{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LAKPMO2DPYV3JZ4Z6BFQ6PFGUD","short_pith_number":"pith:LAKPMO2D","schema_version":"1.0","canonical_sha256":"5814f63b437e2bb4e799f04b0f3ca6a0cf3c57ad052276ef826db26c263e4131","source":{"kind":"arxiv","id":"2605.29992","version":1},"attestation_state":"computed","paper":{"title":"Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Banu Diri, M. Ali Bayram, Sava\\c{s} Y{\\i}ld{\\i}r{\\i}m","submitted_at":"2026-05-28T14:24:50Z","abstract_excerpt":"Sentence embeddings are a foundational component for semantic search, clustering, classification, and retrieval-augmented generation. This paper presents embeddingmagibu-200m, a Turkish-focused sentence embedding model that produces 768-dimensional L2-normalized vectors and supports an 8,192-token context window, far exceeding the 512-token limit of earlier BERT-based Turkish encoders. Instead of full pretraining, an efficient three-stage adaptation pipeline is introduced: (1) construct a Turkish-optimized multilingual tokenizer with a 131,072 vocabulary by pruning redundant tokens from the te"},"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":"2605.29992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T14:24:50Z","cross_cats_sorted":[],"title_canon_sha256":"1b9a0a96021a85ad29b5224fc33b19e185fb5eb0b2693884aeb9b24f5ee2791e","abstract_canon_sha256":"3bc0cff6c09d956d71eac425c35c28066932f3ecd34e011262c8da7aa02da2af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:05.797958Z","signature_b64":"bPIp6pQqm1qLohOPe5Y4NbDEV5hLdcKL5ghJt1UEHHuPNUNX/NRgCw4C0MYliWkwt6OVeQr8f1c0oupJj3W5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5814f63b437e2bb4e799f04b0f3ca6a0cf3c57ad052276ef826db26c263e4131","last_reissued_at":"2026-05-29T02:06:05.797189Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:05.797189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Banu Diri, M. Ali Bayram, Sava\\c{s} Y{\\i}ld{\\i}r{\\i}m","submitted_at":"2026-05-28T14:24:50Z","abstract_excerpt":"Sentence embeddings are a foundational component for semantic search, clustering, classification, and retrieval-augmented generation. This paper presents embeddingmagibu-200m, a Turkish-focused sentence embedding model that produces 768-dimensional L2-normalized vectors and supports an 8,192-token context window, far exceeding the 512-token limit of earlier BERT-based Turkish encoders. Instead of full pretraining, an efficient three-stage adaptation pipeline is introduced: (1) construct a Turkish-optimized multilingual tokenizer with a 131,072 vocabulary by pruning redundant tokens from the te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29992","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/2605.29992/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":"2605.29992","created_at":"2026-05-29T02:06:05.797307+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29992v1","created_at":"2026-05-29T02:06:05.797307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29992","created_at":"2026-05-29T02:06:05.797307+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAKPMO2DPYV3","created_at":"2026-05-29T02:06:05.797307+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAKPMO2DPYV3JZ4Z","created_at":"2026-05-29T02:06:05.797307+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAKPMO2D","created_at":"2026-05-29T02:06:05.797307+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/LAKPMO2DPYV3JZ4Z6BFQ6PFGUD","json":"https://pith.science/pith/LAKPMO2DPYV3JZ4Z6BFQ6PFGUD.json","graph_json":"https://pith.science/api/pith-number/LAKPMO2DPYV3JZ4Z6BFQ6PFGUD/graph.json","events_json":"https://pith.science/api/pith-number/LAKPMO2DPYV3JZ4Z6BFQ6PFGUD/events.json","paper":"https://pith.science/paper/LAKPMO2D"},"agent_actions":{"view_html":"https://pith.science/pith/LAKPMO2DPYV3JZ4Z6BFQ6PFGUD","download_json":"https://pith.science/pith/LAKPMO2DPYV3JZ4Z6BFQ6PFGUD.json","view_paper":"https://pith.science/paper/LAKPMO2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29992&json=true","fetch_graph":"https://pith.science/api/pith-number/LAKPMO2DPYV3JZ4Z6BFQ6PFGUD/graph.json","fetch_events":"https://pith.science/api/pith-number/LAKPMO2DPYV3JZ4Z6BFQ6PFGUD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAKPMO2DPYV3JZ4Z6BFQ6PFGUD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAKPMO2DPYV3JZ4Z6BFQ6PFGUD/action/storage_attestation","attest_author":"https://pith.science/pith/LAKPMO2DPYV3JZ4Z6BFQ6PFGUD/action/author_attestation","sign_citation":"https://pith.science/pith/LAKPMO2DPYV3JZ4Z6BFQ6PFGUD/action/citation_signature","submit_replication":"https://pith.science/pith/LAKPMO2DPYV3JZ4Z6BFQ6PFGUD/action/replication_record"}},"created_at":"2026-05-29T02:06:05.797307+00:00","updated_at":"2026-05-29T02:06:05.797307+00:00"}