{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3AQDZGI5KFKJ2KGYU3SB2S7I6N","short_pith_number":"pith:3AQDZGI5","schema_version":"1.0","canonical_sha256":"d8203c991d51549d28d8a6e41d4be8f36563f642c06db0319555971febab6967","source":{"kind":"arxiv","id":"2605.28965","version":1},"attestation_state":"computed","paper":{"title":"Frontier LLM-based agents can overcome the ontology curation bottleneck for natural phenotypes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hilmar Lapp, James P. Balhoff","submitted_at":"2026-05-27T18:08:46Z","abstract_excerpt":"Linking free-text phenotype descriptions to ontology terms, typically referred to as phenotype annotation, is essential for the cross-study integration of comparative morphological data. This labor intensive process has heavily relied on highly trained human experts, which makes it challenging to scale and thus a key bottleneck. Dahdul et al. (2018) established a Gold Standard (GS) of Entity-Quality (EQ) annotations across seven phylogenetic studies and used it to evaluate three human curators and the Semantic CharaParser NLP tool with ontology-based semantic similarity metrics; they reported "},"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":"2605.28965","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T18:08:46Z","cross_cats_sorted":[],"title_canon_sha256":"345a150754f51014cf4cc12798654b7b08781a3eb41ea333065f0e3eef25c6b8","abstract_canon_sha256":"89aaa85b2dc5852a98fc99aac9d1c2468f32345dce9002b58005ac7c17e009e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:41.774378Z","signature_b64":"kv03NrdVVi0HGR3PuZRAhKBInEPrmK2X+WfcXDA6tpjUXVWx12migFIsVmzli9sHgjJNt4UVoKlZ9iLo56v+Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8203c991d51549d28d8a6e41d4be8f36563f642c06db0319555971febab6967","last_reissued_at":"2026-05-29T01:04:41.773901Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:41.773901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frontier LLM-based agents can overcome the ontology curation bottleneck for natural phenotypes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hilmar Lapp, James P. Balhoff","submitted_at":"2026-05-27T18:08:46Z","abstract_excerpt":"Linking free-text phenotype descriptions to ontology terms, typically referred to as phenotype annotation, is essential for the cross-study integration of comparative morphological data. This labor intensive process has heavily relied on highly trained human experts, which makes it challenging to scale and thus a key bottleneck. Dahdul et al. (2018) established a Gold Standard (GS) of Entity-Quality (EQ) annotations across seven phylogenetic studies and used it to evaluate three human curators and the Semantic CharaParser NLP tool with ontology-based semantic similarity metrics; they reported "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28965","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/2605.28965/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":"2605.28965","created_at":"2026-05-29T01:04:41.773963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28965v1","created_at":"2026-05-29T01:04:41.773963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28965","created_at":"2026-05-29T01:04:41.773963+00:00"},{"alias_kind":"pith_short_12","alias_value":"3AQDZGI5KFKJ","created_at":"2026-05-29T01:04:41.773963+00:00"},{"alias_kind":"pith_short_16","alias_value":"3AQDZGI5KFKJ2KGY","created_at":"2026-05-29T01:04:41.773963+00:00"},{"alias_kind":"pith_short_8","alias_value":"3AQDZGI5","created_at":"2026-05-29T01:04:41.773963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3AQDZGI5KFKJ2KGYU3SB2S7I6N","json":"https://pith.science/pith/3AQDZGI5KFKJ2KGYU3SB2S7I6N.json","graph_json":"https://pith.science/api/pith-number/3AQDZGI5KFKJ2KGYU3SB2S7I6N/graph.json","events_json":"https://pith.science/api/pith-number/3AQDZGI5KFKJ2KGYU3SB2S7I6N/events.json","paper":"https://pith.science/paper/3AQDZGI5"},"agent_actions":{"view_html":"https://pith.science/pith/3AQDZGI5KFKJ2KGYU3SB2S7I6N","download_json":"https://pith.science/pith/3AQDZGI5KFKJ2KGYU3SB2S7I6N.json","view_paper":"https://pith.science/paper/3AQDZGI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28965&json=true","fetch_graph":"https://pith.science/api/pith-number/3AQDZGI5KFKJ2KGYU3SB2S7I6N/graph.json","fetch_events":"https://pith.science/api/pith-number/3AQDZGI5KFKJ2KGYU3SB2S7I6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3AQDZGI5KFKJ2KGYU3SB2S7I6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3AQDZGI5KFKJ2KGYU3SB2S7I6N/action/storage_attestation","attest_author":"https://pith.science/pith/3AQDZGI5KFKJ2KGYU3SB2S7I6N/action/author_attestation","sign_citation":"https://pith.science/pith/3AQDZGI5KFKJ2KGYU3SB2S7I6N/action/citation_signature","submit_replication":"https://pith.science/pith/3AQDZGI5KFKJ2KGYU3SB2S7I6N/action/replication_record"}},"created_at":"2026-05-29T01:04:41.773963+00:00","updated_at":"2026-05-29T01:04:41.773963+00:00"}