{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UXRK7QTF3KZMLVA7QK5TLMW7NJ","short_pith_number":"pith:UXRK7QTF","schema_version":"1.0","canonical_sha256":"a5e2afc265dab2c5d41f82bb35b2df6a4beffbfc9ce06fdb9e292f6c2679a11b","source":{"kind":"arxiv","id":"1903.04360","version":1},"attestation_state":"computed","paper":{"title":"Automatic Ontology Learning from Domain-Specific Short Unstructured Text Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Diego Klabjan, Dnyanesh Rajpathak, Ian Gibbs, Yiming Xu","submitted_at":"2019-03-07T18:48:02Z","abstract_excerpt":"Ontology learning is a critical task in industry, dealing with identifying and extracting concepts captured in text data such that these concepts can be used in different tasks, e.g. information retrieval. Ontology learning is non-trivial due to several reasons with limited amount of prior research work that automatically learns a domain specific ontology from data. In our work, we propose a two-stage classification system to automatically learn an ontology from unstructured text data. We first collect candidate concepts, which are classified into concepts and irrelevant collocates by our firs"},"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":"1903.04360","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-03-07T18:48:02Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7d4a256c6100f667d986679d8ee6947dfca6facdb52891542d7eb6a7c51bd92b","abstract_canon_sha256":"3f40e2e91a72d07d8d86ac42a80eb23e0a9bdcfb362023f2d85691daa137e662"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:35.557922Z","signature_b64":"HWGVkALZYzN84CctRARdzXa8o06sEW/qOm3okSYCs136kWOY9A+D2Kbs95fh9kFeoZVdNljg0I00e7Fwp7NbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5e2afc265dab2c5d41f82bb35b2df6a4beffbfc9ce06fdb9e292f6c2679a11b","last_reissued_at":"2026-05-17T23:51:35.557221Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:35.557221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automatic Ontology Learning from Domain-Specific Short Unstructured Text Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.IR","authors_text":"Diego Klabjan, Dnyanesh Rajpathak, Ian Gibbs, Yiming Xu","submitted_at":"2019-03-07T18:48:02Z","abstract_excerpt":"Ontology learning is a critical task in industry, dealing with identifying and extracting concepts captured in text data such that these concepts can be used in different tasks, e.g. information retrieval. Ontology learning is non-trivial due to several reasons with limited amount of prior research work that automatically learns a domain specific ontology from data. In our work, we propose a two-stage classification system to automatically learn an ontology from unstructured text data. We first collect candidate concepts, which are classified into concepts and irrelevant collocates by our firs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.04360","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":"1903.04360","created_at":"2026-05-17T23:51:35.557332+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.04360v1","created_at":"2026-05-17T23:51:35.557332+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04360","created_at":"2026-05-17T23:51:35.557332+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXRK7QTF3KZM","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXRK7QTF3KZMLVA7","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXRK7QTF","created_at":"2026-05-18T12:33:30.264802+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/UXRK7QTF3KZMLVA7QK5TLMW7NJ","json":"https://pith.science/pith/UXRK7QTF3KZMLVA7QK5TLMW7NJ.json","graph_json":"https://pith.science/api/pith-number/UXRK7QTF3KZMLVA7QK5TLMW7NJ/graph.json","events_json":"https://pith.science/api/pith-number/UXRK7QTF3KZMLVA7QK5TLMW7NJ/events.json","paper":"https://pith.science/paper/UXRK7QTF"},"agent_actions":{"view_html":"https://pith.science/pith/UXRK7QTF3KZMLVA7QK5TLMW7NJ","download_json":"https://pith.science/pith/UXRK7QTF3KZMLVA7QK5TLMW7NJ.json","view_paper":"https://pith.science/paper/UXRK7QTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.04360&json=true","fetch_graph":"https://pith.science/api/pith-number/UXRK7QTF3KZMLVA7QK5TLMW7NJ/graph.json","fetch_events":"https://pith.science/api/pith-number/UXRK7QTF3KZMLVA7QK5TLMW7NJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXRK7QTF3KZMLVA7QK5TLMW7NJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXRK7QTF3KZMLVA7QK5TLMW7NJ/action/storage_attestation","attest_author":"https://pith.science/pith/UXRK7QTF3KZMLVA7QK5TLMW7NJ/action/author_attestation","sign_citation":"https://pith.science/pith/UXRK7QTF3KZMLVA7QK5TLMW7NJ/action/citation_signature","submit_replication":"https://pith.science/pith/UXRK7QTF3KZMLVA7QK5TLMW7NJ/action/replication_record"}},"created_at":"2026-05-17T23:51:35.557332+00:00","updated_at":"2026-05-17T23:51:35.557332+00:00"}