{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:C4YFIFLRLBNPEQ2PBOWZRJNDZ6","short_pith_number":"pith:C4YFIFLR","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"},"canonical_sha256":"1730541571585af2434f0bad98a5a3cf8005e92a73e50e2dd944595473c5889d","source":{"kind":"arxiv","id":"2605.30407","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30407","created_at":"2026-06-01T00:02:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30407v1","created_at":"2026-06-01T00:02:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30407","created_at":"2026-06-01T00:02:09Z"},{"alias_kind":"pith_short_12","alias_value":"C4YFIFLRLBNP","created_at":"2026-06-01T00:02:09Z"},{"alias_kind":"pith_short_16","alias_value":"C4YFIFLRLBNPEQ2P","created_at":"2026-06-01T00:02:09Z"},{"alias_kind":"pith_short_8","alias_value":"C4YFIFLR","created_at":"2026-06-01T00:02:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:C4YFIFLRLBNPEQ2PBOWZRJNDZ6","target":"record","payload":{"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"},"canonical_sha256":"1730541571585af2434f0bad98a5a3cf8005e92a73e50e2dd944595473c5889d","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"},"source_kind":"arxiv","source_id":"2605.30407","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T00:02:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o+rHuCcd+XJ3fT9QSvalATObbqUDYeazAkSpeIqC/aSNsPHG49+7qq+zoBjz1EyQoVwXGgvUdOKyIVl1ZX7OAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T23:01:19.010891Z"},"content_sha256":"6f64711923a36f6b4d9e4e4b01dff6861f4b2ce8b0729547cb4658a34863da45","schema_version":"1.0","event_id":"sha256:6f64711923a36f6b4d9e4e4b01dff6861f4b2ce8b0729547cb4658a34863da45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:C4YFIFLRLBNPEQ2PBOWZRJNDZ6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-01T00:02:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"giimI/WCTP/SqRf9BtEm058M0jlc2KN9WucC/71uS0Es/eMMuuqAcwAxAqFRdVOYAPbgZ5oVOOVXF1GNn3LsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T23:01:19.011712Z"},"content_sha256":"0f27cbb87b65294dab3320f16806297c19517481ac7c9e3f8e28f4d874162428","schema_version":"1.0","event_id":"sha256:0f27cbb87b65294dab3320f16806297c19517481ac7c9e3f8e28f4d874162428"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C4YFIFLRLBNPEQ2PBOWZRJNDZ6/bundle.json","state_url":"https://pith.science/pith/C4YFIFLRLBNPEQ2PBOWZRJNDZ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C4YFIFLRLBNPEQ2PBOWZRJNDZ6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T23:01:19Z","links":{"resolver":"https://pith.science/pith/C4YFIFLRLBNPEQ2PBOWZRJNDZ6","bundle":"https://pith.science/pith/C4YFIFLRLBNPEQ2PBOWZRJNDZ6/bundle.json","state":"https://pith.science/pith/C4YFIFLRLBNPEQ2PBOWZRJNDZ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C4YFIFLRLBNPEQ2PBOWZRJNDZ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C4YFIFLRLBNPEQ2PBOWZRJNDZ6","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":"016bb3e4c0e493e423dce820ff4c2d25212ad80e0ae4dbb4ce3c5436a051021f","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T17:50:10Z","title_canon_sha256":"b0f9e8025326644602c615e9c10aba3cac67a183c8d33a2439ea8f93aaed7982"},"schema_version":"1.0","source":{"id":"2605.30407","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30407","created_at":"2026-06-01T00:02:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30407v1","created_at":"2026-06-01T00:02:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30407","created_at":"2026-06-01T00:02:09Z"},{"alias_kind":"pith_short_12","alias_value":"C4YFIFLRLBNP","created_at":"2026-06-01T00:02:09Z"},{"alias_kind":"pith_short_16","alias_value":"C4YFIFLRLBNPEQ2P","created_at":"2026-06-01T00:02:09Z"},{"alias_kind":"pith_short_8","alias_value":"C4YFIFLR","created_at":"2026-06-01T00:02:09Z"}],"graph_snapshots":[{"event_id":"sha256:0f27cbb87b65294dab3320f16806297c19517481ac7c9e3f8e28f4d874162428","target":"graph","created_at":"2026-06-01T00:02:09Z","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/2605.30407/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T17:50:10Z","title":"Exploring Autonomous Agentic Data Engineering for Model Specialization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30407","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":"sha256:6f64711923a36f6b4d9e4e4b01dff6861f4b2ce8b0729547cb4658a34863da45","target":"record","created_at":"2026-06-01T00:02:09Z","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":"016bb3e4c0e493e423dce820ff4c2d25212ad80e0ae4dbb4ce3c5436a051021f","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T17:50:10Z","title_canon_sha256":"b0f9e8025326644602c615e9c10aba3cac67a183c8d33a2439ea8f93aaed7982"},"schema_version":"1.0","source":{"id":"2605.30407","kind":"arxiv","version":1}},"canonical_sha256":"1730541571585af2434f0bad98a5a3cf8005e92a73e50e2dd944595473c5889d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1730541571585af2434f0bad98a5a3cf8005e92a73e50e2dd944595473c5889d","first_computed_at":"2026-06-01T00:02:09.381748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T00:02:09.381748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8q6/l0Mj5PcZIxjZne3zIiAwbyB6PC1cX9WAR/Hbz6MMb+sFQI3mWN9HeJ50OGrdssh/QGF1mzArTNUC2CbUBg==","signature_status":"signed_v1","signed_at":"2026-06-01T00:02:09.382242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30407","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f64711923a36f6b4d9e4e4b01dff6861f4b2ce8b0729547cb4658a34863da45","sha256:0f27cbb87b65294dab3320f16806297c19517481ac7c9e3f8e28f4d874162428"],"state_sha256":"2b60a49d4d605cc3361e5ede2e8c31b8e72f03acc19d11458c24c489ff163a57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bYp1y+acoMnG1BYYW/1zFEWMWpj6PTInLFmcBGEgm+5b0sD4KpcPgHCS4ELSMj92XGUcCieHi2cz8b0fT0AeAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T23:01:19.016621Z","bundle_sha256":"8d6599dc2dafa55a416e9693ceea8509b0b4355a3c42d3e9232ed9c11ccbdb1f"}}