{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SZKLXFLNOJTQUE2GWCNR5RNL3M","short_pith_number":"pith:SZKLXFLN","schema_version":"1.0","canonical_sha256":"9654bb956d72670a1346b09b1ec5abdb21ac7ba355e51e504bf21859932e9e08","source":{"kind":"arxiv","id":"2310.19341","version":1},"attestation_state":"computed","paper":{"title":"Skywork: A More Open Bilingual Foundation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Biye Li, Bo Zhu, Cheng cheng, Chenxia Li, Chuanhai Dong, Haihua Yang, Han Fang, Jianhao Zhang, Lei Lin, Liang Zhao, Lichang Zhang, Lijie Wang, Liu Yang, Lunan Liu, Peng Cheng, Rui Hu, Shuicheng Yan, Tianwen Wei, Weiwei L\\\"u, Wenjun Cheng, Xiaojuan Liang, Xiaokun Wang, Xiaoyu Zhang, Xilin Luo, Xuejie Wu, Yahui Zhou, Yanqi Sun, Yifu Chen, Yongyi Peng, Yutuan Ma","submitted_at":"2023-10-30T08:31:47Z","abstract_excerpt":"In this technical report, we present Skywork-13B, a family of large language models (LLMs) trained on a corpus of over 3.2 trillion tokens drawn from both English and Chinese texts. This bilingual foundation model is the most extensively trained and openly published LLMs of comparable size to date. We introduce a two-stage training methodology using a segmented corpus, targeting general purpose training and then domain-specific enhancement training, respectively. We show that our model not only excels on popular benchmarks, but also achieves \\emph{state of the art} performance in Chinese langu"},"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":"2310.19341","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-30T08:31:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"23ad66a69a4be979ea5a305436346f65b3f5143fafcc676eda372b106598a5f2","abstract_canon_sha256":"1420b96fd803e65ab13ea33d4002f755b3a7add47aaf605642d44b18a3f52310"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:49.667685Z","signature_b64":"NjN+F5ef1BMcoCTe0pqkat6oCH915bCeFKwiYr++KGSkbu9f2XrqyDwDju5cFm+ltefkkFmqAuf/FbQelioiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9654bb956d72670a1346b09b1ec5abdb21ac7ba355e51e504bf21859932e9e08","last_reissued_at":"2026-07-05T07:06:49.667150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:49.667150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Skywork: A More Open Bilingual Foundation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Biye Li, Bo Zhu, Cheng cheng, Chenxia Li, Chuanhai Dong, Haihua Yang, Han Fang, Jianhao Zhang, Lei Lin, Liang Zhao, Lichang Zhang, Lijie Wang, Liu Yang, Lunan Liu, Peng Cheng, Rui Hu, Shuicheng Yan, Tianwen Wei, Weiwei L\\\"u, Wenjun Cheng, Xiaojuan Liang, Xiaokun Wang, Xiaoyu Zhang, Xilin Luo, Xuejie Wu, Yahui Zhou, Yanqi Sun, Yifu Chen, Yongyi Peng, Yutuan Ma","submitted_at":"2023-10-30T08:31:47Z","abstract_excerpt":"In this technical report, we present Skywork-13B, a family of large language models (LLMs) trained on a corpus of over 3.2 trillion tokens drawn from both English and Chinese texts. This bilingual foundation model is the most extensively trained and openly published LLMs of comparable size to date. We introduce a two-stage training methodology using a segmented corpus, targeting general purpose training and then domain-specific enhancement training, respectively. We show that our model not only excels on popular benchmarks, but also achieves \\emph{state of the art} performance in Chinese langu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19341","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/2310.19341/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":"2310.19341","created_at":"2026-07-05T07:06:49.667213+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.19341v1","created_at":"2026-07-05T07:06:49.667213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19341","created_at":"2026-07-05T07:06:49.667213+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZKLXFLNOJTQ","created_at":"2026-07-05T07:06:49.667213+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZKLXFLNOJTQUE2G","created_at":"2026-07-05T07:06:49.667213+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZKLXFLN","created_at":"2026-07-05T07:06:49.667213+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.12138","citing_title":"Exploring Code Analysis: Zero-Shot Insights on Syntax and Semantics with LLMs","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2505.18128","citing_title":"Frankentext: Stitching random text fragments into long-form narratives","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2511.07003","citing_title":"NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2401.16420","citing_title":"InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2403.17297","citing_title":"InternLM2 Technical Report","ref_index":145,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13429","citing_title":"TokAlign++: Advancing Vocabulary Adaptation via Better Token Alignment","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2312.14238","citing_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","ref_index":155,"is_internal_anchor":false},{"citing_arxiv_id":"2401.02385","citing_title":"TinyLlama: An Open-Source Small Language Model","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2404.16821","citing_title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2303.18223","citing_title":"A Survey of Large Language Models","ref_index":105,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SZKLXFLNOJTQUE2GWCNR5RNL3M","json":"https://pith.science/pith/SZKLXFLNOJTQUE2GWCNR5RNL3M.json","graph_json":"https://pith.science/api/pith-number/SZKLXFLNOJTQUE2GWCNR5RNL3M/graph.json","events_json":"https://pith.science/api/pith-number/SZKLXFLNOJTQUE2GWCNR5RNL3M/events.json","paper":"https://pith.science/paper/SZKLXFLN"},"agent_actions":{"view_html":"https://pith.science/pith/SZKLXFLNOJTQUE2GWCNR5RNL3M","download_json":"https://pith.science/pith/SZKLXFLNOJTQUE2GWCNR5RNL3M.json","view_paper":"https://pith.science/paper/SZKLXFLN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.19341&json=true","fetch_graph":"https://pith.science/api/pith-number/SZKLXFLNOJTQUE2GWCNR5RNL3M/graph.json","fetch_events":"https://pith.science/api/pith-number/SZKLXFLNOJTQUE2GWCNR5RNL3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZKLXFLNOJTQUE2GWCNR5RNL3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZKLXFLNOJTQUE2GWCNR5RNL3M/action/storage_attestation","attest_author":"https://pith.science/pith/SZKLXFLNOJTQUE2GWCNR5RNL3M/action/author_attestation","sign_citation":"https://pith.science/pith/SZKLXFLNOJTQUE2GWCNR5RNL3M/action/citation_signature","submit_replication":"https://pith.science/pith/SZKLXFLNOJTQUE2GWCNR5RNL3M/action/replication_record"}},"created_at":"2026-07-05T07:06:49.667213+00:00","updated_at":"2026-07-05T07:06:49.667213+00:00"}