{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XQZPFSBVAC7Y25GYCVG73IFECR","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":"78e43bcc4a92eb6c9da6fc89d34c9c33bf3796613a2b374698a7098363245f96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-02T11:37:16Z","title_canon_sha256":"3af4becb03a5843f82620ce7186ab100a151cd8d2385c460eed03f718d9ad283"},"schema_version":"1.0","source":{"id":"2508.01326","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.01326","created_at":"2026-07-05T11:47:37Z"},{"alias_kind":"arxiv_version","alias_value":"2508.01326v1","created_at":"2026-07-05T11:47:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.01326","created_at":"2026-07-05T11:47:37Z"},{"alias_kind":"pith_short_12","alias_value":"XQZPFSBVAC7Y","created_at":"2026-07-05T11:47:37Z"},{"alias_kind":"pith_short_16","alias_value":"XQZPFSBVAC7Y25GY","created_at":"2026-07-05T11:47:37Z"},{"alias_kind":"pith_short_8","alias_value":"XQZPFSBV","created_at":"2026-07-05T11:47:37Z"}],"graph_snapshots":[{"event_id":"sha256:ed4772887ed2bb2145c9c7808bd0d0dd4338b4cc704c1bbbb2899424008c4ede","target":"graph","created_at":"2026-07-05T11:47:37Z","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/2508.01326/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The scarcity of high-quality, knowledge-intensive training data hinders the development of large language models (LLMs), as traditional corpora provide limited information. Previous studies have synthesized and integrated corpora-dependent question-answering (QA) data to improve model performance but face challenges in QA data scalability and knowledge diversity, particularly in cross-domain contexts. Furthermore, leveraging our designed discipline and difficulty annotation system, we probe model deficiencies in STEM disciplines and high-difficulty data. To overcome these limitations, we propo","authors_text":"Can Ren, Chengying Tu, Hongfei Yan, Jingang Wang, Rongxiang Weng, Xuemiao Zhang, Xunliang Cai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-02T11:37:16Z","title":"Large-Scale Diverse Synthesis for Mid-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.01326","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":"sha256:7fefc145127ad2cd1af049131fb3fd59aa65c98cea271fda1793eb853f7e6f46","target":"record","created_at":"2026-07-05T11:47:37Z","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":"78e43bcc4a92eb6c9da6fc89d34c9c33bf3796613a2b374698a7098363245f96","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-02T11:37:16Z","title_canon_sha256":"3af4becb03a5843f82620ce7186ab100a151cd8d2385c460eed03f718d9ad283"},"schema_version":"1.0","source":{"id":"2508.01326","kind":"arxiv","version":1}},"canonical_sha256":"bc32f2c83500bf8d74d8154dfda0a41446eba6217dbbe3e2b5772abe3c972372","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bc32f2c83500bf8d74d8154dfda0a41446eba6217dbbe3e2b5772abe3c972372","first_computed_at":"2026-07-05T11:47:37.395419Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:37.395419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Pftbr6Kl1teUyy4RKsrkhP4a2Xc7R/seTaLERxgwc/SwAmeO1iBqtWIZl4bP+BVcD4Lf0hoL7cTiZFoiHsS9Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:37.395918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.01326","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fefc145127ad2cd1af049131fb3fd59aa65c98cea271fda1793eb853f7e6f46","sha256:ed4772887ed2bb2145c9c7808bd0d0dd4338b4cc704c1bbbb2899424008c4ede"],"state_sha256":"ad3d133d573e91823c997d3702d8c7202871ac82c9ec79bd3388e6e69e433d3c"}