{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QV5IQS3TDSTUNI7ZKX3DV2PRBI","short_pith_number":"pith:QV5IQS3T","schema_version":"1.0","canonical_sha256":"857a884b731ca746a3f955f63ae9f10a3d51b77b49eb2e54a3f78ef5d87e014b","source":{"kind":"arxiv","id":"2105.14462","version":1},"attestation_state":"computed","paper":{"title":"Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ben Kao, Lingpeng Kong, Wei Bi, Xiang Li, Zhiyong Wu","submitted_at":"2021-05-30T08:27:16Z","abstract_excerpt":"A neural multimodal machine translation (MMT) system is one that aims to perform better translation by extending conventional text-only translation models with multimodal information. Many recent studies report improvements when equipping their models with the multimodal module, despite the controversy of whether such improvements indeed come from the multimodal part. We revisit the contribution of multimodal information in MMT by devising two interpretable MMT models. To our surprise, although our models replicate similar gains as recently developed multimodal-integrated systems achieved, our"},"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":"2105.14462","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-30T08:27:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"679b3ff29ed3ca2cb9bde3bf0780fefc33d60c28a6cbe8a5f1406eb318098c6f","abstract_canon_sha256":"e24b8983e1ce0a266e986fc2517ca9e406f433e4e57ac3021804377ff573c645"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:24.166195Z","signature_b64":"WBy2aGy1aNOrCKnZkUP7usM+C9j8NU835rk/2zbpu6c6uMe1GWPlKMtjQAPGJJAFSLlVW+lgNOU9WlF3k2kFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"857a884b731ca746a3f955f63ae9f10a3d51b77b49eb2e54a3f78ef5d87e014b","last_reissued_at":"2026-07-05T02:44:24.165767Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:24.165767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ben Kao, Lingpeng Kong, Wei Bi, Xiang Li, Zhiyong Wu","submitted_at":"2021-05-30T08:27:16Z","abstract_excerpt":"A neural multimodal machine translation (MMT) system is one that aims to perform better translation by extending conventional text-only translation models with multimodal information. Many recent studies report improvements when equipping their models with the multimodal module, despite the controversy of whether such improvements indeed come from the multimodal part. We revisit the contribution of multimodal information in MMT by devising two interpretable MMT models. To our surprise, although our models replicate similar gains as recently developed multimodal-integrated systems achieved, our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14462","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/2105.14462/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":"2105.14462","created_at":"2026-07-05T02:44:24.165830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.14462v1","created_at":"2026-07-05T02:44:24.165830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14462","created_at":"2026-07-05T02:44:24.165830+00:00"},{"alias_kind":"pith_short_12","alias_value":"QV5IQS3TDSTU","created_at":"2026-07-05T02:44:24.165830+00:00"},{"alias_kind":"pith_short_16","alias_value":"QV5IQS3TDSTUNI7Z","created_at":"2026-07-05T02:44:24.165830+00:00"},{"alias_kind":"pith_short_8","alias_value":"QV5IQS3T","created_at":"2026-07-05T02:44:24.165830+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05714","citing_title":"TopicVD: A Topic-Based Dataset of Video-Guided Multimodal Machine Translation for Documentaries","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QV5IQS3TDSTUNI7ZKX3DV2PRBI","json":"https://pith.science/pith/QV5IQS3TDSTUNI7ZKX3DV2PRBI.json","graph_json":"https://pith.science/api/pith-number/QV5IQS3TDSTUNI7ZKX3DV2PRBI/graph.json","events_json":"https://pith.science/api/pith-number/QV5IQS3TDSTUNI7ZKX3DV2PRBI/events.json","paper":"https://pith.science/paper/QV5IQS3T"},"agent_actions":{"view_html":"https://pith.science/pith/QV5IQS3TDSTUNI7ZKX3DV2PRBI","download_json":"https://pith.science/pith/QV5IQS3TDSTUNI7ZKX3DV2PRBI.json","view_paper":"https://pith.science/paper/QV5IQS3T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.14462&json=true","fetch_graph":"https://pith.science/api/pith-number/QV5IQS3TDSTUNI7ZKX3DV2PRBI/graph.json","fetch_events":"https://pith.science/api/pith-number/QV5IQS3TDSTUNI7ZKX3DV2PRBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QV5IQS3TDSTUNI7ZKX3DV2PRBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QV5IQS3TDSTUNI7ZKX3DV2PRBI/action/storage_attestation","attest_author":"https://pith.science/pith/QV5IQS3TDSTUNI7ZKX3DV2PRBI/action/author_attestation","sign_citation":"https://pith.science/pith/QV5IQS3TDSTUNI7ZKX3DV2PRBI/action/citation_signature","submit_replication":"https://pith.science/pith/QV5IQS3TDSTUNI7ZKX3DV2PRBI/action/replication_record"}},"created_at":"2026-07-05T02:44:24.165830+00:00","updated_at":"2026-07-05T02:44:24.165830+00:00"}