{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YKNGRXN5JKC5KIZDT662TDY3BV","short_pith_number":"pith:YKNGRXN5","schema_version":"1.0","canonical_sha256":"c29a68ddbd4a85d523239fbda98f1b0d5f535eef2c1d3dea4dde4ce3e54fced4","source":{"kind":"arxiv","id":"2404.03608","version":1},"attestation_state":"computed","paper":{"title":"Sailor: Open Language Models for South-East Asia","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guangtao Zeng, Jia Guo, Jiahui Zhou, Longxu Dou, Min Lin, Qian Liu, Wei Lu","submitted_at":"2024-04-04T17:31:32Z","abstract_excerpt":"We present Sailor, a family of open language models ranging from 0.5B to 7B parameters, tailored for South-East Asian (SEA) languages. These models are continually pre-trained from Qwen1.5, a great language model for multilingual use cases. From Qwen1.5, Sailor models accept 200B to 400B tokens, primarily covering the languages of English, Chinese, Vietnamese, Thai, Indonesian, Malay, and Lao. The training leverages several techniques, including BPE dropout for improving the model robustness, aggressive data cleaning and deduplication, and small proxy models to optimize data mixture. Experimen"},"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":"2404.03608","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-04T17:31:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cf70f841319ad669b9962d56241870f02ea327b3f3cfe60f687b8f16ac41bf36","abstract_canon_sha256":"9fb1a401d3769674efcb15bfa76f9ec5f75c78c0983c71502cadc10442555849"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:28.096849Z","signature_b64":"t4tNUOokKA1oxJGzcjT1bnibOLYDeTwlLfBMcgO6hEggKnyyCcy9cY/gqoZQL/zJHchmRxhJClo7tOyZLKuGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c29a68ddbd4a85d523239fbda98f1b0d5f535eef2c1d3dea4dde4ce3e54fced4","last_reissued_at":"2026-07-05T08:04:28.096500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:28.096500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sailor: Open Language Models for South-East Asia","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guangtao Zeng, Jia Guo, Jiahui Zhou, Longxu Dou, Min Lin, Qian Liu, Wei Lu","submitted_at":"2024-04-04T17:31:32Z","abstract_excerpt":"We present Sailor, a family of open language models ranging from 0.5B to 7B parameters, tailored for South-East Asian (SEA) languages. These models are continually pre-trained from Qwen1.5, a great language model for multilingual use cases. From Qwen1.5, Sailor models accept 200B to 400B tokens, primarily covering the languages of English, Chinese, Vietnamese, Thai, Indonesian, Malay, and Lao. The training leverages several techniques, including BPE dropout for improving the model robustness, aggressive data cleaning and deduplication, and small proxy models to optimize data mixture. Experimen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03608","kind":"arxiv","version":1},"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/2404.03608/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":"2404.03608","created_at":"2026-07-05T08:04:28.096558+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.03608v1","created_at":"2026-07-05T08:04:28.096558+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03608","created_at":"2026-07-05T08:04:28.096558+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKNGRXN5JKC5","created_at":"2026-07-05T08:04:28.096558+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKNGRXN5JKC5KIZD","created_at":"2026-07-05T08:04:28.096558+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKNGRXN5","created_at":"2026-07-05T08:04:28.096558+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YKNGRXN5JKC5KIZDT662TDY3BV","json":"https://pith.science/pith/YKNGRXN5JKC5KIZDT662TDY3BV.json","graph_json":"https://pith.science/api/pith-number/YKNGRXN5JKC5KIZDT662TDY3BV/graph.json","events_json":"https://pith.science/api/pith-number/YKNGRXN5JKC5KIZDT662TDY3BV/events.json","paper":"https://pith.science/paper/YKNGRXN5"},"agent_actions":{"view_html":"https://pith.science/pith/YKNGRXN5JKC5KIZDT662TDY3BV","download_json":"https://pith.science/pith/YKNGRXN5JKC5KIZDT662TDY3BV.json","view_paper":"https://pith.science/paper/YKNGRXN5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.03608&json=true","fetch_graph":"https://pith.science/api/pith-number/YKNGRXN5JKC5KIZDT662TDY3BV/graph.json","fetch_events":"https://pith.science/api/pith-number/YKNGRXN5JKC5KIZDT662TDY3BV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKNGRXN5JKC5KIZDT662TDY3BV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKNGRXN5JKC5KIZDT662TDY3BV/action/storage_attestation","attest_author":"https://pith.science/pith/YKNGRXN5JKC5KIZDT662TDY3BV/action/author_attestation","sign_citation":"https://pith.science/pith/YKNGRXN5JKC5KIZDT662TDY3BV/action/citation_signature","submit_replication":"https://pith.science/pith/YKNGRXN5JKC5KIZDT662TDY3BV/action/replication_record"}},"created_at":"2026-07-05T08:04:28.096558+00:00","updated_at":"2026-07-05T08:04:28.096558+00:00"}