{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FKVW6GERYIKD5YM3J23O7WFLST","short_pith_number":"pith:FKVW6GER","schema_version":"1.0","canonical_sha256":"2aab6f1891c2143ee19b4eb6efd8ab94c7155ce7367588e92a573b5af5baf4ab","source":{"kind":"arxiv","id":"2606.18717","version":1},"attestation_state":"computed","paper":{"title":"Morpheus: A Morphology-Aware Neural Tokenizer and Word Embedder for Turkish","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Tolga \\c{S}akar","submitted_at":"2026-06-17T05:55:50Z","abstract_excerpt":"Turkish is agglutinative: meaning is carried by morphemes, yet the subword tokenizers that drive modern language models split words by corpus statistics, fragmenting semantically loaded suffixes and -- in the case of WordPiece and rule-based analyzers -- failing to decode their output back to the original text. This paper presents \\textbf{Morpheus}, a neural morpheme-boundary model for Turkish that is at once a lossless, morphology-aware tokenizer and a word-embedding producer. A differentiable Poisson-binomial dynamic program turns per-character boundary probabilities into soft morpheme membe"},"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":"2606.18717","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T05:55:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d64e2fa82f345a83fbf53fa3f92c830d3a6e36fa138fc50345738d0e41617a26","abstract_canon_sha256":"b44473375acf3dbf53ce90f0b64651a670a77731066f8bff6e670964ffb8c57f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:45.539279Z","signature_b64":"+W3ow48i7kvh0KJeeIREwje7d2F1dbC4Kqnx77g59HTDWXaeLD2i13YMcWpBVKyPFU9vryJGQ5TFR83fEfslAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2aab6f1891c2143ee19b4eb6efd8ab94c7155ce7367588e92a573b5af5baf4ab","last_reissued_at":"2026-06-19T16:11:45.538917Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:45.538917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Morpheus: A Morphology-Aware Neural Tokenizer and Word Embedder for Turkish","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Tolga \\c{S}akar","submitted_at":"2026-06-17T05:55:50Z","abstract_excerpt":"Turkish is agglutinative: meaning is carried by morphemes, yet the subword tokenizers that drive modern language models split words by corpus statistics, fragmenting semantically loaded suffixes and -- in the case of WordPiece and rule-based analyzers -- failing to decode their output back to the original text. This paper presents \\textbf{Morpheus}, a neural morpheme-boundary model for Turkish that is at once a lossless, morphology-aware tokenizer and a word-embedding producer. A differentiable Poisson-binomial dynamic program turns per-character boundary probabilities into soft morpheme membe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18717","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/2606.18717/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":"2606.18717","created_at":"2026-06-19T16:11:45.538977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18717v1","created_at":"2026-06-19T16:11:45.538977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18717","created_at":"2026-06-19T16:11:45.538977+00:00"},{"alias_kind":"pith_short_12","alias_value":"FKVW6GERYIKD","created_at":"2026-06-19T16:11:45.538977+00:00"},{"alias_kind":"pith_short_16","alias_value":"FKVW6GERYIKD5YM3","created_at":"2026-06-19T16:11:45.538977+00:00"},{"alias_kind":"pith_short_8","alias_value":"FKVW6GER","created_at":"2026-06-19T16:11:45.538977+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/FKVW6GERYIKD5YM3J23O7WFLST","json":"https://pith.science/pith/FKVW6GERYIKD5YM3J23O7WFLST.json","graph_json":"https://pith.science/api/pith-number/FKVW6GERYIKD5YM3J23O7WFLST/graph.json","events_json":"https://pith.science/api/pith-number/FKVW6GERYIKD5YM3J23O7WFLST/events.json","paper":"https://pith.science/paper/FKVW6GER"},"agent_actions":{"view_html":"https://pith.science/pith/FKVW6GERYIKD5YM3J23O7WFLST","download_json":"https://pith.science/pith/FKVW6GERYIKD5YM3J23O7WFLST.json","view_paper":"https://pith.science/paper/FKVW6GER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18717&json=true","fetch_graph":"https://pith.science/api/pith-number/FKVW6GERYIKD5YM3J23O7WFLST/graph.json","fetch_events":"https://pith.science/api/pith-number/FKVW6GERYIKD5YM3J23O7WFLST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FKVW6GERYIKD5YM3J23O7WFLST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FKVW6GERYIKD5YM3J23O7WFLST/action/storage_attestation","attest_author":"https://pith.science/pith/FKVW6GERYIKD5YM3J23O7WFLST/action/author_attestation","sign_citation":"https://pith.science/pith/FKVW6GERYIKD5YM3J23O7WFLST/action/citation_signature","submit_replication":"https://pith.science/pith/FKVW6GERYIKD5YM3J23O7WFLST/action/replication_record"}},"created_at":"2026-06-19T16:11:45.538977+00:00","updated_at":"2026-06-19T16:11:45.538977+00:00"}