{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3J7UGQVPCT5KGYMRSSUB3R6WFC","short_pith_number":"pith:3J7UGQVP","canonical_record":{"source":{"id":"2503.07920","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T23:54:52Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"fbb14fc5feb54675447768d563d261c82a13d31030cb90fe9723162369736843","abstract_canon_sha256":"91ee7edb51f30821082a515319cdb10e558b364b8d1046ce1840819e388c1721"},"schema_version":"1.0"},"canonical_sha256":"da7f4342af14faa3619194a81dc7d6289a27fc4bc48fa25f86dc50e29ce074dd","source":{"kind":"arxiv","id":"2503.07920","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07920","created_at":"2026-07-05T10:33:49Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07920v2","created_at":"2026-07-05T10:33:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07920","created_at":"2026-07-05T10:33:49Z"},{"alias_kind":"pith_short_12","alias_value":"3J7UGQVPCT5K","created_at":"2026-07-05T10:33:49Z"},{"alias_kind":"pith_short_16","alias_value":"3J7UGQVPCT5KGYMR","created_at":"2026-07-05T10:33:49Z"},{"alias_kind":"pith_short_8","alias_value":"3J7UGQVP","created_at":"2026-07-05T10:33:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3J7UGQVPCT5KGYMRSSUB3R6WFC","target":"record","payload":{"canonical_record":{"source":{"id":"2503.07920","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T23:54:52Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"fbb14fc5feb54675447768d563d261c82a13d31030cb90fe9723162369736843","abstract_canon_sha256":"91ee7edb51f30821082a515319cdb10e558b364b8d1046ce1840819e388c1721"},"schema_version":"1.0"},"canonical_sha256":"da7f4342af14faa3619194a81dc7d6289a27fc4bc48fa25f86dc50e29ce074dd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:49.882691Z","signature_b64":"TZA+zfzkx8UEX/EBu2IXWadlaWi/9sXGdla2NxzcLi37Q06CusViGwNoOVPQ2lf7Sryf9F3GOQ6NaiQ+IWLEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da7f4342af14faa3619194a81dc7d6289a27fc4bc48fa25f86dc50e29ce074dd","last_reissued_at":"2026-07-05T10:33:49.882206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:49.882206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.07920","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:33:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hLXqjoCY4k6ekfDXi9Gyom5vyDzXkYZuf2ZRtcErxd4PGCshgtXVO0Ft8ulBpO5Jcf6Xki6ddlm1/CFuCrFUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:21:37.522435Z"},"content_sha256":"ee100e3a0f5d6ef30b04829e83915434daecc0d5035241574802201df5af1796","schema_version":"1.0","event_id":"sha256:ee100e3a0f5d6ef30b04829e83915434daecc0d5035241574802201df5af1796"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3J7UGQVPCT5KGYMRSSUB3R6WFC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Adisai Na-Thalang, Adrian Xuan Wei Lim, Alham Fikri Aji, Amit Agarwal, Anab Maulana Barik, Anjela Gail Santos, Audra Aurora Izzani, Aye Hninn Khine, Ayushman Singh, Bahrul Ilmi Nasution, Bin Wang, B\\\"orje F. Karlsson, Can Udomcharoenchaikit, Carlos Rafael Catalan, Chengwei Wei, Christian Simon, Dan John Velasco, David Anugraha, Eryawan Presma Yulianrifat, Evan, Fadil Risdian Ansori, Fajri Koto, Fenal Ashokbhai Ilasariya, Filbert Aurelian Tjiaranata, Frederikus Hudi, Genta Indra Winata, Giang Nguyen, Hanif Muhammad Zhafran, Haochen Li, Hitesh Laxmichand Patel, Holy Lovenia, Ikhlasul Akmal Hanif, Isaiah Flores, Jan Christian Blaise Cruz, Jauza Akbar Krito, Jiayun Luo, Joel Ruben Antony Moniz, John Amadeo Daniswara, Joseph Marvin Imperial, Jostin Jerico Rosal, Jun Kevin, Kadek Hendrawan Palgunadi, Kanyakorn Veerakanjana, Karissa Vincentio, Kaung Si Phyo, Kenneth Ko Han Chen, Kevin Pratama, Kun Kerdthaisong, Lester James V. Miranda, Lynnette Hui Xian Ng, Mahardika Krisna Ihsani, M.Alif Al Hakim, Manuel Antonio Rufino, Matthew Theodore Roque, Meisyarah Dwiastuti, Michael Anugraha, Ming Shan Hee, Mithil Bangera, Mohamed Fazli Imam, Mohammad Rifqi Farhansyah, Muhammad Ravi Shulthan Habibi, Muhammad Reza Qorib, Muhammad Rizky Sya'ban, Onno P. Kampman, Patricia Nicole Monderin, Peerat Limkonchotiwat, Phakphum Artkaew, Piyalitt Ittichaiwong, Priyaranjan Pattnayak, Rian Adam Rajagede, Richardy Lobo' Sapan, Rifo Ahmad Genadi, Robert Wijaya, Rochana Prih Hastuti, Ruochen Zhang, Salsabila Zahirah Pranida, Samuel Cahyawijaya, Saptarshi Saha, Supryadi, Tack Hwa Wong, Takdanai Kreangphet, Taki Hasan Rafi, Teddy Ferdinan, Thant Thiri Maung, Tim Santos, Tirana Noor Fatyanosa, Vicky Feliren, Wan Shen Lim, William Nixon, Yanzhi Yu, Yeshil Bangera, Yueqi Song","submitted_at":"2025-03-10T23:54:52Z","abstract_excerpt":"Southeast Asia (SEA) is a region of extraordinary linguistic and cultural diversity, yet it remains significantly underrepresented in vision-language (VL) research. This often results in artificial intelligence (AI) models that fail to capture SEA cultural nuances. To fill this gap, we present SEA-VL, an open-source initiative dedicated to developing high-quality, culturally relevant data for SEA languages. By involving contributors from SEA countries, SEA-VL aims to ensure better cultural relevance and diversity, fostering greater inclusivity of underrepresented languages in VL research. Beyo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07920","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/2503.07920/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":"2026-07-05T10:33:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iWaPC+P4jhLEfa76MD7aW8J8mlfNimlDQIxOgkZ9mym4BKzh8KjolzX+ph/zR8nOkFhsM6p2hgIwcM6fI1L8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:21:37.523125Z"},"content_sha256":"090c731b5f707914ae35b0bb0a2b1d9977c0ebc5ee8c7eca2c83fe88a40eb668","schema_version":"1.0","event_id":"sha256:090c731b5f707914ae35b0bb0a2b1d9977c0ebc5ee8c7eca2c83fe88a40eb668"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3J7UGQVPCT5KGYMRSSUB3R6WFC/bundle.json","state_url":"https://pith.science/pith/3J7UGQVPCT5KGYMRSSUB3R6WFC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3J7UGQVPCT5KGYMRSSUB3R6WFC/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":"2026-07-07T07:21:37Z","links":{"resolver":"https://pith.science/pith/3J7UGQVPCT5KGYMRSSUB3R6WFC","bundle":"https://pith.science/pith/3J7UGQVPCT5KGYMRSSUB3R6WFC/bundle.json","state":"https://pith.science/pith/3J7UGQVPCT5KGYMRSSUB3R6WFC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3J7UGQVPCT5KGYMRSSUB3R6WFC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3J7UGQVPCT5KGYMRSSUB3R6WFC","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":"91ee7edb51f30821082a515319cdb10e558b364b8d1046ce1840819e388c1721","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T23:54:52Z","title_canon_sha256":"fbb14fc5feb54675447768d563d261c82a13d31030cb90fe9723162369736843"},"schema_version":"1.0","source":{"id":"2503.07920","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07920","created_at":"2026-07-05T10:33:49Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07920v2","created_at":"2026-07-05T10:33:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07920","created_at":"2026-07-05T10:33:49Z"},{"alias_kind":"pith_short_12","alias_value":"3J7UGQVPCT5K","created_at":"2026-07-05T10:33:49Z"},{"alias_kind":"pith_short_16","alias_value":"3J7UGQVPCT5KGYMR","created_at":"2026-07-05T10:33:49Z"},{"alias_kind":"pith_short_8","alias_value":"3J7UGQVP","created_at":"2026-07-05T10:33:49Z"}],"graph_snapshots":[{"event_id":"sha256:090c731b5f707914ae35b0bb0a2b1d9977c0ebc5ee8c7eca2c83fe88a40eb668","target":"graph","created_at":"2026-07-05T10:33:49Z","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/2503.07920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Southeast Asia (SEA) is a region of extraordinary linguistic and cultural diversity, yet it remains significantly underrepresented in vision-language (VL) research. This often results in artificial intelligence (AI) models that fail to capture SEA cultural nuances. To fill this gap, we present SEA-VL, an open-source initiative dedicated to developing high-quality, culturally relevant data for SEA languages. By involving contributors from SEA countries, SEA-VL aims to ensure better cultural relevance and diversity, fostering greater inclusivity of underrepresented languages in VL research. Beyo","authors_text":"Adisai Na-Thalang, Adrian Xuan Wei Lim, Alham Fikri Aji, Amit Agarwal, Anab Maulana Barik, Anjela Gail Santos, Audra Aurora Izzani, Aye Hninn Khine, Ayushman Singh, Bahrul Ilmi Nasution, Bin Wang, B\\\"orje F. Karlsson, Can Udomcharoenchaikit, Carlos Rafael Catalan, Chengwei Wei, Christian Simon, Dan John Velasco, David Anugraha, Eryawan Presma Yulianrifat, Evan, Fadil Risdian Ansori, Fajri Koto, Fenal Ashokbhai Ilasariya, Filbert Aurelian Tjiaranata, Frederikus Hudi, Genta Indra Winata, Giang Nguyen, Hanif Muhammad Zhafran, Haochen Li, Hitesh Laxmichand Patel, Holy Lovenia, Ikhlasul Akmal Hanif, Isaiah Flores, Jan Christian Blaise Cruz, Jauza Akbar Krito, Jiayun Luo, Joel Ruben Antony Moniz, John Amadeo Daniswara, Joseph Marvin Imperial, Jostin Jerico Rosal, Jun Kevin, Kadek Hendrawan Palgunadi, Kanyakorn Veerakanjana, Karissa Vincentio, Kaung Si Phyo, Kenneth Ko Han Chen, Kevin Pratama, Kun Kerdthaisong, Lester James V. Miranda, Lynnette Hui Xian Ng, Mahardika Krisna Ihsani, M.Alif Al Hakim, Manuel Antonio Rufino, Matthew Theodore Roque, Meisyarah Dwiastuti, Michael Anugraha, Ming Shan Hee, Mithil Bangera, Mohamed Fazli Imam, Mohammad Rifqi Farhansyah, Muhammad Ravi Shulthan Habibi, Muhammad Reza Qorib, Muhammad Rizky Sya'ban, Onno P. Kampman, Patricia Nicole Monderin, Peerat Limkonchotiwat, Phakphum Artkaew, Piyalitt Ittichaiwong, Priyaranjan Pattnayak, Rian Adam Rajagede, Richardy Lobo' Sapan, Rifo Ahmad Genadi, Robert Wijaya, Rochana Prih Hastuti, Ruochen Zhang, Salsabila Zahirah Pranida, Samuel Cahyawijaya, Saptarshi Saha, Supryadi, Tack Hwa Wong, Takdanai Kreangphet, Taki Hasan Rafi, Teddy Ferdinan, Thant Thiri Maung, Tim Santos, Tirana Noor Fatyanosa, Vicky Feliren, Wan Shen Lim, William Nixon, Yanzhi Yu, Yeshil Bangera, Yueqi Song","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T23:54:52Z","title":"Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07920","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:ee100e3a0f5d6ef30b04829e83915434daecc0d5035241574802201df5af1796","target":"record","created_at":"2026-07-05T10:33:49Z","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":"91ee7edb51f30821082a515319cdb10e558b364b8d1046ce1840819e388c1721","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T23:54:52Z","title_canon_sha256":"fbb14fc5feb54675447768d563d261c82a13d31030cb90fe9723162369736843"},"schema_version":"1.0","source":{"id":"2503.07920","kind":"arxiv","version":2}},"canonical_sha256":"da7f4342af14faa3619194a81dc7d6289a27fc4bc48fa25f86dc50e29ce074dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da7f4342af14faa3619194a81dc7d6289a27fc4bc48fa25f86dc50e29ce074dd","first_computed_at":"2026-07-05T10:33:49.882206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:49.882206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TZA+zfzkx8UEX/EBu2IXWadlaWi/9sXGdla2NxzcLi37Q06CusViGwNoOVPQ2lf7Sryf9F3GOQ6NaiQ+IWLEDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:49.882691Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.07920","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee100e3a0f5d6ef30b04829e83915434daecc0d5035241574802201df5af1796","sha256:090c731b5f707914ae35b0bb0a2b1d9977c0ebc5ee8c7eca2c83fe88a40eb668"],"state_sha256":"114252388f863bd860d20a6662221a65eaa3c794319bef780001eb16709172c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hQEshIFlHdBoAc5+Jt52MlseZfhyRxQ3LM7j4cofRpEECPBgS38xJlwd516zdBzv5OCc0Sp6mhH+VQcTG4tiDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:21:37.527145Z","bundle_sha256":"6d2d88e8d0359b6379f9055a22c98e10265e0724402f55c968c7eb566663289e"}}