{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5FWOQWKALLP26QY374GUOTC7AU","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":"2b09cec59205f8f66a27b3ce60f435b8666f9fc35bdaf045280ccc07c0b6a6a4","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-18T00:45:16Z","title_canon_sha256":"6aaacbe4ac3598bf3adb10762e684cdad7b0a2bdb035616a5dc8049c5b6818a8"},"schema_version":"1.0","source":{"id":"1908.07832","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.07832","created_at":"2026-07-05T00:19:10Z"},{"alias_kind":"arxiv_version","alias_value":"1908.07832v2","created_at":"2026-07-05T00:19:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.07832","created_at":"2026-07-05T00:19:10Z"},{"alias_kind":"pith_short_12","alias_value":"5FWOQWKALLP2","created_at":"2026-07-05T00:19:10Z"},{"alias_kind":"pith_short_16","alias_value":"5FWOQWKALLP26QY3","created_at":"2026-07-05T00:19:10Z"},{"alias_kind":"pith_short_8","alias_value":"5FWOQWKA","created_at":"2026-07-05T00:19:10Z"}],"graph_snapshots":[{"event_id":"sha256:0fff49064e182938e8bc49968f8d5c41d6b8f822ae0166d9140f320f5319feac","target":"graph","created_at":"2026-07-05T00:19:10Z","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/1908.07832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Traditionally, many text-mining tasks treat individual word-tokens as the finest meaningful semantic granularity. However, in many languages and specialized corpora, words are composed by concatenating semantically meaningful subword structures. Word-level analysis cannot leverage the semantic information present in such subword structures. With regard to word embedding techniques, this leads to not only poor embeddings for infrequent words in long-tailed text corpora but also weak capabilities for handling out-of-vocabulary words. In this paper we propose MorphMine for unsupervised morpheme s","authors_text":"Ahmed El-Kishky, Aston Zhang, Frank Xu, Jiawei Han","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-18T00:45:16Z","title":"Parsimonious Morpheme Segmentation with an Application to Enriching Word Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07832","kind":"arxiv","version":2},"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:f2a975f792674b1042d4adf97a97b11f930161d7ffd6e5c6110eb93b8a623c03","target":"record","created_at":"2026-07-05T00:19:10Z","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":"2b09cec59205f8f66a27b3ce60f435b8666f9fc35bdaf045280ccc07c0b6a6a4","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-18T00:45:16Z","title_canon_sha256":"6aaacbe4ac3598bf3adb10762e684cdad7b0a2bdb035616a5dc8049c5b6818a8"},"schema_version":"1.0","source":{"id":"1908.07832","kind":"arxiv","version":2}},"canonical_sha256":"e96ce859405adfaf431bff0d474c5f051eae3bf2166b1043c3e73cfd9cc51a96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e96ce859405adfaf431bff0d474c5f051eae3bf2166b1043c3e73cfd9cc51a96","first_computed_at":"2026-07-05T00:19:10.158898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:19:10.158898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xzeXdmgut2paWXFeVUWYlpfmalVVWqMDNuDS67poeMfESazoQ6lm9w2i7B/kR7m6FcZbwJbmoLxgLUxDmvY7Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:19:10.159402Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.07832","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2a975f792674b1042d4adf97a97b11f930161d7ffd6e5c6110eb93b8a623c03","sha256:0fff49064e182938e8bc49968f8d5c41d6b8f822ae0166d9140f320f5319feac"],"state_sha256":"96e43f1d494e1cabe11958a6e0965459363b4d361e5ad78bbdf5240fbf77f5f0"}