{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H2ZKK26IRWIPB6ENFG3GQNJ5VP","short_pith_number":"pith:H2ZKK26I","schema_version":"1.0","canonical_sha256":"3eb2a56bc88d90f0f88d29b668353dabd743033c22ff4877579a4ee5a6d5c096","source":{"kind":"arxiv","id":"2412.17743","version":2},"attestation_state":"computed","paper":{"title":"YuLan-Mini: An Open Data-efficient Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huatong Song, Jia Deng, Jiapeng Wang, Jie Chen, Jinhao Jiang, Ji-Rong Wen, Kun Zhou, Wayne Xin Zhao, Yiwen Hu, Yutao Zhu, Zican Dong","submitted_at":"2024-12-23T17:47:53Z","abstract_excerpt":"Effective pre-training of large language models (LLMs) has been challenging due to the immense resource demands and the complexity of the technical processes involved. This paper presents a detailed technical report on YuLan-Mini, a highly capable base model with 2.42B parameters that achieves top-tier performance among models of similar parameter scale. Our pre-training approach focuses on enhancing training efficacy through three key technical contributions: an elaborate data pipeline combines data cleaning with data schedule strategies, a robust optimization method to mitigate training inst"},"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":"2412.17743","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T17:47:53Z","cross_cats_sorted":[],"title_canon_sha256":"c5e867b05fb5213c49645ebb4f8bcecf1cda75ce33482d56c3156ece9f204a1a","abstract_canon_sha256":"16362ab1054d3d676434a84e46ba50bb7c5703e0c94177249b93c76d43a6d2a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:48.397588Z","signature_b64":"3+r5Blaa34kopn2wptKlCkWs3NGWPpHjaH2DJLX723LoVdD+hjs1suWQtypEtd78TrE5ybRHy3pWXopxQCfnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3eb2a56bc88d90f0f88d29b668353dabd743033c22ff4877579a4ee5a6d5c096","last_reissued_at":"2026-07-05T09:53:48.397081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:48.397081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"YuLan-Mini: An Open Data-efficient Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huatong Song, Jia Deng, Jiapeng Wang, Jie Chen, Jinhao Jiang, Ji-Rong Wen, Kun Zhou, Wayne Xin Zhao, Yiwen Hu, Yutao Zhu, Zican Dong","submitted_at":"2024-12-23T17:47:53Z","abstract_excerpt":"Effective pre-training of large language models (LLMs) has been challenging due to the immense resource demands and the complexity of the technical processes involved. This paper presents a detailed technical report on YuLan-Mini, a highly capable base model with 2.42B parameters that achieves top-tier performance among models of similar parameter scale. Our pre-training approach focuses on enhancing training efficacy through three key technical contributions: an elaborate data pipeline combines data cleaning with data schedule strategies, a robust optimization method to mitigate training inst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17743","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/2412.17743/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":"2412.17743","created_at":"2026-07-05T09:53:48.397144+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17743v2","created_at":"2026-07-05T09:53:48.397144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17743","created_at":"2026-07-05T09:53:48.397144+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2ZKK26IRWIP","created_at":"2026-07-05T09:53:48.397144+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2ZKK26IRWIPB6EN","created_at":"2026-07-05T09:53:48.397144+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2ZKK26I","created_at":"2026-07-05T09:53:48.397144+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31175","citing_title":"Towards Efficient LLMs Annealing with Principled Sample Selection","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H2ZKK26IRWIPB6ENFG3GQNJ5VP","json":"https://pith.science/pith/H2ZKK26IRWIPB6ENFG3GQNJ5VP.json","graph_json":"https://pith.science/api/pith-number/H2ZKK26IRWIPB6ENFG3GQNJ5VP/graph.json","events_json":"https://pith.science/api/pith-number/H2ZKK26IRWIPB6ENFG3GQNJ5VP/events.json","paper":"https://pith.science/paper/H2ZKK26I"},"agent_actions":{"view_html":"https://pith.science/pith/H2ZKK26IRWIPB6ENFG3GQNJ5VP","download_json":"https://pith.science/pith/H2ZKK26IRWIPB6ENFG3GQNJ5VP.json","view_paper":"https://pith.science/paper/H2ZKK26I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17743&json=true","fetch_graph":"https://pith.science/api/pith-number/H2ZKK26IRWIPB6ENFG3GQNJ5VP/graph.json","fetch_events":"https://pith.science/api/pith-number/H2ZKK26IRWIPB6ENFG3GQNJ5VP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2ZKK26IRWIPB6ENFG3GQNJ5VP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2ZKK26IRWIPB6ENFG3GQNJ5VP/action/storage_attestation","attest_author":"https://pith.science/pith/H2ZKK26IRWIPB6ENFG3GQNJ5VP/action/author_attestation","sign_citation":"https://pith.science/pith/H2ZKK26IRWIPB6ENFG3GQNJ5VP/action/citation_signature","submit_replication":"https://pith.science/pith/H2ZKK26IRWIPB6ENFG3GQNJ5VP/action/replication_record"}},"created_at":"2026-07-05T09:53:48.397144+00:00","updated_at":"2026-07-05T09:53:48.397144+00:00"}