{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OYZNRCHW4N6N6YCOIPVMTRTP7O","short_pith_number":"pith:OYZNRCHW","schema_version":"1.0","canonical_sha256":"7632d888f6e37cdf604e43eac9c66ffbacfcc2dfabbd5ca23bbca340cca8c28d","source":{"kind":"arxiv","id":"1906.02053","version":1},"attestation_state":"computed","paper":{"title":"KAS-term: Extracting Slovene Terms from Doctoral Theses via Supervised Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Darja Fi\\v{s}er, Nikola Ljube\\v{s}i\\'c, Toma\\v{z} Erjavec","submitted_at":"2019-06-05T14:36:59Z","abstract_excerpt":"This paper presents a dataset and supervised learning experiments for term extraction from Slovene academic texts. Term candidates in the dataset were extracted via morphosyntactic patterns and annotated for their termness by four annotators. Experiments on the dataset show that most co-occurrence statistics, applied after morphosyntactic patterns and a frequency threshold, perform close to random and that the results can be significantly improved by combining, with supervised machine learning, all the seven statistic measures included in the dataset. On multi-word terms the model using all st"},"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":"1906.02053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-05T14:36:59Z","cross_cats_sorted":[],"title_canon_sha256":"7534044f879cbae801b565b4f756ca69dd83c27ace916711fb4e72536346d591","abstract_canon_sha256":"73a09e1344f21cc38a6c93d6a3ca02e9844a4aa9bfc0b445aac51a02cd4514de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:05.383661Z","signature_b64":"sq9bh9NDBFqApm4v237gsesWLovHX/7z6uvRhmmQ10HI1wFeeRE0YReGwckhH+Mi4nFZHr20f8TC1PeveUH0DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7632d888f6e37cdf604e43eac9c66ffbacfcc2dfabbd5ca23bbca340cca8c28d","last_reissued_at":"2026-05-17T23:44:05.383227Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:05.383227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KAS-term: Extracting Slovene Terms from Doctoral Theses via Supervised Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Darja Fi\\v{s}er, Nikola Ljube\\v{s}i\\'c, Toma\\v{z} Erjavec","submitted_at":"2019-06-05T14:36:59Z","abstract_excerpt":"This paper presents a dataset and supervised learning experiments for term extraction from Slovene academic texts. Term candidates in the dataset were extracted via morphosyntactic patterns and annotated for their termness by four annotators. Experiments on the dataset show that most co-occurrence statistics, applied after morphosyntactic patterns and a frequency threshold, perform close to random and that the results can be significantly improved by combining, with supervised machine learning, all the seven statistic measures included in the dataset. On multi-word terms the model using all st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02053","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":"1906.02053","created_at":"2026-05-17T23:44:05.383290+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.02053v1","created_at":"2026-05-17T23:44:05.383290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02053","created_at":"2026-05-17T23:44:05.383290+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYZNRCHW4N6N","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYZNRCHW4N6N6YCO","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYZNRCHW","created_at":"2026-05-18T12:33:24.271573+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/OYZNRCHW4N6N6YCOIPVMTRTP7O","json":"https://pith.science/pith/OYZNRCHW4N6N6YCOIPVMTRTP7O.json","graph_json":"https://pith.science/api/pith-number/OYZNRCHW4N6N6YCOIPVMTRTP7O/graph.json","events_json":"https://pith.science/api/pith-number/OYZNRCHW4N6N6YCOIPVMTRTP7O/events.json","paper":"https://pith.science/paper/OYZNRCHW"},"agent_actions":{"view_html":"https://pith.science/pith/OYZNRCHW4N6N6YCOIPVMTRTP7O","download_json":"https://pith.science/pith/OYZNRCHW4N6N6YCOIPVMTRTP7O.json","view_paper":"https://pith.science/paper/OYZNRCHW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.02053&json=true","fetch_graph":"https://pith.science/api/pith-number/OYZNRCHW4N6N6YCOIPVMTRTP7O/graph.json","fetch_events":"https://pith.science/api/pith-number/OYZNRCHW4N6N6YCOIPVMTRTP7O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYZNRCHW4N6N6YCOIPVMTRTP7O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYZNRCHW4N6N6YCOIPVMTRTP7O/action/storage_attestation","attest_author":"https://pith.science/pith/OYZNRCHW4N6N6YCOIPVMTRTP7O/action/author_attestation","sign_citation":"https://pith.science/pith/OYZNRCHW4N6N6YCOIPVMTRTP7O/action/citation_signature","submit_replication":"https://pith.science/pith/OYZNRCHW4N6N6YCOIPVMTRTP7O/action/replication_record"}},"created_at":"2026-05-17T23:44:05.383290+00:00","updated_at":"2026-05-17T23:44:05.383290+00:00"}