{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TGU3F4DJJIKKBPYUTQBJWZEENN","short_pith_number":"pith:TGU3F4DJ","schema_version":"1.0","canonical_sha256":"99a9b2f0694a14a0bf149c029b64846b76d9b6a614e05b4c25523d0c751faf26","source":{"kind":"arxiv","id":"1811.00357","version":2},"attestation_state":"computed","paper":{"title":"Latent Variable Model for Multi-modal Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iacer Calixto, Miguel Rios, Wilker Aziz","submitted_at":"2018-11-01T13:19:27Z","abstract_excerpt":"In this work, we propose to model the interaction between visual and textual features for multi-modal neural machine translation (MMT) through a latent variable model. This latent variable can be seen as a multi-modal stochastic embedding of an image and its description in a foreign language. It is used in a target-language decoder and also to predict image features. Importantly, our model formulation utilises visual and textual inputs during training but does not require that images be available at test time. We show that our latent variable MMT formulation improves considerably over strong b"},"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":"1811.00357","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-01T13:19:27Z","cross_cats_sorted":[],"title_canon_sha256":"1af3973fa61227078536cee1efb9760af6de02f7cb6718bccddc78b5f6b5ae1e","abstract_canon_sha256":"8920a32d01480dbef52b701203b5e3fe81698d0c21ce0e51f57fe7f51f2aeab8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:03.873392Z","signature_b64":"HPLI8bttbFVfErskPP6FlVZRK2ykpeG0zvn4lkMDHVqrbZYGE40b8QL3s3fsNJQ2jIC00WQ4IJSpDtwbqeQGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99a9b2f0694a14a0bf149c029b64846b76d9b6a614e05b4c25523d0c751faf26","last_reissued_at":"2026-05-17T23:46:03.872748Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:03.872748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Latent Variable Model for Multi-modal Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Iacer Calixto, Miguel Rios, Wilker Aziz","submitted_at":"2018-11-01T13:19:27Z","abstract_excerpt":"In this work, we propose to model the interaction between visual and textual features for multi-modal neural machine translation (MMT) through a latent variable model. This latent variable can be seen as a multi-modal stochastic embedding of an image and its description in a foreign language. It is used in a target-language decoder and also to predict image features. Importantly, our model formulation utilises visual and textual inputs during training but does not require that images be available at test time. We show that our latent variable MMT formulation improves considerably over strong b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.00357","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":"1811.00357","created_at":"2026-05-17T23:46:03.872834+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.00357v2","created_at":"2026-05-17T23:46:03.872834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.00357","created_at":"2026-05-17T23:46:03.872834+00:00"},{"alias_kind":"pith_short_12","alias_value":"TGU3F4DJJIKK","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"TGU3F4DJJIKKBPYU","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"TGU3F4DJ","created_at":"2026-05-18T12:32:53.628368+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/TGU3F4DJJIKKBPYUTQBJWZEENN","json":"https://pith.science/pith/TGU3F4DJJIKKBPYUTQBJWZEENN.json","graph_json":"https://pith.science/api/pith-number/TGU3F4DJJIKKBPYUTQBJWZEENN/graph.json","events_json":"https://pith.science/api/pith-number/TGU3F4DJJIKKBPYUTQBJWZEENN/events.json","paper":"https://pith.science/paper/TGU3F4DJ"},"agent_actions":{"view_html":"https://pith.science/pith/TGU3F4DJJIKKBPYUTQBJWZEENN","download_json":"https://pith.science/pith/TGU3F4DJJIKKBPYUTQBJWZEENN.json","view_paper":"https://pith.science/paper/TGU3F4DJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.00357&json=true","fetch_graph":"https://pith.science/api/pith-number/TGU3F4DJJIKKBPYUTQBJWZEENN/graph.json","fetch_events":"https://pith.science/api/pith-number/TGU3F4DJJIKKBPYUTQBJWZEENN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TGU3F4DJJIKKBPYUTQBJWZEENN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TGU3F4DJJIKKBPYUTQBJWZEENN/action/storage_attestation","attest_author":"https://pith.science/pith/TGU3F4DJJIKKBPYUTQBJWZEENN/action/author_attestation","sign_citation":"https://pith.science/pith/TGU3F4DJJIKKBPYUTQBJWZEENN/action/citation_signature","submit_replication":"https://pith.science/pith/TGU3F4DJJIKKBPYUTQBJWZEENN/action/replication_record"}},"created_at":"2026-05-17T23:46:03.872834+00:00","updated_at":"2026-05-17T23:46:03.872834+00:00"}