{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7YNPNOUNNTMJS6HP2JS4ZCNACG","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":"d3078dfe97110cdb70a26ca17cde4a2c5b31903ab9359ebfe2fe85562b635141","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-03-06T10:58:59Z","title_canon_sha256":"664574b73a03c2208c5084fe66e6f17f0014af5e672361fc6be8b1296a5ffb58"},"schema_version":"1.0","source":{"id":"2003.03131","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.03131","created_at":"2026-07-05T00:46:10Z"},{"alias_kind":"arxiv_version","alias_value":"2003.03131v1","created_at":"2026-07-05T00:46:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03131","created_at":"2026-07-05T00:46:10Z"},{"alias_kind":"pith_short_12","alias_value":"7YNPNOUNNTMJ","created_at":"2026-07-05T00:46:10Z"},{"alias_kind":"pith_short_16","alias_value":"7YNPNOUNNTMJS6HP","created_at":"2026-07-05T00:46:10Z"},{"alias_kind":"pith_short_8","alias_value":"7YNPNOUN","created_at":"2026-07-05T00:46:10Z"}],"graph_snapshots":[{"event_id":"sha256:66653faafffc3ff95dee40fa06736343f61b9e53199d28a790f565d23acad39f","target":"graph","created_at":"2026-07-05T00:46:10Z","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/2003.03131/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data-driven segmentation of words into subword units has been used in various natural language processing applications such as automatic speech recognition and statistical machine translation for almost 20 years. Recently it has became more widely adopted, as models based on deep neural networks often benefit from subword units even for morphologically simpler languages. In this paper, we discuss and compare training algorithms for a unigram subword model, based on the Expectation Maximization algorithm and lexicon pruning. Using English, Finnish, North Sami, and Turkish data sets, we show tha","authors_text":"Mikko Kurimo, Sami Virpioja, Stig-Arne Gr\\\"onroos","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-03-06T10:58:59Z","title":"Morfessor EM+Prune: Improved Subword Segmentation with Expectation Maximization and Pruning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.03131","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:e2f91c94fd2d7a87e371852c4cef40853973da54f4503dc2fbcfcebe7151bc3e","target":"record","created_at":"2026-07-05T00:46:10Z","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":"d3078dfe97110cdb70a26ca17cde4a2c5b31903ab9359ebfe2fe85562b635141","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-03-06T10:58:59Z","title_canon_sha256":"664574b73a03c2208c5084fe66e6f17f0014af5e672361fc6be8b1296a5ffb58"},"schema_version":"1.0","source":{"id":"2003.03131","kind":"arxiv","version":1}},"canonical_sha256":"fe1af6ba8d6cd89978efd265cc89a011ae0c0157cb266f2424399f8c806c4fc3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe1af6ba8d6cd89978efd265cc89a011ae0c0157cb266f2424399f8c806c4fc3","first_computed_at":"2026-07-05T00:46:10.145378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:46:10.145378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rQ9TJjzKK274cJQ5F2u161RCwR/wD9EbivWtGpWQObSO+7x0/ILHpdXZ9YFa4x5wdZnbO5DR/b4FsC+OEFfZAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:46:10.145744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.03131","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2f91c94fd2d7a87e371852c4cef40853973da54f4503dc2fbcfcebe7151bc3e","sha256:66653faafffc3ff95dee40fa06736343f61b9e53199d28a790f565d23acad39f"],"state_sha256":"4df876c68a073859d0ce9a83845b0ac5099817c5a68af2e7d67d87ce28cbe651"}