{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XEZOFC52ADT3SJ75NAB77RBZJ4","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":"9d8b4ccf08461449f3be745797e6b29586478aa238620085f1011c668b3504dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T01:39:16Z","title_canon_sha256":"a41062a59ee45e3efea9a2998dad23cc0d716b34ea9369b104a9c35e465be78d"},"schema_version":"1.0","source":{"id":"2412.06136","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.06136","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"arxiv_version","alias_value":"2412.06136v2","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06136","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"pith_short_12","alias_value":"XEZOFC52ADT3","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"pith_short_16","alias_value":"XEZOFC52ADT3SJ75","created_at":"2026-07-05T11:36:55Z"},{"alias_kind":"pith_short_8","alias_value":"XEZOFC52","created_at":"2026-07-05T11:36:55Z"}],"graph_snapshots":[{"event_id":"sha256:18864b6c726abe48038f87f9e46cf9c761920241a1cac0b1dbfe9d7107917f62","target":"graph","created_at":"2026-07-05T11:36:55Z","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/2412.06136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning large language models (LLMs) for specific tasks requires diverse, high-quality training data. However, obtaining sufficient relevant data remains a significant challenge. Existing data synthesis methods either depend on extensive seed datasets or struggle to balance task relevance and data diversity. To address these challenges, we propose Attribute-guided multI-hop Data Expansion (AIDE), a novel data synthesis framework that uses a multi-hop process to expand very few seed data points while ensuring data diversity and task relevance. AIDE extracts the main topic and key knowledge ","authors_text":"Fang Liu, Jiayu Li, Xuan Zhu, Yanjun Qi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T01:39:16Z","title":"AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06136","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":"sha256:7313353ae32072d1cadf1fb975a2d6061f5ba825e9cb65957dfe0060ffe57674","target":"record","created_at":"2026-07-05T11:36:55Z","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":"9d8b4ccf08461449f3be745797e6b29586478aa238620085f1011c668b3504dc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T01:39:16Z","title_canon_sha256":"a41062a59ee45e3efea9a2998dad23cc0d716b34ea9369b104a9c35e465be78d"},"schema_version":"1.0","source":{"id":"2412.06136","kind":"arxiv","version":2}},"canonical_sha256":"b932e28bba00e7b927fd6803ffc4394f2a95dd2c8d5419b3ab793cab1c31d223","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b932e28bba00e7b927fd6803ffc4394f2a95dd2c8d5419b3ab793cab1c31d223","first_computed_at":"2026-07-05T11:36:55.051836Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:55.051836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ISYXkm1sUXxGRNfrjhNadhPQ1y82sFgxTfY7jJYs8GxUHn8Q2aW0Lve7oXMvopqhIFB917YvF5SkC+GPd0XKCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:55.052367Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.06136","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7313353ae32072d1cadf1fb975a2d6061f5ba825e9cb65957dfe0060ffe57674","sha256:18864b6c726abe48038f87f9e46cf9c761920241a1cac0b1dbfe9d7107917f62"],"state_sha256":"3d1a0ba807975ec3c6853f8336808ae539d2763990b0d26b91d1966f21092e36"}