{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:UJ3HINPCW5OP5TR7CKQO6BFMPR","short_pith_number":"pith:UJ3HINPC","schema_version":"1.0","canonical_sha256":"a2767435e2b75cfece3f12a0ef04ac7c7d4901c99406315cee9b8ee9cbb68919","source":{"kind":"arxiv","id":"1605.00459","version":1},"attestation_state":"computed","paper":{"title":"Multi30K: Multilingual English-German Image Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Desmond Elliott, Khalil Sima'an, Lucia Specia, Stella Frank","submitted_at":"2016-05-02T12:38:03Z","abstract_excerpt":"We introduce the Multi30K dataset to stimulate multilingual multimodal research. Recent advances in image description have been demonstrated on English-language datasets almost exclusively, but image description should not be limited to English. This dataset extends the Flickr30K dataset with i) German translations created by professional translators over a subset of the English descriptions, and ii) descriptions crowdsourced independently of the original English descriptions. We outline how the data can be used for multilingual image description and multimodal machine translation, but we anti"},"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":"1605.00459","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-02T12:38:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e1cbe896af4768baa905fb332e887fdec110a64cd336dbdcee704513660b503c","abstract_canon_sha256":"6d000845e2d2df5a0874eb45298638c6f8404059e97dd97e3ac35ee3b83189f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:15:55.731967Z","signature_b64":"V8EgGUA+HhdTrMgxXtBY7ceXtK1k8+NNozOhrdrDxLqWYioJLYXfbdtqE6GzXWiXJhIprrhRSsN9BIYpbTkjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2767435e2b75cfece3f12a0ef04ac7c7d4901c99406315cee9b8ee9cbb68919","last_reissued_at":"2026-05-18T01:15:55.731372Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:15:55.731372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi30K: Multilingual English-German Image Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Desmond Elliott, Khalil Sima'an, Lucia Specia, Stella Frank","submitted_at":"2016-05-02T12:38:03Z","abstract_excerpt":"We introduce the Multi30K dataset to stimulate multilingual multimodal research. Recent advances in image description have been demonstrated on English-language datasets almost exclusively, but image description should not be limited to English. This dataset extends the Flickr30K dataset with i) German translations created by professional translators over a subset of the English descriptions, and ii) descriptions crowdsourced independently of the original English descriptions. We outline how the data can be used for multilingual image description and multimodal machine translation, but we anti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.00459","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":""},"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":"1605.00459","created_at":"2026-05-18T01:15:55.731459+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.00459v1","created_at":"2026-05-18T01:15:55.731459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.00459","created_at":"2026-05-18T01:15:55.731459+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJ3HINPCW5OP","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJ3HINPCW5OP5TR7","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJ3HINPC","created_at":"2026-05-18T12:30:46.583412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.08948","citing_title":"Hindi Visual Genome: A Dataset for Multimodal English-to-Hindi Machine Translation","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2505.03736","citing_title":"Decentralized Nonconvex Optimization under Heavy-Tailed Noise: Normalization and Optimal Convergence","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06789","citing_title":"Video-guided Machine Translation with Global Video Context","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02035","citing_title":"VIDA: A dataset for Visually Dependent Ambiguity in Multimodal Machine Translation","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UJ3HINPCW5OP5TR7CKQO6BFMPR","json":"https://pith.science/pith/UJ3HINPCW5OP5TR7CKQO6BFMPR.json","graph_json":"https://pith.science/api/pith-number/UJ3HINPCW5OP5TR7CKQO6BFMPR/graph.json","events_json":"https://pith.science/api/pith-number/UJ3HINPCW5OP5TR7CKQO6BFMPR/events.json","paper":"https://pith.science/paper/UJ3HINPC"},"agent_actions":{"view_html":"https://pith.science/pith/UJ3HINPCW5OP5TR7CKQO6BFMPR","download_json":"https://pith.science/pith/UJ3HINPCW5OP5TR7CKQO6BFMPR.json","view_paper":"https://pith.science/paper/UJ3HINPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.00459&json=true","fetch_graph":"https://pith.science/api/pith-number/UJ3HINPCW5OP5TR7CKQO6BFMPR/graph.json","fetch_events":"https://pith.science/api/pith-number/UJ3HINPCW5OP5TR7CKQO6BFMPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJ3HINPCW5OP5TR7CKQO6BFMPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJ3HINPCW5OP5TR7CKQO6BFMPR/action/storage_attestation","attest_author":"https://pith.science/pith/UJ3HINPCW5OP5TR7CKQO6BFMPR/action/author_attestation","sign_citation":"https://pith.science/pith/UJ3HINPCW5OP5TR7CKQO6BFMPR/action/citation_signature","submit_replication":"https://pith.science/pith/UJ3HINPCW5OP5TR7CKQO6BFMPR/action/replication_record"}},"created_at":"2026-05-18T01:15:55.731459+00:00","updated_at":"2026-05-18T01:15:55.731459+00:00"}