{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QYMQ5F3AUPYCTWGY2XC6TO7HWD","short_pith_number":"pith:QYMQ5F3A","schema_version":"1.0","canonical_sha256":"86190e9760a3f029d8d8d5c5e9bbe7b0c6a40c2b8028334d6dcf7f4d12dc4e65","source":{"kind":"arxiv","id":"2412.02035","version":1},"attestation_state":"computed","paper":{"title":"LLMs4Life: Large Language Models for Ontology Learning in Life Sciences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alsayed Algergawy, Nadeen Fathallah, Steffen Staab","submitted_at":"2024-12-02T23:31:52Z","abstract_excerpt":"Ontology learning in complex domains, such as life sciences, poses significant challenges for current Large Language Models (LLMs). Existing LLMs struggle to generate ontologies with multiple hierarchical levels, rich interconnections, and comprehensive class coverage due to constraints on the number of tokens they can generate and inadequate domain adaptation. To address these issues, we extend the NeOn-GPT pipeline for ontology learning using LLMs with advanced prompt engineering techniques and ontology reuse to enhance the generated ontologies' domain-specific reasoning and structural depth"},"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":"2412.02035","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-02T23:31:52Z","cross_cats_sorted":[],"title_canon_sha256":"a059323729b981770c5895d5ca1fabe5c44fe9e22bb0ccb49f3b89c91fbe5f04","abstract_canon_sha256":"53dfc9f3a04220baf815c3b2398e865802dd7b409053102afc295b6717724acd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:42.682135Z","signature_b64":"H9dEI78HS4+zUcR350vBj3NzSCvmZcNCkhLfFKSvkhGa7bPzdH2chxCfw/yWiq/2JAMERfeQ3lKaN7sofsUnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86190e9760a3f029d8d8d5c5e9bbe7b0c6a40c2b8028334d6dcf7f4d12dc4e65","last_reissued_at":"2026-07-05T09:43:42.681672Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:42.681672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMs4Life: Large Language Models for Ontology Learning in Life Sciences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alsayed Algergawy, Nadeen Fathallah, Steffen Staab","submitted_at":"2024-12-02T23:31:52Z","abstract_excerpt":"Ontology learning in complex domains, such as life sciences, poses significant challenges for current Large Language Models (LLMs). Existing LLMs struggle to generate ontologies with multiple hierarchical levels, rich interconnections, and comprehensive class coverage due to constraints on the number of tokens they can generate and inadequate domain adaptation. To address these issues, we extend the NeOn-GPT pipeline for ontology learning using LLMs with advanced prompt engineering techniques and ontology reuse to enhance the generated ontologies' domain-specific reasoning and structural depth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02035","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/2412.02035/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":"2412.02035","created_at":"2026-07-05T09:43:42.681727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.02035v1","created_at":"2026-07-05T09:43:42.681727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02035","created_at":"2026-07-05T09:43:42.681727+00:00"},{"alias_kind":"pith_short_12","alias_value":"QYMQ5F3AUPYC","created_at":"2026-07-05T09:43:42.681727+00:00"},{"alias_kind":"pith_short_16","alias_value":"QYMQ5F3AUPYCTWGY","created_at":"2026-07-05T09:43:42.681727+00:00"},{"alias_kind":"pith_short_8","alias_value":"QYMQ5F3A","created_at":"2026-07-05T09:43:42.681727+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28070","citing_title":"JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28070","citing_title":"JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QYMQ5F3AUPYCTWGY2XC6TO7HWD","json":"https://pith.science/pith/QYMQ5F3AUPYCTWGY2XC6TO7HWD.json","graph_json":"https://pith.science/api/pith-number/QYMQ5F3AUPYCTWGY2XC6TO7HWD/graph.json","events_json":"https://pith.science/api/pith-number/QYMQ5F3AUPYCTWGY2XC6TO7HWD/events.json","paper":"https://pith.science/paper/QYMQ5F3A"},"agent_actions":{"view_html":"https://pith.science/pith/QYMQ5F3AUPYCTWGY2XC6TO7HWD","download_json":"https://pith.science/pith/QYMQ5F3AUPYCTWGY2XC6TO7HWD.json","view_paper":"https://pith.science/paper/QYMQ5F3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.02035&json=true","fetch_graph":"https://pith.science/api/pith-number/QYMQ5F3AUPYCTWGY2XC6TO7HWD/graph.json","fetch_events":"https://pith.science/api/pith-number/QYMQ5F3AUPYCTWGY2XC6TO7HWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QYMQ5F3AUPYCTWGY2XC6TO7HWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QYMQ5F3AUPYCTWGY2XC6TO7HWD/action/storage_attestation","attest_author":"https://pith.science/pith/QYMQ5F3AUPYCTWGY2XC6TO7HWD/action/author_attestation","sign_citation":"https://pith.science/pith/QYMQ5F3AUPYCTWGY2XC6TO7HWD/action/citation_signature","submit_replication":"https://pith.science/pith/QYMQ5F3AUPYCTWGY2XC6TO7HWD/action/replication_record"}},"created_at":"2026-07-05T09:43:42.681727+00:00","updated_at":"2026-07-05T09:43:42.681727+00:00"}