{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NYLLVVGKSC6PI7OE5HKG554QFN","short_pith_number":"pith:NYLLVVGK","schema_version":"1.0","canonical_sha256":"6e16bad4ca90bcf47dc4e9d46ef7902b7684439f23bb88e77affb428f043cf16","source":{"kind":"arxiv","id":"2507.06137","version":1},"attestation_state":"computed","paper":{"title":"NeoBabel: A Multilingual Open Tower for Visual Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Cees G. M. Snoek, Dheeraj Varghese, Marzieh Fadaee, Mohammad Mahdi Derakhshani","submitted_at":"2025-07-08T16:19:45Z","abstract_excerpt":"Text-to-image generation advancements have been predominantly English-centric, creating barriers for non-English speakers and perpetuating digital inequities. While existing systems rely on translation pipelines, these introduce semantic drift, computational overhead, and cultural misalignment. We introduce NeoBabel, a novel multilingual image generation framework that sets a new Pareto frontier in performance, efficiency and inclusivity, supporting six languages: English, Chinese, Dutch, French, Hindi, and Persian. The model is trained using a combination of large-scale multilingual pretraini"},"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":"2507.06137","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-08T16:19:45Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"acf9ca696cb7fc3e1f8edd1f742213b04d4b2c31edd9794a6f23675b46767a90","abstract_canon_sha256":"c973a56e2417a8f7a97598ab6f699bcf87cbb77f25de804916ff843c13dfea24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:41.821857Z","signature_b64":"WGlE6FzMJqQFsul1YZcSLPt77FB+3gNiPYRZAxn+MKzRMSQrbiK2jD8zqZ10NQIOZPSQJYlBZoCvBfP5RMxZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e16bad4ca90bcf47dc4e9d46ef7902b7684439f23bb88e77affb428f043cf16","last_reissued_at":"2026-07-05T11:33:41.821214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:41.821214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"NeoBabel: A Multilingual Open Tower for Visual Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Cees G. M. Snoek, Dheeraj Varghese, Marzieh Fadaee, Mohammad Mahdi Derakhshani","submitted_at":"2025-07-08T16:19:45Z","abstract_excerpt":"Text-to-image generation advancements have been predominantly English-centric, creating barriers for non-English speakers and perpetuating digital inequities. While existing systems rely on translation pipelines, these introduce semantic drift, computational overhead, and cultural misalignment. We introduce NeoBabel, a novel multilingual image generation framework that sets a new Pareto frontier in performance, efficiency and inclusivity, supporting six languages: English, Chinese, Dutch, French, Hindi, and Persian. The model is trained using a combination of large-scale multilingual pretraini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06137","kind":"arxiv","version":1},"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/2507.06137/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":"2507.06137","created_at":"2026-07-05T11:33:41.821271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.06137v1","created_at":"2026-07-05T11:33:41.821271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06137","created_at":"2026-07-05T11:33:41.821271+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYLLVVGKSC6P","created_at":"2026-07-05T11:33:41.821271+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYLLVVGKSC6PI7OE","created_at":"2026-07-05T11:33:41.821271+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYLLVVGK","created_at":"2026-07-05T11:33:41.821271+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NYLLVVGKSC6PI7OE5HKG554QFN","json":"https://pith.science/pith/NYLLVVGKSC6PI7OE5HKG554QFN.json","graph_json":"https://pith.science/api/pith-number/NYLLVVGKSC6PI7OE5HKG554QFN/graph.json","events_json":"https://pith.science/api/pith-number/NYLLVVGKSC6PI7OE5HKG554QFN/events.json","paper":"https://pith.science/paper/NYLLVVGK"},"agent_actions":{"view_html":"https://pith.science/pith/NYLLVVGKSC6PI7OE5HKG554QFN","download_json":"https://pith.science/pith/NYLLVVGKSC6PI7OE5HKG554QFN.json","view_paper":"https://pith.science/paper/NYLLVVGK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.06137&json=true","fetch_graph":"https://pith.science/api/pith-number/NYLLVVGKSC6PI7OE5HKG554QFN/graph.json","fetch_events":"https://pith.science/api/pith-number/NYLLVVGKSC6PI7OE5HKG554QFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYLLVVGKSC6PI7OE5HKG554QFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYLLVVGKSC6PI7OE5HKG554QFN/action/storage_attestation","attest_author":"https://pith.science/pith/NYLLVVGKSC6PI7OE5HKG554QFN/action/author_attestation","sign_citation":"https://pith.science/pith/NYLLVVGKSC6PI7OE5HKG554QFN/action/citation_signature","submit_replication":"https://pith.science/pith/NYLLVVGKSC6PI7OE5HKG554QFN/action/replication_record"}},"created_at":"2026-07-05T11:33:41.821271+00:00","updated_at":"2026-07-05T11:33:41.821271+00:00"}