{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CKLN26HTE7QYHPHJB4WAB523U5","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":"abca86b482c2619b4adb35a71608059fff41cdf00240622786fad82f4a0b3c93","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T14:08:23Z","title_canon_sha256":"20f037af72a80c6c9b7137b6735f62d887bf194f9743ecfb14112b481c8dce81"},"schema_version":"1.0","source":{"id":"2408.15079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.15079","created_at":"2026-07-05T08:59:43Z"},{"alias_kind":"arxiv_version","alias_value":"2408.15079v1","created_at":"2026-07-05T08:59:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.15079","created_at":"2026-07-05T08:59:43Z"},{"alias_kind":"pith_short_12","alias_value":"CKLN26HTE7QY","created_at":"2026-07-05T08:59:43Z"},{"alias_kind":"pith_short_16","alias_value":"CKLN26HTE7QYHPHJ","created_at":"2026-07-05T08:59:43Z"},{"alias_kind":"pith_short_8","alias_value":"CKLN26HT","created_at":"2026-07-05T08:59:43Z"}],"graph_snapshots":[{"event_id":"sha256:a378e4f86109fbd8ed2749fcf6c95b2e5853a7d3298a8e3ec93bfc8e5f4ee0b2","target":"graph","created_at":"2026-07-05T08:59:43Z","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/2408.15079/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The general capabilities of Large Language Models (LLM) highly rely on the composition and selection on extensive pretraining datasets, treated as commercial secrets by several institutions. To mitigate this issue, we open-source the details of a universally applicable data processing pipeline and validate its effectiveness and potential by introducing a competitive LLM baseline. Specifically, the data processing pipeline consists of broad collection to scale up and reweighting to improve quality. We then pretrain a 7B model BaichuanSEED with 3T tokens processed by our pipeline without any del","authors_text":"Bingning Wang, Da Pan, Fan Yang, Guosheng Dong, Haoze Sun, Jianhua Xu, Jiaxin Mao, Lei Su, MingAn Lin, Shusen Zhang, Tianpeng Li, Weipeng Chen, Wentao Zhang, Xiaonan Nie, Xin Wu, Yanjun Shen, Yiding Sun, Yufan Zhang, Zenan Zhou, Zheng Liang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T14:08:23Z","title":"BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.15079","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":"sha256:1ae162738e6285df2fd1aa59db5402b97151546034e064f5348c51bf782b4784","target":"record","created_at":"2026-07-05T08:59:43Z","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":"abca86b482c2619b4adb35a71608059fff41cdf00240622786fad82f4a0b3c93","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-27T14:08:23Z","title_canon_sha256":"20f037af72a80c6c9b7137b6735f62d887bf194f9743ecfb14112b481c8dce81"},"schema_version":"1.0","source":{"id":"2408.15079","kind":"arxiv","version":1}},"canonical_sha256":"1296dd78f327e183bce90f2c00f75ba7514bff9272c1fee4a969c4fc57bf8940","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1296dd78f327e183bce90f2c00f75ba7514bff9272c1fee4a969c4fc57bf8940","first_computed_at":"2026-07-05T08:59:43.083343Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:43.083343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LBrTCLummFKTTsw+jv7TEZ1iXGHCxQ4+hrOSfjsEqrOzec+KXUUOHRJj082DXUyX5Wv8IyFK4UknMDc2WbhiBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:43.083726Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.15079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ae162738e6285df2fd1aa59db5402b97151546034e064f5348c51bf782b4784","sha256:a378e4f86109fbd8ed2749fcf6c95b2e5853a7d3298a8e3ec93bfc8e5f4ee0b2"],"state_sha256":"c8aa150a834751ce84e8ee91957036e2c542702779db93ebdecab57e3455ccb6"}