{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KSLM7ZGFBQGN2HRFJISAYXWODB","short_pith_number":"pith:KSLM7ZGF","schema_version":"1.0","canonical_sha256":"5496cfe4c50c0cdd1e254a240c5ece187c2b3f88f6842b807ad6f878d158c5ea","source":{"kind":"arxiv","id":"2502.06635","version":2},"attestation_state":"computed","paper":{"title":"Steel-LLM:From Scratch to Open Source -- A Personal Journey in Building a Chinese-Centric LLM","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Qingshui Gu, Shu Li, Tianyu Zheng, Zhaoxiang Zhang","submitted_at":"2025-02-10T16:31:37Z","abstract_excerpt":"Steel-LLM is a Chinese-centric language model developed from scratch with the goal of creating a high-quality, open-source model despite limited computational resources. Launched in March 2024, the project aimed to train a 1-billion-parameter model on a large-scale dataset, prioritizing transparency and the sharing of practical insights to assist others in the community. The training process primarily focused on Chinese data, with a small proportion of English data included, addressing gaps in existing open-source LLMs by providing a more detailed and practical account of the model-building jo"},"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":"2502.06635","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-10T16:31:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"64e476f07e33b4705b3b7966b465b3a1f9b9592880fa5183d5f920d281153649","abstract_canon_sha256":"f621b3491f61f7bc46c3a85996ab855a6995eeaf0bf667f7dce9bf9815b0ec96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:48.159664Z","signature_b64":"XnNYJN8xjhe7OsfUCXHXWdH6xSL2CMMEhQ2Kdg7fYCCfQ9GiRLIbsQgU4oIC7q6tcnnUEhctWrshStHg19KwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5496cfe4c50c0cdd1e254a240c5ece187c2b3f88f6842b807ad6f878d158c5ea","last_reissued_at":"2026-07-05T10:13:48.159071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:48.159071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Steel-LLM:From Scratch to Open Source -- A Personal Journey in Building a Chinese-Centric LLM","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Qingshui Gu, Shu Li, Tianyu Zheng, Zhaoxiang Zhang","submitted_at":"2025-02-10T16:31:37Z","abstract_excerpt":"Steel-LLM is a Chinese-centric language model developed from scratch with the goal of creating a high-quality, open-source model despite limited computational resources. Launched in March 2024, the project aimed to train a 1-billion-parameter model on a large-scale dataset, prioritizing transparency and the sharing of practical insights to assist others in the community. The training process primarily focused on Chinese data, with a small proportion of English data included, addressing gaps in existing open-source LLMs by providing a more detailed and practical account of the model-building jo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06635","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/2502.06635/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":"2502.06635","created_at":"2026-07-05T10:13:48.159127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06635v2","created_at":"2026-07-05T10:13:48.159127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06635","created_at":"2026-07-05T10:13:48.159127+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSLM7ZGFBQGN","created_at":"2026-07-05T10:13:48.159127+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSLM7ZGFBQGN2HRF","created_at":"2026-07-05T10:13:48.159127+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSLM7ZGF","created_at":"2026-07-05T10:13:48.159127+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/KSLM7ZGFBQGN2HRFJISAYXWODB","json":"https://pith.science/pith/KSLM7ZGFBQGN2HRFJISAYXWODB.json","graph_json":"https://pith.science/api/pith-number/KSLM7ZGFBQGN2HRFJISAYXWODB/graph.json","events_json":"https://pith.science/api/pith-number/KSLM7ZGFBQGN2HRFJISAYXWODB/events.json","paper":"https://pith.science/paper/KSLM7ZGF"},"agent_actions":{"view_html":"https://pith.science/pith/KSLM7ZGFBQGN2HRFJISAYXWODB","download_json":"https://pith.science/pith/KSLM7ZGFBQGN2HRFJISAYXWODB.json","view_paper":"https://pith.science/paper/KSLM7ZGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06635&json=true","fetch_graph":"https://pith.science/api/pith-number/KSLM7ZGFBQGN2HRFJISAYXWODB/graph.json","fetch_events":"https://pith.science/api/pith-number/KSLM7ZGFBQGN2HRFJISAYXWODB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSLM7ZGFBQGN2HRFJISAYXWODB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSLM7ZGFBQGN2HRFJISAYXWODB/action/storage_attestation","attest_author":"https://pith.science/pith/KSLM7ZGFBQGN2HRFJISAYXWODB/action/author_attestation","sign_citation":"https://pith.science/pith/KSLM7ZGFBQGN2HRFJISAYXWODB/action/citation_signature","submit_replication":"https://pith.science/pith/KSLM7ZGFBQGN2HRFJISAYXWODB/action/replication_record"}},"created_at":"2026-07-05T10:13:48.159127+00:00","updated_at":"2026-07-05T10:13:48.159127+00:00"}