{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:LYZ7YVANCHN2EZWM475C5Z6G77","short_pith_number":"pith:LYZ7YVAN","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"},"canonical_sha256":"5e33fc540d11dba266cce7fa2ee7c6fff275391324745794eda8e9827a8f89ee","source":{"kind":"arxiv","id":"2607.28109","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28109","created_at":"2026-07-31T01:35:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28109v1","created_at":"2026-07-31T01:35:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28109","created_at":"2026-07-31T01:35:47Z"},{"alias_kind":"pith_short_12","alias_value":"LYZ7YVANCHN2","created_at":"2026-07-31T01:35:47Z"},{"alias_kind":"pith_short_16","alias_value":"LYZ7YVANCHN2EZWM","created_at":"2026-07-31T01:35:47Z"},{"alias_kind":"pith_short_8","alias_value":"LYZ7YVAN","created_at":"2026-07-31T01:35:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:LYZ7YVANCHN2EZWM475C5Z6G77","target":"record","payload":{"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"},"canonical_sha256":"5e33fc540d11dba266cce7fa2ee7c6fff275391324745794eda8e9827a8f89ee","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"},"source_kind":"arxiv","source_id":"2607.28109","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:35:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+KdRIcm2mYBkyOCJsLGhSLICeDoA1vd6LlC5mhdkuivMj9wudFPUrd4/yPOgjHi2HiNW/JDA5D9kOoG9mbyMBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:34:36.479223Z"},"content_sha256":"f56c7cd4c7fe23b5b5c0f7127aa81e3dbe83ffd2c69ac3bdcee42e8fef9174c9","schema_version":"1.0","event_id":"sha256:f56c7cd4c7fe23b5b5c0f7127aa81e3dbe83ffd2c69ac3bdcee42e8fef9174c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:LYZ7YVANCHN2EZWM475C5Z6G77","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-31T01:35:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sfc3GZeQQ/xUn7W1QlCocD6TNe7cs0oCGZ4XlbK1D/MmGcUh90U9eGJQKNz5b01XeHdMmNr0dFPJIfXPtsmvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:34:36.479758Z"},"content_sha256":"5655054ad8d0010fe1a3d7997e96364943c8020e56a71dc44423b65c4e5aefc1","schema_version":"1.0","event_id":"sha256:5655054ad8d0010fe1a3d7997e96364943c8020e56a71dc44423b65c4e5aefc1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LYZ7YVANCHN2EZWM475C5Z6G77/bundle.json","state_url":"https://pith.science/pith/LYZ7YVANCHN2EZWM475C5Z6G77/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LYZ7YVANCHN2EZWM475C5Z6G77/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T03:34:36Z","links":{"resolver":"https://pith.science/pith/LYZ7YVANCHN2EZWM475C5Z6G77","bundle":"https://pith.science/pith/LYZ7YVANCHN2EZWM475C5Z6G77/bundle.json","state":"https://pith.science/pith/LYZ7YVANCHN2EZWM475C5Z6G77/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LYZ7YVANCHN2EZWM475C5Z6G77/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LYZ7YVANCHN2EZWM475C5Z6G77","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":"36d27c5e935de81fd788ffe427b1dba2ab77a83775fa5e6f4bb16662e1417b55","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T12:15:41Z","title_canon_sha256":"7dde4519e3f893739bb05fe05a4636a54cc8eecd15c73f8b0346effecd3d01e0"},"schema_version":"1.0","source":{"id":"2607.28109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28109","created_at":"2026-07-31T01:35:47Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28109v1","created_at":"2026-07-31T01:35:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28109","created_at":"2026-07-31T01:35:47Z"},{"alias_kind":"pith_short_12","alias_value":"LYZ7YVANCHN2","created_at":"2026-07-31T01:35:47Z"},{"alias_kind":"pith_short_16","alias_value":"LYZ7YVANCHN2EZWM","created_at":"2026-07-31T01:35:47Z"},{"alias_kind":"pith_short_8","alias_value":"LYZ7YVAN","created_at":"2026-07-31T01:35:47Z"}],"graph_snapshots":[{"event_id":"sha256:5655054ad8d0010fe1a3d7997e96364943c8020e56a71dc44423b65c4e5aefc1","target":"graph","created_at":"2026-07-31T01:35:47Z","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/2607.28109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guoan Wang, Jiawen Tao, Maxm Pan, Mengzhou Wu, Miao Peng, Nuo Chen, Tong Yang, Wenhan Yu, Xiaokun Yuan, Yaoming Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T12:15:41Z","title":"Beyond Rephrasing: Book-Level Organization Improves Synthetic Textbook Data for Mid-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28109","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:f56c7cd4c7fe23b5b5c0f7127aa81e3dbe83ffd2c69ac3bdcee42e8fef9174c9","target":"record","created_at":"2026-07-31T01:35:47Z","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":"36d27c5e935de81fd788ffe427b1dba2ab77a83775fa5e6f4bb16662e1417b55","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-30T12:15:41Z","title_canon_sha256":"7dde4519e3f893739bb05fe05a4636a54cc8eecd15c73f8b0346effecd3d01e0"},"schema_version":"1.0","source":{"id":"2607.28109","kind":"arxiv","version":1}},"canonical_sha256":"5e33fc540d11dba266cce7fa2ee7c6fff275391324745794eda8e9827a8f89ee","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e33fc540d11dba266cce7fa2ee7c6fff275391324745794eda8e9827a8f89ee","first_computed_at":"2026-07-31T01:35:47.244794Z","kind":"pith_receipt","last_reissued_at":"2026-07-31T01:35:47.244794Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.28109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f56c7cd4c7fe23b5b5c0f7127aa81e3dbe83ffd2c69ac3bdcee42e8fef9174c9","sha256:5655054ad8d0010fe1a3d7997e96364943c8020e56a71dc44423b65c4e5aefc1"],"state_sha256":"17694d03ffac373f0d6601ef78d4fcfa3f8ff5af2767aaaae9be1241c24ea26c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E6UKyjt6DKxMHAVBgVUBVL23y6iY2Ee3du/Pr0aQ7kXOcjufgW5PzsxSrhd/Ysn7C9fk7kq0lsuaMJkzajbxBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:34:36.483754Z","bundle_sha256":"e6c9e6cbb0b10ac326eed8932eae9ce4433658177d6b4808b035916bf217e232"}}