{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:23T6LYUAS5625L3PVOTZM6B53E","short_pith_number":"pith:23T6LYUA","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"},"canonical_sha256":"d6e7e5e280977daeaf6faba796783dd929d2eab6f0f12dab0346b1e12e025df6","source":{"kind":"arxiv","id":"1709.07470","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.07470","created_at":"2026-05-18T00:34:35Z"},{"alias_kind":"arxiv_version","alias_value":"1709.07470v1","created_at":"2026-05-18T00:34:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.07470","created_at":"2026-05-18T00:34:35Z"},{"alias_kind":"pith_short_12","alias_value":"23T6LYUAS562","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"23T6LYUAS5625L3P","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"23T6LYUA","created_at":"2026-05-18T12:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:23T6LYUAS5625L3PVOTZM6B53E","target":"record","payload":{"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"},"canonical_sha256":"d6e7e5e280977daeaf6faba796783dd929d2eab6f0f12dab0346b1e12e025df6","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"},"source_kind":"arxiv","source_id":"1709.07470","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:34:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sypSMyxOfOsbXj+om8oeVAkWTPWLj0CYxgxfadNVtgngdYEjQtmZBaT0ScouLqHGA2tlSN/1ebJ55jYzaa9rCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T11:34:03.766428Z"},"content_sha256":"7aa28d6e7cb66eaa3255932e164d87fd17505d1a9ca9fedab2246e563a6a95c2","schema_version":"1.0","event_id":"sha256:7aa28d6e7cb66eaa3255932e164d87fd17505d1a9ca9fedab2246e563a6a95c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:23T6LYUAS5625L3PVOTZM6B53E","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:34:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K3iXixwUfgK+izbT7k3fHfp0GlHngaA2RMIrsX5iAPSl6JBMnCJgRHUz76JrpO6KDPwM8UaIzaCXRNWgIqCtDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T11:34:03.766767Z"},"content_sha256":"c373c870ba1e29a94309a61dd9d90122b26368294761cf6a51a7d2bc187f2d5f","schema_version":"1.0","event_id":"sha256:c373c870ba1e29a94309a61dd9d90122b26368294761cf6a51a7d2bc187f2d5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/23T6LYUAS5625L3PVOTZM6B53E/bundle.json","state_url":"https://pith.science/pith/23T6LYUAS5625L3PVOTZM6B53E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/23T6LYUAS5625L3PVOTZM6B53E/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":"2026-07-04T11:34:03Z","links":{"resolver":"https://pith.science/pith/23T6LYUAS5625L3PVOTZM6B53E","bundle":"https://pith.science/pith/23T6LYUAS5625L3PVOTZM6B53E/bundle.json","state":"https://pith.science/pith/23T6LYUAS5625L3PVOTZM6B53E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/23T6LYUAS5625L3PVOTZM6B53E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:23T6LYUAS5625L3PVOTZM6B53E","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":"4d299d5e7c84df2d36447cd34fcabedcd0f51d048c5602224d35767d31a1311b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-21T18:17:36Z","title_canon_sha256":"205e70ac985232236d51f41175ecf1c1feaecc6d676a1e5e199852167aa031da"},"schema_version":"1.0","source":{"id":"1709.07470","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.07470","created_at":"2026-05-18T00:34:35Z"},{"alias_kind":"arxiv_version","alias_value":"1709.07470v1","created_at":"2026-05-18T00:34:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.07470","created_at":"2026-05-18T00:34:35Z"},{"alias_kind":"pith_short_12","alias_value":"23T6LYUAS562","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"23T6LYUAS5625L3P","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"23T6LYUA","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:c373c870ba1e29a94309a61dd9d90122b26368294761cf6a51a7d2bc187f2d5f","target":"graph","created_at":"2026-05-18T00:34:35Z","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"},"paper":{"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, ","authors_text":"Arpita Roy, Shimei Pan, Youngja Park","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-21T18:17:36Z","title":"Learning Domain-Specific Word Embeddings from Sparse Cybersecurity Texts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.07470","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":"sha256:7aa28d6e7cb66eaa3255932e164d87fd17505d1a9ca9fedab2246e563a6a95c2","target":"record","created_at":"2026-05-18T00:34:35Z","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":"4d299d5e7c84df2d36447cd34fcabedcd0f51d048c5602224d35767d31a1311b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-21T18:17:36Z","title_canon_sha256":"205e70ac985232236d51f41175ecf1c1feaecc6d676a1e5e199852167aa031da"},"schema_version":"1.0","source":{"id":"1709.07470","kind":"arxiv","version":1}},"canonical_sha256":"d6e7e5e280977daeaf6faba796783dd929d2eab6f0f12dab0346b1e12e025df6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6e7e5e280977daeaf6faba796783dd929d2eab6f0f12dab0346b1e12e025df6","first_computed_at":"2026-05-18T00:34:35.730427Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:34:35.730427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6EKfq0F+8lJigmDD9CH64TkEznmtRNExrnsIu1dKcvelBkrnOfCVbJA3q2rlsAv6V0+nyGa1hdfPFCL0hFLSAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:34:35.730933Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.07470","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7aa28d6e7cb66eaa3255932e164d87fd17505d1a9ca9fedab2246e563a6a95c2","sha256:c373c870ba1e29a94309a61dd9d90122b26368294761cf6a51a7d2bc187f2d5f"],"state_sha256":"61e996ba6be44b3fef3f7f50a4360700594a22d325b4f7bcd8da7a708c20e420"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PfoHI6vw5V37xAjJZ4+oFHRpV72ek/MqBzD09/oWXv+IK4rpVFVjhsMgQvf2W5XpLI8MIHIANmDev7+C077tAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T11:34:03.769032Z","bundle_sha256":"a828fa4030d86c7b9d0f915394d1d9bccf7be55443700a1dfd743dfd971fdbd5"}}