{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YKNGRXN5JKC5KIZDT662TDY3BV","short_pith_number":"pith:YKNGRXN5","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"},"canonical_sha256":"c29a68ddbd4a85d523239fbda98f1b0d5f535eef2c1d3dea4dde4ce3e54fced4","source":{"kind":"arxiv","id":"2404.03608","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03608","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03608v1","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03608","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"YKNGRXN5JKC5","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"pith_short_16","alias_value":"YKNGRXN5JKC5KIZD","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"pith_short_8","alias_value":"YKNGRXN5","created_at":"2026-07-05T08:04:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YKNGRXN5JKC5KIZDT662TDY3BV","target":"record","payload":{"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"},"canonical_sha256":"c29a68ddbd4a85d523239fbda98f1b0d5f535eef2c1d3dea4dde4ce3e54fced4","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"},"source_kind":"arxiv","source_id":"2404.03608","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:04:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PVlQ0sz7frhFuCTYxneFtSfXysXzsEULFVN9eMz3ZSVL67Kf5WhcQzzgnP5xIosN3M2s311nqlNsg3HPPSjRBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T02:45:34.471655Z"},"content_sha256":"11b6cac64f99827cbaa351926de993b32f28f678f8249129294481ec9094a29f","schema_version":"1.0","event_id":"sha256:11b6cac64f99827cbaa351926de993b32f28f678f8249129294481ec9094a29f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YKNGRXN5JKC5KIZDT662TDY3BV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:04:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d/X5MBaF1aR7ctwosKm05nIert/abXq84rW4hw4WSbj6PadYAcJ79KVehykpYvN1Qfq4EkjS15KjiyooYdlyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T02:45:34.472022Z"},"content_sha256":"f13b3b421109fa8d53160aff098dbfed4bfdd4b98632ad9fd46d357ea61da6b1","schema_version":"1.0","event_id":"sha256:f13b3b421109fa8d53160aff098dbfed4bfdd4b98632ad9fd46d357ea61da6b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YKNGRXN5JKC5KIZDT662TDY3BV/bundle.json","state_url":"https://pith.science/pith/YKNGRXN5JKC5KIZDT662TDY3BV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YKNGRXN5JKC5KIZDT662TDY3BV/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":"2026-07-08T02:45:34Z","links":{"resolver":"https://pith.science/pith/YKNGRXN5JKC5KIZDT662TDY3BV","bundle":"https://pith.science/pith/YKNGRXN5JKC5KIZDT662TDY3BV/bundle.json","state":"https://pith.science/pith/YKNGRXN5JKC5KIZDT662TDY3BV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YKNGRXN5JKC5KIZDT662TDY3BV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YKNGRXN5JKC5KIZDT662TDY3BV","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":"9fb1a401d3769674efcb15bfa76f9ec5f75c78c0983c71502cadc10442555849","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-04T17:31:32Z","title_canon_sha256":"cf70f841319ad669b9962d56241870f02ea327b3f3cfe60f687b8f16ac41bf36"},"schema_version":"1.0","source":{"id":"2404.03608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.03608","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"2404.03608v1","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.03608","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"YKNGRXN5JKC5","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"pith_short_16","alias_value":"YKNGRXN5JKC5KIZD","created_at":"2026-07-05T08:04:28Z"},{"alias_kind":"pith_short_8","alias_value":"YKNGRXN5","created_at":"2026-07-05T08:04:28Z"}],"graph_snapshots":[{"event_id":"sha256:f13b3b421109fa8d53160aff098dbfed4bfdd4b98632ad9fd46d357ea61da6b1","target":"graph","created_at":"2026-07-05T08:04:28Z","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/2404.03608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guangtao Zeng, Jia Guo, Jiahui Zhou, Longxu Dou, Min Lin, Qian Liu, Wei Lu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-04T17:31:32Z","title":"Sailor: Open Language Models for South-East Asia"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.03608","kind":"arxiv","version":1},"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":"sha256:11b6cac64f99827cbaa351926de993b32f28f678f8249129294481ec9094a29f","target":"record","created_at":"2026-07-05T08:04:28Z","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":"9fb1a401d3769674efcb15bfa76f9ec5f75c78c0983c71502cadc10442555849","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-04T17:31:32Z","title_canon_sha256":"cf70f841319ad669b9962d56241870f02ea327b3f3cfe60f687b8f16ac41bf36"},"schema_version":"1.0","source":{"id":"2404.03608","kind":"arxiv","version":1}},"canonical_sha256":"c29a68ddbd4a85d523239fbda98f1b0d5f535eef2c1d3dea4dde4ce3e54fced4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c29a68ddbd4a85d523239fbda98f1b0d5f535eef2c1d3dea4dde4ce3e54fced4","first_computed_at":"2026-07-05T08:04:28.096500Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:28.096500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t4tNUOokKA1oxJGzcjT1bnibOLYDeTwlLfBMcgO6hEggKnyyCcy9cY/gqoZQL/zJHchmRxhJClo7tOyZLKuGCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:28.096849Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.03608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11b6cac64f99827cbaa351926de993b32f28f678f8249129294481ec9094a29f","sha256:f13b3b421109fa8d53160aff098dbfed4bfdd4b98632ad9fd46d357ea61da6b1"],"state_sha256":"b84316d024d10756643a19640f270308c782fc4768cb54a78287f04f206332c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VU02x9SRlvoe2tunsHkJOPmD2uQU9r4rUEG2R4f0J21Y2y8lIOXPHzeF9DBMRABofaRs4I52ArtI5uk75gZgBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T02:45:34.474006Z","bundle_sha256":"8083ac57639c02e73cc136a31fba908aa3c927d156e4e201f4da3381f32fceac"}}