{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LYZ7YVANCHN2EZWM475C5Z6G77","short_pith_number":"pith:LYZ7YVAN","schema_version":"1.0","canonical_sha256":"5e33fc540d11dba266cce7fa2ee7c6fff275391324745794eda8e9827a8f89ee","source":{"kind":"arxiv","id":"2607.28109","version":1},"attestation_state":"computed","paper":{"title":"Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guoan Wang, Jiawen Tao, Maxm Pan, Mengzhou Wu, Miao Peng, Nuo Chen, Tong Yang, Wenhan Yu, Xiaokun Yuan, Yaoming Li","submitted_at":"2026-07-30T12:15:41Z","abstract_excerpt":"Synthetic textbook data has improved language model pre-training, but prior work largely treats the benefit as a property of generated content or local rewriting style. We study a different factor: whether related content is organized into coherent book-level documents. We contribute both a scalable synthesis pipeline and controlled evidence that this organization matters. The pipeline retrieves source material from a pre-training corpus, clusters it into topical units, plans hierarchical tables of contents, and assembles source-grounded sections into complete books (our Full setting), yieldin"},"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":"2607.28109","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T12:15:41Z","cross_cats_sorted":[],"title_canon_sha256":"7dde4519e3f893739bb05fe05a4636a54cc8eecd15c73f8b0346effecd3d01e0","abstract_canon_sha256":"36d27c5e935de81fd788ffe427b1dba2ab77a83775fa5e6f4bb16662e1417b55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e33fc540d11dba266cce7fa2ee7c6fff275391324745794eda8e9827a8f89ee","last_reissued_at":"2026-07-31T01:35:47.244794Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-31T01:35:47.244794Z"},"graph_snapshot":{"paper":{"title":"Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guoan Wang, Jiawen Tao, Maxm Pan, Mengzhou Wu, Miao Peng, Nuo Chen, Tong Yang, Wenhan Yu, Xiaokun Yuan, Yaoming Li","submitted_at":"2026-07-30T12:15:41Z","abstract_excerpt":"Synthetic textbook data has improved language model pre-training, but prior work largely treats the benefit as a property of generated content or local rewriting style. We study a different factor: whether related content is organized into coherent book-level documents. We contribute both a scalable synthesis pipeline and controlled evidence that this organization matters. The pipeline retrieves source material from a pre-training corpus, clusters it into topical units, plans hierarchical tables of contents, and assembles source-grounded sections into complete books (our Full setting), yieldin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28109","kind":"arxiv","version":1},"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/2607.28109/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":"2607.28109","created_at":"2026-07-31T01:35:47.247920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28109v1","created_at":"2026-07-31T01:35:47.247920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28109","created_at":"2026-07-31T01:35:47.247920+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYZ7YVANCHN2","created_at":"2026-07-31T01:35:47.247920+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYZ7YVANCHN2EZWM","created_at":"2026-07-31T01:35:47.247920+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYZ7YVAN","created_at":"2026-07-31T01:35:47.247920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.09093","citing_title":"The Announcement Carries the Cue: Markup, Boundaries, and the Notation of Pre-Training Corpora","ref_index":78,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LYZ7YVANCHN2EZWM475C5Z6G77","json":"https://pith.science/pith/LYZ7YVANCHN2EZWM475C5Z6G77.json","graph_json":"https://pith.science/api/pith-number/LYZ7YVANCHN2EZWM475C5Z6G77/graph.json","events_json":"https://pith.science/api/pith-number/LYZ7YVANCHN2EZWM475C5Z6G77/events.json","paper":"https://pith.science/paper/LYZ7YVAN"},"agent_actions":{"view_html":"https://pith.science/pith/LYZ7YVANCHN2EZWM475C5Z6G77","download_json":"https://pith.science/pith/LYZ7YVANCHN2EZWM475C5Z6G77.json","view_paper":"https://pith.science/paper/LYZ7YVAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28109&json=true","fetch_graph":"https://pith.science/api/pith-number/LYZ7YVANCHN2EZWM475C5Z6G77/graph.json","fetch_events":"https://pith.science/api/pith-number/LYZ7YVANCHN2EZWM475C5Z6G77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYZ7YVANCHN2EZWM475C5Z6G77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYZ7YVANCHN2EZWM475C5Z6G77/action/storage_attestation","attest_author":"https://pith.science/pith/LYZ7YVANCHN2EZWM475C5Z6G77/action/author_attestation","sign_citation":"https://pith.science/pith/LYZ7YVANCHN2EZWM475C5Z6G77/action/citation_signature","submit_replication":"https://pith.science/pith/LYZ7YVANCHN2EZWM475C5Z6G77/action/replication_record"}},"created_at":"2026-07-31T01:35:47.247920+00:00","updated_at":"2026-07-31T01:35:47.247920+00:00"}