{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R227JTCS65FUGVH4XE6KASWWDK","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":"1f0478a13498ef8cb43c978d290c220739b1d6ec14d3503cbbc1c0e721da7db7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T03:38:23Z","title_canon_sha256":"36bdc046cd5687db04e0c6daf2ec69249c1ed368455703cffba2a3bf38aa2494"},"schema_version":"1.0","source":{"id":"2401.14624","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.14624","created_at":"2026-07-05T11:08:37Z"},{"alias_kind":"arxiv_version","alias_value":"2401.14624v4","created_at":"2026-07-05T11:08:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14624","created_at":"2026-07-05T11:08:37Z"},{"alias_kind":"pith_short_12","alias_value":"R227JTCS65FU","created_at":"2026-07-05T11:08:37Z"},{"alias_kind":"pith_short_16","alias_value":"R227JTCS65FUGVH4","created_at":"2026-07-05T11:08:37Z"},{"alias_kind":"pith_short_8","alias_value":"R227JTCS","created_at":"2026-07-05T11:08:37Z"}],"graph_snapshots":[{"event_id":"sha256:14fa4da78eebafb500a693bb92758ae249cd44bfb8dda9272f4e05b100dd9e8b","target":"graph","created_at":"2026-07-05T11:08:37Z","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/2401.14624/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 potential in various tasks, however, there remains a significant lack of open-source models and data for specific domains. Previous work has primarily focused on manually specifying resources and collecting high-quality data for specific domains, which is extremely time-consuming and labor-intensive. To address this limitation, we introduce large models into the data collection pipeline to guide the generation of domain-specific information and retrieve relevant data from Common Crawl (CC), a large public corpus. We refer to this approa","authors_text":"Conghui He, Dahua Lin, Hang Yan, Linyang Li, Qipeng Guo, Xipeng Qiu, Yunfan Shao, Zhaoye Fei, Zhiyuan Zeng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T03:38:23Z","title":"Unearthing Large Scale Domain-Specific Knowledge from Public Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14624","kind":"arxiv","version":4},"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:dbf5ad67520c587a17289243efbfd1014f54f7b56b364e7cce15fa388b4302b8","target":"record","created_at":"2026-07-05T11:08:37Z","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":"1f0478a13498ef8cb43c978d290c220739b1d6ec14d3503cbbc1c0e721da7db7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T03:38:23Z","title_canon_sha256":"36bdc046cd5687db04e0c6daf2ec69249c1ed368455703cffba2a3bf38aa2494"},"schema_version":"1.0","source":{"id":"2401.14624","kind":"arxiv","version":4}},"canonical_sha256":"8eb5f4cc52f74b4354fcb93ca04ad61a84b0bd784478d7233151c2e81a9f889d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8eb5f4cc52f74b4354fcb93ca04ad61a84b0bd784478d7233151c2e81a9f889d","first_computed_at":"2026-07-05T11:08:37.784033Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:37.784033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3F4m9/CuR7xYzMvcz2/0MoeGj9Yhg7sigtv9B86eQmmj4ZfwMhWQcdqTlox/4N3lm/fdIXoC7fd4NzXK8ndKDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:37.784523Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.14624","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbf5ad67520c587a17289243efbfd1014f54f7b56b364e7cce15fa388b4302b8","sha256:14fa4da78eebafb500a693bb92758ae249cd44bfb8dda9272f4e05b100dd9e8b"],"state_sha256":"0088da09f89dec18b6a8b42f0a8568ec8fc9d72b25b2078f30e01e599e01d5d3"}