{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EOAZUQSYEAPCLX7BMIZOQWXB73","short_pith_number":"pith:EOAZUQSY","schema_version":"1.0","canonical_sha256":"23819a4258201e25dfe16232e85ae1fee4a0ead41d7791174d7a849bf0cc1e6f","source":{"kind":"arxiv","id":"2411.14497","version":1},"attestation_state":"computed","paper":{"title":"Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Hang Zhou, Haochen Qin, Kai Han, Renren Jin, Yehui Tang, Yujie Yang, Yunhe Wang","submitted_at":"2024-11-21T02:30:53Z","abstract_excerpt":"The efficacy of large language models (LLMs) on downstream tasks usually hinges on instruction tuning, which relies critically on the quality of training data. Unfortunately, collecting high-quality and diverse data is both expensive and time-consuming. To mitigate this issue, we propose a novel Star-Agents framework, which automates the enhancement of data quality across datasets through multi-agent collaboration and assessment. The framework adopts a three-pronged strategy. It initially generates diverse instruction data with multiple LLM agents through a bespoke sampling method. Subsequentl"},"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":"2411.14497","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T02:30:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7d76ea2e696e428185da18c2f5cb7028415930e80b8abea91fbd90f8ccb35cf3","abstract_canon_sha256":"2dc334e259ec50d7c7407241612cf0294b116bd5ef46b44c94d4f1717bc45ad8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:52.240335Z","signature_b64":"nb7hA7iBH9de76MrfSZbXJGMXEdo/BLRVSntmWvMxv2DoTQIIt9J55GOatKXsXJqdS8s5FyXyVImN5ZCDTxxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23819a4258201e25dfe16232e85ae1fee4a0ead41d7791174d7a849bf0cc1e6f","last_reissued_at":"2026-07-05T09:38:52.239896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:52.239896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Hang Zhou, Haochen Qin, Kai Han, Renren Jin, Yehui Tang, Yujie Yang, Yunhe Wang","submitted_at":"2024-11-21T02:30:53Z","abstract_excerpt":"The efficacy of large language models (LLMs) on downstream tasks usually hinges on instruction tuning, which relies critically on the quality of training data. Unfortunately, collecting high-quality and diverse data is both expensive and time-consuming. To mitigate this issue, we propose a novel Star-Agents framework, which automates the enhancement of data quality across datasets through multi-agent collaboration and assessment. The framework adopts a three-pronged strategy. It initially generates diverse instruction data with multiple LLM agents through a bespoke sampling method. Subsequentl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14497","kind":"arxiv","version":1},"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/2411.14497/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":"2411.14497","created_at":"2026-07-05T09:38:52.239947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14497v1","created_at":"2026-07-05T09:38:52.239947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14497","created_at":"2026-07-05T09:38:52.239947+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOAZUQSYEAPC","created_at":"2026-07-05T09:38:52.239947+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOAZUQSYEAPCLX7B","created_at":"2026-07-05T09:38:52.239947+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOAZUQSY","created_at":"2026-07-05T09:38:52.239947+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/EOAZUQSYEAPCLX7BMIZOQWXB73","json":"https://pith.science/pith/EOAZUQSYEAPCLX7BMIZOQWXB73.json","graph_json":"https://pith.science/api/pith-number/EOAZUQSYEAPCLX7BMIZOQWXB73/graph.json","events_json":"https://pith.science/api/pith-number/EOAZUQSYEAPCLX7BMIZOQWXB73/events.json","paper":"https://pith.science/paper/EOAZUQSY"},"agent_actions":{"view_html":"https://pith.science/pith/EOAZUQSYEAPCLX7BMIZOQWXB73","download_json":"https://pith.science/pith/EOAZUQSYEAPCLX7BMIZOQWXB73.json","view_paper":"https://pith.science/paper/EOAZUQSY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14497&json=true","fetch_graph":"https://pith.science/api/pith-number/EOAZUQSYEAPCLX7BMIZOQWXB73/graph.json","fetch_events":"https://pith.science/api/pith-number/EOAZUQSYEAPCLX7BMIZOQWXB73/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOAZUQSYEAPCLX7BMIZOQWXB73/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOAZUQSYEAPCLX7BMIZOQWXB73/action/storage_attestation","attest_author":"https://pith.science/pith/EOAZUQSYEAPCLX7BMIZOQWXB73/action/author_attestation","sign_citation":"https://pith.science/pith/EOAZUQSYEAPCLX7BMIZOQWXB73/action/citation_signature","submit_replication":"https://pith.science/pith/EOAZUQSYEAPCLX7BMIZOQWXB73/action/replication_record"}},"created_at":"2026-07-05T09:38:52.239947+00:00","updated_at":"2026-07-05T09:38:52.239947+00:00"}