{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XEZOFC52ADT3SJ75NAB77RBZJ4","short_pith_number":"pith:XEZOFC52","schema_version":"1.0","canonical_sha256":"b932e28bba00e7b927fd6803ffc4394f2a95dd2c8d5419b3ab793cab1c31d223","source":{"kind":"arxiv","id":"2412.06136","version":2},"attestation_state":"computed","paper":{"title":"AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fang Liu, Jiayu Li, Xuan Zhu, Yanjun Qi","submitted_at":"2024-12-09T01:39:16Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.06136","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-09T01:39:16Z","cross_cats_sorted":[],"title_canon_sha256":"a41062a59ee45e3efea9a2998dad23cc0d716b34ea9369b104a9c35e465be78d","abstract_canon_sha256":"9d8b4ccf08461449f3be745797e6b29586478aa238620085f1011c668b3504dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:55.052367Z","signature_b64":"ISYXkm1sUXxGRNfrjhNadhPQ1y82sFgxTfY7jJYs8GxUHn8Q2aW0Lve7oXMvopqhIFB917YvF5SkC+GPd0XKCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b932e28bba00e7b927fd6803ffc4394f2a95dd2c8d5419b3ab793cab1c31d223","last_reissued_at":"2026-07-05T11:36:55.051836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:55.051836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AIDE: Attribute-Guided MultI-Hop Data Expansion for Data Scarcity in Task-Specific Fine-tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fang Liu, Jiayu Li, Xuan Zhu, Yanjun Qi","submitted_at":"2024-12-09T01:39:16Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06136","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2412.06136/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.06136","created_at":"2026-07-05T11:36:55.051893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06136v2","created_at":"2026-07-05T11:36:55.051893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06136","created_at":"2026-07-05T11:36:55.051893+00:00"},{"alias_kind":"pith_short_12","alias_value":"XEZOFC52ADT3","created_at":"2026-07-05T11:36:55.051893+00:00"},{"alias_kind":"pith_short_16","alias_value":"XEZOFC52ADT3SJ75","created_at":"2026-07-05T11:36:55.051893+00:00"},{"alias_kind":"pith_short_8","alias_value":"XEZOFC52","created_at":"2026-07-05T11:36:55.051893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XEZOFC52ADT3SJ75NAB77RBZJ4","json":"https://pith.science/pith/XEZOFC52ADT3SJ75NAB77RBZJ4.json","graph_json":"https://pith.science/api/pith-number/XEZOFC52ADT3SJ75NAB77RBZJ4/graph.json","events_json":"https://pith.science/api/pith-number/XEZOFC52ADT3SJ75NAB77RBZJ4/events.json","paper":"https://pith.science/paper/XEZOFC52"},"agent_actions":{"view_html":"https://pith.science/pith/XEZOFC52ADT3SJ75NAB77RBZJ4","download_json":"https://pith.science/pith/XEZOFC52ADT3SJ75NAB77RBZJ4.json","view_paper":"https://pith.science/paper/XEZOFC52","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06136&json=true","fetch_graph":"https://pith.science/api/pith-number/XEZOFC52ADT3SJ75NAB77RBZJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/XEZOFC52ADT3SJ75NAB77RBZJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XEZOFC52ADT3SJ75NAB77RBZJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XEZOFC52ADT3SJ75NAB77RBZJ4/action/storage_attestation","attest_author":"https://pith.science/pith/XEZOFC52ADT3SJ75NAB77RBZJ4/action/author_attestation","sign_citation":"https://pith.science/pith/XEZOFC52ADT3SJ75NAB77RBZJ4/action/citation_signature","submit_replication":"https://pith.science/pith/XEZOFC52ADT3SJ75NAB77RBZJ4/action/replication_record"}},"created_at":"2026-07-05T11:36:55.051893+00:00","updated_at":"2026-07-05T11:36:55.051893+00:00"}