{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KQVP2LR6CFFUIQGVVMCBEAPMBK","short_pith_number":"pith:KQVP2LR6","canonical_record":{"source":{"id":"2406.10118","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T15:23:39Z","cross_cats_sorted":[],"title_canon_sha256":"87043a9d94fe7a4a14049b6d8ea66f8d55807eefe8828515e2841eb54410c977","abstract_canon_sha256":"01d5582df54fa7a9f7a19dfdd86cd5a1a42448d6bb6a6297765caff8028b78e4"},"schema_version":"1.0"},"canonical_sha256":"542afd2e3e114b4440d5ab041201ec0a9045ca1bc43a48c2427314cd14e95f19","source":{"kind":"arxiv","id":"2406.10118","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10118","created_at":"2026-07-05T10:28:18Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10118v5","created_at":"2026-07-05T10:28:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10118","created_at":"2026-07-05T10:28:18Z"},{"alias_kind":"pith_short_12","alias_value":"KQVP2LR6CFFU","created_at":"2026-07-05T10:28:18Z"},{"alias_kind":"pith_short_16","alias_value":"KQVP2LR6CFFUIQGV","created_at":"2026-07-05T10:28:18Z"},{"alias_kind":"pith_short_8","alias_value":"KQVP2LR6","created_at":"2026-07-05T10:28:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KQVP2LR6CFFUIQGVVMCBEAPMBK","target":"record","payload":{"canonical_record":{"source":{"id":"2406.10118","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T15:23:39Z","cross_cats_sorted":[],"title_canon_sha256":"87043a9d94fe7a4a14049b6d8ea66f8d55807eefe8828515e2841eb54410c977","abstract_canon_sha256":"01d5582df54fa7a9f7a19dfdd86cd5a1a42448d6bb6a6297765caff8028b78e4"},"schema_version":"1.0"},"canonical_sha256":"542afd2e3e114b4440d5ab041201ec0a9045ca1bc43a48c2427314cd14e95f19","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:18.049592Z","signature_b64":"qSQ6qg2BZicmM5nhSzxxvoIhFZLbOkJ4n1ahCKaZF/R55mnkwYuCkJ6wg5H8fJU9s5pExbT7X3ZMEUl4LdNTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"542afd2e3e114b4440d5ab041201ec0a9045ca1bc43a48c2427314cd14e95f19","last_reissued_at":"2026-07-05T10:28:18.048929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:18.048929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.10118","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:28:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t8usWl9gkYoi2d6CXY5snye+vFuajEhgFg1Fyv5vnRV705jeAti101MWGLQ8xfF317NpDdGLAm16wAj3f5J6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T18:37:59.253616Z"},"content_sha256":"4d63ed653e703bdd6b0f86c34e1e524ec8e2c5fa6373882f351cc8cbe96a716c","schema_version":"1.0","event_id":"sha256:4d63ed653e703bdd6b0f86c34e1e524ec8e2c5fa6373882f351cc8cbe96a716c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KQVP2LR6CFFUIQGVVMCBEAPMBK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akhdan Fadhilah, Alham Fikri Aji, Amirbek Djanibekov, Ayu Purwarianti, Bin Wang, B\\\"orje F. Karlsson, Chenxi Whitehouse, Dan John Velasco, Elyanah Aco, Fajri Koto, Frederikus Hudi, Genta Indra Winata, Haochen Li, Holy Lovenia, Ilham Firdausi Putra, Ivan Halim Parmonangan, James Jaya, Jan Christian Blaise Cruz, Jennifer Santoso, Joanito Agili Lopo, Joel Ruben Antony Moniz, Johanes Lee, Jonibek Mansurov, Joseph Marvin Imperial, Lester James V. Miranda, Lucky Susanto, Maria Khelli, Muhammad Dehan Al Kautsar, Muhammad Farid Adilazuarda, Muhammad Ravi Shulthan Habibi, Muhammad Reza Qorib, Ngee Chia Tai, Niklas Muennighoff, Noah Flynn, Onno P. Kampman, Patrick Amadeus, Peerat Limkonchotiwat, Quyet V. Do, Rahmad Mahendra, Railey Montalan, R. Damanhuri, Reynard Adha Ryanda, Ruochen Zhang, Ryandito Diandaru, Ryan Ignatius, Salsabil Maulana Akbar, Samuel Cahyawijaya, Sebastian Ruder, Sedrick Keh, Shuo Sun, Sonny Lazuardi Hermawan, Tanrada Pansuwan, Wei Qi Leong, Wenyu Zhang, William Nixon, William Tjhi, Willy Fitra Hendria, Yan Xu, Yasmin Moslem, Yuze Gao, Zheng-Xin Yong","submitted_at":"2024-06-14T15:23:39Z","abstract_excerpt":"Southeast Asia (SEA) is a region rich in linguistic diversity and cultural variety, with over 1,300 indigenous languages and a population of 671 million people. However, prevailing AI models suffer from a significant lack of representation of texts, images, and audio datasets from SEA, compromising the quality of AI models for SEA languages. Evaluating models for SEA languages is challenging due to the scarcity of high-quality datasets, compounded by the dominance of English training data, raising concerns about potential cultural misrepresentation. To address these challenges, we introduce SE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10118","kind":"arxiv","version":5},"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/2406.10118/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":"2026-07-05T10:28:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nUbH8i7pS2+R5RsJgEuvuV0h0k51JTv3eOZMpPPIq0pi31OjYe1j90U+wei3CQmStpXPpe9G7+dO6jU0lOmbBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T18:37:59.254007Z"},"content_sha256":"01245b668a304b6651db986d5ccf8030027a6524b454e6d4b06967bbb6c25059","schema_version":"1.0","event_id":"sha256:01245b668a304b6651db986d5ccf8030027a6524b454e6d4b06967bbb6c25059"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KQVP2LR6CFFUIQGVVMCBEAPMBK/bundle.json","state_url":"https://pith.science/pith/KQVP2LR6CFFUIQGVVMCBEAPMBK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KQVP2LR6CFFUIQGVVMCBEAPMBK/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":"2026-07-08T18:37:59Z","links":{"resolver":"https://pith.science/pith/KQVP2LR6CFFUIQGVVMCBEAPMBK","bundle":"https://pith.science/pith/KQVP2LR6CFFUIQGVVMCBEAPMBK/bundle.json","state":"https://pith.science/pith/KQVP2LR6CFFUIQGVVMCBEAPMBK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KQVP2LR6CFFUIQGVVMCBEAPMBK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KQVP2LR6CFFUIQGVVMCBEAPMBK","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":"01d5582df54fa7a9f7a19dfdd86cd5a1a42448d6bb6a6297765caff8028b78e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T15:23:39Z","title_canon_sha256":"87043a9d94fe7a4a14049b6d8ea66f8d55807eefe8828515e2841eb54410c977"},"schema_version":"1.0","source":{"id":"2406.10118","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10118","created_at":"2026-07-05T10:28:18Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10118v5","created_at":"2026-07-05T10:28:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10118","created_at":"2026-07-05T10:28:18Z"},{"alias_kind":"pith_short_12","alias_value":"KQVP2LR6CFFU","created_at":"2026-07-05T10:28:18Z"},{"alias_kind":"pith_short_16","alias_value":"KQVP2LR6CFFUIQGV","created_at":"2026-07-05T10:28:18Z"},{"alias_kind":"pith_short_8","alias_value":"KQVP2LR6","created_at":"2026-07-05T10:28:18Z"}],"graph_snapshots":[{"event_id":"sha256:01245b668a304b6651db986d5ccf8030027a6524b454e6d4b06967bbb6c25059","target":"graph","created_at":"2026-07-05T10:28:18Z","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/2406.10118/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Southeast Asia (SEA) is a region rich in linguistic diversity and cultural variety, with over 1,300 indigenous languages and a population of 671 million people. However, prevailing AI models suffer from a significant lack of representation of texts, images, and audio datasets from SEA, compromising the quality of AI models for SEA languages. Evaluating models for SEA languages is challenging due to the scarcity of high-quality datasets, compounded by the dominance of English training data, raising concerns about potential cultural misrepresentation. To address these challenges, we introduce SE","authors_text":"Akhdan Fadhilah, Alham Fikri Aji, Amirbek Djanibekov, Ayu Purwarianti, Bin Wang, B\\\"orje F. Karlsson, Chenxi Whitehouse, Dan John Velasco, Elyanah Aco, Fajri Koto, Frederikus Hudi, Genta Indra Winata, Haochen Li, Holy Lovenia, Ilham Firdausi Putra, Ivan Halim Parmonangan, James Jaya, Jan Christian Blaise Cruz, Jennifer Santoso, Joanito Agili Lopo, Joel Ruben Antony Moniz, Johanes Lee, Jonibek Mansurov, Joseph Marvin Imperial, Lester James V. Miranda, Lucky Susanto, Maria Khelli, Muhammad Dehan Al Kautsar, Muhammad Farid Adilazuarda, Muhammad Ravi Shulthan Habibi, Muhammad Reza Qorib, Ngee Chia Tai, Niklas Muennighoff, Noah Flynn, Onno P. Kampman, Patrick Amadeus, Peerat Limkonchotiwat, Quyet V. Do, Rahmad Mahendra, Railey Montalan, R. Damanhuri, Reynard Adha Ryanda, Ruochen Zhang, Ryandito Diandaru, Ryan Ignatius, Salsabil Maulana Akbar, Samuel Cahyawijaya, Sebastian Ruder, Sedrick Keh, Shuo Sun, Sonny Lazuardi Hermawan, Tanrada Pansuwan, Wei Qi Leong, Wenyu Zhang, William Nixon, William Tjhi, Willy Fitra Hendria, Yan Xu, Yasmin Moslem, Yuze Gao, Zheng-Xin Yong","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T15:23:39Z","title":"SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10118","kind":"arxiv","version":5},"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":"sha256:4d63ed653e703bdd6b0f86c34e1e524ec8e2c5fa6373882f351cc8cbe96a716c","target":"record","created_at":"2026-07-05T10:28:18Z","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":"01d5582df54fa7a9f7a19dfdd86cd5a1a42448d6bb6a6297765caff8028b78e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T15:23:39Z","title_canon_sha256":"87043a9d94fe7a4a14049b6d8ea66f8d55807eefe8828515e2841eb54410c977"},"schema_version":"1.0","source":{"id":"2406.10118","kind":"arxiv","version":5}},"canonical_sha256":"542afd2e3e114b4440d5ab041201ec0a9045ca1bc43a48c2427314cd14e95f19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"542afd2e3e114b4440d5ab041201ec0a9045ca1bc43a48c2427314cd14e95f19","first_computed_at":"2026-07-05T10:28:18.048929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:18.048929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qSQ6qg2BZicmM5nhSzxxvoIhFZLbOkJ4n1ahCKaZF/R55mnkwYuCkJ6wg5H8fJU9s5pExbT7X3ZMEUl4LdNTCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:18.049592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10118","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d63ed653e703bdd6b0f86c34e1e524ec8e2c5fa6373882f351cc8cbe96a716c","sha256:01245b668a304b6651db986d5ccf8030027a6524b454e6d4b06967bbb6c25059"],"state_sha256":"e70bd8b9b4763567df278c8f6c588c50aeea12b9de47d38c49aa073b034d9ab7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7zsriSPn/cKuePgbOW2T6VhzDUsik8tPL23716eJcd9DiVHGO673FwQtWE09RQuLD+T2Kr3PrbmQk3RjrIHiCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T18:37:59.256083Z","bundle_sha256":"cd484089507236d9dcba545398c3c3390297b6defde81b6ae1b554b1860ee838"}}