{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:SW7M3AJS54KLEZPICNDT5P6VOM","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":"7a796bf24857b1b93a508cc82cf171f8ee0890a66f97c8b0b6ddd5f8adbd0542","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T11:40:36Z","title_canon_sha256":"3009a17fddcbad642074b3b43eb41d026469b5add8e2757608c3c2797d1bce38"},"schema_version":"1.0","source":{"id":"2112.08804","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.08804","created_at":"2026-07-05T06:14:03Z"},{"alias_kind":"arxiv_version","alias_value":"2112.08804v3","created_at":"2026-07-05T06:14:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08804","created_at":"2026-07-05T06:14:03Z"},{"alias_kind":"pith_short_12","alias_value":"SW7M3AJS54KL","created_at":"2026-07-05T06:14:03Z"},{"alias_kind":"pith_short_16","alias_value":"SW7M3AJS54KLEZPI","created_at":"2026-07-05T06:14:03Z"},{"alias_kind":"pith_short_8","alias_value":"SW7M3AJS","created_at":"2026-07-05T06:14:03Z"}],"graph_snapshots":[{"event_id":"sha256:a275462a6c53ed8301bf06a9dded8191f3aebf6c512557dae8fa5fbdf3f573d9","target":"graph","created_at":"2026-07-05T06:14:03Z","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/2112.08804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present CrossSum, a large-scale cross-lingual summarization dataset comprising 1.68 million article-summary samples in 1,500+ language pairs. We create CrossSum by aligning parallel articles written in different languages via cross-lingual retrieval from a multilingual abstractive summarization dataset and perform a controlled human evaluation to validate its quality. We propose a multistage data sampling algorithm to effectively train a cross-lingual summarization model capable of summarizing an article in any target language. We also introduce LaSE, an embedding-based metric for automatic","authors_text":"Abhik Bhattacharjee, Rifat Shahriyar, Tahmid Hasan, Wasi Uddin Ahmad, Yong-Bin Kang, Yuan-Fang Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T11:40:36Z","title":"CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08804","kind":"arxiv","version":3},"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":"sha256:2e9625b46ccf62adb6fe3e9ffe4199d135d4cfd5f76de7d0ef6b50e2d861c954","target":"record","created_at":"2026-07-05T06:14:03Z","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":"7a796bf24857b1b93a508cc82cf171f8ee0890a66f97c8b0b6ddd5f8adbd0542","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-16T11:40:36Z","title_canon_sha256":"3009a17fddcbad642074b3b43eb41d026469b5add8e2757608c3c2797d1bce38"},"schema_version":"1.0","source":{"id":"2112.08804","kind":"arxiv","version":3}},"canonical_sha256":"95becd8132ef14b265e813473ebfd5732a465c1de0aec258b91ca08fc7670e9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95becd8132ef14b265e813473ebfd5732a465c1de0aec258b91ca08fc7670e9b","first_computed_at":"2026-07-05T06:14:03.268228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:03.268228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0lzoPVDt10GLAjFZJHGu021TG33YtMfC1fbh5mpcO/Ir0xFMULhNRRC5qbsP7CZAuzooE4cuXj/ckqe5df7EAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:03.268654Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.08804","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e9625b46ccf62adb6fe3e9ffe4199d135d4cfd5f76de7d0ef6b50e2d861c954","sha256:a275462a6c53ed8301bf06a9dded8191f3aebf6c512557dae8fa5fbdf3f573d9"],"state_sha256":"a96604db1332c08284a045a02acb237b09695067656aaa3a6537f8894cbca824"}