{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R227JTCS65FUGVH4XE6KASWWDK","short_pith_number":"pith:R227JTCS","schema_version":"1.0","canonical_sha256":"8eb5f4cc52f74b4354fcb93ca04ad61a84b0bd784478d7233151c2e81a9f889d","source":{"kind":"arxiv","id":"2401.14624","version":4},"attestation_state":"computed","paper":{"title":"Unearthing Large Scale Domain-Specific Knowledge from Public Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Conghui He, Dahua Lin, Hang Yan, Linyang Li, Qipeng Guo, Xipeng Qiu, Yunfan Shao, Zhaoye Fei, Zhiyuan Zeng","submitted_at":"2024-01-26T03:38:23Z","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"},"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":"2401.14624","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-26T03:38:23Z","cross_cats_sorted":[],"title_canon_sha256":"36bdc046cd5687db04e0c6daf2ec69249c1ed368455703cffba2a3bf38aa2494","abstract_canon_sha256":"1f0478a13498ef8cb43c978d290c220739b1d6ec14d3503cbbc1c0e721da7db7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:37.784523Z","signature_b64":"3F4m9/CuR7xYzMvcz2/0MoeGj9Yhg7sigtv9B86eQmmj4ZfwMhWQcdqTlox/4N3lm/fdIXoC7fd4NzXK8ndKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8eb5f4cc52f74b4354fcb93ca04ad61a84b0bd784478d7233151c2e81a9f889d","last_reissued_at":"2026-07-05T11:08:37.784033Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:37.784033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unearthing Large Scale Domain-Specific Knowledge from Public Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Conghui He, Dahua Lin, Hang Yan, Linyang Li, Qipeng Guo, Xipeng Qiu, Yunfan Shao, Zhaoye Fei, Zhiyuan Zeng","submitted_at":"2024-01-26T03:38:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14624","kind":"arxiv","version":4},"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/2401.14624/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":"2401.14624","created_at":"2026-07-05T11:08:37.784091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.14624v4","created_at":"2026-07-05T11:08:37.784091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14624","created_at":"2026-07-05T11:08:37.784091+00:00"},{"alias_kind":"pith_short_12","alias_value":"R227JTCS65FU","created_at":"2026-07-05T11:08:37.784091+00:00"},{"alias_kind":"pith_short_16","alias_value":"R227JTCS65FUGVH4","created_at":"2026-07-05T11:08:37.784091+00:00"},{"alias_kind":"pith_short_8","alias_value":"R227JTCS","created_at":"2026-07-05T11:08:37.784091+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/R227JTCS65FUGVH4XE6KASWWDK","json":"https://pith.science/pith/R227JTCS65FUGVH4XE6KASWWDK.json","graph_json":"https://pith.science/api/pith-number/R227JTCS65FUGVH4XE6KASWWDK/graph.json","events_json":"https://pith.science/api/pith-number/R227JTCS65FUGVH4XE6KASWWDK/events.json","paper":"https://pith.science/paper/R227JTCS"},"agent_actions":{"view_html":"https://pith.science/pith/R227JTCS65FUGVH4XE6KASWWDK","download_json":"https://pith.science/pith/R227JTCS65FUGVH4XE6KASWWDK.json","view_paper":"https://pith.science/paper/R227JTCS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.14624&json=true","fetch_graph":"https://pith.science/api/pith-number/R227JTCS65FUGVH4XE6KASWWDK/graph.json","fetch_events":"https://pith.science/api/pith-number/R227JTCS65FUGVH4XE6KASWWDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R227JTCS65FUGVH4XE6KASWWDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R227JTCS65FUGVH4XE6KASWWDK/action/storage_attestation","attest_author":"https://pith.science/pith/R227JTCS65FUGVH4XE6KASWWDK/action/author_attestation","sign_citation":"https://pith.science/pith/R227JTCS65FUGVH4XE6KASWWDK/action/citation_signature","submit_replication":"https://pith.science/pith/R227JTCS65FUGVH4XE6KASWWDK/action/replication_record"}},"created_at":"2026-07-05T11:08:37.784091+00:00","updated_at":"2026-07-05T11:08:37.784091+00:00"}