{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7APWNFK5PSEINRUKPWDWW2AGNC","short_pith_number":"pith:7APWNFK5","canonical_record":{"source":{"id":"1905.10464","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-05-24T22:11:57Z","cross_cats_sorted":[],"title_canon_sha256":"99f50cb6aeeb9e9d91418d9deda7d9ce4dfe6b259c402240491b04bebf248640","abstract_canon_sha256":"ad9b4089f1aedfe32bb8a5d35fd75a391b2355ebb98a2ede8a7f874f1aaa8c49"},"schema_version":"1.0"},"canonical_sha256":"f81f66955d7c8886c68a7d876b68066882635de98aca8cfb60c56e4e0c31fc17","source":{"kind":"arxiv","id":"1905.10464","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10464","created_at":"2026-05-17T23:42:41Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10464v3","created_at":"2026-05-17T23:42:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10464","created_at":"2026-05-17T23:42:41Z"},{"alias_kind":"pith_short_12","alias_value":"7APWNFK5PSEI","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7APWNFK5PSEINRUK","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7APWNFK5","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7APWNFK5PSEINRUKPWDWW2AGNC","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10464","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-05-24T22:11:57Z","cross_cats_sorted":[],"title_canon_sha256":"99f50cb6aeeb9e9d91418d9deda7d9ce4dfe6b259c402240491b04bebf248640","abstract_canon_sha256":"ad9b4089f1aedfe32bb8a5d35fd75a391b2355ebb98a2ede8a7f874f1aaa8c49"},"schema_version":"1.0"},"canonical_sha256":"f81f66955d7c8886c68a7d876b68066882635de98aca8cfb60c56e4e0c31fc17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:41.557914Z","signature_b64":"kOc9L2JuBstKARLiLxF/UnRuhm+BaPHXSMfVkPRXzqIr9wREDH/Kw3AwbCZjC8MgEiih8wKWZv7Y4afkW23ABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f81f66955d7c8886c68a7d876b68066882635de98aca8cfb60c56e4e0c31fc17","last_reissued_at":"2026-05-17T23:42:41.557179Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:41.557179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10464","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wW4c38ZgEn8b8HPUCohXT1OfCcEkyDrwaKIV6OnFlUCVAeyVniLbfF+Mtu5uqlC5D4M7uK+wH5eQ7ph9k4EfDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T13:53:15.155999Z"},"content_sha256":"1c7a74ab67fdf90172926bda33056d163633484fd201d9a360ed782e2f9803ad","schema_version":"1.0","event_id":"sha256:1c7a74ab67fdf90172926bda33056d163633484fd201d9a360ed782e2f9803ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7APWNFK5PSEINRUKPWDWW2AGNC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Debiasing Word Embeddings Improves Multimodal Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mamoru Komachi, Tosho Hirasawa","submitted_at":"2019-05-24T22:11:57Z","abstract_excerpt":"In recent years, pretrained word embeddings have proved useful for multimodal neural machine translation (NMT) models to address the shortage of available datasets. However, the integration of pretrained word embeddings has not yet been explored extensively. Further, pretrained word embeddings in high dimensional spaces have been reported to suffer from the hubness problem. Although some debiasing techniques have been proposed to address this problem for other natural language processing tasks, they have seldom been studied for multimodal NMT models. In this study, we examine various kinds of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10464","kind":"arxiv","version":3},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:42:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HQbApw+ECWZonQ6nrl8RqplopIBEZWPOtZk+2RpGvN2o2DDZh8L6PodQCfVnJnucUebbnAHhEm1xTqryPJiTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T13:53:15.156353Z"},"content_sha256":"ed311b4b4c015db6558c822591bca78f028acbfb9ba6c49b712cae2c5155bd16","schema_version":"1.0","event_id":"sha256:ed311b4b4c015db6558c822591bca78f028acbfb9ba6c49b712cae2c5155bd16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7APWNFK5PSEINRUKPWDWW2AGNC/bundle.json","state_url":"https://pith.science/pith/7APWNFK5PSEINRUKPWDWW2AGNC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7APWNFK5PSEINRUKPWDWW2AGNC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-26T13:53:15Z","links":{"resolver":"https://pith.science/pith/7APWNFK5PSEINRUKPWDWW2AGNC","bundle":"https://pith.science/pith/7APWNFK5PSEINRUKPWDWW2AGNC/bundle.json","state":"https://pith.science/pith/7APWNFK5PSEINRUKPWDWW2AGNC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7APWNFK5PSEINRUKPWDWW2AGNC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7APWNFK5PSEINRUKPWDWW2AGNC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ad9b4089f1aedfe32bb8a5d35fd75a391b2355ebb98a2ede8a7f874f1aaa8c49","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-05-24T22:11:57Z","title_canon_sha256":"99f50cb6aeeb9e9d91418d9deda7d9ce4dfe6b259c402240491b04bebf248640"},"schema_version":"1.0","source":{"id":"1905.10464","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10464","created_at":"2026-05-17T23:42:41Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10464v3","created_at":"2026-05-17T23:42:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10464","created_at":"2026-05-17T23:42:41Z"},{"alias_kind":"pith_short_12","alias_value":"7APWNFK5PSEI","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7APWNFK5PSEINRUK","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7APWNFK5","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:ed311b4b4c015db6558c822591bca78f028acbfb9ba6c49b712cae2c5155bd16","target":"graph","created_at":"2026-05-17T23:42:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"In recent years, pretrained word embeddings have proved useful for multimodal neural machine translation (NMT) models to address the shortage of available datasets. However, the integration of pretrained word embeddings has not yet been explored extensively. Further, pretrained word embeddings in high dimensional spaces have been reported to suffer from the hubness problem. Although some debiasing techniques have been proposed to address this problem for other natural language processing tasks, they have seldom been studied for multimodal NMT models. In this study, we examine various kinds of ","authors_text":"Mamoru Komachi, Tosho Hirasawa","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-05-24T22:11:57Z","title":"Debiasing Word Embeddings Improves Multimodal Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10464","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1c7a74ab67fdf90172926bda33056d163633484fd201d9a360ed782e2f9803ad","target":"record","created_at":"2026-05-17T23:42:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ad9b4089f1aedfe32bb8a5d35fd75a391b2355ebb98a2ede8a7f874f1aaa8c49","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-05-24T22:11:57Z","title_canon_sha256":"99f50cb6aeeb9e9d91418d9deda7d9ce4dfe6b259c402240491b04bebf248640"},"schema_version":"1.0","source":{"id":"1905.10464","kind":"arxiv","version":3}},"canonical_sha256":"f81f66955d7c8886c68a7d876b68066882635de98aca8cfb60c56e4e0c31fc17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f81f66955d7c8886c68a7d876b68066882635de98aca8cfb60c56e4e0c31fc17","first_computed_at":"2026-05-17T23:42:41.557179Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:41.557179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kOc9L2JuBstKARLiLxF/UnRuhm+BaPHXSMfVkPRXzqIr9wREDH/Kw3AwbCZjC8MgEiih8wKWZv7Y4afkW23ABw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:41.557914Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10464","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c7a74ab67fdf90172926bda33056d163633484fd201d9a360ed782e2f9803ad","sha256:ed311b4b4c015db6558c822591bca78f028acbfb9ba6c49b712cae2c5155bd16"],"state_sha256":"7a968625d2b63631120164a6e12c2ec1d21c634f9711bae42f93ca6e7f0bb94e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pr7VQZ284Dk23jduWnDeWGFcLlJ6nabiE+2X6jotG0R8tgtvyRFZ5D/fH2i4a8ciPqhUPR4prtXpi2toojorAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T13:53:15.158252Z","bundle_sha256":"10ced4526f4e21f12692878825b73dec329a06f662bb15805c7790faaca15594"}}