{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XN67PDONNH5GZSZ5FBTU2DQKMZ","short_pith_number":"pith:XN67PDON","schema_version":"1.0","canonical_sha256":"bb7df78dcd69fa6ccb3d28674d0e0a6669f9e408c5abd65832e9c9ec8fcf2b28","source":{"kind":"arxiv","id":"2406.13560","version":2},"attestation_state":"computed","paper":{"title":"Lexically Grounded Subword Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jind\\v{r}ich Helcl, Jind\\v{r}ich Libovick\\'y","submitted_at":"2024-06-19T13:48:19Z","abstract_excerpt":"We present three innovations in tokenization and subword segmentation. First, we propose to use unsupervised morphological analysis with Morfessor as pre-tokenization. Second, we present an algebraic method for obtaining subword embeddings grounded in a word embedding space. Based on that, we design a novel subword segmentation algorithm that uses the embeddings, ensuring that the procedure considers lexical meaning. Third, we introduce an efficient segmentation algorithm based on a subword bigram model that can be initialized with the lexically aware segmentation method to avoid using Morfess"},"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":"2406.13560","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T13:48:19Z","cross_cats_sorted":[],"title_canon_sha256":"409a9915de822614696af5872655c73f5f31dc5db86c70b7549c1b898aa0a5af","abstract_canon_sha256":"b523d68798cdd8ecac860819d0434efa955fc396ca6f811851560a45f5a1cea6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:11.970980Z","signature_b64":"i5CqSybySKQ7ya+si5nFjuykgfAb3HSfahiOOY8TK8flS/xrFt8eTV0VETCG85XCYtEgF8+E09W56+ftH0tbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb7df78dcd69fa6ccb3d28674d0e0a6669f9e408c5abd65832e9c9ec8fcf2b28","last_reissued_at":"2026-07-05T09:15:11.970570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:11.970570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lexically Grounded Subword Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jind\\v{r}ich Helcl, Jind\\v{r}ich Libovick\\'y","submitted_at":"2024-06-19T13:48:19Z","abstract_excerpt":"We present three innovations in tokenization and subword segmentation. First, we propose to use unsupervised morphological analysis with Morfessor as pre-tokenization. Second, we present an algebraic method for obtaining subword embeddings grounded in a word embedding space. Based on that, we design a novel subword segmentation algorithm that uses the embeddings, ensuring that the procedure considers lexical meaning. Third, we introduce an efficient segmentation algorithm based on a subword bigram model that can be initialized with the lexically aware segmentation method to avoid using Morfess"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13560","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/2406.13560/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":"2406.13560","created_at":"2026-07-05T09:15:11.970626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13560v2","created_at":"2026-07-05T09:15:11.970626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13560","created_at":"2026-07-05T09:15:11.970626+00:00"},{"alias_kind":"pith_short_12","alias_value":"XN67PDONNH5G","created_at":"2026-07-05T09:15:11.970626+00:00"},{"alias_kind":"pith_short_16","alias_value":"XN67PDONNH5GZSZ5","created_at":"2026-07-05T09:15:11.970626+00:00"},{"alias_kind":"pith_short_8","alias_value":"XN67PDON","created_at":"2026-07-05T09:15:11.970626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14198","citing_title":"Why do language models perform worse for morphologically complex languages?","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ","json":"https://pith.science/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ.json","graph_json":"https://pith.science/api/pith-number/XN67PDONNH5GZSZ5FBTU2DQKMZ/graph.json","events_json":"https://pith.science/api/pith-number/XN67PDONNH5GZSZ5FBTU2DQKMZ/events.json","paper":"https://pith.science/paper/XN67PDON"},"agent_actions":{"view_html":"https://pith.science/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ","download_json":"https://pith.science/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ.json","view_paper":"https://pith.science/paper/XN67PDON","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13560&json=true","fetch_graph":"https://pith.science/api/pith-number/XN67PDONNH5GZSZ5FBTU2DQKMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XN67PDONNH5GZSZ5FBTU2DQKMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ/action/storage_attestation","attest_author":"https://pith.science/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ/action/author_attestation","sign_citation":"https://pith.science/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ/action/citation_signature","submit_replication":"https://pith.science/pith/XN67PDONNH5GZSZ5FBTU2DQKMZ/action/replication_record"}},"created_at":"2026-07-05T09:15:11.970626+00:00","updated_at":"2026-07-05T09:15:11.970626+00:00"}