{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4OK47KLN5J4KYCABPI2F7PK3PP","short_pith_number":"pith:4OK47KLN","schema_version":"1.0","canonical_sha256":"e395cfa96dea78ac08017a345fbd5b7bc08ea7acf707bea502ffda3ca6c425c4","source":{"kind":"arxiv","id":"2402.03242","version":1},"attestation_state":"computed","paper":{"title":"JOBSKAPE: A Framework for Generating Synthetic Job Postings to Enhance Skill Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Dai, Antoine Bosselut, Antoine Magron, Mike Zhang, Syrielle Montariol","submitted_at":"2024-02-05T17:57:26Z","abstract_excerpt":"Recent approaches in skill matching, employing synthetic training data for classification or similarity model training, have shown promising results, reducing the need for time-consuming and expensive annotations. However, previous synthetic datasets have limitations, such as featuring only one skill per sentence and generally comprising short sentences. In this paper, we introduce JobSkape, a framework to generate synthetic data that tackles these limitations, specifically designed to enhance skill-to-taxonomy matching. Within this framework, we create SkillSkape, a comprehensive open-source "},"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":"2402.03242","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-05T17:57:26Z","cross_cats_sorted":[],"title_canon_sha256":"741dfcf5126d82ebc5e148c68f29f4bd3c42a09ac7d1c697d7983859108f053c","abstract_canon_sha256":"c1f99f1cbc3ee16c2291ce7a3baffc918be23b90ee9e14780e664c028b661bda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:32.821497Z","signature_b64":"cWctYv0Sj9sHKwi+C9qYkYPhzfmWCIqtuQa7PEvOnbNNpzVog2MFEo6/qmpPkNCaQphpe174HOo3PjxlzTKDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e395cfa96dea78ac08017a345fbd5b7bc08ea7acf707bea502ffda3ca6c425c4","last_reissued_at":"2026-07-05T07:41:32.821007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:32.821007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JOBSKAPE: A Framework for Generating Synthetic Job Postings to Enhance Skill Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Dai, Antoine Bosselut, Antoine Magron, Mike Zhang, Syrielle Montariol","submitted_at":"2024-02-05T17:57:26Z","abstract_excerpt":"Recent approaches in skill matching, employing synthetic training data for classification or similarity model training, have shown promising results, reducing the need for time-consuming and expensive annotations. However, previous synthetic datasets have limitations, such as featuring only one skill per sentence and generally comprising short sentences. In this paper, we introduce JobSkape, a framework to generate synthetic data that tackles these limitations, specifically designed to enhance skill-to-taxonomy matching. Within this framework, we create SkillSkape, a comprehensive open-source "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03242","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/2402.03242/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":"2402.03242","created_at":"2026-07-05T07:41:32.821066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03242v1","created_at":"2026-07-05T07:41:32.821066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03242","created_at":"2026-07-05T07:41:32.821066+00:00"},{"alias_kind":"pith_short_12","alias_value":"4OK47KLN5J4K","created_at":"2026-07-05T07:41:32.821066+00:00"},{"alias_kind":"pith_short_16","alias_value":"4OK47KLN5J4KYCAB","created_at":"2026-07-05T07:41:32.821066+00:00"},{"alias_kind":"pith_short_8","alias_value":"4OK47KLN","created_at":"2026-07-05T07:41:32.821066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.28282","citing_title":"(Towards) Scalable Reliable Automated Evaluation with Large Language Models","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4OK47KLN5J4KYCABPI2F7PK3PP","json":"https://pith.science/pith/4OK47KLN5J4KYCABPI2F7PK3PP.json","graph_json":"https://pith.science/api/pith-number/4OK47KLN5J4KYCABPI2F7PK3PP/graph.json","events_json":"https://pith.science/api/pith-number/4OK47KLN5J4KYCABPI2F7PK3PP/events.json","paper":"https://pith.science/paper/4OK47KLN"},"agent_actions":{"view_html":"https://pith.science/pith/4OK47KLN5J4KYCABPI2F7PK3PP","download_json":"https://pith.science/pith/4OK47KLN5J4KYCABPI2F7PK3PP.json","view_paper":"https://pith.science/paper/4OK47KLN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03242&json=true","fetch_graph":"https://pith.science/api/pith-number/4OK47KLN5J4KYCABPI2F7PK3PP/graph.json","fetch_events":"https://pith.science/api/pith-number/4OK47KLN5J4KYCABPI2F7PK3PP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4OK47KLN5J4KYCABPI2F7PK3PP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4OK47KLN5J4KYCABPI2F7PK3PP/action/storage_attestation","attest_author":"https://pith.science/pith/4OK47KLN5J4KYCABPI2F7PK3PP/action/author_attestation","sign_citation":"https://pith.science/pith/4OK47KLN5J4KYCABPI2F7PK3PP/action/citation_signature","submit_replication":"https://pith.science/pith/4OK47KLN5J4KYCABPI2F7PK3PP/action/replication_record"}},"created_at":"2026-07-05T07:41:32.821066+00:00","updated_at":"2026-07-05T07:41:32.821066+00:00"}