{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MDBU6SPTM6T6PHPQVS4VVEFLFR","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":"cea702701d9c5618d023901db45d201d278363ac06db8ce7fb7d6d303f2d5f73","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:59:58Z","title_canon_sha256":"328981d25d42eee15998802793698d9d4589de415c907e36287ebf60f063dcf2"},"schema_version":"1.0","source":{"id":"2402.14818","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14818","created_at":"2026-07-05T07:52:16Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14818v2","created_at":"2026-07-05T07:52:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14818","created_at":"2026-07-05T07:52:16Z"},{"alias_kind":"pith_short_12","alias_value":"MDBU6SPTM6T6","created_at":"2026-07-05T07:52:16Z"},{"alias_kind":"pith_short_16","alias_value":"MDBU6SPTM6T6PHPQ","created_at":"2026-07-05T07:52:16Z"},{"alias_kind":"pith_short_8","alias_value":"MDBU6SPT","created_at":"2026-07-05T07:52:16Z"}],"graph_snapshots":[{"event_id":"sha256:447aaebee495582822169c5b8e772f5d0ce9ed84a9825fcef91530b4923a32fa","target":"graph","created_at":"2026-07-05T07:52:16Z","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/2402.14818/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abdelrahman Shaker, Fahad S. Khan, Hanoona Rasheed, Hisham Cholakal, Michael Felsberg, Muhammad Maaz, Rao M. Anwer, Salman Khan, Tim Baldwin","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:59:58Z","title":"PALO: A Polyglot Large Multimodal Model for 5B People"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14818","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":"sha256:53c39b3e1187500f493d1a4f23727e709c2454328906597c70217ddca6478768","target":"record","created_at":"2026-07-05T07:52:16Z","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":"cea702701d9c5618d023901db45d201d278363ac06db8ce7fb7d6d303f2d5f73","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-22T18:59:58Z","title_canon_sha256":"328981d25d42eee15998802793698d9d4589de415c907e36287ebf60f063dcf2"},"schema_version":"1.0","source":{"id":"2402.14818","kind":"arxiv","version":2}},"canonical_sha256":"60c34f49f367a7e79df0acb95a90ab2c4bea8b44f792b10b04dc6d2787db4cfc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60c34f49f367a7e79df0acb95a90ab2c4bea8b44f792b10b04dc6d2787db4cfc","first_computed_at":"2026-07-05T07:52:16.176884Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:52:16.176884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"icBuU0hujN7e4MTtxZufuQc1AeQ2V9xf7h5JoFPUpMpWWsF0WUYb4X0NkEqDst4M+YxiywhzfeEtYBenYjNvCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:52:16.177340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14818","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53c39b3e1187500f493d1a4f23727e709c2454328906597c70217ddca6478768","sha256:447aaebee495582822169c5b8e772f5d0ce9ed84a9825fcef91530b4923a32fa"],"state_sha256":"bc93739fa5abbf4887a236543e79390c174a6ac9df3f33b4141d7315672c57f9"}