{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ME4UPMG3NE7XSPZIJYXS7W4ND6","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":"85aca1781dff03c04c4e9ce05a05cb4894e3734b839ec01238678b6b9bf598b7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-04T16:53:20Z","title_canon_sha256":"3b35aa5ac0d7db891d37150604ac21b858b7f8a917bca791807faa87dfa03863"},"schema_version":"1.0","source":{"id":"2508.10000","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.10000","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"arxiv_version","alias_value":"2508.10000v1","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10000","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"pith_short_12","alias_value":"ME4UPMG3NE7X","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"pith_short_16","alias_value":"ME4UPMG3NE7XSPZI","created_at":"2026-07-05T11:53:28Z"},{"alias_kind":"pith_short_8","alias_value":"ME4UPMG3","created_at":"2026-07-05T11:53:28Z"}],"graph_snapshots":[{"event_id":"sha256:2ce0649232c80714ebb6300679a4d0eb528c18123e42e8c84a8cbb1e51fdb5b5","target":"graph","created_at":"2026-07-05T11:53:28Z","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/2508.10000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When developing text classification models for real world applications, one major challenge is the difficulty to collect sufficient data for all text classes. In this work, we address this challenge by utilizing large language models (LLMs) to generate synthetic data and using such data to improve the performance of the models without waiting for more real data to be collected and labelled. As an LLM generates different synthetic data in response to different input examples, we formulate an automated workflow, which searches for input examples that lead to more ``effective'' synthetic data for","authors_text":"Adrian Carrasco-Revilla, Chenhao Xue, Joyraj Chakraborty, Min Chen, Yuanzhe Jin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-04T16:53:20Z","title":"AutoGeTS: Knowledge-based Automated Generation of Text Synthetics for Improving Text Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10000","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":"sha256:4c6344be64ee90936b5145ffccb0d5cd5f8ac8d9e16e43fe08a9f3a06868e42e","target":"record","created_at":"2026-07-05T11:53:28Z","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":"85aca1781dff03c04c4e9ce05a05cb4894e3734b839ec01238678b6b9bf598b7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-04T16:53:20Z","title_canon_sha256":"3b35aa5ac0d7db891d37150604ac21b858b7f8a917bca791807faa87dfa03863"},"schema_version":"1.0","source":{"id":"2508.10000","kind":"arxiv","version":1}},"canonical_sha256":"613947b0db693f793f284e2f2fdb8d1fa50c4f4a7f617919512cdf9fcd49b752","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"613947b0db693f793f284e2f2fdb8d1fa50c4f4a7f617919512cdf9fcd49b752","first_computed_at":"2026-07-05T11:53:28.841308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:28.841308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/5DqNr7wNOLEHVQPeC+iIyIQPBgawtoZOGjWitM/hFOX4JJPoI/o3lITjwOF8vPcgB7yKPN07tPfmLr3L+uSDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:28.841820Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.10000","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c6344be64ee90936b5145ffccb0d5cd5f8ac8d9e16e43fe08a9f3a06868e42e","sha256:2ce0649232c80714ebb6300679a4d0eb528c18123e42e8c84a8cbb1e51fdb5b5"],"state_sha256":"3c7e882fa8c2fdaae2d950d5094171eda72010741a66265436218e0135f61e97"}