{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F3VDCAN7HBZF6KVVXP6WJK2XVT","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":"fff71e542027873e22f222a7845ce641e627b80a12ccb8b28261bc11ae9f358e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-04T06:37:09Z","title_canon_sha256":"2a2e8abf04f9332ebeff7c1b7eb8d14e025d31189011fe643a3ea2ac2b093955"},"schema_version":"1.0","source":{"id":"2407.03672","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03672","created_at":"2026-07-05T08:40:21Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03672v1","created_at":"2026-07-05T08:40:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03672","created_at":"2026-07-05T08:40:21Z"},{"alias_kind":"pith_short_12","alias_value":"F3VDCAN7HBZF","created_at":"2026-07-05T08:40:21Z"},{"alias_kind":"pith_short_16","alias_value":"F3VDCAN7HBZF6KVV","created_at":"2026-07-05T08:40:21Z"},{"alias_kind":"pith_short_8","alias_value":"F3VDCAN7","created_at":"2026-07-05T08:40:21Z"}],"graph_snapshots":[{"event_id":"sha256:005f3b9bbe4fa2273c81949a6e5734c927fcc26a83769d7aa9ffe78560bc5f72","target":"graph","created_at":"2026-07-05T08:40:21Z","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/2407.03672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper provides a detailed survey of synthetic data techniques. We first discuss the expected goals of using synthetic data in data augmentation, which can be divided into four parts: 1) Improving Diversity, 2) Data Balancing, 3) Addressing Domain Shift, and 4) Resolving Edge Cases. Synthesizing data are closely related to the prevailing machine learning techniques at the time, therefore, we summarize the domain of synthetic data techniques into four categories: 1) Expert-knowledge, 2) Direct Training, 3) Pre-train then Fine-tune, and 4) Foundation Models without Fine-tuning. Next, we cate","authors_text":"Chang-Sheng Kao, Hsin-Yu Chang, Hsuan-Yun Yu, Pei-Yu Chen, Tun-Hsiang Chou, Yen-Ting Lin, Yun-Nung Chen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-04T06:37:09Z","title":"A Survey of Data Synthesis Approaches"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03672","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":"sha256:706c4d84e8434ddc14450bdfa8cd651adca84abd76c98319b7d5bf8eeca42347","target":"record","created_at":"2026-07-05T08:40:21Z","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":"fff71e542027873e22f222a7845ce641e627b80a12ccb8b28261bc11ae9f358e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-04T06:37:09Z","title_canon_sha256":"2a2e8abf04f9332ebeff7c1b7eb8d14e025d31189011fe643a3ea2ac2b093955"},"schema_version":"1.0","source":{"id":"2407.03672","kind":"arxiv","version":1}},"canonical_sha256":"2eea3101bf38725f2ab5bbfd64ab57acd05b601fa89cdae5df9770d5ae8ecbe8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2eea3101bf38725f2ab5bbfd64ab57acd05b601fa89cdae5df9770d5ae8ecbe8","first_computed_at":"2026-07-05T08:40:21.808796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:40:21.808796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nljtfeK0EWNMpRhvSq1dSIQnKJI0yhUR4J35Flfa5E+5Z+q+3JkryoH1Rv6MzNtkLm4/f8Wjp132sFjYfFYlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:40:21.809251Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03672","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:706c4d84e8434ddc14450bdfa8cd651adca84abd76c98319b7d5bf8eeca42347","sha256:005f3b9bbe4fa2273c81949a6e5734c927fcc26a83769d7aa9ffe78560bc5f72"],"state_sha256":"0833d7aca9da040d546a1f2faef3dd6737160d1f6c2b26d3b5b35f9df0a0e701"}