{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:RP2GX56LD6CG6PZ4HRC3KUSSEW","short_pith_number":"pith:RP2GX56L","canonical_record":{"source":{"id":"1706.01967","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-06T20:45:30Z","cross_cats_sorted":[],"title_canon_sha256":"3e426d852f010416b211ca5e39cebf2fe48397e1ac5a116a5cc80bb3d9b0d53f","abstract_canon_sha256":"69ae8329f2788dac0c6ed92942b767b03c80d980aadba77c826393fab1266786"},"schema_version":"1.0"},"canonical_sha256":"8bf46bf7cb1f846f3f3c3c45b5525225919f041004604c448adadb5783f503f1","source":{"kind":"arxiv","id":"1706.01967","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.01967","created_at":"2026-05-17T23:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"1706.01967v2","created_at":"2026-05-17T23:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01967","created_at":"2026-05-17T23:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"RP2GX56LD6CG","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RP2GX56LD6CG6PZ4","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RP2GX56L","created_at":"2026-05-18T12:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:RP2GX56LD6CG6PZ4HRC3KUSSEW","target":"record","payload":{"canonical_record":{"source":{"id":"1706.01967","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-06T20:45:30Z","cross_cats_sorted":[],"title_canon_sha256":"3e426d852f010416b211ca5e39cebf2fe48397e1ac5a116a5cc80bb3d9b0d53f","abstract_canon_sha256":"69ae8329f2788dac0c6ed92942b767b03c80d980aadba77c826393fab1266786"},"schema_version":"1.0"},"canonical_sha256":"8bf46bf7cb1f846f3f3c3c45b5525225919f041004604c448adadb5783f503f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:04.900902Z","signature_b64":"vkdl4wnjLfdbznaLfOlgWM4HBxxx4wLUHCC3RqyDZQlDJeSz8WBUUJz14/Zmx8YkSYjBe6woXxIVt4avsU1XCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bf46bf7cb1f846f3f3c3c45b5525225919f041004604c448adadb5783f503f1","last_reissued_at":"2026-05-17T23:44:04.900370Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:04.900370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.01967","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":"2026-05-17T23:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sq6nnpIDN7LT0pEtjIwjHqJ24WOrG9QbtrpvV4JLpVqrye0+G0j390TRKFL/jbxJ9Vu/fVPg9HhcRvTjn1jxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:55:19.642687Z"},"content_sha256":"a1c471f52ed336833deef5fcaf4e2572d7b016f052306cb7a38b2f9cd8a66606","schema_version":"1.0","event_id":"sha256:a1c471f52ed336833deef5fcaf4e2572d7b016f052306cb7a38b2f9cd8a66606"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:RP2GX56LD6CG6PZ4HRC3KUSSEW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synergistic Union of Word2Vec and Lexicon for Domain Specific Semantic Similarity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amal Shehan Perera, Buddhi Ayesha, Dimuthu Lakmal, Keet Sugathadasa, Madhavi Perera, Nisansa de Silva, Vindula Jayawardana","submitted_at":"2017-06-06T20:45:30Z","abstract_excerpt":"Semantic similarity measures are an important part in Natural Language Processing tasks. However Semantic similarity measures built for general use do not perform well within specific domains. Therefore in this study we introduce a domain specific semantic similarity measure that was created by the synergistic union of word2vec, a word embedding method that is used for semantic similarity calculation and lexicon based (lexical) semantic similarity methods. We prove that this proposed methodology out performs word embedding methods trained on generic corpus and methods trained on domain specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01967","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":""},"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":"2026-05-17T23:44:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M8oB0JHd+oxppMhVQX2VX0jKuA9iLQncUMzNq/fEXDtkhzlhtB3TQSv2drymoEk1HiwfnDno4FsaU5poIM4ECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T07:55:19.643071Z"},"content_sha256":"318703fdb72574f101ee652cead17f76f17cfd37f7dfa1ab74f17de087124148","schema_version":"1.0","event_id":"sha256:318703fdb72574f101ee652cead17f76f17cfd37f7dfa1ab74f17de087124148"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RP2GX56LD6CG6PZ4HRC3KUSSEW/bundle.json","state_url":"https://pith.science/pith/RP2GX56LD6CG6PZ4HRC3KUSSEW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RP2GX56LD6CG6PZ4HRC3KUSSEW/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":"2026-05-31T07:55:19Z","links":{"resolver":"https://pith.science/pith/RP2GX56LD6CG6PZ4HRC3KUSSEW","bundle":"https://pith.science/pith/RP2GX56LD6CG6PZ4HRC3KUSSEW/bundle.json","state":"https://pith.science/pith/RP2GX56LD6CG6PZ4HRC3KUSSEW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RP2GX56LD6CG6PZ4HRC3KUSSEW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:RP2GX56LD6CG6PZ4HRC3KUSSEW","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":"69ae8329f2788dac0c6ed92942b767b03c80d980aadba77c826393fab1266786","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-06T20:45:30Z","title_canon_sha256":"3e426d852f010416b211ca5e39cebf2fe48397e1ac5a116a5cc80bb3d9b0d53f"},"schema_version":"1.0","source":{"id":"1706.01967","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.01967","created_at":"2026-05-17T23:44:04Z"},{"alias_kind":"arxiv_version","alias_value":"1706.01967v2","created_at":"2026-05-17T23:44:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01967","created_at":"2026-05-17T23:44:04Z"},{"alias_kind":"pith_short_12","alias_value":"RP2GX56LD6CG","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"RP2GX56LD6CG6PZ4","created_at":"2026-05-18T12:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"RP2GX56L","created_at":"2026-05-18T12:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:318703fdb72574f101ee652cead17f76f17cfd37f7dfa1ab74f17de087124148","target":"graph","created_at":"2026-05-17T23:44:04Z","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":"Semantic similarity measures are an important part in Natural Language Processing tasks. However Semantic similarity measures built for general use do not perform well within specific domains. Therefore in this study we introduce a domain specific semantic similarity measure that was created by the synergistic union of word2vec, a word embedding method that is used for semantic similarity calculation and lexicon based (lexical) semantic similarity methods. We prove that this proposed methodology out performs word embedding methods trained on generic corpus and methods trained on domain specifi","authors_text":"Amal Shehan Perera, Buddhi Ayesha, Dimuthu Lakmal, Keet Sugathadasa, Madhavi Perera, Nisansa de Silva, Vindula Jayawardana","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-06T20:45:30Z","title":"Synergistic Union of Word2Vec and Lexicon for Domain Specific Semantic Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01967","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:a1c471f52ed336833deef5fcaf4e2572d7b016f052306cb7a38b2f9cd8a66606","target":"record","created_at":"2026-05-17T23:44:04Z","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":"69ae8329f2788dac0c6ed92942b767b03c80d980aadba77c826393fab1266786","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-06-06T20:45:30Z","title_canon_sha256":"3e426d852f010416b211ca5e39cebf2fe48397e1ac5a116a5cc80bb3d9b0d53f"},"schema_version":"1.0","source":{"id":"1706.01967","kind":"arxiv","version":2}},"canonical_sha256":"8bf46bf7cb1f846f3f3c3c45b5525225919f041004604c448adadb5783f503f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bf46bf7cb1f846f3f3c3c45b5525225919f041004604c448adadb5783f503f1","first_computed_at":"2026-05-17T23:44:04.900370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:04.900370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vkdl4wnjLfdbznaLfOlgWM4HBxxx4wLUHCC3RqyDZQlDJeSz8WBUUJz14/Zmx8YkSYjBe6woXxIVt4avsU1XCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:04.900902Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.01967","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1c471f52ed336833deef5fcaf4e2572d7b016f052306cb7a38b2f9cd8a66606","sha256:318703fdb72574f101ee652cead17f76f17cfd37f7dfa1ab74f17de087124148"],"state_sha256":"32c1b0aa790c31fa30b267fd508b291b981dc84cd26d58b36c09b6baf379ce0d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZqW+d22bc6hGN/eacv91K3QcEQJUJK7BsmSBy61Y3Dx+R/RPXB/hgL5TMoCmMB42eK0IZoW+UiGsDhPNwgKVAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T07:55:19.645386Z","bundle_sha256":"e379579bad5031b678a68c4bc42cbe58a4e4ca80e9315d2869cc905a1764108e"}}