{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QEGI2KCQD32DNW2JKBOPW6IIIW","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":"e9961a3c22c74980f4b6528f938f91f7a1bf45b91b2af570f63d937193076ee0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T03:40:39Z","title_canon_sha256":"6b02286cc4f8de9af0a54154d471372673f0029f02f67813def6a3182ee6d1c3"},"schema_version":"1.0","source":{"id":"2505.00979","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00979","created_at":"2026-07-05T12:11:17Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00979v3","created_at":"2026-07-05T12:11:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00979","created_at":"2026-07-05T12:11:17Z"},{"alias_kind":"pith_short_12","alias_value":"QEGI2KCQD32D","created_at":"2026-07-05T12:11:17Z"},{"alias_kind":"pith_short_16","alias_value":"QEGI2KCQD32DNW2J","created_at":"2026-07-05T12:11:17Z"},{"alias_kind":"pith_short_8","alias_value":"QEGI2KCQ","created_at":"2026-07-05T12:11:17Z"}],"graph_snapshots":[{"event_id":"sha256:473703ef324546228f42fa612e3c0b7c3c8f33bc414165a4233aca17ca5ddabb","target":"graph","created_at":"2026-07-05T12:11:17Z","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/2505.00979/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have achieved remarkable success but remain data-inefficient, especially when learning from small, specialized corpora with limited and proprietary data. Existing synthetic data generation methods for continue pre-training focus on intra-document content and overlook cross-document knowledge associations, limiting content diversity and depth. We propose Synthetic-on-Graph (SoG), a synthetic data generation framework that incorporates cross-document knowledge associations for efficient corpus expansion. SoG constructs a context graph by extracting entities and conce","authors_text":"Cehao Yang, Chengjin Xu, Jian Guo, Liyu Zhang, Shengjie Ma, Xuhui Jiang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T03:40:39Z","title":"Synthesize-on-Graph: Knowledgeable Synthetic Data Generation for Continue Pre-training of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00979","kind":"arxiv","version":3},"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":"sha256:5a29b6e135aae5a2b19c4b6c83ab10b2372a5e857b1993a3b6ea9ef53d1607ce","target":"record","created_at":"2026-07-05T12:11:17Z","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":"e9961a3c22c74980f4b6528f938f91f7a1bf45b91b2af570f63d937193076ee0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-02T03:40:39Z","title_canon_sha256":"6b02286cc4f8de9af0a54154d471372673f0029f02f67813def6a3182ee6d1c3"},"schema_version":"1.0","source":{"id":"2505.00979","kind":"arxiv","version":3}},"canonical_sha256":"810c8d28501ef436db49505cfb790845886c2238aa178668062ed51f903d35d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"810c8d28501ef436db49505cfb790845886c2238aa178668062ed51f903d35d6","first_computed_at":"2026-07-05T12:11:17.572300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:11:17.572300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"00XkbhyUmTWmulSf+g2egQAffqSiNgd/7YW/hmB7g6pb/Qm1WjIovXWdutxe9+AcuV3XUr5Y55O6uL3qxoy7Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:11:17.573011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.00979","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a29b6e135aae5a2b19c4b6c83ab10b2372a5e857b1993a3b6ea9ef53d1607ce","sha256:473703ef324546228f42fa612e3c0b7c3c8f33bc414165a4233aca17ca5ddabb"],"state_sha256":"53ae1e277a26808a8adabc84959b0ef121641b6778fbfa4517a5ec7bed213ec7"}