{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7UOZVBRCXCML7FJHRREXVAD36I","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":"3d652233cd58de73721774bbfde6cae817248d7026db00fac0013b3476802f17","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T05:43:33Z","title_canon_sha256":"7732b600b39334ca36273ef5ea69bcd29805bb1529779fab1c8735d28adc2445"},"schema_version":"1.0","source":{"id":"2401.15896","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.15896","created_at":"2026-07-05T07:41:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.15896v2","created_at":"2026-07-05T07:41:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.15896","created_at":"2026-07-05T07:41:02Z"},{"alias_kind":"pith_short_12","alias_value":"7UOZVBRCXCML","created_at":"2026-07-05T07:41:02Z"},{"alias_kind":"pith_short_16","alias_value":"7UOZVBRCXCML7FJH","created_at":"2026-07-05T07:41:02Z"},{"alias_kind":"pith_short_8","alias_value":"7UOZVBRC","created_at":"2026-07-05T07:41:02Z"}],"graph_snapshots":[{"event_id":"sha256:953ca406aa94fbc05d95be0638645be67b8262ef9104c31798a3a1a2d02db4b5","target":"graph","created_at":"2026-07-05T07:41:02Z","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/2401.15896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Furong Xu, Hanxiao Zhang, Jian Wang, Jingdong Chen, Lin Ju, Ming Yang, Qingpei Guo, Wang Ren, Ziping Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T05:43:33Z","title":"M2-Encoder: Advancing Bilingual Image-Text Understanding by Large-scale Efficient Pretraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.15896","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:b53cb6181d431727c7348f59ed35b217a759566e1fb7ff8b37bc14ef38b5a583","target":"record","created_at":"2026-07-05T07:41:02Z","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":"3d652233cd58de73721774bbfde6cae817248d7026db00fac0013b3476802f17","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-29T05:43:33Z","title_canon_sha256":"7732b600b39334ca36273ef5ea69bcd29805bb1529779fab1c8735d28adc2445"},"schema_version":"1.0","source":{"id":"2401.15896","kind":"arxiv","version":2}},"canonical_sha256":"fd1d9a8622b898bf95278c497a807bf23f054529c78ce286aa15b58ec8d72e63","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd1d9a8622b898bf95278c497a807bf23f054529c78ce286aa15b58ec8d72e63","first_computed_at":"2026-07-05T07:41:02.947873Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:02.947873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ft47bntPh13YwR+5SjaG97iJJf4bXwEWrgf5iCp7D7Y9jMPfTiLgpz80eQDeNkV4i6izJs7Wemt6AQfLiZWdAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:02.948306Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.15896","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b53cb6181d431727c7348f59ed35b217a759566e1fb7ff8b37bc14ef38b5a583","sha256:953ca406aa94fbc05d95be0638645be67b8262ef9104c31798a3a1a2d02db4b5"],"state_sha256":"5b270bd3404aa722862a971ef0ad8bc9f9d4cbb8191144a3bfb7dc619c71b6a9"}