{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MDBU6SPTM6T6PHPQVS4VVEFLFR","short_pith_number":"pith:MDBU6SPT","schema_version":"1.0","canonical_sha256":"60c34f49f367a7e79df0acb95a90ab2c4bea8b44f792b10b04dc6d2787db4cfc","source":{"kind":"arxiv","id":"2402.14818","version":2},"attestation_state":"computed","paper":{"title":"PALO: A Polyglot Large Multimodal Model for 5B People","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Shaker, Fahad S. Khan, Hanoona Rasheed, Hisham Cholakal, Michael Felsberg, Muhammad Maaz, Rao M. Anwer, Salman Khan, Tim Baldwin","submitted_at":"2024-02-22T18:59:58Z","abstract_excerpt":"In pursuit of more inclusive Vision-Language Models (VLMs), this study introduces a Large Multilingual Multimodal Model called PALO. PALO offers visual reasoning capabilities in 10 major languages, including English, Chinese, Hindi, Spanish, French, Arabic, Bengali, Russian, Urdu, and Japanese, that span a total of ~5B people (65% of the world population). Our approach involves a semi-automated translation approach to adapt the multimodal instruction dataset from English to the target languages using a fine-tuned Large Language Model, thereby ensuring high linguistic fidelity while allowing sc"},"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":"2402.14818","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:59:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"328981d25d42eee15998802793698d9d4589de415c907e36287ebf60f063dcf2","abstract_canon_sha256":"cea702701d9c5618d023901db45d201d278363ac06db8ce7fb7d6d303f2d5f73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:16.177340Z","signature_b64":"icBuU0hujN7e4MTtxZufuQc1AeQ2V9xf7h5JoFPUpMpWWsF0WUYb4X0NkEqDst4M+YxiywhzfeEtYBenYjNvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60c34f49f367a7e79df0acb95a90ab2c4bea8b44f792b10b04dc6d2787db4cfc","last_reissued_at":"2026-07-05T07:52:16.176884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:16.176884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PALO: A Polyglot Large Multimodal Model for 5B People","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Abdelrahman Shaker, Fahad S. Khan, Hanoona Rasheed, Hisham Cholakal, Michael Felsberg, Muhammad Maaz, Rao M. Anwer, Salman Khan, Tim Baldwin","submitted_at":"2024-02-22T18:59:58Z","abstract_excerpt":"In pursuit of more inclusive Vision-Language Models (VLMs), this study introduces a Large Multilingual Multimodal Model called PALO. PALO offers visual reasoning capabilities in 10 major languages, including English, Chinese, Hindi, Spanish, French, Arabic, Bengali, Russian, Urdu, and Japanese, that span a total of ~5B people (65% of the world population). Our approach involves a semi-automated translation approach to adapt the multimodal instruction dataset from English to the target languages using a fine-tuned Large Language Model, thereby ensuring high linguistic fidelity while allowing sc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14818","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/2402.14818/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":"2402.14818","created_at":"2026-07-05T07:52:16.176948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14818v2","created_at":"2026-07-05T07:52:16.176948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14818","created_at":"2026-07-05T07:52:16.176948+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDBU6SPTM6T6","created_at":"2026-07-05T07:52:16.176948+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDBU6SPTM6T6PHPQ","created_at":"2026-07-05T07:52:16.176948+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDBU6SPT","created_at":"2026-07-05T07:52:16.176948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03793","citing_title":"Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDBU6SPTM6T6PHPQVS4VVEFLFR","json":"https://pith.science/pith/MDBU6SPTM6T6PHPQVS4VVEFLFR.json","graph_json":"https://pith.science/api/pith-number/MDBU6SPTM6T6PHPQVS4VVEFLFR/graph.json","events_json":"https://pith.science/api/pith-number/MDBU6SPTM6T6PHPQVS4VVEFLFR/events.json","paper":"https://pith.science/paper/MDBU6SPT"},"agent_actions":{"view_html":"https://pith.science/pith/MDBU6SPTM6T6PHPQVS4VVEFLFR","download_json":"https://pith.science/pith/MDBU6SPTM6T6PHPQVS4VVEFLFR.json","view_paper":"https://pith.science/paper/MDBU6SPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14818&json=true","fetch_graph":"https://pith.science/api/pith-number/MDBU6SPTM6T6PHPQVS4VVEFLFR/graph.json","fetch_events":"https://pith.science/api/pith-number/MDBU6SPTM6T6PHPQVS4VVEFLFR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDBU6SPTM6T6PHPQVS4VVEFLFR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDBU6SPTM6T6PHPQVS4VVEFLFR/action/storage_attestation","attest_author":"https://pith.science/pith/MDBU6SPTM6T6PHPQVS4VVEFLFR/action/author_attestation","sign_citation":"https://pith.science/pith/MDBU6SPTM6T6PHPQVS4VVEFLFR/action/citation_signature","submit_replication":"https://pith.science/pith/MDBU6SPTM6T6PHPQVS4VVEFLFR/action/replication_record"}},"created_at":"2026-07-05T07:52:16.176948+00:00","updated_at":"2026-07-05T07:52:16.176948+00:00"}