{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XJ3ECPGIWZES5SLKFN4V6NXCLB","short_pith_number":"pith:XJ3ECPGI","canonical_record":{"source":{"id":"2103.08849","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-16T04:37:40Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"525d9274bb94cd1775d39419b9688d25dde3f6b8619ea600aa75c72cdf4d1097","abstract_canon_sha256":"9f75df1588d7c2253839d2d06a1a5ad20c6efc6db7c3ebb5f7e034cfc5e794c7"},"schema_version":"1.0"},"canonical_sha256":"ba76413cc8b6492ec96a2b795f36e2586e37d9265b052f8cb1ec8665d28d9238","source":{"kind":"arxiv","id":"2103.08849","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.08849","created_at":"2026-07-05T02:32:16Z"},{"alias_kind":"arxiv_version","alias_value":"2103.08849v3","created_at":"2026-07-05T02:32:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08849","created_at":"2026-07-05T02:32:16Z"},{"alias_kind":"pith_short_12","alias_value":"XJ3ECPGIWZES","created_at":"2026-07-05T02:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"XJ3ECPGIWZES5SLK","created_at":"2026-07-05T02:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"XJ3ECPGI","created_at":"2026-07-05T02:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XJ3ECPGIWZES5SLKFN4V6NXCLB","target":"record","payload":{"canonical_record":{"source":{"id":"2103.08849","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-16T04:37:40Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"525d9274bb94cd1775d39419b9688d25dde3f6b8619ea600aa75c72cdf4d1097","abstract_canon_sha256":"9f75df1588d7c2253839d2d06a1a5ad20c6efc6db7c3ebb5f7e034cfc5e794c7"},"schema_version":"1.0"},"canonical_sha256":"ba76413cc8b6492ec96a2b795f36e2586e37d9265b052f8cb1ec8665d28d9238","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:16.679188Z","signature_b64":"TPgWXPGOzD0TWd7e+HipovgO2lNT3QvZGQJGO3ONUfQBVi4r9RVc6ePf6SagedvfE/UyftRaFwRiPabxZ7vbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba76413cc8b6492ec96a2b795f36e2586e37d9265b052f8cb1ec8665d28d9238","last_reissued_at":"2026-07-05T02:32:16.678772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:16.678772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.08849","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":"2026-07-05T02:32:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5EOcbaup95BZpVwd2qJOT4mQS0ynRer+VOny9nMWcxJzUK/BPicq//FBCQv54je1YMSLJF6uCjcg0RG+RHveBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T15:49:33.130764Z"},"content_sha256":"7fb8814266bea81c3dcc3062ced2585332c30fa28678a6b01bd9464fd1bdfaab","schema_version":"1.0","event_id":"sha256:7fb8814266bea81c3dcc3062ced2585332c30fa28678a6b01bd9464fd1bdfaab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XJ3ECPGIWZES5SLKFN4V6NXCLB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Alexander Hauptmann, Florian Metze, Graham Neubig, Junjie Hu, Mandela Patrick, Po-Yao Huang","submitted_at":"2021-03-16T04:37:40Z","abstract_excerpt":"This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextualized multilingual multimodal embeddings. Under a zero-shot setting, we empirically demonstrate that performance degrades significantly when we query the multilingual text-video model with non-English sentences. To address this problem, we introduce a multilingual multimodal pre-training strategy, and collect a new multilingual instructional video dataset (MultiHowTo100M) for pre-training. Experimen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08849","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.08849/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":"2026-07-05T02:32:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tUrsLETBSbqtYj07aFUrFwSnhhSaHZtBTQPIAeD8TSk2Gy0ztn3YcVb4YQZDIb4yG91P+MS7YQH3dtsvHSMlDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-20T15:49:33.131134Z"},"content_sha256":"6826d7213f47f3f6e46cad4241050662c51740645a376753c1c07dea071c5ed9","schema_version":"1.0","event_id":"sha256:6826d7213f47f3f6e46cad4241050662c51740645a376753c1c07dea071c5ed9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XJ3ECPGIWZES5SLKFN4V6NXCLB/bundle.json","state_url":"https://pith.science/pith/XJ3ECPGIWZES5SLKFN4V6NXCLB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XJ3ECPGIWZES5SLKFN4V6NXCLB/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":"2026-07-20T15:49:33Z","links":{"resolver":"https://pith.science/pith/XJ3ECPGIWZES5SLKFN4V6NXCLB","bundle":"https://pith.science/pith/XJ3ECPGIWZES5SLKFN4V6NXCLB/bundle.json","state":"https://pith.science/pith/XJ3ECPGIWZES5SLKFN4V6NXCLB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XJ3ECPGIWZES5SLKFN4V6NXCLB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XJ3ECPGIWZES5SLKFN4V6NXCLB","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":"9f75df1588d7c2253839d2d06a1a5ad20c6efc6db7c3ebb5f7e034cfc5e794c7","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-16T04:37:40Z","title_canon_sha256":"525d9274bb94cd1775d39419b9688d25dde3f6b8619ea600aa75c72cdf4d1097"},"schema_version":"1.0","source":{"id":"2103.08849","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.08849","created_at":"2026-07-05T02:32:16Z"},{"alias_kind":"arxiv_version","alias_value":"2103.08849v3","created_at":"2026-07-05T02:32:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.08849","created_at":"2026-07-05T02:32:16Z"},{"alias_kind":"pith_short_12","alias_value":"XJ3ECPGIWZES","created_at":"2026-07-05T02:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"XJ3ECPGIWZES5SLK","created_at":"2026-07-05T02:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"XJ3ECPGI","created_at":"2026-07-05T02:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:6826d7213f47f3f6e46cad4241050662c51740645a376753c1c07dea071c5ed9","target":"graph","created_at":"2026-07-05T02:32:16Z","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/2103.08849/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextualized multilingual multimodal embeddings. Under a zero-shot setting, we empirically demonstrate that performance degrades significantly when we query the multilingual text-video model with non-English sentences. To address this problem, we introduce a multilingual multimodal pre-training strategy, and collect a new multilingual instructional video dataset (MultiHowTo100M) for pre-training. Experimen","authors_text":"Alexander Hauptmann, Florian Metze, Graham Neubig, Junjie Hu, Mandela Patrick, Po-Yao Huang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-16T04:37:40Z","title":"Multilingual Multimodal Pre-training for Zero-Shot Cross-Lingual Transfer of Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.08849","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":"sha256:7fb8814266bea81c3dcc3062ced2585332c30fa28678a6b01bd9464fd1bdfaab","target":"record","created_at":"2026-07-05T02:32:16Z","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":"9f75df1588d7c2253839d2d06a1a5ad20c6efc6db7c3ebb5f7e034cfc5e794c7","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-16T04:37:40Z","title_canon_sha256":"525d9274bb94cd1775d39419b9688d25dde3f6b8619ea600aa75c72cdf4d1097"},"schema_version":"1.0","source":{"id":"2103.08849","kind":"arxiv","version":3}},"canonical_sha256":"ba76413cc8b6492ec96a2b795f36e2586e37d9265b052f8cb1ec8665d28d9238","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba76413cc8b6492ec96a2b795f36e2586e37d9265b052f8cb1ec8665d28d9238","first_computed_at":"2026-07-05T02:32:16.678772Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:16.678772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TPgWXPGOzD0TWd7e+HipovgO2lNT3QvZGQJGO3ONUfQBVi4r9RVc6ePf6SagedvfE/UyftRaFwRiPabxZ7vbBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:16.679188Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.08849","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fb8814266bea81c3dcc3062ced2585332c30fa28678a6b01bd9464fd1bdfaab","sha256:6826d7213f47f3f6e46cad4241050662c51740645a376753c1c07dea071c5ed9"],"state_sha256":"623d234891bf9edac2fadff838b052d9180e5947c5f9d7f398ff123fc385a07c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IeIwQinp+QPHvZ6lG+BMS0JfeW1enBaMcX6Au1AfE+Pm/g16VE1imJh8xW4Z+LmhBjqHCFGcqDbKESW7eWp/CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-20T15:49:33.133618Z","bundle_sha256":"5aaccdb7c9b90707e0064f1ea7f8c14a4e0f3d3c32f5c48bdb65aab4111276d7"}}