{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F5ZCGSY4EV7MYOYKMTYQW52LFK","short_pith_number":"pith:F5ZCGSY4","canonical_record":{"source":{"id":"2410.16153","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T16:19:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"27020d102e99ad57608d8c9f0dd969f38ccb96bba8be8948c3a40adc3a5c69b4","abstract_canon_sha256":"cd19f99f1c16bead99a6f918f7c9f2e58bf8ef202ce20090847b1168a26d373c"},"schema_version":"1.0"},"canonical_sha256":"2f72234b1c257ecc3b0a64f10b774b2a8236592aeb1eaa292705aa37025f0d5b","source":{"kind":"arxiv","id":"2410.16153","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16153","created_at":"2026-07-05T10:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16153v3","created_at":"2026-07-05T10:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16153","created_at":"2026-07-05T10:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"F5ZCGSY4EV7M","created_at":"2026-07-05T10:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"F5ZCGSY4EV7MYOYK","created_at":"2026-07-05T10:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"F5ZCGSY4","created_at":"2026-07-05T10:05:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F5ZCGSY4EV7MYOYKMTYQW52LFK","target":"record","payload":{"canonical_record":{"source":{"id":"2410.16153","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T16:19:41Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"27020d102e99ad57608d8c9f0dd969f38ccb96bba8be8948c3a40adc3a5c69b4","abstract_canon_sha256":"cd19f99f1c16bead99a6f918f7c9f2e58bf8ef202ce20090847b1168a26d373c"},"schema_version":"1.0"},"canonical_sha256":"2f72234b1c257ecc3b0a64f10b774b2a8236592aeb1eaa292705aa37025f0d5b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:13.781554Z","signature_b64":"37cxnbkbLSpEIZwzOmiyiuct5X16U/6In7z/UGFySq9uQrAqR8J0c5vCYq8uCyUHpB949UvFqLvy1OWiIKI7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f72234b1c257ecc3b0a64f10b774b2a8236592aeb1eaa292705aa37025f0d5b","last_reissued_at":"2026-07-05T10:05:13.781040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:13.781040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.16153","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2NvQbFwKGd8eSbCTZ5VJDNh992/QVAdt70yrxFhRYIcd2UYlYBiCY8G3oFDFhRu7XvqK6xSLfxv5ABZcSkodDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:00:43.221907Z"},"content_sha256":"e2e3fd5b650fd4d9a46fd6826c6eb24113da9598a011833c9ca89427d7a62953","schema_version":"1.0","event_id":"sha256:e2e3fd5b650fd4d9a46fd6826c6eb24113da9598a011833c9ca89427d7a62953"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F5ZCGSY4EV7MYOYKMTYQW52LFK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Akari Asai, Anjali Kantharuban, Graham Neubig, Jean de Dieu Nyandwi, Lintang Sutawika, Sathyanarayanan Ramamoorthy, Seungone Kim, Simran Khanuja, Xiang Yue, Yueqi Song","submitted_at":"2024-10-21T16:19:41Z","abstract_excerpt":"Despite recent advances in multimodal large language models (MLLMs), their development has predominantly focused on English- and western-centric datasets and tasks, leaving most of the world's languages and diverse cultural contexts underrepresented. This paper introduces Pangea, a multilingual multimodal LLM trained on PangeaIns, a diverse 6M instruction dataset spanning 39 languages. PangeaIns features: 1) high-quality English instructions, 2) carefully machine-translated instructions, and 3) culturally relevant multimodal tasks to ensure cross-cultural coverage. To rigorously assess models'"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16153","kind":"arxiv","version":3},"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/2410.16153/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8g27bSsQyZyXrSsP0MEdwdy7NAvZJIHmQoRVAUmyBjabKXWu9N1sR0Hu5FtWQ7VZ5wDu19NMVXdNSfqdcETgCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:00:43.222677Z"},"content_sha256":"52e68f03b6c2773dd0e867629002acb416fcf1b7dd4aa482ed1589d9809a4b81","schema_version":"1.0","event_id":"sha256:52e68f03b6c2773dd0e867629002acb416fcf1b7dd4aa482ed1589d9809a4b81"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5ZCGSY4EV7MYOYKMTYQW52LFK/bundle.json","state_url":"https://pith.science/pith/F5ZCGSY4EV7MYOYKMTYQW52LFK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5ZCGSY4EV7MYOYKMTYQW52LFK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T06:00:43Z","links":{"resolver":"https://pith.science/pith/F5ZCGSY4EV7MYOYKMTYQW52LFK","bundle":"https://pith.science/pith/F5ZCGSY4EV7MYOYKMTYQW52LFK/bundle.json","state":"https://pith.science/pith/F5ZCGSY4EV7MYOYKMTYQW52LFK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5ZCGSY4EV7MYOYKMTYQW52LFK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F5ZCGSY4EV7MYOYKMTYQW52LFK","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":"cd19f99f1c16bead99a6f918f7c9f2e58bf8ef202ce20090847b1168a26d373c","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T16:19:41Z","title_canon_sha256":"27020d102e99ad57608d8c9f0dd969f38ccb96bba8be8948c3a40adc3a5c69b4"},"schema_version":"1.0","source":{"id":"2410.16153","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.16153","created_at":"2026-07-05T10:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2410.16153v3","created_at":"2026-07-05T10:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16153","created_at":"2026-07-05T10:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"F5ZCGSY4EV7M","created_at":"2026-07-05T10:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"F5ZCGSY4EV7MYOYK","created_at":"2026-07-05T10:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"F5ZCGSY4","created_at":"2026-07-05T10:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:52e68f03b6c2773dd0e867629002acb416fcf1b7dd4aa482ed1589d9809a4b81","target":"graph","created_at":"2026-07-05T10:05:13Z","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/2410.16153/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advances in multimodal large language models (MLLMs), their development has predominantly focused on English- and western-centric datasets and tasks, leaving most of the world's languages and diverse cultural contexts underrepresented. This paper introduces Pangea, a multilingual multimodal LLM trained on PangeaIns, a diverse 6M instruction dataset spanning 39 languages. PangeaIns features: 1) high-quality English instructions, 2) carefully machine-translated instructions, and 3) culturally relevant multimodal tasks to ensure cross-cultural coverage. To rigorously assess models'","authors_text":"Akari Asai, Anjali Kantharuban, Graham Neubig, Jean de Dieu Nyandwi, Lintang Sutawika, Sathyanarayanan Ramamoorthy, Seungone Kim, Simran Khanuja, Xiang Yue, Yueqi Song","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T16:19:41Z","title":"Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16153","kind":"arxiv","version":3},"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:e2e3fd5b650fd4d9a46fd6826c6eb24113da9598a011833c9ca89427d7a62953","target":"record","created_at":"2026-07-05T10:05:13Z","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":"cd19f99f1c16bead99a6f918f7c9f2e58bf8ef202ce20090847b1168a26d373c","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-21T16:19:41Z","title_canon_sha256":"27020d102e99ad57608d8c9f0dd969f38ccb96bba8be8948c3a40adc3a5c69b4"},"schema_version":"1.0","source":{"id":"2410.16153","kind":"arxiv","version":3}},"canonical_sha256":"2f72234b1c257ecc3b0a64f10b774b2a8236592aeb1eaa292705aa37025f0d5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f72234b1c257ecc3b0a64f10b774b2a8236592aeb1eaa292705aa37025f0d5b","first_computed_at":"2026-07-05T10:05:13.781040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:13.781040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"37cxnbkbLSpEIZwzOmiyiuct5X16U/6In7z/UGFySq9uQrAqR8J0c5vCYq8uCyUHpB949UvFqLvy1OWiIKI7Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:13.781554Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.16153","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2e3fd5b650fd4d9a46fd6826c6eb24113da9598a011833c9ca89427d7a62953","sha256:52e68f03b6c2773dd0e867629002acb416fcf1b7dd4aa482ed1589d9809a4b81"],"state_sha256":"32f49d13ba67f451c48e7d897bc279cb17cae62879d90fdfbbed172120467f97"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VA/1mcX2oNS9/XIbjq+K3eRYqbbIhWGMfSfw478sfKO+HjVN3Rka5QxI8W54iTTHRMsizaQ1tvDpf+x9Z/NvDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:00:43.226105Z","bundle_sha256":"f82f87a43049c510a6c45773bef0250cdc2cc2fdb3b140a517120c8d5b506563"}}