{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6RYCS34NLP2WCKD4CVQISCYSOI","short_pith_number":"pith:6RYCS34N","schema_version":"1.0","canonical_sha256":"f470296f8d5bf561287c1560890b12720a91645cd807ca8ecd3ba553421d67a1","source":{"kind":"arxiv","id":"2511.07380","version":2},"attestation_state":"computed","paper":{"title":"Mining Useful General Data for Low-Resource Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongcheng Liu, Pingjie Wang, Shuo Tang, Yanfeng Wang, Yaxin Du, Yusheng Liao, Yu Wang, Ziqing Fan","submitted_at":"2025-11-10T18:41:23Z","abstract_excerpt":"Adapting large language models (LLMs) to low-resource domains remains challenging due to the scarcity of domain-specific data. While in-domain data is limited, there exists a vast amount of general-domain data that shares similar question-answer formats and reasoning patterns with domain tasks. This observation raises an important question: can useful general-domain data be mined to improve low-resource domain adaptation? Our initial findings show that general-domain chain-of-thought data contains useful auxiliary signals for domain adaptation, even without careful selection. This observation "},"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":"2511.07380","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-10T18:41:23Z","cross_cats_sorted":[],"title_canon_sha256":"50b327f310fb5714e5e8c53ea752998865ab86e89c7c73d04d61a12395cfaddc","abstract_canon_sha256":"77caaa0338bac8d7533e1731867d3182fd5ef88676f094d0071372996e94ede7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:03.992414Z","signature_b64":"zJF0TxTzqm929rwSiBbwSQrQFCDPcbiL3hs/7ccqwdbe4J/LDXrSv6tzjPf/3NVoWDwUocCwJK69tGmBUF9/CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f470296f8d5bf561287c1560890b12720a91645cd807ca8ecd3ba553421d67a1","last_reissued_at":"2026-06-08T01:05:03.991349Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:03.991349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mining Useful General Data for Low-Resource Domain Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongcheng Liu, Pingjie Wang, Shuo Tang, Yanfeng Wang, Yaxin Du, Yusheng Liao, Yu Wang, Ziqing Fan","submitted_at":"2025-11-10T18:41:23Z","abstract_excerpt":"Adapting large language models (LLMs) to low-resource domains remains challenging due to the scarcity of domain-specific data. While in-domain data is limited, there exists a vast amount of general-domain data that shares similar question-answer formats and reasoning patterns with domain tasks. This observation raises an important question: can useful general-domain data be mined to improve low-resource domain adaptation? Our initial findings show that general-domain chain-of-thought data contains useful auxiliary signals for domain adaptation, even without careful selection. This observation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.07380","kind":"arxiv","version":2},"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/2511.07380/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":"2511.07380","created_at":"2026-06-08T01:05:03.991492+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.07380v2","created_at":"2026-06-08T01:05:03.991492+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.07380","created_at":"2026-06-08T01:05:03.991492+00:00"},{"alias_kind":"pith_short_12","alias_value":"6RYCS34NLP2W","created_at":"2026-06-08T01:05:03.991492+00:00"},{"alias_kind":"pith_short_16","alias_value":"6RYCS34NLP2WCKD4","created_at":"2026-06-08T01:05:03.991492+00:00"},{"alias_kind":"pith_short_8","alias_value":"6RYCS34N","created_at":"2026-06-08T01:05:03.991492+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.27991","citing_title":"Gradient-Flow Optimization as Dynamic Random-Effects Inference: Testing and Early Stopping with Applications to Deep Learning","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00571","citing_title":"On the Difficulty of Learning a Meta-network for Training Data Selection","ref_index":106,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6RYCS34NLP2WCKD4CVQISCYSOI","json":"https://pith.science/pith/6RYCS34NLP2WCKD4CVQISCYSOI.json","graph_json":"https://pith.science/api/pith-number/6RYCS34NLP2WCKD4CVQISCYSOI/graph.json","events_json":"https://pith.science/api/pith-number/6RYCS34NLP2WCKD4CVQISCYSOI/events.json","paper":"https://pith.science/paper/6RYCS34N"},"agent_actions":{"view_html":"https://pith.science/pith/6RYCS34NLP2WCKD4CVQISCYSOI","download_json":"https://pith.science/pith/6RYCS34NLP2WCKD4CVQISCYSOI.json","view_paper":"https://pith.science/paper/6RYCS34N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.07380&json=true","fetch_graph":"https://pith.science/api/pith-number/6RYCS34NLP2WCKD4CVQISCYSOI/graph.json","fetch_events":"https://pith.science/api/pith-number/6RYCS34NLP2WCKD4CVQISCYSOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6RYCS34NLP2WCKD4CVQISCYSOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6RYCS34NLP2WCKD4CVQISCYSOI/action/storage_attestation","attest_author":"https://pith.science/pith/6RYCS34NLP2WCKD4CVQISCYSOI/action/author_attestation","sign_citation":"https://pith.science/pith/6RYCS34NLP2WCKD4CVQISCYSOI/action/citation_signature","submit_replication":"https://pith.science/pith/6RYCS34NLP2WCKD4CVQISCYSOI/action/replication_record"}},"created_at":"2026-06-08T01:05:03.991492+00:00","updated_at":"2026-06-08T01:05:03.991492+00:00"}