{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AHSLECIHUKA77BSFGYTQWTS3LQ","short_pith_number":"pith:AHSLECIH","canonical_record":{"source":{"id":"2505.20416","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T18:06:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c019b3514dbd9b854023d381904bc0c525ead44fdee008cf81321dfcf08c2322","abstract_canon_sha256":"b31368a2d96d82f3e5ecdbf2b237b2984c161c1c0e7245ac36b29e2bee299390"},"schema_version":"1.0"},"canonical_sha256":"01e4b20907a281ff864536270b4e5b5c2a4daea7a46d15beebdc39f95bfc02f2","source":{"kind":"arxiv","id":"2505.20416","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20416","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20416v1","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20416","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"pith_short_12","alias_value":"AHSLECIHUKA7","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"pith_short_16","alias_value":"AHSLECIHUKA77BSF","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"pith_short_8","alias_value":"AHSLECIH","created_at":"2026-07-05T11:10:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AHSLECIHUKA77BSFGYTQWTS3LQ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.20416","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T18:06:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c019b3514dbd9b854023d381904bc0c525ead44fdee008cf81321dfcf08c2322","abstract_canon_sha256":"b31368a2d96d82f3e5ecdbf2b237b2984c161c1c0e7245ac36b29e2bee299390"},"schema_version":"1.0"},"canonical_sha256":"01e4b20907a281ff864536270b4e5b5c2a4daea7a46d15beebdc39f95bfc02f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:12.298001Z","signature_b64":"urAB0S5Gi89bfZIqmxAYM36Ngxy5R9jvkyq2ZPqNNzs7gt839vWfAItNjOpzbyAHElbZKcIpuHGg8/5U2O6HBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01e4b20907a281ff864536270b4e5b5c2a4daea7a46d15beebdc39f95bfc02f2","last_reissued_at":"2026-07-05T11:10:12.297537Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:12.297537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.20416","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":"2026-07-05T11:10:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"naqkNoodangrve5V6SkjTOR0N9zCRDkE/t4sMqtXkXv6ai/nQCwTjOx/zOGsLDoblTD/E6RQNRmmCuadnCInBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:56:10.516537Z"},"content_sha256":"415a52407f2fa3d4d6f6f4bbbcdbf7bd5e04387ed4ed6bfffe7f69cc4e5fe139","schema_version":"1.0","event_id":"sha256:415a52407f2fa3d4d6f6f4bbbcdbf7bd5e04387ed4ed6bfffe7f69cc4e5fe139"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AHSLECIHUKA77BSFGYTQWTS3LQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Huanjun Kong, Jinzhe Li, Nanqing Dong, Wanli Jiang, Wanli Ouyang, Zhonghang Yuan, Zihong Chen","submitted_at":"2025-05-26T18:06:50Z","abstract_excerpt":"Fine-tuning for large language models (LLMs) typically requires substantial amounts of high-quality supervised data, which is both costly and labor-intensive to acquire. While synthetic data generation has emerged as a promising solution, existing approaches frequently suffer from factual inaccuracies, insufficient long-tail coverage, simplistic knowledge structures, and homogenized outputs. To address these challenges, we introduce GraphGen, a knowledge graph-guided framework designed for three key question-answering (QA) scenarios: atomic QA, aggregated QA, and multi-hop QA. It begins by con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20416","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/2505.20416/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":"2026-07-05T11:10:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+8y0adONAXDGZHsFHJymkzbkKq6gNnlyLUz7Jf3KYG4xnY71J0uBI5RALjgBGxo3m6JlOm/+7kuJsIITqrh6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:56:10.517217Z"},"content_sha256":"361b4ebd7c45cce3f05645d79a5669cfbf8a3aa1b259ef878748ee9f58e5a5aa","schema_version":"1.0","event_id":"sha256:361b4ebd7c45cce3f05645d79a5669cfbf8a3aa1b259ef878748ee9f58e5a5aa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AHSLECIHUKA77BSFGYTQWTS3LQ/bundle.json","state_url":"https://pith.science/pith/AHSLECIHUKA77BSFGYTQWTS3LQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AHSLECIHUKA77BSFGYTQWTS3LQ/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":"2026-08-07T10:56:10Z","links":{"resolver":"https://pith.science/pith/AHSLECIHUKA77BSFGYTQWTS3LQ","bundle":"https://pith.science/pith/AHSLECIHUKA77BSFGYTQWTS3LQ/bundle.json","state":"https://pith.science/pith/AHSLECIHUKA77BSFGYTQWTS3LQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AHSLECIHUKA77BSFGYTQWTS3LQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AHSLECIHUKA77BSFGYTQWTS3LQ","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":"b31368a2d96d82f3e5ecdbf2b237b2984c161c1c0e7245ac36b29e2bee299390","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T18:06:50Z","title_canon_sha256":"c019b3514dbd9b854023d381904bc0c525ead44fdee008cf81321dfcf08c2322"},"schema_version":"1.0","source":{"id":"2505.20416","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20416","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20416v1","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20416","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"pith_short_12","alias_value":"AHSLECIHUKA7","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"pith_short_16","alias_value":"AHSLECIHUKA77BSF","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"pith_short_8","alias_value":"AHSLECIH","created_at":"2026-07-05T11:10:12Z"}],"graph_snapshots":[{"event_id":"sha256:361b4ebd7c45cce3f05645d79a5669cfbf8a3aa1b259ef878748ee9f58e5a5aa","target":"graph","created_at":"2026-07-05T11:10:12Z","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/2505.20416/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning for large language models (LLMs) typically requires substantial amounts of high-quality supervised data, which is both costly and labor-intensive to acquire. While synthetic data generation has emerged as a promising solution, existing approaches frequently suffer from factual inaccuracies, insufficient long-tail coverage, simplistic knowledge structures, and homogenized outputs. To address these challenges, we introduce GraphGen, a knowledge graph-guided framework designed for three key question-answering (QA) scenarios: atomic QA, aggregated QA, and multi-hop QA. It begins by con","authors_text":"Huanjun Kong, Jinzhe Li, Nanqing Dong, Wanli Jiang, Wanli Ouyang, Zhonghang Yuan, Zihong Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T18:06:50Z","title":"GraphGen: Enhancing Supervised Fine-Tuning for LLMs with Knowledge-Driven Synthetic Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20416","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":"sha256:415a52407f2fa3d4d6f6f4bbbcdbf7bd5e04387ed4ed6bfffe7f69cc4e5fe139","target":"record","created_at":"2026-07-05T11:10:12Z","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":"b31368a2d96d82f3e5ecdbf2b237b2984c161c1c0e7245ac36b29e2bee299390","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T18:06:50Z","title_canon_sha256":"c019b3514dbd9b854023d381904bc0c525ead44fdee008cf81321dfcf08c2322"},"schema_version":"1.0","source":{"id":"2505.20416","kind":"arxiv","version":1}},"canonical_sha256":"01e4b20907a281ff864536270b4e5b5c2a4daea7a46d15beebdc39f95bfc02f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01e4b20907a281ff864536270b4e5b5c2a4daea7a46d15beebdc39f95bfc02f2","first_computed_at":"2026-07-05T11:10:12.297537Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:12.297537Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"urAB0S5Gi89bfZIqmxAYM36Ngxy5R9jvkyq2ZPqNNzs7gt839vWfAItNjOpzbyAHElbZKcIpuHGg8/5U2O6HBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:12.298001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20416","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:415a52407f2fa3d4d6f6f4bbbcdbf7bd5e04387ed4ed6bfffe7f69cc4e5fe139","sha256:361b4ebd7c45cce3f05645d79a5669cfbf8a3aa1b259ef878748ee9f58e5a5aa"],"state_sha256":"5a099d3c9a24ed765fd87feaa1e4fda62b7eea8f89d38ffb51df4801524f5e9f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s1ZBvFFiAOOFOjZKz+9Zh28HMRJxMPiQYps8XDpKFaxUVkpRuHlHxWXM1a0yV01sE+PtId2LDcjkbUrJvT6cDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:56:10.521460Z","bundle_sha256":"d2781fd025f86bb1bfcc7c5853ed51c0d5bb7cf37d230dc2dcdf9d91c863e131"}}