{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GOE5EMIULAFXBRZWMN6N2ORZCY","short_pith_number":"pith:GOE5EMIU","canonical_record":{"source":{"id":"2101.10044","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-25T12:46:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a54679f89913da2299fafd39bd1583dd1c6a51141dc76213587cd5c87e915b02","abstract_canon_sha256":"aa94d7f4bc1b17ed94108385cbeda756fbbfd13fb040f63854900eeff04324a9"},"schema_version":"1.0"},"canonical_sha256":"3389d23114580b70c736637cdd3a39162281ecf31aa2275097bdd91f74087e61","source":{"kind":"arxiv","id":"2101.10044","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GOE5EMIULAFXBRZWMN6N2ORZCY","target":"record","payload":{"canonical_record":{"source":{"id":"2101.10044","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-25T12:46:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"a54679f89913da2299fafd39bd1583dd1c6a51141dc76213587cd5c87e915b02","abstract_canon_sha256":"aa94d7f4bc1b17ed94108385cbeda756fbbfd13fb040f63854900eeff04324a9"},"schema_version":"1.0"},"canonical_sha256":"3389d23114580b70c736637cdd3a39162281ecf31aa2275097bdd91f74087e61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:33:57.190474Z","signature_b64":"CWlVKBVVVY2wTNnZ9TRci1PFyU6BV+CkP1hznijxDNIW82v1WIKvq7YtOtUIx23Fc5rP3icKxFTh8vy7lMCoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3389d23114580b70c736637cdd3a39162281ecf31aa2275097bdd91f74087e61","last_reissued_at":"2026-07-05T02:33:57.190022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:33:57.190022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.10044","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:33:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WsdDH78FMzhm+Wqs77jcHbpDBl3zAuwVeNANbfvkkiBxQoUowjH9fmK1n+iZCd7XzmcRwF9p8FzLIYONTyftAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:40:56.502228Z"},"content_sha256":"2cc763f605a3b605f8dfbac758b7b3869e21523c0afd8763c05392f51c6de28c","schema_version":"1.0","event_id":"sha256:2cc763f605a3b605f8dfbac758b7b3869e21523c0afd8763c05392f51c6de28c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GOE5EMIULAFXBRZWMN6N2ORZCY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-lingual Visual Pre-training for Multimodal Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Aykut Erdem, Erkut Erdem, Lucia Specia, Menekse Kuyu, Mustafa Sercan Amac, Ozan Caglayan, Pranava Madhyastha","submitted_at":"2021-01-25T12:46:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.10044","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2101.10044/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:33:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vUHm7aK1J8attwfguFNt2VetRtZt9aUlulR2IhFIjNmzUSjVYGL4XFB6P4h9E38wD+9ZIyc9QugKeDSjF29SBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:40:56.502714Z"},"content_sha256":"ac5de8b607b58f49b417dd2d6b48582ddd1f8e01334fb1b4b3b12ba1ddf9da1a","schema_version":"1.0","event_id":"sha256:ac5de8b607b58f49b417dd2d6b48582ddd1f8e01334fb1b4b3b12ba1ddf9da1a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GOE5EMIULAFXBRZWMN6N2ORZCY/bundle.json","state_url":"https://pith.science/pith/GOE5EMIULAFXBRZWMN6N2ORZCY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GOE5EMIULAFXBRZWMN6N2ORZCY/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":"2026-08-04T15:40:56Z","links":{"resolver":"https://pith.science/pith/GOE5EMIULAFXBRZWMN6N2ORZCY","bundle":"https://pith.science/pith/GOE5EMIULAFXBRZWMN6N2ORZCY/bundle.json","state":"https://pith.science/pith/GOE5EMIULAFXBRZWMN6N2ORZCY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GOE5EMIULAFXBRZWMN6N2ORZCY/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"87Mba0vcKqKRUKqPgZvsVlEbEspjsR502GvRKWtFBswVgGUhbscBK8Zn7KeF4Y6VdIe3yFYPAd6c22h8gQuMAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:40:56.505893Z","bundle_sha256":"6eb17ff54dacd7c74b73cbaf2ebf9de872357b6d0225241318ee0dfffe6ee43b"}}