{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:N6LEERFVX3L7IWR4JOV62JN2VE","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":"89728fc7e92d592ee6d352c0f599769275b29602081aa9b61c0a98627d0f7d38","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T08:27:32Z","title_canon_sha256":"025e89d922cf2fb9327f6619909eae0996bb5205ed7fba514948317392bb01c2"},"schema_version":"1.0","source":{"id":"2403.09167","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09167","created_at":"2026-07-05T07:56:06Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09167v1","created_at":"2026-07-05T07:56:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09167","created_at":"2026-07-05T07:56:06Z"},{"alias_kind":"pith_short_12","alias_value":"N6LEERFVX3L7","created_at":"2026-07-05T07:56:06Z"},{"alias_kind":"pith_short_16","alias_value":"N6LEERFVX3L7IWR4","created_at":"2026-07-05T07:56:06Z"},{"alias_kind":"pith_short_8","alias_value":"N6LEERFV","created_at":"2026-07-05T07:56:06Z"}],"graph_snapshots":[{"event_id":"sha256:8c9761d356e4e292247d0a28475ad878fc152cfcd8cfeb3570e42b30cd8ef5ae","target":"graph","created_at":"2026-07-05T07:56:06Z","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/2403.09167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The efficacy of large language models (LLMs) is heavily dependent on the quality of the underlying data, particularly within specialized domains. A common challenge when fine-tuning LLMs for domain-specific applications is the potential degradation of the model's generalization capabilities. To address these issues, we propose a two-stage approach for the construction of production prompts designed to yield high-quality data. This method involves the generation of a diverse array of prompts that encompass a broad spectrum of tasks and exhibit a rich variety of expressions. Furthermore, we intr","authors_text":"Chaoyang Mei, Jianwei Sun, Kaiyu Zheng, Linlin Wei, Ming Cui, Na Liu, Tianyi Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T08:27:32Z","title":"Dial-insight: Fine-tuning Large Language Models with High-Quality Domain-Specific Data Preventing Capability Collapse"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09167","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":"sha256:1c7e0d91d518adecd719269fd7da6fd9c93d7eb070a2c8dceaeb43ed3db0dd06","target":"record","created_at":"2026-07-05T07:56:06Z","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":"89728fc7e92d592ee6d352c0f599769275b29602081aa9b61c0a98627d0f7d38","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-14T08:27:32Z","title_canon_sha256":"025e89d922cf2fb9327f6619909eae0996bb5205ed7fba514948317392bb01c2"},"schema_version":"1.0","source":{"id":"2403.09167","kind":"arxiv","version":1}},"canonical_sha256":"6f964244b5bed7f45a3c4babed25baa9225075c39342dc50224bb598cecac5fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6f964244b5bed7f45a3c4babed25baa9225075c39342dc50224bb598cecac5fd","first_computed_at":"2026-07-05T07:56:06.293486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:06.293486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d5MYK+Kd+yE2eOhZyfYfjuqU8dIrzGuX92ArVe+Oc0KrpEBzhoLmLNcTDY+5e7gHy86GIdbHewYSU2YYVbj4DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:06.293944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09167","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c7e0d91d518adecd719269fd7da6fd9c93d7eb070a2c8dceaeb43ed3db0dd06","sha256:8c9761d356e4e292247d0a28475ad878fc152cfcd8cfeb3570e42b30cd8ef5ae"],"state_sha256":"a475b102b4b7b7e867fa00dc4c79e5716cc7231a2a1262376ce494d3e4936073"}