{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:I73DWHUBYUKPU4K6ZAZWLCY4XJ","short_pith_number":"pith:I73DWHUB","schema_version":"1.0","canonical_sha256":"47f63b1e81c514fa715ec833658b1cba581c41718edc7118b7204b9de4146fe9","source":{"kind":"arxiv","id":"2112.03473","version":1},"attestation_state":"computed","paper":{"title":"Improving Neural Cross-Lingual Summarization via Employing Optimal Transport Distance for Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Luu Anh Tuan, Thong Nguyen","submitted_at":"2021-12-07T03:45:02Z","abstract_excerpt":"Current state-of-the-art cross-lingual summarization models employ multi-task learning paradigm, which works on a shared vocabulary module and relies on the self-attention mechanism to attend among tokens in two languages. However, correlation learned by self-attention is often loose and implicit, inefficient in capturing crucial cross-lingual representations between languages. The matter worsens when performing on languages with separate morphological or structural features, making the cross-lingual alignment more challenging, resulting in the performance drop. To overcome this problem, we pr"},"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":"2112.03473","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-07T03:45:02Z","cross_cats_sorted":[],"title_canon_sha256":"d8a0a26462019b75872cda471b9b07c2d9b30c6b585bd4ef38a60788c38b8746","abstract_canon_sha256":"276a2991001a5fe9ce1bd38fcd48bf0f3975f25ca2e817c3acd7eebee922dca9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:45.998529Z","signature_b64":"GsiIR9QefLScq67cdqTbos6ref0a1kWSlBVTP/wDBm96jbbZNBEmJgsnwCyLuaoEHUG5XG3Z1YIDAKIU0x9uDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47f63b1e81c514fa715ec833658b1cba581c41718edc7118b7204b9de4146fe9","last_reissued_at":"2026-07-05T03:38:45.998092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:45.998092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Neural Cross-Lingual Summarization via Employing Optimal Transport Distance for Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Luu Anh Tuan, Thong Nguyen","submitted_at":"2021-12-07T03:45:02Z","abstract_excerpt":"Current state-of-the-art cross-lingual summarization models employ multi-task learning paradigm, which works on a shared vocabulary module and relies on the self-attention mechanism to attend among tokens in two languages. However, correlation learned by self-attention is often loose and implicit, inefficient in capturing crucial cross-lingual representations between languages. The matter worsens when performing on languages with separate morphological or structural features, making the cross-lingual alignment more challenging, resulting in the performance drop. To overcome this problem, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03473","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/2112.03473/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":"2112.03473","created_at":"2026-07-05T03:38:45.998161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.03473v1","created_at":"2026-07-05T03:38:45.998161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03473","created_at":"2026-07-05T03:38:45.998161+00:00"},{"alias_kind":"pith_short_12","alias_value":"I73DWHUBYUKP","created_at":"2026-07-05T03:38:45.998161+00:00"},{"alias_kind":"pith_short_16","alias_value":"I73DWHUBYUKPU4K6","created_at":"2026-07-05T03:38:45.998161+00:00"},{"alias_kind":"pith_short_8","alias_value":"I73DWHUB","created_at":"2026-07-05T03:38:45.998161+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I73DWHUBYUKPU4K6ZAZWLCY4XJ","json":"https://pith.science/pith/I73DWHUBYUKPU4K6ZAZWLCY4XJ.json","graph_json":"https://pith.science/api/pith-number/I73DWHUBYUKPU4K6ZAZWLCY4XJ/graph.json","events_json":"https://pith.science/api/pith-number/I73DWHUBYUKPU4K6ZAZWLCY4XJ/events.json","paper":"https://pith.science/paper/I73DWHUB"},"agent_actions":{"view_html":"https://pith.science/pith/I73DWHUBYUKPU4K6ZAZWLCY4XJ","download_json":"https://pith.science/pith/I73DWHUBYUKPU4K6ZAZWLCY4XJ.json","view_paper":"https://pith.science/paper/I73DWHUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.03473&json=true","fetch_graph":"https://pith.science/api/pith-number/I73DWHUBYUKPU4K6ZAZWLCY4XJ/graph.json","fetch_events":"https://pith.science/api/pith-number/I73DWHUBYUKPU4K6ZAZWLCY4XJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I73DWHUBYUKPU4K6ZAZWLCY4XJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I73DWHUBYUKPU4K6ZAZWLCY4XJ/action/storage_attestation","attest_author":"https://pith.science/pith/I73DWHUBYUKPU4K6ZAZWLCY4XJ/action/author_attestation","sign_citation":"https://pith.science/pith/I73DWHUBYUKPU4K6ZAZWLCY4XJ/action/citation_signature","submit_replication":"https://pith.science/pith/I73DWHUBYUKPU4K6ZAZWLCY4XJ/action/replication_record"}},"created_at":"2026-07-05T03:38:45.998161+00:00","updated_at":"2026-07-05T03:38:45.998161+00:00"}