{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LIYVWOU3VOFRC7C4QV43LUEUUG","short_pith_number":"pith:LIYVWOU3","schema_version":"1.0","canonical_sha256":"5a315b3a9bab8b117c5c8579b5d094a1aff1ebdea2eec437f28eb7f6d344c93b","source":{"kind":"arxiv","id":"2410.01188","version":1},"attestation_state":"computed","paper":{"title":"Gold Panning in Vocabulary: An Adaptive Method for Vocabulary Expansion of Domain-Specific LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changlong Sun, Chengyuan Liu, Fei Wu, Kun Kuang, Lizhi Qing, Shihang Wang, Yangyang Kang","submitted_at":"2024-10-02T02:47:39Z","abstract_excerpt":"While Large Language Models (LLMs) demonstrate impressive generation abilities, they frequently struggle when it comes to specialized domains due to their limited domain-specific knowledge. Studies on domain-specific LLMs resort to expanding the vocabulary before fine-tuning on domain-specific corpus, aiming to decrease the sequence length and enhance efficiency during decoding, without thoroughly investigating the results of vocabulary expansion to LLMs over different domains. Our pilot study reveals that expansion with only a subset of the entire vocabulary may lead to superior performance. "},"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":"2410.01188","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-02T02:47:39Z","cross_cats_sorted":[],"title_canon_sha256":"ff4b61cf20951b19a9ceabd94ea35b94a1d2867e1fb66183a1244ddad748406a","abstract_canon_sha256":"31c1e9c255552492c63440f64c110d966f5b4b2a61bbca9c6b26dc31fe098796"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:44.501207Z","signature_b64":"M5YfWuNfXu69kotmGEYPUB1EQye6BTpxbvklDy0OCULTsZd0E39AkiT0idCG3j6V+KfcHW718IKQtp2autl5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a315b3a9bab8b117c5c8579b5d094a1aff1ebdea2eec437f28eb7f6d344c93b","last_reissued_at":"2026-07-05T09:14:44.500797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:44.500797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gold Panning in Vocabulary: An Adaptive Method for Vocabulary Expansion of Domain-Specific LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changlong Sun, Chengyuan Liu, Fei Wu, Kun Kuang, Lizhi Qing, Shihang Wang, Yangyang Kang","submitted_at":"2024-10-02T02:47:39Z","abstract_excerpt":"While Large Language Models (LLMs) demonstrate impressive generation abilities, they frequently struggle when it comes to specialized domains due to their limited domain-specific knowledge. Studies on domain-specific LLMs resort to expanding the vocabulary before fine-tuning on domain-specific corpus, aiming to decrease the sequence length and enhance efficiency during decoding, without thoroughly investigating the results of vocabulary expansion to LLMs over different domains. Our pilot study reveals that expansion with only a subset of the entire vocabulary may lead to superior performance. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01188","kind":"arxiv","version":1},"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/2410.01188/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":"2410.01188","created_at":"2026-07-05T09:14:44.500854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.01188v1","created_at":"2026-07-05T09:14:44.500854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01188","created_at":"2026-07-05T09:14:44.500854+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIYVWOU3VOFR","created_at":"2026-07-05T09:14:44.500854+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIYVWOU3VOFRC7C4","created_at":"2026-07-05T09:14:44.500854+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIYVWOU3","created_at":"2026-07-05T09:14:44.500854+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/LIYVWOU3VOFRC7C4QV43LUEUUG","json":"https://pith.science/pith/LIYVWOU3VOFRC7C4QV43LUEUUG.json","graph_json":"https://pith.science/api/pith-number/LIYVWOU3VOFRC7C4QV43LUEUUG/graph.json","events_json":"https://pith.science/api/pith-number/LIYVWOU3VOFRC7C4QV43LUEUUG/events.json","paper":"https://pith.science/paper/LIYVWOU3"},"agent_actions":{"view_html":"https://pith.science/pith/LIYVWOU3VOFRC7C4QV43LUEUUG","download_json":"https://pith.science/pith/LIYVWOU3VOFRC7C4QV43LUEUUG.json","view_paper":"https://pith.science/paper/LIYVWOU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.01188&json=true","fetch_graph":"https://pith.science/api/pith-number/LIYVWOU3VOFRC7C4QV43LUEUUG/graph.json","fetch_events":"https://pith.science/api/pith-number/LIYVWOU3VOFRC7C4QV43LUEUUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIYVWOU3VOFRC7C4QV43LUEUUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIYVWOU3VOFRC7C4QV43LUEUUG/action/storage_attestation","attest_author":"https://pith.science/pith/LIYVWOU3VOFRC7C4QV43LUEUUG/action/author_attestation","sign_citation":"https://pith.science/pith/LIYVWOU3VOFRC7C4QV43LUEUUG/action/citation_signature","submit_replication":"https://pith.science/pith/LIYVWOU3VOFRC7C4QV43LUEUUG/action/replication_record"}},"created_at":"2026-07-05T09:14:44.500854+00:00","updated_at":"2026-07-05T09:14:44.500854+00:00"}