{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:THSJVGPPXZQUKMN4CKKD4V7YDE","short_pith_number":"pith:THSJVGPP","schema_version":"1.0","canonical_sha256":"99e49a99efbe614531bc12943e57f8190e2b2c88f18f1926a189d8f58790961d","source":{"kind":"arxiv","id":"2304.11060","version":2},"attestation_state":"computed","paper":{"title":"SkillGPT: a RESTful API service for skill extraction and standardization using a Large Language Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Kang, Nan Li, Tijl De Bie","submitted_at":"2023-04-17T08:43:20Z","abstract_excerpt":"We present SkillGPT, a tool for skill extraction and standardization (SES) from free-style job descriptions and user profiles with an open-source Large Language Model (LLM) as backbone. Most previous methods for similar tasks either need supervision or rely on heavy data-preprocessing and feature engineering. Directly prompting the latest conversational LLM for standard skills, however, is slow, costly and inaccurate. In contrast, SkillGPT utilizes a LLM to perform its tasks in steps via summarization and vector similarity search, to balance speed with precision. The backbone LLM of SkillGPT i"},"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":"2304.11060","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-04-17T08:43:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8733839abadf59cbb99813e9dcc23c548373a4f87689ec92756db46f27a473fe","abstract_canon_sha256":"f2a55eb875429bc0ce72b8cb056c1c80f39224e6566d7eb80682fa165686b8e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:01.271485Z","signature_b64":"W3KYP2R3pPMf3QNUiRPlnUBQIWUEZjSvHO0kFJHudCNSYdC/HqTFGUqhLVGUCgR0aUBgVzyevkN3QCojNwAPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99e49a99efbe614531bc12943e57f8190e2b2c88f18f1926a189d8f58790961d","last_reissued_at":"2026-07-05T07:02:01.271005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:01.271005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SkillGPT: a RESTful API service for skill extraction and standardization using a Large Language Model","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bo Kang, Nan Li, Tijl De Bie","submitted_at":"2023-04-17T08:43:20Z","abstract_excerpt":"We present SkillGPT, a tool for skill extraction and standardization (SES) from free-style job descriptions and user profiles with an open-source Large Language Model (LLM) as backbone. Most previous methods for similar tasks either need supervision or rely on heavy data-preprocessing and feature engineering. Directly prompting the latest conversational LLM for standard skills, however, is slow, costly and inaccurate. In contrast, SkillGPT utilizes a LLM to perform its tasks in steps via summarization and vector similarity search, to balance speed with precision. The backbone LLM of SkillGPT i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11060","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/2304.11060/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":"2304.11060","created_at":"2026-07-05T07:02:01.271066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.11060v2","created_at":"2026-07-05T07:02:01.271066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11060","created_at":"2026-07-05T07:02:01.271066+00:00"},{"alias_kind":"pith_short_12","alias_value":"THSJVGPPXZQU","created_at":"2026-07-05T07:02:01.271066+00:00"},{"alias_kind":"pith_short_16","alias_value":"THSJVGPPXZQUKMN4","created_at":"2026-07-05T07:02:01.271066+00:00"},{"alias_kind":"pith_short_8","alias_value":"THSJVGPP","created_at":"2026-07-05T07:02:01.271066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.25401","citing_title":"DGAI: Decoupled On-Disk Graph-Based ANN Index for Efficient Updates and Queries","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10135","citing_title":"ScaleGANN: Accelerate Large-Scale ANN Indexing by Cost-effective Cloud GPUs","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/THSJVGPPXZQUKMN4CKKD4V7YDE","json":"https://pith.science/pith/THSJVGPPXZQUKMN4CKKD4V7YDE.json","graph_json":"https://pith.science/api/pith-number/THSJVGPPXZQUKMN4CKKD4V7YDE/graph.json","events_json":"https://pith.science/api/pith-number/THSJVGPPXZQUKMN4CKKD4V7YDE/events.json","paper":"https://pith.science/paper/THSJVGPP"},"agent_actions":{"view_html":"https://pith.science/pith/THSJVGPPXZQUKMN4CKKD4V7YDE","download_json":"https://pith.science/pith/THSJVGPPXZQUKMN4CKKD4V7YDE.json","view_paper":"https://pith.science/paper/THSJVGPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.11060&json=true","fetch_graph":"https://pith.science/api/pith-number/THSJVGPPXZQUKMN4CKKD4V7YDE/graph.json","fetch_events":"https://pith.science/api/pith-number/THSJVGPPXZQUKMN4CKKD4V7YDE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/THSJVGPPXZQUKMN4CKKD4V7YDE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/THSJVGPPXZQUKMN4CKKD4V7YDE/action/storage_attestation","attest_author":"https://pith.science/pith/THSJVGPPXZQUKMN4CKKD4V7YDE/action/author_attestation","sign_citation":"https://pith.science/pith/THSJVGPPXZQUKMN4CKKD4V7YDE/action/citation_signature","submit_replication":"https://pith.science/pith/THSJVGPPXZQUKMN4CKKD4V7YDE/action/replication_record"}},"created_at":"2026-07-05T07:02:01.271066+00:00","updated_at":"2026-07-05T07:02:01.271066+00:00"}