{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SNT6HOVUEYPDTLNWGQHDLP62AC","short_pith_number":"pith:SNT6HOVU","schema_version":"1.0","canonical_sha256":"9367e3bab4261e39adb6340e35bfda009c6b6f64f420b5a3b5b7d2236f1e499c","source":{"kind":"arxiv","id":"1906.07591","version":1},"attestation_state":"computed","paper":{"title":"Query Generation for Patent Retrieval with Keyword Extraction based on Syntactic Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Evangelos Kanoulas, Julien Rossi, Matthias Wirth","submitted_at":"2019-06-18T14:03:14Z","abstract_excerpt":"This paper describes a new method to extract relevant keywords from patent claims, as part of the task of retrieving other patents with similar claims (search for prior art). The method combines a qualitative analysis of the writing style of the claims with NLP methods to parse text, in order to represent a legal text as a specialization arborescence of terms. In this setting, the set of extracted keywords are yielding better search results than keywords extracted with traditional methods such as tf-idf. The performance is measured on the search results of a query consisting of the extracted k"},"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":"1906.07591","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2019-06-18T14:03:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"63af46bbbcb88d89588dbf6fe50683a6b92dd551c97e7c4880cf0d41d1a9c919","abstract_canon_sha256":"1070328140a5a426d1eb378829d2326ebd22bc9e98a6c167ffb6681a889030b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:07.397600Z","signature_b64":"al0FNqLWa0JrgTtJrjvCw9WHqYpMMHK7sV57AcY5zeOTqTBbggSp7Vcg1Wve+x4GJclMIe6HHd1TkNxMDImaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9367e3bab4261e39adb6340e35bfda009c6b6f64f420b5a3b5b7d2236f1e499c","last_reissued_at":"2026-05-17T23:43:07.397114Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:07.397114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Query Generation for Patent Retrieval with Keyword Extraction based on Syntactic Features","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Evangelos Kanoulas, Julien Rossi, Matthias Wirth","submitted_at":"2019-06-18T14:03:14Z","abstract_excerpt":"This paper describes a new method to extract relevant keywords from patent claims, as part of the task of retrieving other patents with similar claims (search for prior art). The method combines a qualitative analysis of the writing style of the claims with NLP methods to parse text, in order to represent a legal text as a specialization arborescence of terms. In this setting, the set of extracted keywords are yielding better search results than keywords extracted with traditional methods such as tf-idf. The performance is measured on the search results of a query consisting of the extracted k"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07591","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":"1906.07591","created_at":"2026-05-17T23:43:07.397185+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.07591v1","created_at":"2026-05-17T23:43:07.397185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07591","created_at":"2026-05-17T23:43:07.397185+00:00"},{"alias_kind":"pith_short_12","alias_value":"SNT6HOVUEYPD","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"SNT6HOVUEYPDTLNW","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"SNT6HOVU","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14946","citing_title":"FullRecall: A Semantic Search-Based Ranking Approach for Maximizing Recall in Patent Retrieval","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SNT6HOVUEYPDTLNWGQHDLP62AC","json":"https://pith.science/pith/SNT6HOVUEYPDTLNWGQHDLP62AC.json","graph_json":"https://pith.science/api/pith-number/SNT6HOVUEYPDTLNWGQHDLP62AC/graph.json","events_json":"https://pith.science/api/pith-number/SNT6HOVUEYPDTLNWGQHDLP62AC/events.json","paper":"https://pith.science/paper/SNT6HOVU"},"agent_actions":{"view_html":"https://pith.science/pith/SNT6HOVUEYPDTLNWGQHDLP62AC","download_json":"https://pith.science/pith/SNT6HOVUEYPDTLNWGQHDLP62AC.json","view_paper":"https://pith.science/paper/SNT6HOVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.07591&json=true","fetch_graph":"https://pith.science/api/pith-number/SNT6HOVUEYPDTLNWGQHDLP62AC/graph.json","fetch_events":"https://pith.science/api/pith-number/SNT6HOVUEYPDTLNWGQHDLP62AC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SNT6HOVUEYPDTLNWGQHDLP62AC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SNT6HOVUEYPDTLNWGQHDLP62AC/action/storage_attestation","attest_author":"https://pith.science/pith/SNT6HOVUEYPDTLNWGQHDLP62AC/action/author_attestation","sign_citation":"https://pith.science/pith/SNT6HOVUEYPDTLNWGQHDLP62AC/action/citation_signature","submit_replication":"https://pith.science/pith/SNT6HOVUEYPDTLNWGQHDLP62AC/action/replication_record"}},"created_at":"2026-05-17T23:43:07.397185+00:00","updated_at":"2026-05-17T23:43:07.397185+00:00"}