{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5FWOQWKALLP26QY374GUOTC7AU","short_pith_number":"pith:5FWOQWKA","canonical_record":{"source":{"id":"1908.07832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-18T00:45:16Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"6aaacbe4ac3598bf3adb10762e684cdad7b0a2bdb035616a5dc8049c5b6818a8","abstract_canon_sha256":"2b09cec59205f8f66a27b3ce60f435b8666f9fc35bdaf045280ccc07c0b6a6a4"},"schema_version":"1.0"},"canonical_sha256":"e96ce859405adfaf431bff0d474c5f051eae3bf2166b1043c3e73cfd9cc51a96","source":{"kind":"arxiv","id":"1908.07832","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5FWOQWKALLP26QY374GUOTC7AU","target":"record","payload":{"canonical_record":{"source":{"id":"1908.07832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-18T00:45:16Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"6aaacbe4ac3598bf3adb10762e684cdad7b0a2bdb035616a5dc8049c5b6818a8","abstract_canon_sha256":"2b09cec59205f8f66a27b3ce60f435b8666f9fc35bdaf045280ccc07c0b6a6a4"},"schema_version":"1.0"},"canonical_sha256":"e96ce859405adfaf431bff0d474c5f051eae3bf2166b1043c3e73cfd9cc51a96","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:10.159402Z","signature_b64":"xzeXdmgut2paWXFeVUWYlpfmalVVWqMDNuDS67poeMfESazoQ6lm9w2i7B/kR7m6FcZbwJbmoLxgLUxDmvY7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e96ce859405adfaf431bff0d474c5f051eae3bf2166b1043c3e73cfd9cc51a96","last_reissued_at":"2026-07-05T00:19:10.158898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:10.158898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1908.07832","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:19:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UBTPavLqCeB8ExeaOnYWOxDQ/TTZWW6qxyMUvB/YDKI20XHW/y6TjToF2BMkuwT3spD7FVpBxDj3Ziz5evgqAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T12:09:17.301417Z"},"content_sha256":"f2a975f792674b1042d4adf97a97b11f930161d7ffd6e5c6110eb93b8a623c03","schema_version":"1.0","event_id":"sha256:f2a975f792674b1042d4adf97a97b11f930161d7ffd6e5c6110eb93b8a623c03"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5FWOQWKALLP26QY374GUOTC7AU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parsimonious Morpheme Segmentation with an Application to Enriching Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Ahmed El-Kishky, Aston Zhang, Frank Xu, Jiawei Han","submitted_at":"2019-08-18T00:45:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.07832","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.07832/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:19:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sqDkINfu+Z1CGZLOK6JGT2c027YC37y5W75/sOYoGGxUO8eAC6jlQaKpIx/fBvmgiiSwq8is97SZ0WvrraRaAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T12:09:17.305342Z"},"content_sha256":"0fff49064e182938e8bc49968f8d5c41d6b8f822ae0166d9140f320f5319feac","schema_version":"1.0","event_id":"sha256:0fff49064e182938e8bc49968f8d5c41d6b8f822ae0166d9140f320f5319feac"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5FWOQWKALLP26QY374GUOTC7AU/bundle.json","state_url":"https://pith.science/pith/5FWOQWKALLP26QY374GUOTC7AU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5FWOQWKALLP26QY374GUOTC7AU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-16T12:09:17Z","links":{"resolver":"https://pith.science/pith/5FWOQWKALLP26QY374GUOTC7AU","bundle":"https://pith.science/pith/5FWOQWKALLP26QY374GUOTC7AU/bundle.json","state":"https://pith.science/pith/5FWOQWKALLP26QY374GUOTC7AU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5FWOQWKALLP26QY374GUOTC7AU/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lZd5LLzfa8fjijWXSKKAIhx58puDUpmNzdiv19hl07fn5cqo8gmZADhMy8WZkHvO5xkfJ+DtLtcso49cfObbAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T12:09:17.318962Z","bundle_sha256":"405fe87b41c1c63ad86ea93a4e6b0e6a774fa59363e1fb9a0d45fd636e1822ba"}}