{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O5B5E2R25W7P7TESDAATW5HNKC","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":"f2dd7ffe088aa469aa876a27bfeac1bb80b310af9067ae4c3ecda2e56fcdf8bc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T11:32:10Z","title_canon_sha256":"1a58ac9521f6936644f3deca201d7ac4db811ff61bc0ba8a7673a70a6e0d0b38"},"schema_version":"1.0","source":{"id":"2608.03494","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03494","created_at":"2026-08-05T01:35:57Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03494v1","created_at":"2026-08-05T01:35:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03494","created_at":"2026-08-05T01:35:57Z"},{"alias_kind":"pith_short_12","alias_value":"O5B5E2R25W7P","created_at":"2026-08-05T01:35:57Z"},{"alias_kind":"pith_short_16","alias_value":"O5B5E2R25W7P7TES","created_at":"2026-08-05T01:35:57Z"},{"alias_kind":"pith_short_8","alias_value":"O5B5E2R2","created_at":"2026-08-05T01:35:57Z"}],"graph_snapshots":[{"event_id":"sha256:928fab0243c4c4c0071f1e87a00162ad77278d92d95316bd6ed91037819bd618","target":"graph","created_at":"2026-08-05T01:35:57Z","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/2608.03494/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vocabulary extension is an efficient way to adapt pretrained large language models (LLMs) to new languages, but the initialization of newly added token embeddings can strongly affect continued pre-training (CPT) efficiency. We present a systematic study of more than 20 initialization strategies for Hindi vocabulary extension in Nemotron-3-Nano-30B-A3B. Our comparison spans vocabulary-averaging baselines; external and learned initialization methods, including FOCUS, top-k semantic retrieval, and residual MLP mappings; subword composition; norm calibration; and input-output asymmetry. We find th","authors_text":"Niranjan Wartikar, Raviraj Joshi, Sanjay Singh Chauhan, Utkarsh Vaidya","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T11:32:10Z","title":"Beyond Initialization Loss: A Systematic Study of Token Embedding Initialization Strategies for LLM Vocabulary Extension"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03494","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":"sha256:2e9245caa2dbe29eaa59717d6a47534b175caeeb92701f7d9b4fdb4612bd81c1","target":"record","created_at":"2026-08-05T01:35:57Z","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":"f2dd7ffe088aa469aa876a27bfeac1bb80b310af9067ae4c3ecda2e56fcdf8bc","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-08-04T11:32:10Z","title_canon_sha256":"1a58ac9521f6936644f3deca201d7ac4db811ff61bc0ba8a7673a70a6e0d0b38"},"schema_version":"1.0","source":{"id":"2608.03494","kind":"arxiv","version":1}},"canonical_sha256":"7743d26a3aedbeffcc9218013b74ed50b8c59feaab557f421a9b1d9d6bb569dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7743d26a3aedbeffcc9218013b74ed50b8c59feaab557f421a9b1d9d6bb569dc","first_computed_at":"2026-08-05T01:35:57.774963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:35:57.774963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jPGNuUzrbTCOutHonm4eEVM9GkDbbHI4+pFDOpJ5GBqupE3HmAlO9B1z6joBH2y3NIRuctY347HEy18t7VcwBg==","signature_status":"signed_v1","signed_at":"2026-08-05T01:35:57.776763Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03494","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e9245caa2dbe29eaa59717d6a47534b175caeeb92701f7d9b4fdb4612bd81c1","sha256:928fab0243c4c4c0071f1e87a00162ad77278d92d95316bd6ed91037819bd618"],"state_sha256":"ed5a3ad004f6e4c40ab8f6de16ed485cf42f685a4611539f82823c7ed4e8e01b"}