{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FKVW6GERYIKD5YM3J23O7WFLST","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":"b44473375acf3dbf53ce90f0b64651a670a77731066f8bff6e670964ffb8c57f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T05:55:50Z","title_canon_sha256":"d64e2fa82f345a83fbf53fa3f92c830d3a6e36fa138fc50345738d0e41617a26"},"schema_version":"1.0","source":{"id":"2606.18717","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18717","created_at":"2026-06-19T16:11:45Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18717v1","created_at":"2026-06-19T16:11:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18717","created_at":"2026-06-19T16:11:45Z"},{"alias_kind":"pith_short_12","alias_value":"FKVW6GERYIKD","created_at":"2026-06-19T16:11:45Z"},{"alias_kind":"pith_short_16","alias_value":"FKVW6GERYIKD5YM3","created_at":"2026-06-19T16:11:45Z"},{"alias_kind":"pith_short_8","alias_value":"FKVW6GER","created_at":"2026-06-19T16:11:45Z"}],"graph_snapshots":[{"event_id":"sha256:5674509efac3cbe2976de3450af273e0252f80665c9a90812852924c48dd8d59","target":"graph","created_at":"2026-06-19T16:11:45Z","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/2606.18717/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Tolga \\c{S}akar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T05:55:50Z","title":"Morpheus: A Morphology-Aware Neural Tokenizer and Word Embedder for Turkish"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18717","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":"sha256:944fdcac866009e38cbc5c0a6896447f460b056239d34a9941d9cae8bea2caac","target":"record","created_at":"2026-06-19T16:11:45Z","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":"b44473375acf3dbf53ce90f0b64651a670a77731066f8bff6e670964ffb8c57f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-17T05:55:50Z","title_canon_sha256":"d64e2fa82f345a83fbf53fa3f92c830d3a6e36fa138fc50345738d0e41617a26"},"schema_version":"1.0","source":{"id":"2606.18717","kind":"arxiv","version":1}},"canonical_sha256":"2aab6f1891c2143ee19b4eb6efd8ab94c7155ce7367588e92a573b5af5baf4ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2aab6f1891c2143ee19b4eb6efd8ab94c7155ce7367588e92a573b5af5baf4ab","first_computed_at":"2026-06-19T16:11:45.538917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:45.538917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+W3ow48i7kvh0KJeeIREwje7d2F1dbC4Kqnx77g59HTDWXaeLD2i13YMcWpBVKyPFU9vryJGQ5TFR83fEfslAg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:45.539279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18717","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:944fdcac866009e38cbc5c0a6896447f460b056239d34a9941d9cae8bea2caac","sha256:5674509efac3cbe2976de3450af273e0252f80665c9a90812852924c48dd8d59"],"state_sha256":"55211098466b31e9b2d3b5410a80320cea6917cce748b86420cb495c82ea823e"}