{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:D3MVJ7JSSELQXSHHWNY4IR3SHT","short_pith_number":"pith:D3MVJ7JS","canonical_record":{"source":{"id":"2308.12038","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-23T09:55:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"50a8ce38c277f96b54b52cd9e3c4848864127c3ded34149bd6cbc7468cfbe057","abstract_canon_sha256":"f76f5eea3ffaf01e3096548b6595432de610457d608dea443feeee6e6b4f8403"},"schema_version":"1.0"},"canonical_sha256":"1ed954fd3291170bc8e7b371c447723ceee471a418de888f59c9ffb3a1692ea1","source":{"kind":"arxiv","id":"2308.12038","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12038","created_at":"2026-07-05T07:59:17Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12038v3","created_at":"2026-07-05T07:59:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12038","created_at":"2026-07-05T07:59:17Z"},{"alias_kind":"pith_short_12","alias_value":"D3MVJ7JSSELQ","created_at":"2026-07-05T07:59:17Z"},{"alias_kind":"pith_short_16","alias_value":"D3MVJ7JSSELQXSHH","created_at":"2026-07-05T07:59:17Z"},{"alias_kind":"pith_short_8","alias_value":"D3MVJ7JS","created_at":"2026-07-05T07:59:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:D3MVJ7JSSELQXSHHWNY4IR3SHT","target":"record","payload":{"canonical_record":{"source":{"id":"2308.12038","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-23T09:55:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"50a8ce38c277f96b54b52cd9e3c4848864127c3ded34149bd6cbc7468cfbe057","abstract_canon_sha256":"f76f5eea3ffaf01e3096548b6595432de610457d608dea443feeee6e6b4f8403"},"schema_version":"1.0"},"canonical_sha256":"1ed954fd3291170bc8e7b371c447723ceee471a418de888f59c9ffb3a1692ea1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:17.585602Z","signature_b64":"mXlv1+8got77V/V5IQsGePZT3GEZ04z73IYqi2kpzmVE6p1Qxn4IKhDLRoxi7f73/YvCNbNyQgfd6QA+SIxEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ed954fd3291170bc8e7b371c447723ceee471a418de888f59c9ffb3a1692ea1","last_reissued_at":"2026-07-05T07:59:17.585134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:17.585134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.12038","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":"2026-07-05T07:59:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H9uaBFhTN30GhY3Uo18XQLcSp2W+TZx6WgHVMPmsP+MOr1MSE6KrDR1+aSs02G42r5Pzna9mVzGuUbKwbJ6RBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:52:26.569234Z"},"content_sha256":"1e52be8fa3d145ae90caacf8e58b2ecd676855ff57996e8ab04e1cd4ce88716f","schema_version":"1.0","event_id":"sha256:1e52be8fa3d145ae90caacf8e58b2ecd676855ff57996e8ab04e1cd4ce88716f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:D3MVJ7JSSELQXSHHWNY4IR3SHT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Chongyi Wang, Dahai Li, Hanghao Wu, Haoye Zhang, Jiao Xue, Jinyi Hu, Maosong Sun, Qianyu Chen, Shan Wang, Tianyu Yu, Xu Han, Yankai Lin, Yinxu Pan, Yuan Yao, Yue Zhao, Zhiyuan Liu","submitted_at":"2023-08-23T09:55:41Z","abstract_excerpt":"Recently there has been a significant surge in multimodal learning in terms of both image-to-text and text-to-image generation. However, the success is typically limited to English, leaving other languages largely behind. Building a competitive counterpart in other languages is highly challenging due to the low-resource nature of non-English multimodal data (i.e., lack of large-scale, high-quality image-text data). In this work, we propose MPM, an effective training paradigm for training large multimodal models in non-English languages. MPM demonstrates that Multilingual language models can Pi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12038","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/2308.12038/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":"2026-07-05T07:59:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cvsyhjXRT6Qn2D/OKxX2FYwAOzopwAYkAurGqEIgWEX/EZuBFzHb095K8gTOuuDNUEN6nEx4oUgx+Oz2WGkDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:52:26.569626Z"},"content_sha256":"dc262511180a0b58d4d491d5499309b904e48385e552ff43bd0da57f5aa4288e","schema_version":"1.0","event_id":"sha256:dc262511180a0b58d4d491d5499309b904e48385e552ff43bd0da57f5aa4288e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D3MVJ7JSSELQXSHHWNY4IR3SHT/bundle.json","state_url":"https://pith.science/pith/D3MVJ7JSSELQXSHHWNY4IR3SHT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D3MVJ7JSSELQXSHHWNY4IR3SHT/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":"2026-07-06T08:52:26Z","links":{"resolver":"https://pith.science/pith/D3MVJ7JSSELQXSHHWNY4IR3SHT","bundle":"https://pith.science/pith/D3MVJ7JSSELQXSHHWNY4IR3SHT/bundle.json","state":"https://pith.science/pith/D3MVJ7JSSELQXSHHWNY4IR3SHT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D3MVJ7JSSELQXSHHWNY4IR3SHT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:D3MVJ7JSSELQXSHHWNY4IR3SHT","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":"f76f5eea3ffaf01e3096548b6595432de610457d608dea443feeee6e6b4f8403","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-23T09:55:41Z","title_canon_sha256":"50a8ce38c277f96b54b52cd9e3c4848864127c3ded34149bd6cbc7468cfbe057"},"schema_version":"1.0","source":{"id":"2308.12038","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.12038","created_at":"2026-07-05T07:59:17Z"},{"alias_kind":"arxiv_version","alias_value":"2308.12038v3","created_at":"2026-07-05T07:59:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12038","created_at":"2026-07-05T07:59:17Z"},{"alias_kind":"pith_short_12","alias_value":"D3MVJ7JSSELQ","created_at":"2026-07-05T07:59:17Z"},{"alias_kind":"pith_short_16","alias_value":"D3MVJ7JSSELQXSHH","created_at":"2026-07-05T07:59:17Z"},{"alias_kind":"pith_short_8","alias_value":"D3MVJ7JS","created_at":"2026-07-05T07:59:17Z"}],"graph_snapshots":[{"event_id":"sha256:dc262511180a0b58d4d491d5499309b904e48385e552ff43bd0da57f5aa4288e","target":"graph","created_at":"2026-07-05T07:59:17Z","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/2308.12038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently there has been a significant surge in multimodal learning in terms of both image-to-text and text-to-image generation. However, the success is typically limited to English, leaving other languages largely behind. Building a competitive counterpart in other languages is highly challenging due to the low-resource nature of non-English multimodal data (i.e., lack of large-scale, high-quality image-text data). In this work, we propose MPM, an effective training paradigm for training large multimodal models in non-English languages. MPM demonstrates that Multilingual language models can Pi","authors_text":"Chongyi Wang, Dahai Li, Hanghao Wu, Haoye Zhang, Jiao Xue, Jinyi Hu, Maosong Sun, Qianyu Chen, Shan Wang, Tianyu Yu, Xu Han, Yankai Lin, Yinxu Pan, Yuan Yao, Yue Zhao, Zhiyuan Liu","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-23T09:55:41Z","title":"Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12038","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":"sha256:1e52be8fa3d145ae90caacf8e58b2ecd676855ff57996e8ab04e1cd4ce88716f","target":"record","created_at":"2026-07-05T07:59:17Z","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":"f76f5eea3ffaf01e3096548b6595432de610457d608dea443feeee6e6b4f8403","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-23T09:55:41Z","title_canon_sha256":"50a8ce38c277f96b54b52cd9e3c4848864127c3ded34149bd6cbc7468cfbe057"},"schema_version":"1.0","source":{"id":"2308.12038","kind":"arxiv","version":3}},"canonical_sha256":"1ed954fd3291170bc8e7b371c447723ceee471a418de888f59c9ffb3a1692ea1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ed954fd3291170bc8e7b371c447723ceee471a418de888f59c9ffb3a1692ea1","first_computed_at":"2026-07-05T07:59:17.585134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:17.585134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mXlv1+8got77V/V5IQsGePZT3GEZ04z73IYqi2kpzmVE6p1Qxn4IKhDLRoxi7f73/YvCNbNyQgfd6QA+SIxEDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:17.585602Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.12038","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1e52be8fa3d145ae90caacf8e58b2ecd676855ff57996e8ab04e1cd4ce88716f","sha256:dc262511180a0b58d4d491d5499309b904e48385e552ff43bd0da57f5aa4288e"],"state_sha256":"c3fb958e17aa90ba41665a080209ae8c14fb63fc1c797f43803c2a2841e2f616"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vs0kyV+GIU+0DkTiQ9mjtWkHmeGS+dnuCVVAi4IweuogtxWlCTT7csrsswMKv6ALX16AzZ/62KH1CPlXMT7LAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:52:26.571611Z","bundle_sha256":"0021e76e78ac0521d8670a61ad3a8090614173f0c89cbbd941f7e9a797b35016"}}