{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LAKPMO2DPYV3JZ4Z6BFQ6PFGUD","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":"3bc0cff6c09d956d71eac425c35c28066932f3ecd34e011262c8da7aa02da2af","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T14:24:50Z","title_canon_sha256":"1b9a0a96021a85ad29b5224fc33b19e185fb5eb0b2693884aeb9b24f5ee2791e"},"schema_version":"1.0","source":{"id":"2605.29992","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29992","created_at":"2026-05-29T02:06:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29992v1","created_at":"2026-05-29T02:06:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29992","created_at":"2026-05-29T02:06:05Z"},{"alias_kind":"pith_short_12","alias_value":"LAKPMO2DPYV3","created_at":"2026-05-29T02:06:05Z"},{"alias_kind":"pith_short_16","alias_value":"LAKPMO2DPYV3JZ4Z","created_at":"2026-05-29T02:06:05Z"},{"alias_kind":"pith_short_8","alias_value":"LAKPMO2D","created_at":"2026-05-29T02:06:05Z"}],"graph_snapshots":[{"event_id":"sha256:161b671a81d319725a89bc5f09a4dc9a9ad70e59b7f762a08612acb5be345217","target":"graph","created_at":"2026-05-29T02:06:05Z","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/2605.29992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Banu Diri, M. Ali Bayram, Sava\\c{s} Y{\\i}ld{\\i}r{\\i}m","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T14:24:50Z","title":"Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29992","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":"sha256:0a8f2562f9dde49e41f055eef78fc4eb95e3a608eb786510f3588c4591b3d0c8","target":"record","created_at":"2026-05-29T02:06:05Z","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":"3bc0cff6c09d956d71eac425c35c28066932f3ecd34e011262c8da7aa02da2af","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-28T14:24:50Z","title_canon_sha256":"1b9a0a96021a85ad29b5224fc33b19e185fb5eb0b2693884aeb9b24f5ee2791e"},"schema_version":"1.0","source":{"id":"2605.29992","kind":"arxiv","version":1}},"canonical_sha256":"5814f63b437e2bb4e799f04b0f3ca6a0cf3c57ad052276ef826db26c263e4131","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5814f63b437e2bb4e799f04b0f3ca6a0cf3c57ad052276ef826db26c263e4131","first_computed_at":"2026-05-29T02:06:05.797189Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:05.797189Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bPIp6pQqm1qLohOPe5Y4NbDEV5hLdcKL5ghJt1UEHHuPNUNX/NRgCw4C0MYliWkwt6OVeQr8f1c0oupJj3W5BA==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:05.797958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29992","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a8f2562f9dde49e41f055eef78fc4eb95e3a608eb786510f3588c4591b3d0c8","sha256:161b671a81d319725a89bc5f09a4dc9a9ad70e59b7f762a08612acb5be345217"],"state_sha256":"2378e2384c4b1cbcc2fe59f16002382572fe2af1df1789bf65609e150812d639"}