{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:N6IUA3UXOOPMZAFMQCEW3TBQEZ","short_pith_number":"pith:N6IUA3UX","schema_version":"1.0","canonical_sha256":"6f91406e97739ecc80ac80896dcc30266bf99dc0932be467e401356d531c25ad","source":{"kind":"arxiv","id":"1705.06123","version":2},"attestation_state":"computed","paper":{"title":"JCTC: A Large Job posting Corpus for Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"2), (2) University of Chinese Academy of Sciences, 3), (3) Department of Communication, (4) Department of Mathematics, China, Chinese Academy of Sciences, Chongyang Gu (1, Han Zhou (1), Haoyu Xu (1, Hong Kong SAR), Information Engineering, Junjie Zhang (3) ((1) Shanghai Advanced Research Institute, Sengpan Kou (4), Shanghai University, The Chinese University of Hong Kong","submitted_at":"2017-05-17T12:32:05Z","abstract_excerpt":"The absence of an appropriate text classification corpus makes the massive amount of online job information unusable for labor market analysis. This paper presents JCTC, a large job posting corpus for text classification. In JCTC construction framework, a formal specification issued by the Chinese central government is chosen as the classification standard. The unsupervised learning (WE-cos), supervised learning algorithm (SVM) and human judgements are all used in the construction process. JCTC has 102581 online job postings distributed in 465 categories. The method proposed here can not only "},"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":"1705.06123","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-05-17T12:32:05Z","cross_cats_sorted":[],"title_canon_sha256":"37c46ea558f95010a0982e57500eda49b894d9d5b6cef14fa1040dca47aeed2d","abstract_canon_sha256":"01cfb250809e48f14c2afc19b437144e27ea0ef923e62ec47f602b4186ec574f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:42:38.740121Z","signature_b64":"KAd/q7jARfD1lqnQ9pU8cKIjBMuALU6MjRNHuolaVY/OdGDSVi6WyoRKiNfbSTYZPGLCopIvhVYaXr13skHpBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f91406e97739ecc80ac80896dcc30266bf99dc0932be467e401356d531c25ad","last_reissued_at":"2026-05-18T00:42:38.739488Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:42:38.739488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JCTC: A Large Job posting Corpus for Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"2), (2) University of Chinese Academy of Sciences, 3), (3) Department of Communication, (4) Department of Mathematics, China, Chinese Academy of Sciences, Chongyang Gu (1, Han Zhou (1), Haoyu Xu (1, Hong Kong SAR), Information Engineering, Junjie Zhang (3) ((1) Shanghai Advanced Research Institute, Sengpan Kou (4), Shanghai University, The Chinese University of Hong Kong","submitted_at":"2017-05-17T12:32:05Z","abstract_excerpt":"The absence of an appropriate text classification corpus makes the massive amount of online job information unusable for labor market analysis. This paper presents JCTC, a large job posting corpus for text classification. In JCTC construction framework, a formal specification issued by the Chinese central government is chosen as the classification standard. The unsupervised learning (WE-cos), supervised learning algorithm (SVM) and human judgements are all used in the construction process. JCTC has 102581 online job postings distributed in 465 categories. The method proposed here can not only "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.06123","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":"1705.06123","created_at":"2026-05-18T00:42:38.739582+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.06123v2","created_at":"2026-05-18T00:42:38.739582+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.06123","created_at":"2026-05-18T00:42:38.739582+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6IUA3UXOOPM","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6IUA3UXOOPMZAFM","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6IUA3UX","created_at":"2026-05-18T12:31:31.346846+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/N6IUA3UXOOPMZAFMQCEW3TBQEZ","json":"https://pith.science/pith/N6IUA3UXOOPMZAFMQCEW3TBQEZ.json","graph_json":"https://pith.science/api/pith-number/N6IUA3UXOOPMZAFMQCEW3TBQEZ/graph.json","events_json":"https://pith.science/api/pith-number/N6IUA3UXOOPMZAFMQCEW3TBQEZ/events.json","paper":"https://pith.science/paper/N6IUA3UX"},"agent_actions":{"view_html":"https://pith.science/pith/N6IUA3UXOOPMZAFMQCEW3TBQEZ","download_json":"https://pith.science/pith/N6IUA3UXOOPMZAFMQCEW3TBQEZ.json","view_paper":"https://pith.science/paper/N6IUA3UX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.06123&json=true","fetch_graph":"https://pith.science/api/pith-number/N6IUA3UXOOPMZAFMQCEW3TBQEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/N6IUA3UXOOPMZAFMQCEW3TBQEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6IUA3UXOOPMZAFMQCEW3TBQEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6IUA3UXOOPMZAFMQCEW3TBQEZ/action/storage_attestation","attest_author":"https://pith.science/pith/N6IUA3UXOOPMZAFMQCEW3TBQEZ/action/author_attestation","sign_citation":"https://pith.science/pith/N6IUA3UXOOPMZAFMQCEW3TBQEZ/action/citation_signature","submit_replication":"https://pith.science/pith/N6IUA3UXOOPMZAFMQCEW3TBQEZ/action/replication_record"}},"created_at":"2026-05-18T00:42:38.739582+00:00","updated_at":"2026-05-18T00:42:38.739582+00:00"}