{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C4YFIFLRLBNPEQ2PBOWZRJNDZ6","short_pith_number":"pith:C4YFIFLR","schema_version":"1.0","canonical_sha256":"1730541571585af2434f0bad98a5a3cf8005e92a73e50e2dd944595473c5889d","source":{"kind":"arxiv","id":"2605.30407","version":1},"attestation_state":"computed","paper":{"title":"Exploring Autonomous Agentic Data Engineering for Model Specialization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiang Bian, Jingjing Wang, Jingsheng Zheng, Jintian Zhang, Kewei Xu, Runnan Fang, Shumin Deng, Xiangyuan Ru, Ye Liu, Yujie Luo, Yuqi Zhu, Zang Li, Zheng Wei","submitted_at":"2026-05-28T17:50:10Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated strong performance on general tasks, while often struggling to adapt to specialized domains without high-quality domain-specific data. Existing LLM-based data curation methods primarily rely on human-designed workflows, leaving it unexamined whether LLMs can autonomously execute an end-to-end data engineering pipeline for model specialization. We formalize \\textbf{Autonomous Agentic Data Engineering}, a novel task designed to evaluate LLMs as autonomous data engineers that drive model specialization through end-to-end data curation. We frame data "},"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":"2605.30407","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T17:50:10Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"b0f9e8025326644602c615e9c10aba3cac67a183c8d33a2439ea8f93aaed7982","abstract_canon_sha256":"016bb3e4c0e493e423dce820ff4c2d25212ad80e0ae4dbb4ce3c5436a051021f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T00:02:09.382242Z","signature_b64":"8q6/l0Mj5PcZIxjZne3zIiAwbyB6PC1cX9WAR/Hbz6MMb+sFQI3mWN9HeJ50OGrdssh/QGF1mzArTNUC2CbUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1730541571585af2434f0bad98a5a3cf8005e92a73e50e2dd944595473c5889d","last_reissued_at":"2026-06-01T00:02:09.381748Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T00:02:09.381748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Autonomous Agentic Data Engineering for Model Specialization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiang Bian, Jingjing Wang, Jingsheng Zheng, Jintian Zhang, Kewei Xu, Runnan Fang, Shumin Deng, Xiangyuan Ru, Ye Liu, Yujie Luo, Yuqi Zhu, Zang Li, Zheng Wei","submitted_at":"2026-05-28T17:50:10Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated strong performance on general tasks, while often struggling to adapt to specialized domains without high-quality domain-specific data. Existing LLM-based data curation methods primarily rely on human-designed workflows, leaving it unexamined whether LLMs can autonomously execute an end-to-end data engineering pipeline for model specialization. We formalize \\textbf{Autonomous Agentic Data Engineering}, a novel task designed to evaluate LLMs as autonomous data engineers that drive model specialization through end-to-end data curation. We frame data "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30407","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/2605.30407/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":"2605.30407","created_at":"2026-06-01T00:02:09.381816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30407v1","created_at":"2026-06-01T00:02:09.381816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30407","created_at":"2026-06-01T00:02:09.381816+00:00"},{"alias_kind":"pith_short_12","alias_value":"C4YFIFLRLBNP","created_at":"2026-06-01T00:02:09.381816+00:00"},{"alias_kind":"pith_short_16","alias_value":"C4YFIFLRLBNPEQ2P","created_at":"2026-06-01T00:02:09.381816+00:00"},{"alias_kind":"pith_short_8","alias_value":"C4YFIFLR","created_at":"2026-06-01T00:02:09.381816+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/C4YFIFLRLBNPEQ2PBOWZRJNDZ6","json":"https://pith.science/pith/C4YFIFLRLBNPEQ2PBOWZRJNDZ6.json","graph_json":"https://pith.science/api/pith-number/C4YFIFLRLBNPEQ2PBOWZRJNDZ6/graph.json","events_json":"https://pith.science/api/pith-number/C4YFIFLRLBNPEQ2PBOWZRJNDZ6/events.json","paper":"https://pith.science/paper/C4YFIFLR"},"agent_actions":{"view_html":"https://pith.science/pith/C4YFIFLRLBNPEQ2PBOWZRJNDZ6","download_json":"https://pith.science/pith/C4YFIFLRLBNPEQ2PBOWZRJNDZ6.json","view_paper":"https://pith.science/paper/C4YFIFLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30407&json=true","fetch_graph":"https://pith.science/api/pith-number/C4YFIFLRLBNPEQ2PBOWZRJNDZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/C4YFIFLRLBNPEQ2PBOWZRJNDZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C4YFIFLRLBNPEQ2PBOWZRJNDZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C4YFIFLRLBNPEQ2PBOWZRJNDZ6/action/storage_attestation","attest_author":"https://pith.science/pith/C4YFIFLRLBNPEQ2PBOWZRJNDZ6/action/author_attestation","sign_citation":"https://pith.science/pith/C4YFIFLRLBNPEQ2PBOWZRJNDZ6/action/citation_signature","submit_replication":"https://pith.science/pith/C4YFIFLRLBNPEQ2PBOWZRJNDZ6/action/replication_record"}},"created_at":"2026-06-01T00:02:09.381816+00:00","updated_at":"2026-06-01T00:02:09.381816+00:00"}