{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5QSQTF67FLMSTYPBW65GJLLBO4","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":"5125a1fe9579933e9dea0fe9e7bda44740c24f384b48a2fe8d2c8b2ec1b688ca","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-21T14:43:23Z","title_canon_sha256":"fef9f4a292af7d995031343321cc81ad173089f6bb8ff0778fca7679a5a5defe"},"schema_version":"1.0","source":{"id":"2503.17195","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.17195","created_at":"2026-07-05T11:25:42Z"},{"alias_kind":"arxiv_version","alias_value":"2503.17195v2","created_at":"2026-07-05T11:25:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17195","created_at":"2026-07-05T11:25:42Z"},{"alias_kind":"pith_short_12","alias_value":"5QSQTF67FLMS","created_at":"2026-07-05T11:25:42Z"},{"alias_kind":"pith_short_16","alias_value":"5QSQTF67FLMSTYPB","created_at":"2026-07-05T11:25:42Z"},{"alias_kind":"pith_short_8","alias_value":"5QSQTF67","created_at":"2026-07-05T11:25:42Z"}],"graph_snapshots":[{"event_id":"sha256:d6d2a791f3d38b21fb146fe472ce8d7a8f89afa1d3317ee42a02ef7e98ec780b","target":"graph","created_at":"2026-07-05T11:25:42Z","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/2503.17195/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model customization necessitates high-quality and diverse datasets, but acquiring such data remains time-consuming and labor-intensive. Despite the great potential of large language models (LLMs) for data synthesis, current approaches are constrained by limited seed data, model biases, and low-variation prompts, resulting in limited diversity and biased distributions with the increase of data scales. To tackle this challenge, we introduce TREESYNTH, a tree-guided subspace-based data synthesis approach inspired by decision trees. It constructs a spatial partitioning tree to recursively divide a","authors_text":"Boyang Xue, Chuan Wu, Jiahui Gao, Jingqi Zhou, Jingwei Dong, Jiyue Jiang, Lingpeng Kong, Pengan Chen, Qintong Li, Sheng Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-21T14:43:23Z","title":"TreeSynth: Synthesizing Diverse Data from Scratch via Tree-Guided Subspace Partitioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17195","kind":"arxiv","version":2},"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":"sha256:68339d848b704e180713f23b05ad597ff8162744e9a508aa191bfe09a8738bc4","target":"record","created_at":"2026-07-05T11:25:42Z","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":"5125a1fe9579933e9dea0fe9e7bda44740c24f384b48a2fe8d2c8b2ec1b688ca","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-21T14:43:23Z","title_canon_sha256":"fef9f4a292af7d995031343321cc81ad173089f6bb8ff0778fca7679a5a5defe"},"schema_version":"1.0","source":{"id":"2503.17195","kind":"arxiv","version":2}},"canonical_sha256":"ec250997df2ad929e1e1b7ba64ad61770cef2870c3f05d6d8e326586939874ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec250997df2ad929e1e1b7ba64ad61770cef2870c3f05d6d8e326586939874ad","first_computed_at":"2026-07-05T11:25:42.990824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:42.990824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+4PQ0qdSQyW3u+ilnfIWM8vX8ww6SyAUxsCpfo3rNcgqViHtwTk/lc0/b6SrbK86fUP5E9H6+F2OYEk+LyJbBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:42.991438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.17195","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68339d848b704e180713f23b05ad597ff8162744e9a508aa191bfe09a8738bc4","sha256:d6d2a791f3d38b21fb146fe472ce8d7a8f89afa1d3317ee42a02ef7e98ec780b"],"state_sha256":"7ef516840d4812a865827f8080cc72978432324aa58056e7e78855ddef0a094a"}