{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BXMOC5FC3AZ7APWCUD37XQAWRY","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":"ca142a66dfe07399bd4377d4ed933ce9f4e7bef5277d2c17d11eb1291c89d541","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T16:47:53Z","title_canon_sha256":"70a0c1bc5b2015dd66a466e8d1ab4eadd719462cc96e6b2b759281e7b920e74d"},"schema_version":"1.0","source":{"id":"2411.03250","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.03250","created_at":"2026-07-05T11:19:01Z"},{"alias_kind":"arxiv_version","alias_value":"2411.03250v2","created_at":"2026-07-05T11:19:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03250","created_at":"2026-07-05T11:19:01Z"},{"alias_kind":"pith_short_12","alias_value":"BXMOC5FC3AZ7","created_at":"2026-07-05T11:19:01Z"},{"alias_kind":"pith_short_16","alias_value":"BXMOC5FC3AZ7APWC","created_at":"2026-07-05T11:19:01Z"},{"alias_kind":"pith_short_8","alias_value":"BXMOC5FC","created_at":"2026-07-05T11:19:01Z"}],"graph_snapshots":[{"event_id":"sha256:94bb5d990b99cc3bdffe2216aa229a9be3f808a2f8e33e7285af74d908d24738","target":"graph","created_at":"2026-07-05T11:19:01Z","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/2411.03250/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) have significantly enhanced their knowledge and generative capabilities, leading to a surge of interest in leveraging LLMs for high-quality data synthesis. However, synthetic data generation via prompting LLMs remains challenging due to LLMs' limited understanding of target data distributions and the complexity of prompt engineering, especially for structured formatted data. To address these issues, we introduce DiffLM, a controllable data synthesis framework based on variational autoencoder (VAE), which further (1) leverages diffusion models","authors_text":"Ben He, Fan Chen, Le Sun, Lexin Tang, Longyin Wen, Xinyao Wang, Yaojie Shen, Ying Zhou, Yulei Niu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T16:47:53Z","title":"DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03250","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:a48909b679fc4ba77240ba4bd572bdb3bc647ca7ed2f9820bf18313cc2708a19","target":"record","created_at":"2026-07-05T11:19:01Z","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":"ca142a66dfe07399bd4377d4ed933ce9f4e7bef5277d2c17d11eb1291c89d541","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T16:47:53Z","title_canon_sha256":"70a0c1bc5b2015dd66a466e8d1ab4eadd719462cc96e6b2b759281e7b920e74d"},"schema_version":"1.0","source":{"id":"2411.03250","kind":"arxiv","version":2}},"canonical_sha256":"0dd8e174a2d833f03ec2a0f7fbc0168e14fefb740ca7c327804c2056d4c4186a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dd8e174a2d833f03ec2a0f7fbc0168e14fefb740ca7c327804c2056d4c4186a","first_computed_at":"2026-07-05T11:19:01.473001Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:01.473001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KdnH3nejZs87Asdxbli57pDQW8n8emcFIrls6SRSzP2lU2Lw9ItmiNlXHW9uYDtP+jGJeLgK/Zj13pXj+D8ICA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:01.473494Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.03250","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a48909b679fc4ba77240ba4bd572bdb3bc647ca7ed2f9820bf18313cc2708a19","sha256:94bb5d990b99cc3bdffe2216aa229a9be3f808a2f8e33e7285af74d908d24738"],"state_sha256":"bd41d8fdc6ceb93c31dadb1ac21fb9f7b0a8843e6a72e795d311f37a198065d8"}