{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7UOZVBRCXCML7FJHRREXVAD36I","short_pith_number":"pith:7UOZVBRC","schema_version":"1.0","canonical_sha256":"fd1d9a8622b898bf95278c497a807bf23f054529c78ce286aa15b58ec8d72e63","source":{"kind":"arxiv","id":"2401.15896","version":2},"attestation_state":"computed","paper":{"title":"M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Furong Xu, Hanxiao Zhang, Jian Wang, Jingdong Chen, Lin Ju, Ming Yang, Qingpei Guo, Wang Ren, Ziping Ma","submitted_at":"2024-01-29T05:43:33Z","abstract_excerpt":"Vision-language foundation models like CLIP have revolutionized the field of artificial intelligence. Nevertheless, VLM models supporting multi-language, e.g., in both Chinese and English, have lagged due to the relative scarcity of large-scale pretraining datasets. Toward this end, we introduce a comprehensive bilingual (Chinese-English) dataset BM-6B with over 6 billion image-text pairs, aimed at enhancing multimodal foundation models to well understand images in both languages. To handle such a scale of dataset, we propose a novel grouped aggregation approach for image-text contrastive loss"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.15896","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T05:43:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7732b600b39334ca36273ef5ea69bcd29805bb1529779fab1c8735d28adc2445","abstract_canon_sha256":"3d652233cd58de73721774bbfde6cae817248d7026db00fac0013b3476802f17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:02.948306Z","signature_b64":"ft47bntPh13YwR+5SjaG97iJJf4bXwEWrgf5iCp7D7Y9jMPfTiLgpz80eQDeNkV4i6izJs7Wemt6AQfLiZWdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd1d9a8622b898bf95278c497a807bf23f054529c78ce286aa15b58ec8d72e63","last_reissued_at":"2026-07-05T07:41:02.947873Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:02.947873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Furong Xu, Hanxiao Zhang, Jian Wang, Jingdong Chen, Lin Ju, Ming Yang, Qingpei Guo, Wang Ren, Ziping Ma","submitted_at":"2024-01-29T05:43:33Z","abstract_excerpt":"Vision-language foundation models like CLIP have revolutionized the field of artificial intelligence. Nevertheless, VLM models supporting multi-language, e.g., in both Chinese and English, have lagged due to the relative scarcity of large-scale pretraining datasets. Toward this end, we introduce a comprehensive bilingual (Chinese-English) dataset BM-6B with over 6 billion image-text pairs, aimed at enhancing multimodal foundation models to well understand images in both languages. To handle such a scale of dataset, we propose a novel grouped aggregation approach for image-text contrastive loss"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15896","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/2401.15896/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.15896","created_at":"2026-07-05T07:41:02.947931+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.15896v2","created_at":"2026-07-05T07:41:02.947931+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15896","created_at":"2026-07-05T07:41:02.947931+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UOZVBRCXCML","created_at":"2026-07-05T07:41:02.947931+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UOZVBRCXCML7FJH","created_at":"2026-07-05T07:41:02.947931+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UOZVBRC","created_at":"2026-07-05T07:41:02.947931+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21786","citing_title":"From Codebooks to VLMs: Evaluating Automated Visual Discourse Analysis for Climate Change on Social Media","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UOZVBRCXCML7FJHRREXVAD36I","json":"https://pith.science/pith/7UOZVBRCXCML7FJHRREXVAD36I.json","graph_json":"https://pith.science/api/pith-number/7UOZVBRCXCML7FJHRREXVAD36I/graph.json","events_json":"https://pith.science/api/pith-number/7UOZVBRCXCML7FJHRREXVAD36I/events.json","paper":"https://pith.science/paper/7UOZVBRC"},"agent_actions":{"view_html":"https://pith.science/pith/7UOZVBRCXCML7FJHRREXVAD36I","download_json":"https://pith.science/pith/7UOZVBRCXCML7FJHRREXVAD36I.json","view_paper":"https://pith.science/paper/7UOZVBRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.15896&json=true","fetch_graph":"https://pith.science/api/pith-number/7UOZVBRCXCML7FJHRREXVAD36I/graph.json","fetch_events":"https://pith.science/api/pith-number/7UOZVBRCXCML7FJHRREXVAD36I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UOZVBRCXCML7FJHRREXVAD36I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UOZVBRCXCML7FJHRREXVAD36I/action/storage_attestation","attest_author":"https://pith.science/pith/7UOZVBRCXCML7FJHRREXVAD36I/action/author_attestation","sign_citation":"https://pith.science/pith/7UOZVBRCXCML7FJHRREXVAD36I/action/citation_signature","submit_replication":"https://pith.science/pith/7UOZVBRCXCML7FJHRREXVAD36I/action/replication_record"}},"created_at":"2026-07-05T07:41:02.947931+00:00","updated_at":"2026-07-05T07:41:02.947931+00:00"}