{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3SMDWHG2NX4G26GTYXI4TKLAYA","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":"02112788495d95018087f0f296c83f0e8711dcb764950b75422b0b04eee1eb5a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-10T17:45:10Z","title_canon_sha256":"8a31af0ad8db57bdd6f9134712fbbd6c32a98a4a445bb04903fb92a6f6ebcb19"},"schema_version":"1.0","source":{"id":"2509.08812","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08812","created_at":"2026-07-05T12:08:36Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08812v1","created_at":"2026-07-05T12:08:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08812","created_at":"2026-07-05T12:08:36Z"},{"alias_kind":"pith_short_12","alias_value":"3SMDWHG2NX4G","created_at":"2026-07-05T12:08:36Z"},{"alias_kind":"pith_short_16","alias_value":"3SMDWHG2NX4G26GT","created_at":"2026-07-05T12:08:36Z"},{"alias_kind":"pith_short_8","alias_value":"3SMDWHG2","created_at":"2026-07-05T12:08:36Z"}],"graph_snapshots":[{"event_id":"sha256:4ccbf6e3d5bf0fce7647667f5df27ac60f93e77593b0fc7c4457f73a5ad65e5b","target":"graph","created_at":"2026-07-05T12:08:36Z","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/2509.08812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Subword-based tokenization methods often fail to preserve morphological boundaries, a limitation especially pronounced in low-resource, morphologically complex languages such as those written in the Geez script. To address this, we present MoVoC (Morpheme-aware Subword Vocabulary Construction) and train MoVoC-Tok, a tokenizer that integrates supervised morphological analysis into the subword vocabulary. This hybrid segmentation approach combines morpheme-based and Byte Pair Encoding (BPE) tokens to preserve morphological integrity while maintaining lexical meaning. To tackle resource scarcity,","authors_text":"Dren Fazlija, Hailay Kidu Teklehaymanot, Wolfgang Nejdl","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-10T17:45:10Z","title":"MoVoC: Morphology-Aware Subword Construction for Geez Script Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08812","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":"sha256:1ddfe8b69559604e00cc3a00cafa4c057c57585ac1d832830b74f04e3f517c58","target":"record","created_at":"2026-07-05T12:08:36Z","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":"02112788495d95018087f0f296c83f0e8711dcb764950b75422b0b04eee1eb5a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-10T17:45:10Z","title_canon_sha256":"8a31af0ad8db57bdd6f9134712fbbd6c32a98a4a445bb04903fb92a6f6ebcb19"},"schema_version":"1.0","source":{"id":"2509.08812","kind":"arxiv","version":1}},"canonical_sha256":"dc983b1cda6df86d78d3c5d1c9a960c01711de93738a2e536cedfa55f60d833f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc983b1cda6df86d78d3c5d1c9a960c01711de93738a2e536cedfa55f60d833f","first_computed_at":"2026-07-05T12:08:36.786060Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:08:36.786060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fxW3gDHGLGrawRNpZkEkMzVPhBqUvxv0V0DwRgxUAkgOx13vxMCg7fgPpDruAHaitgAulyTCNHfQbE4ayo+WBA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:08:36.786505Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.08812","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ddfe8b69559604e00cc3a00cafa4c057c57585ac1d832830b74f04e3f517c58","sha256:4ccbf6e3d5bf0fce7647667f5df27ac60f93e77593b0fc7c4457f73a5ad65e5b"],"state_sha256":"fa16dc9d8b34612593062762162b8548308dcdb4ade46355897ecc4afd237272"}