{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H2ZKK26IRWIPB6ENFG3GQNJ5VP","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":"16362ab1054d3d676434a84e46ba50bb7c5703e0c94177249b93c76d43a6d2a8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T17:47:53Z","title_canon_sha256":"c5e867b05fb5213c49645ebb4f8bcecf1cda75ce33482d56c3156ece9f204a1a"},"schema_version":"1.0","source":{"id":"2412.17743","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17743","created_at":"2026-07-05T09:53:48Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17743v2","created_at":"2026-07-05T09:53:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17743","created_at":"2026-07-05T09:53:48Z"},{"alias_kind":"pith_short_12","alias_value":"H2ZKK26IRWIP","created_at":"2026-07-05T09:53:48Z"},{"alias_kind":"pith_short_16","alias_value":"H2ZKK26IRWIPB6EN","created_at":"2026-07-05T09:53:48Z"},{"alias_kind":"pith_short_8","alias_value":"H2ZKK26I","created_at":"2026-07-05T09:53:48Z"}],"graph_snapshots":[{"event_id":"sha256:b3d1da6042878bade2a6f33a4ba155f71c2dec4a7329c5fb57d2cae40fe68c9d","target":"graph","created_at":"2026-07-05T09:53:48Z","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/2412.17743/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T17:47:53Z","title":"YuLan-Mini: An Open Data-efficient Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17743","kind":"arxiv","version":2},"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":"sha256:7f7f4a2c16de5c1fc2f66396f89e9d267af757ad53621cb66b2dbe6fa183ba83","target":"record","created_at":"2026-07-05T09:53:48Z","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":"16362ab1054d3d676434a84e46ba50bb7c5703e0c94177249b93c76d43a6d2a8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T17:47:53Z","title_canon_sha256":"c5e867b05fb5213c49645ebb4f8bcecf1cda75ce33482d56c3156ece9f204a1a"},"schema_version":"1.0","source":{"id":"2412.17743","kind":"arxiv","version":2}},"canonical_sha256":"3eb2a56bc88d90f0f88d29b668353dabd743033c22ff4877579a4ee5a6d5c096","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3eb2a56bc88d90f0f88d29b668353dabd743033c22ff4877579a4ee5a6d5c096","first_computed_at":"2026-07-05T09:53:48.397081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:48.397081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3+r5Blaa34kopn2wptKlCkWs3NGWPpHjaH2DJLX723LoVdD+hjs1suWQtypEtd78TrE5ybRHy3pWXopxQCfnCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:48.397588Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.17743","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f7f4a2c16de5c1fc2f66396f89e9d267af757ad53621cb66b2dbe6fa183ba83","sha256:b3d1da6042878bade2a6f33a4ba155f71c2dec4a7329c5fb57d2cae40fe68c9d"],"state_sha256":"1bbe37d85341e4a71d913e4f08fbbcad29e60bf054aa53273b3d80e1d0473107"}