{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RQ6IFDUJEHTGMJ2IWXOABLVPMQ","short_pith_number":"pith:RQ6IFDUJ","schema_version":"1.0","canonical_sha256":"8c3c828e8921e6662748b5dc00aeaf6404a0e6d890562d8b49442e8d0cdb5f52","source":{"kind":"arxiv","id":"1805.11611","version":1},"attestation_state":"computed","paper":{"title":"Semantically-informed distance and similarity measures for paraphrase plagiarism identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Esa\\'u Villatoro-Tello, Luis Villase\\~nor-Pineda, Manuel Montes-y-G\\'omez, Marc Franco-Salvador, Miguel A. \\'Alvarez-Carmona, Paolo Rosso","submitted_at":"2018-05-29T17:54:52Z","abstract_excerpt":"Paraphrase plagiarism identification represents a very complex task given that plagiarized texts are intentionally modified through several rewording techniques. Accordingly, this paper introduces two new measures for evaluating the relatedness of two given texts: a semantically-informed similarity measure and a semantically-informed edit distance. Both measures are able to extract semantic information from either an external resource or a distributed representation of words, resulting in informative features for training a supervised classifier for detecting paraphrase plagiarism. Obtained re"},"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":"1805.11611","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-29T17:54:52Z","cross_cats_sorted":[],"title_canon_sha256":"50587c2b9ec2b222a412f995c10a77945b2864c9d56d486f4ca5baa463c76158","abstract_canon_sha256":"85a5a94d974504eb6ea7878cdaafc090a824c33217b45b493f338f73c28b313f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:37.295928Z","signature_b64":"OkX/lvWC38j21EWjHxCgJNzdCsqBAR9SjdGoTXyxqAHqVy1ojxssYg3mPj5f+LTefXEQyCr1SQ/6q/5IthCqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c3c828e8921e6662748b5dc00aeaf6404a0e6d890562d8b49442e8d0cdb5f52","last_reissued_at":"2026-05-18T00:14:37.294924Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:37.294924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantically-informed distance and similarity measures for paraphrase plagiarism identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Esa\\'u Villatoro-Tello, Luis Villase\\~nor-Pineda, Manuel Montes-y-G\\'omez, Marc Franco-Salvador, Miguel A. \\'Alvarez-Carmona, Paolo Rosso","submitted_at":"2018-05-29T17:54:52Z","abstract_excerpt":"Paraphrase plagiarism identification represents a very complex task given that plagiarized texts are intentionally modified through several rewording techniques. Accordingly, this paper introduces two new measures for evaluating the relatedness of two given texts: a semantically-informed similarity measure and a semantically-informed edit distance. Both measures are able to extract semantic information from either an external resource or a distributed representation of words, resulting in informative features for training a supervised classifier for detecting paraphrase plagiarism. Obtained re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11611","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":"1805.11611","created_at":"2026-05-18T00:14:37.295124+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.11611v1","created_at":"2026-05-18T00:14:37.295124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11611","created_at":"2026-05-18T00:14:37.295124+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQ6IFDUJEHTG","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQ6IFDUJEHTGMJ2I","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQ6IFDUJ","created_at":"2026-05-18T12:32:50.500415+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/RQ6IFDUJEHTGMJ2IWXOABLVPMQ","json":"https://pith.science/pith/RQ6IFDUJEHTGMJ2IWXOABLVPMQ.json","graph_json":"https://pith.science/api/pith-number/RQ6IFDUJEHTGMJ2IWXOABLVPMQ/graph.json","events_json":"https://pith.science/api/pith-number/RQ6IFDUJEHTGMJ2IWXOABLVPMQ/events.json","paper":"https://pith.science/paper/RQ6IFDUJ"},"agent_actions":{"view_html":"https://pith.science/pith/RQ6IFDUJEHTGMJ2IWXOABLVPMQ","download_json":"https://pith.science/pith/RQ6IFDUJEHTGMJ2IWXOABLVPMQ.json","view_paper":"https://pith.science/paper/RQ6IFDUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.11611&json=true","fetch_graph":"https://pith.science/api/pith-number/RQ6IFDUJEHTGMJ2IWXOABLVPMQ/graph.json","fetch_events":"https://pith.science/api/pith-number/RQ6IFDUJEHTGMJ2IWXOABLVPMQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQ6IFDUJEHTGMJ2IWXOABLVPMQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQ6IFDUJEHTGMJ2IWXOABLVPMQ/action/storage_attestation","attest_author":"https://pith.science/pith/RQ6IFDUJEHTGMJ2IWXOABLVPMQ/action/author_attestation","sign_citation":"https://pith.science/pith/RQ6IFDUJEHTGMJ2IWXOABLVPMQ/action/citation_signature","submit_replication":"https://pith.science/pith/RQ6IFDUJEHTGMJ2IWXOABLVPMQ/action/replication_record"}},"created_at":"2026-05-18T00:14:37.295124+00:00","updated_at":"2026-05-18T00:14:37.295124+00:00"}