{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:JYANT65SL7IVPXE6WIY4D3HJD2","short_pith_number":"pith:JYANT65S","schema_version":"1.0","canonical_sha256":"4e00d9fbb25fd157dc9eb231c1ece91ebc377332e1667160560b9d1a503cba78","source":{"kind":"arxiv","id":"1408.3731","version":2},"attestation_state":"computed","paper":{"title":"Unsupervised Keyword Extraction from Polish Legal Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Micha{\\l} Jungiewicz, Micha{\\l} {\\L}opuszy\\'nski","submitted_at":"2014-08-16T10:09:28Z","abstract_excerpt":"In this work, we present an application of the recently proposed unsupervised keyword extraction algorithm RAKE to a corpus of Polish legal texts from the field of public procurement. RAKE is essentially a language and domain independent method. Its only language-specific input is a stoplist containing a set of non-content words. The performance of the method heavily depends on the choice of such a stoplist, which should be domain adopted. Therefore, we complement RAKE algorithm with an automatic approach to selecting non-content words, which is based on the statistical properties of term dist"},"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":"1408.3731","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-08-16T10:09:28Z","cross_cats_sorted":[],"title_canon_sha256":"b7f966100bb2b5c06f939c6c6dfce94ad83c62ab9053d2a2f80d0e2c20c229ca","abstract_canon_sha256":"1ac704d99bca72c520777bfff4376eacc697a9b75d90adb3099c2862c028e242"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:38:45.851064Z","signature_b64":"IAA1rAQz+MGYQyBn2dC3UIO190tESIuyY6iPJWfj39OVqxUgvo2ypA2qUWMS/i6V6/sFp+TPA61hn8ZKfIhSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e00d9fbb25fd157dc9eb231c1ece91ebc377332e1667160560b9d1a503cba78","last_reissued_at":"2026-05-18T02:38:45.850591Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:38:45.850591Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Keyword Extraction from Polish Legal Texts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Micha{\\l} Jungiewicz, Micha{\\l} {\\L}opuszy\\'nski","submitted_at":"2014-08-16T10:09:28Z","abstract_excerpt":"In this work, we present an application of the recently proposed unsupervised keyword extraction algorithm RAKE to a corpus of Polish legal texts from the field of public procurement. RAKE is essentially a language and domain independent method. Its only language-specific input is a stoplist containing a set of non-content words. The performance of the method heavily depends on the choice of such a stoplist, which should be domain adopted. Therefore, we complement RAKE algorithm with an automatic approach to selecting non-content words, which is based on the statistical properties of term dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1408.3731","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1408.3731","created_at":"2026-05-18T02:38:45.850662+00:00"},{"alias_kind":"arxiv_version","alias_value":"1408.3731v2","created_at":"2026-05-18T02:38:45.850662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1408.3731","created_at":"2026-05-18T02:38:45.850662+00:00"},{"alias_kind":"pith_short_12","alias_value":"JYANT65SL7IV","created_at":"2026-05-18T12:28:35.611951+00:00"},{"alias_kind":"pith_short_16","alias_value":"JYANT65SL7IVPXE6","created_at":"2026-05-18T12:28:35.611951+00:00"},{"alias_kind":"pith_short_8","alias_value":"JYANT65S","created_at":"2026-05-18T12:28:35.611951+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/JYANT65SL7IVPXE6WIY4D3HJD2","json":"https://pith.science/pith/JYANT65SL7IVPXE6WIY4D3HJD2.json","graph_json":"https://pith.science/api/pith-number/JYANT65SL7IVPXE6WIY4D3HJD2/graph.json","events_json":"https://pith.science/api/pith-number/JYANT65SL7IVPXE6WIY4D3HJD2/events.json","paper":"https://pith.science/paper/JYANT65S"},"agent_actions":{"view_html":"https://pith.science/pith/JYANT65SL7IVPXE6WIY4D3HJD2","download_json":"https://pith.science/pith/JYANT65SL7IVPXE6WIY4D3HJD2.json","view_paper":"https://pith.science/paper/JYANT65S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1408.3731&json=true","fetch_graph":"https://pith.science/api/pith-number/JYANT65SL7IVPXE6WIY4D3HJD2/graph.json","fetch_events":"https://pith.science/api/pith-number/JYANT65SL7IVPXE6WIY4D3HJD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JYANT65SL7IVPXE6WIY4D3HJD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JYANT65SL7IVPXE6WIY4D3HJD2/action/storage_attestation","attest_author":"https://pith.science/pith/JYANT65SL7IVPXE6WIY4D3HJD2/action/author_attestation","sign_citation":"https://pith.science/pith/JYANT65SL7IVPXE6WIY4D3HJD2/action/citation_signature","submit_replication":"https://pith.science/pith/JYANT65SL7IVPXE6WIY4D3HJD2/action/replication_record"}},"created_at":"2026-05-18T02:38:45.850662+00:00","updated_at":"2026-05-18T02:38:45.850662+00:00"}