{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:I5ERV7V75IWFNHSZ76AMZW66PM","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":"938630078d6328e7bbe9ae9b8b827adc6f52dd81c0ee7ff685926ff5bf42c56a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-05T18:55:52Z","title_canon_sha256":"084cb2b9217b78f982f722d9d071d688606922e80bb3b76b20c403474d099bdf"},"schema_version":"1.0","source":{"id":"2210.02509","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.02509","created_at":"2026-07-05T05:03:53Z"},{"alias_kind":"arxiv_version","alias_value":"2210.02509v1","created_at":"2026-07-05T05:03:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.02509","created_at":"2026-07-05T05:03:53Z"},{"alias_kind":"pith_short_12","alias_value":"I5ERV7V75IWF","created_at":"2026-07-05T05:03:53Z"},{"alias_kind":"pith_short_16","alias_value":"I5ERV7V75IWFNHSZ","created_at":"2026-07-05T05:03:53Z"},{"alias_kind":"pith_short_8","alias_value":"I5ERV7V7","created_at":"2026-07-05T05:03:53Z"}],"graph_snapshots":[{"event_id":"sha256:0f2f1bfc41d48d5db135162f54090ebff6db9b6fd2d789c2a989739684dcc079","target":"graph","created_at":"2026-07-05T05:03:53Z","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/2210.02509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language modelling and machine translation tasks mostly use subword or character inputs, but syllables are seldom used. Syllables provide shorter sequences than characters, require less-specialised extracting rules than morphemes, and their segmentation is not impacted by the corpus size. In this study, we first explore the potential of syllables for open-vocabulary language modelling in 21 languages. We use rule-based syllabification methods for six languages and address the rest with hyphenation, which works as a syllabification proxy. With a comparable perplexity, we show that syllables out","authors_text":"Arturo Oncevay, Kervy Dante Rivas Rojas, Liz Karen Chavez Sanchez, Roberto Zariquiey","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-05T18:55:52Z","title":"Revisiting Syllables in Language Modelling and their Application on Low-Resource Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.02509","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":"sha256:5cc20453aa9b9bbed209cc64c3441f440443e2045d113f8bef260f88159fba20","target":"record","created_at":"2026-07-05T05:03:53Z","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":"938630078d6328e7bbe9ae9b8b827adc6f52dd81c0ee7ff685926ff5bf42c56a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-05T18:55:52Z","title_canon_sha256":"084cb2b9217b78f982f722d9d071d688606922e80bb3b76b20c403474d099bdf"},"schema_version":"1.0","source":{"id":"2210.02509","kind":"arxiv","version":1}},"canonical_sha256":"47491afebfea2c569e59ff80ccdbde7b094e615db073d23dee949aa008103d12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47491afebfea2c569e59ff80ccdbde7b094e615db073d23dee949aa008103d12","first_computed_at":"2026-07-05T05:03:53.263929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:53.263929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1aLZ5chtt9aS27bLKq2CEh/dv2uom1A7rIN5AOiAZeVPJB2JpjBe8fohxSOCzUWpf6rQzG7ETN/F1e6Af1RxDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:53.264364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.02509","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cc20453aa9b9bbed209cc64c3441f440443e2045d113f8bef260f88159fba20","sha256:0f2f1bfc41d48d5db135162f54090ebff6db9b6fd2d789c2a989739684dcc079"],"state_sha256":"bfe5d7d1ea044c7964acb3d497754417e6a5fdb5fa4b52a8bfaf5ced9304ac65"}