{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GOE5EMIULAFXBRZWMN6N2ORZCY","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":"aa94d7f4bc1b17ed94108385cbeda756fbbfd13fb040f63854900eeff04324a9","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-25T12:46:41Z","title_canon_sha256":"a54679f89913da2299fafd39bd1583dd1c6a51141dc76213587cd5c87e915b02"},"schema_version":"1.0","source":{"id":"2101.10044","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.10044","created_at":"2026-07-05T02:33:57Z"},{"alias_kind":"arxiv_version","alias_value":"2101.10044v2","created_at":"2026-07-05T02:33:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.10044","created_at":"2026-07-05T02:33:57Z"},{"alias_kind":"pith_short_12","alias_value":"GOE5EMIULAFX","created_at":"2026-07-05T02:33:57Z"},{"alias_kind":"pith_short_16","alias_value":"GOE5EMIULAFXBRZW","created_at":"2026-07-05T02:33:57Z"},{"alias_kind":"pith_short_8","alias_value":"GOE5EMIU","created_at":"2026-07-05T02:33:57Z"}],"graph_snapshots":[{"event_id":"sha256:ac5de8b607b58f49b417dd2d6b48582ddd1f8e01334fb1b4b3b12ba1ddf9da1a","target":"graph","created_at":"2026-07-05T02:33:57Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2101.10044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained language models have been shown to improve performance in many natural language tasks substantially. Although the early focus of such models was single language pre-training, recent advances have resulted in cross-lingual and visual pre-training methods. In this paper, we combine these two approaches to learn visually-grounded cross-lingual representations. Specifically, we extend the translation language modelling (Lample and Conneau, 2019) with masked region classification and perform pre-training with three-way parallel vision & language corpora. We show that when fine-tuned for","authors_text":"Aykut Erdem, Erkut Erdem, Lucia Specia, Menekse Kuyu, Mustafa Sercan Amac, Ozan Caglayan, Pranava Madhyastha","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-25T12:46:41Z","title":"Cross-lingual Visual Pre-training for Multimodal Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.10044","kind":"arxiv","version":2},"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":"sha256:2cc763f605a3b605f8dfbac758b7b3869e21523c0afd8763c05392f51c6de28c","target":"record","created_at":"2026-07-05T02:33:57Z","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":"aa94d7f4bc1b17ed94108385cbeda756fbbfd13fb040f63854900eeff04324a9","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-25T12:46:41Z","title_canon_sha256":"a54679f89913da2299fafd39bd1583dd1c6a51141dc76213587cd5c87e915b02"},"schema_version":"1.0","source":{"id":"2101.10044","kind":"arxiv","version":2}},"canonical_sha256":"3389d23114580b70c736637cdd3a39162281ecf31aa2275097bdd91f74087e61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3389d23114580b70c736637cdd3a39162281ecf31aa2275097bdd91f74087e61","first_computed_at":"2026-07-05T02:33:57.190022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:33:57.190022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CWlVKBVVVY2wTNnZ9TRci1PFyU6BV+CkP1hznijxDNIW82v1WIKvq7YtOtUIx23Fc5rP3icKxFTh8vy7lMCoDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:33:57.190474Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.10044","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2cc763f605a3b605f8dfbac758b7b3869e21523c0afd8763c05392f51c6de28c","sha256:ac5de8b607b58f49b417dd2d6b48582ddd1f8e01334fb1b4b3b12ba1ddf9da1a"],"state_sha256":"52a25ff670ec8f201b74d346c29fb50408e123c17b97b0bf26327709928a154e"}