{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PGQ7ZV6AO63RCIHIG2GC22DE5L","short_pith_number":"pith:PGQ7ZV6A","schema_version":"1.0","canonical_sha256":"79a1fcd7c077b71120e8368c2d6864eaea93b5fc922a25bec5ca6f31b9080d11","source":{"kind":"arxiv","id":"2505.24640","version":1},"attestation_state":"computed","paper":{"title":"Efficient Text Encoders for Labor Market Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chris Develder, Jens-Joris Decorte, Jeroen Van Hautte, Thomas Demeester","submitted_at":"2025-05-30T14:27:25Z","abstract_excerpt":"Labor market analysis relies on extracting insights from job advertisements, which provide valuable yet unstructured information on job titles and corresponding skill requirements. While state-of-the-art methods for skill extraction achieve strong performance, they depend on large language models (LLMs), which are computationally expensive and slow. In this paper, we propose \\textbf{ConTeXT-match}, a novel contrastive learning approach with token-level attention that is well-suited for the extreme multi-label classification task of skill classification. \\textbf{ConTeXT-match} significantly imp"},"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":"2505.24640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T14:27:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"926a759f39ed983c34574874cb72753445143abe55cb9d59b4cafbed2ab5940a","abstract_canon_sha256":"1599969eb92ea9cfcf50fdd32a1c967011507c381904e06e098ae69dbc2d98f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:49.197790Z","signature_b64":"Rl7uA2cf0aEd/wM90Y+rFF/MY5ffF9+fvryYGm8mQOzKFvuoQi3hshQzCuYcdpyvxhu2aIi8HPNDL3+ph8ELAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79a1fcd7c077b71120e8368c2d6864eaea93b5fc922a25bec5ca6f31b9080d11","last_reissued_at":"2026-07-05T11:44:49.197272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:49.197272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Text Encoders for Labor Market Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chris Develder, Jens-Joris Decorte, Jeroen Van Hautte, Thomas Demeester","submitted_at":"2025-05-30T14:27:25Z","abstract_excerpt":"Labor market analysis relies on extracting insights from job advertisements, which provide valuable yet unstructured information on job titles and corresponding skill requirements. While state-of-the-art methods for skill extraction achieve strong performance, they depend on large language models (LLMs), which are computationally expensive and slow. In this paper, we propose \\textbf{ConTeXT-match}, a novel contrastive learning approach with token-level attention that is well-suited for the extreme multi-label classification task of skill classification. \\textbf{ConTeXT-match} significantly imp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24640","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.24640/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2505.24640","created_at":"2026-07-05T11:44:49.197342+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24640v1","created_at":"2026-07-05T11:44:49.197342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24640","created_at":"2026-07-05T11:44:49.197342+00:00"},{"alias_kind":"pith_short_12","alias_value":"PGQ7ZV6AO63R","created_at":"2026-07-05T11:44:49.197342+00:00"},{"alias_kind":"pith_short_16","alias_value":"PGQ7ZV6AO63RCIHI","created_at":"2026-07-05T11:44:49.197342+00:00"},{"alias_kind":"pith_short_8","alias_value":"PGQ7ZV6A","created_at":"2026-07-05T11:44:49.197342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.07969","citing_title":"Unified Work Embeddings: Contrastive Learning of a Bidirectional Multi-task Ranker","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13055","citing_title":"WorkRB: A Community-Driven Evaluation Framework for AI in the Work Domain","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PGQ7ZV6AO63RCIHIG2GC22DE5L","json":"https://pith.science/pith/PGQ7ZV6AO63RCIHIG2GC22DE5L.json","graph_json":"https://pith.science/api/pith-number/PGQ7ZV6AO63RCIHIG2GC22DE5L/graph.json","events_json":"https://pith.science/api/pith-number/PGQ7ZV6AO63RCIHIG2GC22DE5L/events.json","paper":"https://pith.science/paper/PGQ7ZV6A"},"agent_actions":{"view_html":"https://pith.science/pith/PGQ7ZV6AO63RCIHIG2GC22DE5L","download_json":"https://pith.science/pith/PGQ7ZV6AO63RCIHIG2GC22DE5L.json","view_paper":"https://pith.science/paper/PGQ7ZV6A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24640&json=true","fetch_graph":"https://pith.science/api/pith-number/PGQ7ZV6AO63RCIHIG2GC22DE5L/graph.json","fetch_events":"https://pith.science/api/pith-number/PGQ7ZV6AO63RCIHIG2GC22DE5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PGQ7ZV6AO63RCIHIG2GC22DE5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PGQ7ZV6AO63RCIHIG2GC22DE5L/action/storage_attestation","attest_author":"https://pith.science/pith/PGQ7ZV6AO63RCIHIG2GC22DE5L/action/author_attestation","sign_citation":"https://pith.science/pith/PGQ7ZV6AO63RCIHIG2GC22DE5L/action/citation_signature","submit_replication":"https://pith.science/pith/PGQ7ZV6AO63RCIHIG2GC22DE5L/action/replication_record"}},"created_at":"2026-07-05T11:44:49.197342+00:00","updated_at":"2026-07-05T11:44:49.197342+00:00"}