a78b1ad2a864f47","target":"record","created_at":"2026-07-05T00:59:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6a875c49f70f65d6c9fd795917ffc1faa3a0ac7bbe786d325f8ae7f120d40efb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-30T15:58:34Z","title_canon_sha256":"9686c9ae94479d4ac2b8cec7289ecea79980c148fb5b290344ffaf6ac37db755"},"schema_version":"1.0","source":{"id":"2004.14900","kind":"arxiv","version":1}},"canonical_sha256":"1f2a1a82cf926734832b57ec854699681c8a892d8c919ca5ff21602fea69057a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f2a1a82cf926734832b57ec854699681c8a892d8c919ca5ff21602fea69057a","first_computed_at":"2026-07-05T00:59:30.853129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:30.853129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ATqhql5Nd2hhk4ChTR6IJYt6bKdUxeHx2eW6DHsqt0k4MWYrttprziJtYUk5qZL6kI+OTN8F3x1aWA8D4lR5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:30.853629Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14900","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e0e043f0305a413f26562902e3854d3a18f8d4d206d63ff3a78b1ad2a864f47","sha256:94425088241896cb723f47a2eaea51a644adbefe2243ebca1cedc3333e62d68d"],"state_sha256":"e035df5de9a2a2a704d0a520de0417af7169828c18152b744a7bc11b9893bd99"}