{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6KEPIYZYRHST7V27XNHJ5M4QIC","short_pith_number":"pith:6KEPIYZY","schema_version":"1.0","canonical_sha256":"f288f4633889e53fd75fbb4e9eb39040ad3b8c4589ef42798fc3cab01ee181c3","source":{"kind":"arxiv","id":"2309.09708","version":2},"attestation_state":"computed","paper":{"title":"LLM4Jobs: Unsupervised occupation extraction and standardization leveraging Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Kang, Nan Li, Tijl De Bie","submitted_at":"2023-09-18T12:22:00Z","abstract_excerpt":"Automated occupation extraction and standardization from free-text job postings and resumes are crucial for applications like job recommendation and labor market policy formation. This paper introduces LLM4Jobs, a novel unsupervised methodology that taps into the capabilities of large language models (LLMs) for occupation coding. LLM4Jobs uniquely harnesses both the natural language understanding and generation capacities of LLMs. Evaluated on rigorous experimentation on synthetic and real-world datasets, we demonstrate that LLM4Jobs consistently surpasses unsupervised state-of-the-art benchma"},"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":"2309.09708","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-18T12:22:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff6233314418db495308f82529042e133cc0ab4cdb70ec63d3b520a0ca124fb6","abstract_canon_sha256":"b5e28921da1d12eef8f700c8b9cf8a07e894fa543b1c422a13160c571c5462ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:52:08.575373Z","signature_b64":"ocp5t/El2QcMAE1IE9JOcj099gNT80wi9VeDUS9XMuEPigy8noVQKsecThL2orEao3HopAkK+xk9cxFH07X6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f288f4633889e53fd75fbb4e9eb39040ad3b8c4589ef42798fc3cab01ee181c3","last_reissued_at":"2026-07-05T06:52:08.574886Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:52:08.574886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM4Jobs: Unsupervised occupation extraction and standardization leveraging Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Kang, Nan Li, Tijl De Bie","submitted_at":"2023-09-18T12:22:00Z","abstract_excerpt":"Automated occupation extraction and standardization from free-text job postings and resumes are crucial for applications like job recommendation and labor market policy formation. This paper introduces LLM4Jobs, a novel unsupervised methodology that taps into the capabilities of large language models (LLMs) for occupation coding. LLM4Jobs uniquely harnesses both the natural language understanding and generation capacities of LLMs. Evaluated on rigorous experimentation on synthetic and real-world datasets, we demonstrate that LLM4Jobs consistently surpasses unsupervised state-of-the-art benchma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09708","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.09708/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":"2309.09708","created_at":"2026-07-05T06:52:08.574940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09708v2","created_at":"2026-07-05T06:52:08.574940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09708","created_at":"2026-07-05T06:52:08.574940+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KEPIYZYRHST","created_at":"2026-07-05T06:52:08.574940+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KEPIYZYRHST7V27","created_at":"2026-07-05T06:52:08.574940+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KEPIYZY","created_at":"2026-07-05T06:52:08.574940+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.11722","citing_title":"STEP: Career-Path Recommendation via Temporal and Educational Trajectory Modeling","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6KEPIYZYRHST7V27XNHJ5M4QIC","json":"https://pith.science/pith/6KEPIYZYRHST7V27XNHJ5M4QIC.json","graph_json":"https://pith.science/api/pith-number/6KEPIYZYRHST7V27XNHJ5M4QIC/graph.json","events_json":"https://pith.science/api/pith-number/6KEPIYZYRHST7V27XNHJ5M4QIC/events.json","paper":"https://pith.science/paper/6KEPIYZY"},"agent_actions":{"view_html":"https://pith.science/pith/6KEPIYZYRHST7V27XNHJ5M4QIC","download_json":"https://pith.science/pith/6KEPIYZYRHST7V27XNHJ5M4QIC.json","view_paper":"https://pith.science/paper/6KEPIYZY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09708&json=true","fetch_graph":"https://pith.science/api/pith-number/6KEPIYZYRHST7V27XNHJ5M4QIC/graph.json","fetch_events":"https://pith.science/api/pith-number/6KEPIYZYRHST7V27XNHJ5M4QIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KEPIYZYRHST7V27XNHJ5M4QIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KEPIYZYRHST7V27XNHJ5M4QIC/action/storage_attestation","attest_author":"https://pith.science/pith/6KEPIYZYRHST7V27XNHJ5M4QIC/action/author_attestation","sign_citation":"https://pith.science/pith/6KEPIYZYRHST7V27XNHJ5M4QIC/action/citation_signature","submit_replication":"https://pith.science/pith/6KEPIYZYRHST7V27XNHJ5M4QIC/action/replication_record"}},"created_at":"2026-07-05T06:52:08.574940+00:00","updated_at":"2026-07-05T06:52:08.574940+00:00"}