{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:5LTDGGYBEGYRIVN45HSC2IUGCS","short_pith_number":"pith:5LTDGGYB","schema_version":"1.0","canonical_sha256":"eae6331b0121b11455bce9e42d228614884ee5d85d5dee254b22943e24a0fedc","source":{"kind":"arxiv","id":"1510.04709","version":2},"attestation_state":"computed","paper":{"title":"Multilingual Image Description with Neural Sequence Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Desmond Elliott, Eva Hasler, Stella Frank","submitted_at":"2015-10-15T20:29:21Z","abstract_excerpt":"In this paper we present an approach to multi-language image description bringing together insights from neural machine translation and neural image description. To create a description of an image for a given target language, our sequence generation models condition on feature vectors from the image, the description from the source language, and/or a multimodal vector computed over the image and a description in the source language. In image description experiments on the IAPR-TC12 dataset of images aligned with English and German sentences, we find significant and substantial improvements in"},"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":"1510.04709","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-10-15T20:29:21Z","cross_cats_sorted":["cs.CV","cs.LG","cs.NE"],"title_canon_sha256":"ead826bbc76f8737c3b96fbd3a068f079cf40e9f12dba85834bee31b4e60177f","abstract_canon_sha256":"8c8146f4a45ea9131565b9c5389917bd847c135ac07083d9ae4c87988dea6a25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:26:33.668487Z","signature_b64":"HHL6UJEKVW1xdiYD1lto6UhmelCof34HZlpR0W3BKdBj7EWtUDwfc0IuzkYOkuygWygMVPD4kgXHTgnYSi6SCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eae6331b0121b11455bce9e42d228614884ee5d85d5dee254b22943e24a0fedc","last_reissued_at":"2026-05-18T01:26:33.667786Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:26:33.667786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual Image Description with Neural Sequence Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","cs.NE"],"primary_cat":"cs.CL","authors_text":"Desmond Elliott, Eva Hasler, Stella Frank","submitted_at":"2015-10-15T20:29:21Z","abstract_excerpt":"In this paper we present an approach to multi-language image description bringing together insights from neural machine translation and neural image description. To create a description of an image for a given target language, our sequence generation models condition on feature vectors from the image, the description from the source language, and/or a multimodal vector computed over the image and a description in the source language. In image description experiments on the IAPR-TC12 dataset of images aligned with English and German sentences, we find significant and substantial improvements in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1510.04709","kind":"arxiv","version":2},"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":"1510.04709","created_at":"2026-05-18T01:26:33.667897+00:00"},{"alias_kind":"arxiv_version","alias_value":"1510.04709v2","created_at":"2026-05-18T01:26:33.667897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1510.04709","created_at":"2026-05-18T01:26:33.667897+00:00"},{"alias_kind":"pith_short_12","alias_value":"5LTDGGYBEGYR","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_16","alias_value":"5LTDGGYBEGYRIVN4","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_8","alias_value":"5LTDGGYB","created_at":"2026-05-18T12:29:05.191682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2201.01984","citing_title":"Image Captioning via Compact Bidirectional Architecture","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06789","citing_title":"Video-guided Machine Translation with Global Video Context","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5LTDGGYBEGYRIVN45HSC2IUGCS","json":"https://pith.science/pith/5LTDGGYBEGYRIVN45HSC2IUGCS.json","graph_json":"https://pith.science/api/pith-number/5LTDGGYBEGYRIVN45HSC2IUGCS/graph.json","events_json":"https://pith.science/api/pith-number/5LTDGGYBEGYRIVN45HSC2IUGCS/events.json","paper":"https://pith.science/paper/5LTDGGYB"},"agent_actions":{"view_html":"https://pith.science/pith/5LTDGGYBEGYRIVN45HSC2IUGCS","download_json":"https://pith.science/pith/5LTDGGYBEGYRIVN45HSC2IUGCS.json","view_paper":"https://pith.science/paper/5LTDGGYB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1510.04709&json=true","fetch_graph":"https://pith.science/api/pith-number/5LTDGGYBEGYRIVN45HSC2IUGCS/graph.json","fetch_events":"https://pith.science/api/pith-number/5LTDGGYBEGYRIVN45HSC2IUGCS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5LTDGGYBEGYRIVN45HSC2IUGCS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5LTDGGYBEGYRIVN45HSC2IUGCS/action/storage_attestation","attest_author":"https://pith.science/pith/5LTDGGYBEGYRIVN45HSC2IUGCS/action/author_attestation","sign_citation":"https://pith.science/pith/5LTDGGYBEGYRIVN45HSC2IUGCS/action/citation_signature","submit_replication":"https://pith.science/pith/5LTDGGYBEGYRIVN45HSC2IUGCS/action/replication_record"}},"created_at":"2026-05-18T01:26:33.667897+00:00","updated_at":"2026-05-18T01:26:33.667897+00:00"}