{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2005:XX37J33CZPC5ZF2VCZFDDAGYLZ","short_pith_number":"pith:XX37J33C","schema_version":"1.0","canonical_sha256":"bdf7f4ef62cbc5dc9755164a3180d85e512d40b0ec1bd6637cc63d135bd1f248","source":{"kind":"arxiv","id":"cs/0512050","version":1},"attestation_state":"computed","paper":{"title":"Preference Learning in Terminology Extraction: A ROC-based approach","license":"","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"J\\'er\\^ome Az\\'e (LRI), Mathieu Roche (LRI), Mich\\`ele Sebag (LRI), Yves Kodratoff (LRI)","submitted_at":"2005-12-13T13:25:57Z","abstract_excerpt":"A key data preparation step in Text Mining, Term Extraction selects the terms, or collocation of words, attached to specific concepts. In this paper, the task of extracting relevant collocations is achieved through a supervised learning algorithm, exploiting a few collocations manually labelled as relevant/irrelevant. The candidate terms are described along 13 standard statistical criteria measures. From these examples, an evolutionary learning algorithm termed Roger, based on the optimization of the Area under the ROC curve criterion, extracts an order on the candidate terms. The robustness o"},"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":"cs/0512050","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.LG","submitted_at":"2005-12-13T13:25:57Z","cross_cats_sorted":[],"title_canon_sha256":"ad2cee3f8cf2b8dab680ca32dc811307a219ce713585a13cc6620ecb236e5610","abstract_canon_sha256":"64c31c52e181d264de15120f66595998ad7183dd7463ec9117eff0a3186100f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:08:54.929984Z","signature_b64":"ZaMwmNw7+1SuD9QblRMKKJmaoxsS327hug3rHjfVG11G+YX5JJ51kPLyb7mq8Vu31SA9gwpsGx83kjCBi9bgAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdf7f4ef62cbc5dc9755164a3180d85e512d40b0ec1bd6637cc63d135bd1f248","last_reissued_at":"2026-05-18T01:08:54.929292Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:08:54.929292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Preference Learning in Terminology Extraction: A ROC-based approach","license":"","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"J\\'er\\^ome Az\\'e (LRI), Mathieu Roche (LRI), Mich\\`ele Sebag (LRI), Yves Kodratoff (LRI)","submitted_at":"2005-12-13T13:25:57Z","abstract_excerpt":"A key data preparation step in Text Mining, Term Extraction selects the terms, or collocation of words, attached to specific concepts. In this paper, the task of extracting relevant collocations is achieved through a supervised learning algorithm, exploiting a few collocations manually labelled as relevant/irrelevant. The candidate terms are described along 13 standard statistical criteria measures. From these examples, an evolutionary learning algorithm termed Roger, based on the optimization of the Area under the ROC curve criterion, extracts an order on the candidate terms. The robustness o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0512050","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":"cs/0512050","created_at":"2026-05-18T01:08:54.929431+00:00"},{"alias_kind":"arxiv_version","alias_value":"cs/0512050v1","created_at":"2026-05-18T01:08:54.929431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0512050","created_at":"2026-05-18T01:08:54.929431+00:00"},{"alias_kind":"pith_short_12","alias_value":"XX37J33CZPC5","created_at":"2026-05-18T12:25:53.939244+00:00"},{"alias_kind":"pith_short_16","alias_value":"XX37J33CZPC5ZF2V","created_at":"2026-05-18T12:25:53.939244+00:00"},{"alias_kind":"pith_short_8","alias_value":"XX37J33C","created_at":"2026-05-18T12:25:53.939244+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/XX37J33CZPC5ZF2VCZFDDAGYLZ","json":"https://pith.science/pith/XX37J33CZPC5ZF2VCZFDDAGYLZ.json","graph_json":"https://pith.science/api/pith-number/XX37J33CZPC5ZF2VCZFDDAGYLZ/graph.json","events_json":"https://pith.science/api/pith-number/XX37J33CZPC5ZF2VCZFDDAGYLZ/events.json","paper":"https://pith.science/paper/XX37J33C"},"agent_actions":{"view_html":"https://pith.science/pith/XX37J33CZPC5ZF2VCZFDDAGYLZ","download_json":"https://pith.science/pith/XX37J33CZPC5ZF2VCZFDDAGYLZ.json","view_paper":"https://pith.science/paper/XX37J33C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cs/0512050&json=true","fetch_graph":"https://pith.science/api/pith-number/XX37J33CZPC5ZF2VCZFDDAGYLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XX37J33CZPC5ZF2VCZFDDAGYLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XX37J33CZPC5ZF2VCZFDDAGYLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XX37J33CZPC5ZF2VCZFDDAGYLZ/action/storage_attestation","attest_author":"https://pith.science/pith/XX37J33CZPC5ZF2VCZFDDAGYLZ/action/author_attestation","sign_citation":"https://pith.science/pith/XX37J33CZPC5ZF2VCZFDDAGYLZ/action/citation_signature","submit_replication":"https://pith.science/pith/XX37J33CZPC5ZF2VCZFDDAGYLZ/action/replication_record"}},"created_at":"2026-05-18T01:08:54.929431+00:00","updated_at":"2026-05-18T01:08:54.929431+00:00"}