{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OCV6PYIZOA4HBNTPGFABMPDDVW","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":"c8435f50a5ec19d201ec348ff45e2cc67e31ef78403587214a3288c6635f76bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T18:28:41Z","title_canon_sha256":"809945b4762bbab6e34409c74a0eea09dfa03bc2e84a72ecf25d66117afc7baf"},"schema_version":"1.0","source":{"id":"2412.15151","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.15151","created_at":"2026-07-05T10:13:45Z"},{"alias_kind":"arxiv_version","alias_value":"2412.15151v3","created_at":"2026-07-05T10:13:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15151","created_at":"2026-07-05T10:13:45Z"},{"alias_kind":"pith_short_12","alias_value":"OCV6PYIZOA4H","created_at":"2026-07-05T10:13:45Z"},{"alias_kind":"pith_short_16","alias_value":"OCV6PYIZOA4HBNTP","created_at":"2026-07-05T10:13:45Z"},{"alias_kind":"pith_short_8","alias_value":"OCV6PYIZ","created_at":"2026-07-05T10:13:45Z"}],"graph_snapshots":[{"event_id":"sha256:11f4e9cc624b3c760e34465bddb925837ee0e97aac91aaefa7ae060903c5006e","target":"graph","created_at":"2026-07-05T10:13:45Z","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/2412.15151/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities on various tasks, while the further evolvement is limited to the lack of high-quality training data. In addition, traditional training approaches rely too much on expert-labeled data, setting a ceiling on the performance of LLMs. To address this issue, we propose a novel paradigm named LANCE (LANguage models as Continuous self-Evolving data engineers) that enables LLMs to train themselves by autonomously generating, cleaning, reviewing, and annotating data with preference information. Our approach demonstrates that LLMs can","authors_text":"Daling Wang, Kaisong Song, Ming Wang, Peidong Wang, Shi Feng, Xiaocui Yang, Yifei Zhang, Zhiming Ma","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T18:28:41Z","title":"Language Models as Continuous Self-Evolving Data Engineers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15151","kind":"arxiv","version":3},"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":"sha256:83d703e9715890ce5c2613bf1a50f95ab98e9595db6e11b818b1870cfb902310","target":"record","created_at":"2026-07-05T10:13:45Z","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":"c8435f50a5ec19d201ec348ff45e2cc67e31ef78403587214a3288c6635f76bc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-19T18:28:41Z","title_canon_sha256":"809945b4762bbab6e34409c74a0eea09dfa03bc2e84a72ecf25d66117afc7baf"},"schema_version":"1.0","source":{"id":"2412.15151","kind":"arxiv","version":3}},"canonical_sha256":"70abe7e119703870b66f3140163c63ada6ea2396451325c15cd9701b23a4bac7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70abe7e119703870b66f3140163c63ada6ea2396451325c15cd9701b23a4bac7","first_computed_at":"2026-07-05T10:13:45.770702Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:45.770702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9dnfrgAE0Y6OUmOrYaGYTDzYZvAnzv6J+cG6FEXWBupgqouvb/Y0PtTwUxRP8FMBgpYom51QR/exJ1/Z7IsBDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:45.771477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.15151","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83d703e9715890ce5c2613bf1a50f95ab98e9595db6e11b818b1870cfb902310","sha256:11f4e9cc624b3c760e34465bddb925837ee0e97aac91aaefa7ae060903c5006e"],"state_sha256":"c3086ceaf9461811012fb68d9766b6bd92c9ecfce1c708ab83f3bab3253070c4"}