{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4YSTDOABSB3FM2PJ7FFQRF4TO6","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":"be1593dfd441840acb8766a5b05d79851370e543e9fe2f7817677a603c4a24d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T09:24:55Z","title_canon_sha256":"259687e0b976400860f129e9e80cb7ae114863ec49f9420be461f039fdc50480"},"schema_version":"1.0","source":{"id":"2410.03258","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.03258","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"arxiv_version","alias_value":"2410.03258v1","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03258","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"pith_short_12","alias_value":"4YSTDOABSB3F","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"pith_short_16","alias_value":"4YSTDOABSB3FM2PJ","created_at":"2026-07-05T10:54:37Z"},{"alias_kind":"pith_short_8","alias_value":"4YSTDOAB","created_at":"2026-07-05T10:54:37Z"}],"graph_snapshots":[{"event_id":"sha256:0f1d36edab66692e562b21df91030bbb1fa86729a8e6043acf9d249625c88227","target":"graph","created_at":"2026-07-05T10:54:37Z","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/2410.03258/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we show a fundamental limitation in vocabulary adaptation approaches that use Byte-Pair Encoding (BPE) tokenization scheme for fine-tuning pretrained language models (PLMs) to expert domains. Current approaches trivially append the target domain-specific vocabulary at the end of the PLM vocabulary. This approach leads to a lower priority score and causes sub-optimal tokenization in BPE that iteratively uses merge rules to tokenize a given text. To mitigate this issue, we propose AdaptBPE where the BPE tokenization initialization phase is modified to first perform the longest stri","authors_text":"Gunjan Balde, Mainack Mondal, Niloy Ganguly, Soumyadeep Roy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T09:24:55Z","title":"Adaptive BPE Tokenization for Enhanced Vocabulary Adaptation in Finetuning Pretrained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03258","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":"sha256:3da1d0be5a25295e846e4a225d42b18349f6a6c72eb0537533951c5008ea7681","target":"record","created_at":"2026-07-05T10:54:37Z","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":"be1593dfd441840acb8766a5b05d79851370e543e9fe2f7817677a603c4a24d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-04T09:24:55Z","title_canon_sha256":"259687e0b976400860f129e9e80cb7ae114863ec49f9420be461f039fdc50480"},"schema_version":"1.0","source":{"id":"2410.03258","kind":"arxiv","version":1}},"canonical_sha256":"e62531b80190765669e9f94b08979377ad2f87e77c2e7254aba0675cdfc32804","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e62531b80190765669e9f94b08979377ad2f87e77c2e7254aba0675cdfc32804","first_computed_at":"2026-07-05T10:54:37.257406Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:37.257406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dNN0tch89z9nIspfEUPjTiSqM+QYjb+cCONhtazAGJEbCKG6rmL5ERw/wL9kiTw0TlQRyIYDv932Kpb4TE2aAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:37.257967Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.03258","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3da1d0be5a25295e846e4a225d42b18349f6a6c72eb0537533951c5008ea7681","sha256:0f1d36edab66692e562b21df91030bbb1fa86729a8e6043acf9d249625c88227"],"state_sha256":"79e5a6a508b9ddf44834d459fa0d4355782b9c9303d6f630d2c94b3a18b9f4f1"}