{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:23T6LYUAS5625L3PVOTZM6B53E","short_pith_number":"pith:23T6LYUA","schema_version":"1.0","canonical_sha256":"d6e7e5e280977daeaf6faba796783dd929d2eab6f0f12dab0346b1e12e025df6","source":{"kind":"arxiv","id":"1709.07470","version":1},"attestation_state":"computed","paper":{"title":"Learning Domain-Specific Word Embeddings from Sparse Cybersecurity Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arpita Roy, Shimei Pan, Youngja Park","submitted_at":"2017-09-21T18:17:36Z","abstract_excerpt":"Word embedding is a Natural Language Processing (NLP) technique that automatically maps words from a vocabulary to vectors of real numbers in an embedding space. It has been widely used in recent years to boost the performance of a vari-ety of NLP tasks such as Named Entity Recognition, Syntac-tic Parsing and Sentiment Analysis. Classic word embedding methods such as Word2Vec and GloVe work well when they are given a large text corpus. When the input texts are sparse as in many specialized domains (e.g., cybersecurity), these methods often fail to produce high-quality vectors. In this pa-per, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1709.07470","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-21T18:17:36Z","cross_cats_sorted":[],"title_canon_sha256":"205e70ac985232236d51f41175ecf1c1feaecc6d676a1e5e199852167aa031da","abstract_canon_sha256":"4d299d5e7c84df2d36447cd34fcabedcd0f51d048c5602224d35767d31a1311b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:35.730933Z","signature_b64":"6EKfq0F+8lJigmDD9CH64TkEznmtRNExrnsIu1dKcvelBkrnOfCVbJA3q2rlsAv6V0+nyGa1hdfPFCL0hFLSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6e7e5e280977daeaf6faba796783dd929d2eab6f0f12dab0346b1e12e025df6","last_reissued_at":"2026-05-18T00:34:35.730427Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:35.730427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Domain-Specific Word Embeddings from Sparse Cybersecurity Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arpita Roy, Shimei Pan, Youngja Park","submitted_at":"2017-09-21T18:17:36Z","abstract_excerpt":"Word embedding is a Natural Language Processing (NLP) technique that automatically maps words from a vocabulary to vectors of real numbers in an embedding space. It has been widely used in recent years to boost the performance of a vari-ety of NLP tasks such as Named Entity Recognition, Syntac-tic Parsing and Sentiment Analysis. Classic word embedding methods such as Word2Vec and GloVe work well when they are given a large text corpus. When the input texts are sparse as in many specialized domains (e.g., cybersecurity), these methods often fail to produce high-quality vectors. In this pa-per, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.07470","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1709.07470","created_at":"2026-05-18T00:34:35.730505+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.07470v1","created_at":"2026-05-18T00:34:35.730505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.07470","created_at":"2026-05-18T00:34:35.730505+00:00"},{"alias_kind":"pith_short_12","alias_value":"23T6LYUAS562","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"23T6LYUAS5625L3P","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"23T6LYUA","created_at":"2026-05-18T12:30:55.937587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/23T6LYUAS5625L3PVOTZM6B53E","json":"https://pith.science/pith/23T6LYUAS5625L3PVOTZM6B53E.json","graph_json":"https://pith.science/api/pith-number/23T6LYUAS5625L3PVOTZM6B53E/graph.json","events_json":"https://pith.science/api/pith-number/23T6LYUAS5625L3PVOTZM6B53E/events.json","paper":"https://pith.science/paper/23T6LYUA"},"agent_actions":{"view_html":"https://pith.science/pith/23T6LYUAS5625L3PVOTZM6B53E","download_json":"https://pith.science/pith/23T6LYUAS5625L3PVOTZM6B53E.json","view_paper":"https://pith.science/paper/23T6LYUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.07470&json=true","fetch_graph":"https://pith.science/api/pith-number/23T6LYUAS5625L3PVOTZM6B53E/graph.json","fetch_events":"https://pith.science/api/pith-number/23T6LYUAS5625L3PVOTZM6B53E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23T6LYUAS5625L3PVOTZM6B53E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23T6LYUAS5625L3PVOTZM6B53E/action/storage_attestation","attest_author":"https://pith.science/pith/23T6LYUAS5625L3PVOTZM6B53E/action/author_attestation","sign_citation":"https://pith.science/pith/23T6LYUAS5625L3PVOTZM6B53E/action/citation_signature","submit_replication":"https://pith.science/pith/23T6LYUAS5625L3PVOTZM6B53E/action/replication_record"}},"created_at":"2026-05-18T00:34:35.730505+00:00","updated_at":"2026-05-18T00:34:35.730505+00:00"}