{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KQNLCYWPTF5UJWQ3TDNRMB3EBZ","short_pith_number":"pith:KQNLCYWP","canonical_record":{"source":{"id":"2608.00099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.GN","submitted_at":"2026-07-30T19:29:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"53f2147a4d18ac3e73457a92a6532dfc4bbaf1bd52fd00b84b41e4f5f45e8e28","abstract_canon_sha256":"d81c8739edebf7ec3815b15afd00e917342606cb7b4a3fe1f24762114f35445b"},"schema_version":"1.0"},"canonical_sha256":"541ab162cf997b44da1b98db1607640e6ad8dc9c08faa4c90abe6e7255068150","source":{"kind":"arxiv","id":"2608.00099","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00099","created_at":"2026-08-04T00:32:16Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00099v1","created_at":"2026-08-04T00:32:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00099","created_at":"2026-08-04T00:32:16Z"},{"alias_kind":"pith_short_12","alias_value":"KQNLCYWPTF5U","created_at":"2026-08-04T00:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"KQNLCYWPTF5UJWQ3","created_at":"2026-08-04T00:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"KQNLCYWP","created_at":"2026-08-04T00:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KQNLCYWPTF5UJWQ3TDNRMB3EBZ","target":"record","payload":{"canonical_record":{"source":{"id":"2608.00099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.GN","submitted_at":"2026-07-30T19:29:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"53f2147a4d18ac3e73457a92a6532dfc4bbaf1bd52fd00b84b41e4f5f45e8e28","abstract_canon_sha256":"d81c8739edebf7ec3815b15afd00e917342606cb7b4a3fe1f24762114f35445b"},"schema_version":"1.0"},"canonical_sha256":"541ab162cf997b44da1b98db1607640e6ad8dc9c08faa4c90abe6e7255068150","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:32:16.077081Z","signature_b64":"WmF6do1ofaCS0XgTy157tk/qycb6AondaQGKej4Ff5FUrIit0QS6+8gp0A2dmf9cXsHDbtwEvbxwuRzROzBaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"541ab162cf997b44da1b98db1607640e6ad8dc9c08faa4c90abe6e7255068150","last_reissued_at":"2026-08-04T00:32:16.074936Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:32:16.074936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.00099","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T00:32:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V03BPiXI+iFhEvoGm2Jq4OXjM9bdiS6dX+f5pJ1KOzls1AESfxBp6s3YzOBA7AETbSUS6m/x4iFoFvv3+w6fCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:48:14.898491Z"},"content_sha256":"d983d9c71468dc15513743be6630de110616c8e6db555844d708127e8c788f82","schema_version":"1.0","event_id":"sha256:d983d9c71468dc15513743be6630de110616c8e6db555844d708127e8c788f82"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KQNLCYWPTF5UJWQ3TDNRMB3EBZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLMBDC: Language Model for Biological Domains Oriented Clustering of Gene Ontology","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"q-bio.GN","authors_text":"Jiaying Lu, Jie Xu, Peng Jin, Ximing Ran, Zhaohui Qin, Zhexing Wen","submitted_at":"2026-07-30T19:29:22Z","abstract_excerpt":"Gene Ontology (GO) enrichment analysis is a foundational tool for translating large-scale genomic data into biological insights, but typically yields hundreds of redundant terms that obscure overarching themes. Existing summarization tools rely on fixed similarity metrics (REVIGO, GOSemSim, clusterProfiler::simplify()), gene-overlap measures (Metascape), or static hierarchy mappings (GO-slim), and therefore cannot incorporate biological context. Manual curation provides context-aware grouping but is subjective and labor-intensive. A scalable, context-aware framework is needed to cluster GO ter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00099","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/2608.00099/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T00:32:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3qI9vgoC+9Y8fwJTRKUG9UippLzOLMStmqooUjaHDmtZPGFDdoxkbQIA1pi0oERszHX5XSfb2k5oH2Lb2QkrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:48:14.899014Z"},"content_sha256":"89617a342c051b46f7d1155053b7cc39e30d3e5d6a3a445422035a478c25872d","schema_version":"1.0","event_id":"sha256:89617a342c051b46f7d1155053b7cc39e30d3e5d6a3a445422035a478c25872d"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:KQNLCYWPTF5UJWQ3TDNRMB3EBZ","target":"integrity","payload":{"note":"DOI is split by whitespace or line breaks in the printed bibliography. Reconstructed DOI 10.1016/j.xinn.2021.100141 resolves to 'clusterProfiler 4.0: A universal enrichment tool for interpreting omics data'. A reader following the printed text alone cannot reach it.","snippet":"Tian Wu, Eryong Hu, Shuqing Xu, Meng Chen, Peizhi Guo, Zhitang Dai, Ting Feng, Lin Zhou, Wanyi Tang, Li Zhan, Xi Fu, Sheng Liu, Xiaowen Bo, and Guangchuang Yu. 2021. clusterProfiler 4.0: A universal enrichment tool for in- terpreting omics ","arxiv_id":"2608.00099","detector":"doi_compliance","evidence":{"ref_index":28,"verdict_class":"incontrovertible","resolved_title":"clusterProfiler 4.0: A universal enrichment tool for interpreting omics data","printed_excerpt":"10.1016/j.xinn.2021","reconstructed_doi":"10.1016/j.xinn.2021.100141"},"severity":"advisory","ref_index":28,"audited_at":"2026-08-04T01:28:30.258432Z","event_type":"pith.integrity.v1","detected_doi":"10.1016/j.xinn.2021.100141","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"20b9a786655a6cafa89983cdccef83f447311e5bfcc8347efa2eab4add140bd7","paper_version":1,"verdict_class":"incontrovertible","resolved_title":"clusterProfiler 4.0: A universal enrichment tool for interpreting omics data","detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":17787,"payload_sha256":"5e8be75a84d887a11d7ffb1be987a76ecbee6a6fdcdc7d2b4cf3853b82cac5f0","signature_b64":"vPbXDSfAg7G5CERSeh+4OnzEBxzdSGEwPGCZvDROqrORNvhjX8Ho6tlLkHw3C+1JDYTUHmhPT5YaD2tjyxNRAA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T01:28:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F1NsgDBudHDx0R70VRRoJ7t5JhTd60SojRGTxNd0ofbP7GplhVSzGtENCO28hrrIBg8ANdYZvCItNOVKvDV1Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:48:14.901695Z"},"content_sha256":"61d563470d81149a4f82e892f149d492a08cbc2c78977fdb0958c556af36534b","schema_version":"1.0","event_id":"sha256:61d563470d81149a4f82e892f149d492a08cbc2c78977fdb0958c556af36534b"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:KQNLCYWPTF5UJWQ3TDNRMB3EBZ","target":"integrity","payload":{"note":"Identifier '10.1038/s41592-024-02111-4' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"Zhizheng Wang, Qiao Jin, Chih-Hsuan Wei, Shubo Tian, Po-Ting Lai, Qingqing Zhu, Chi-Ping Day, Christina Ross, Robert Leaman, and Zhiyong Lu. 2025. Ge- neAgent: self-verification language agent for gene-set analysis using domain databases. N","arxiv_id":"2608.00099","detector":"doi_compliance","evidence":{"doi":"10.1038/s41592-024-02111-4","arxiv_id":null,"ref_index":26,"raw_excerpt":"Zhizheng Wang, Qiao Jin, Chih-Hsuan Wei, Shubo Tian, Po-Ting Lai, Qingqing Zhu, Chi-Ping Day, Christina Ross, Robert Leaman, and Zhiyong Lu. 2025. Ge- neAgent: self-verification language agent for gene-set analysis using domain databases. Nature Methods (2025). doi:10.1038/s41592-024-02111-4","parse_status":"well_formed","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"],"resolution_status":"hard_miss"},"severity":"critical","ref_index":26,"audited_at":"2026-08-04T01:28:30.258432Z","event_type":"pith.integrity.v1","detected_doi":"10.1038/s41592-024-02111-4","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"c306a6b39cecc39d080cf27cb7939a63deb5f79a59106d947271522b84fc87a9","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":17786,"payload_sha256":"d469bc6af3454277ec2605f2b00afa96a2bde45074afa649a7d8bfb876629ec8","signature_b64":"C9Cfnp9mZkp9R97lyNVIzcFwkFR9iR56CGjrdpmxpfIU0cWCa3u9Rn/+z+7gQVjZZY6pL+LUmI2kR3uQ040BBg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T01:28:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hyy3LL7zF38e3+KgZpLmUy0Lpn99/W0mEunC6uLZGZNsZianhMHG3KTbZ+0zhmGPPvmJFIFkYTAmxTzkuKRpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:48:14.902489Z"},"content_sha256":"a65cfefbe73e7be3548719766620f3195385c0a5b61eee71332458b2d652d05c","schema_version":"1.0","event_id":"sha256:a65cfefbe73e7be3548719766620f3195385c0a5b61eee71332458b2d652d05c"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:KQNLCYWPTF5UJWQ3TDNRMB3EBZ","target":"integrity","payload":{"note":"DOI is split by whitespace or line breaks in the printed bibliography. Reconstructed DOI 10.1093/nar/gkac194 resolves to 'DAVID: a web server for functional enrichment analysis and functional annotation of gene lists (2021 update)'. A reader following the printed text alone cannot reach it.","snippet":"Brad T. Sherman, Ming Hao, Ju Qiu, Xiaoli Jiao, Michael W. Baseler, H. Clifford Lane, Tomozumi Imamichi, and Weizhong Chang. 2022. DA VID: a web server for functional enrichment analysis and functional annotation of gene lists (2021 update)","arxiv_id":"2608.00099","detector":"doi_compliance","evidence":{"ref_index":22,"verdict_class":"incontrovertible","resolved_title":"DAVID: a web server for functional enrichment analysis and functional annotation of gene lists (2021 update)","printed_excerpt":"10.1093/nar/","reconstructed_doi":"10.1093/nar/gkac194"},"severity":"advisory","ref_index":22,"audited_at":"2026-08-04T01:28:30.258432Z","event_type":"pith.integrity.v1","detected_doi":"10.1093/nar/gkac194","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"51fc5e9148c561d62797fd2bab1854dc195ae37326356d8d8410dc817a68593c","paper_version":1,"verdict_class":"incontrovertible","resolved_title":"DAVID: a web server for functional enrichment analysis and functional annotation of gene lists (2021 update)","detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":17785,"payload_sha256":"a23d8388b1d7cb64b5fc91a1ed4dadff506f0a842dd33efbdb86a9b68d87597b","signature_b64":"aK/63/8pkti/ujfi0wY4QOdsQeC7bWG24KWK1FKYmh/flSJ2joNLoWMr26+Ag2aW0NcMf+L9ee2VxkHrtpngBg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T01:28:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JiOCT90AZTXadI6CX6RHyvibi/PkY7kKEM5g5Ker+bB45hE4HrgSihgsdP+a57a3Kd4PTXMpwyTvBdgjN9u1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:48:14.902893Z"},"content_sha256":"881b8ee669dc8a213e19ead5a1f94da0b93d9b2ea52318810c83979229ae4a33","schema_version":"1.0","event_id":"sha256:881b8ee669dc8a213e19ead5a1f94da0b93d9b2ea52318810c83979229ae4a33"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:KQNLCYWPTF5UJWQ3TDNRMB3EBZ","target":"integrity","payload":{"note":"Identifier '10.1038/s41592-024-02120-3' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","snippet":"Mengzhou Hu, Sahar Alkhairy, Ingoo Lee, Rudolf T. Pillich, Dylan Fong, Kevin Smith, Robin Bachelder, Trey Ideker, and Dexter Pratt. 2025. Evaluation of large language models for discovery of gene set function. Nature Methods 22 (2025), 82–9","arxiv_id":"2608.00099","detector":"doi_compliance","evidence":{"doi":"10.1038/s41592-024-02120-3","arxiv_id":null,"ref_index":10,"raw_excerpt":"Mengzhou Hu, Sahar Alkhairy, Ingoo Lee, Rudolf T. Pillich, Dylan Fong, Kevin Smith, Robin Bachelder, Trey Ideker, and Dexter Pratt. 2025. Evaluation of large language models for discovery of gene set function. Nature Methods 22 (2025), 82–91. doi:10.1038/s41592-024-02120-3","parse_status":"well_formed","verdict_class":"cross_source","checked_sources":["crossref_by_doi","openalex_by_doi","doi_org_head"],"resolution_status":"hard_miss"},"severity":"critical","ref_index":10,"audited_at":"2026-08-04T01:28:30.258432Z","event_type":"pith.integrity.v1","detected_doi":"10.1038/s41592-024-02120-3","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"unresolvable_identifier","evidence_hash":"6c089f1870b356b61aff994a27c643ef62e6bdc8f2a4e8bb5483cb8e3bc88879","paper_version":1,"verdict_class":"cross_source","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":17784,"payload_sha256":"82c3aa7a6ea7d6ecb0514983f75b061fa98d6ccb5bf617faa5d003e1affbb065","signature_b64":"Y1gV+lm58qDdO0uLgIY0wKzdRmhw6AtbHAx2fLzPb8LuJngy/jJUTlHaqQrio3s6BrnkfZ9Ekyv2NTJ0zNcqCA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T01:28:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qW6lBRWqogCqUmx9pCO2p7u9q83KlbNpWlPi2d1qF1mM/hajWHXEVySmlT0fqlKDPffbzuDegazGh+vOyiRtDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:48:14.903411Z"},"content_sha256":"3aff76d997dfc86c081ead4605439538b5450de06de6f42a3084fc949fcfbae7","schema_version":"1.0","event_id":"sha256:3aff76d997dfc86c081ead4605439538b5450de06de6f42a3084fc949fcfbae7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KQNLCYWPTF5UJWQ3TDNRMB3EBZ/bundle.json","state_url":"https://pith.science/pith/KQNLCYWPTF5UJWQ3TDNRMB3EBZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KQNLCYWPTF5UJWQ3TDNRMB3EBZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T08:48:14Z","links":{"resolver":"https://pith.science/pith/KQNLCYWPTF5UJWQ3TDNRMB3EBZ","bundle":"https://pith.science/pith/KQNLCYWPTF5UJWQ3TDNRMB3EBZ/bundle.json","state":"https://pith.science/pith/KQNLCYWPTF5UJWQ3TDNRMB3EBZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KQNLCYWPTF5UJWQ3TDNRMB3EBZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KQNLCYWPTF5UJWQ3TDNRMB3EBZ","merge_version":"pith-open-graph-merge-v1","event_count":6,"valid_event_count":6,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d81c8739edebf7ec3815b15afd00e917342606cb7b4a3fe1f24762114f35445b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.GN","submitted_at":"2026-07-30T19:29:22Z","title_canon_sha256":"53f2147a4d18ac3e73457a92a6532dfc4bbaf1bd52fd00b84b41e4f5f45e8e28"},"schema_version":"1.0","source":{"id":"2608.00099","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.00099","created_at":"2026-08-04T00:32:16Z"},{"alias_kind":"arxiv_version","alias_value":"2608.00099v1","created_at":"2026-08-04T00:32:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00099","created_at":"2026-08-04T00:32:16Z"},{"alias_kind":"pith_short_12","alias_value":"KQNLCYWPTF5U","created_at":"2026-08-04T00:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"KQNLCYWPTF5UJWQ3","created_at":"2026-08-04T00:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"KQNLCYWP","created_at":"2026-08-04T00:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:89617a342c051b46f7d1155053b7cc39e30d3e5d6a3a445422035a478c25872d","target":"graph","created_at":"2026-08-04T00:32:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2608.00099/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gene Ontology (GO) enrichment analysis is a foundational tool for translating large-scale genomic data into biological insights, but typically yields hundreds of redundant terms that obscure overarching themes. Existing summarization tools rely on fixed similarity metrics (REVIGO, GOSemSim, clusterProfiler::simplify()), gene-overlap measures (Metascape), or static hierarchy mappings (GO-slim), and therefore cannot incorporate biological context. Manual curation provides context-aware grouping but is subjective and labor-intensive. A scalable, context-aware framework is needed to cluster GO ter","authors_text":"Jiaying Lu, Jie Xu, Peng Jin, Ximing Ran, Zhaohui Qin, Zhexing Wen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.GN","submitted_at":"2026-07-30T19:29:22Z","title":"LLMBDC: Language Model for Biological Domains Oriented Clustering of Gene Ontology"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00099","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d983d9c71468dc15513743be6630de110616c8e6db555844d708127e8c788f82","target":"record","created_at":"2026-08-04T00:32:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d81c8739edebf7ec3815b15afd00e917342606cb7b4a3fe1f24762114f35445b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.GN","submitted_at":"2026-07-30T19:29:22Z","title_canon_sha256":"53f2147a4d18ac3e73457a92a6532dfc4bbaf1bd52fd00b84b41e4f5f45e8e28"},"schema_version":"1.0","source":{"id":"2608.00099","kind":"arxiv","version":1}},"canonical_sha256":"541ab162cf997b44da1b98db1607640e6ad8dc9c08faa4c90abe6e7255068150","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"541ab162cf997b44da1b98db1607640e6ad8dc9c08faa4c90abe6e7255068150","first_computed_at":"2026-08-04T00:32:16.074936Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T00:32:16.074936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WmF6do1ofaCS0XgTy157tk/qycb6AondaQGKej4Ff5FUrIit0QS6+8gp0A2dmf9cXsHDbtwEvbxwuRzROzBaCA==","signature_status":"signed_v1","signed_at":"2026-08-04T00:32:16.077081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.00099","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:3aff76d997dfc86c081ead4605439538b5450de06de6f42a3084fc949fcfbae7","sha256:61d563470d81149a4f82e892f149d492a08cbc2c78977fdb0958c556af36534b","sha256:881b8ee669dc8a213e19ead5a1f94da0b93d9b2ea52318810c83979229ae4a33","sha256:a65cfefbe73e7be3548719766620f3195385c0a5b61eee71332458b2d652d05c"]}],"invalid_events":[],"applied_event_ids":["sha256:d983d9c71468dc15513743be6630de110616c8e6db555844d708127e8c788f82","sha256:89617a342c051b46f7d1155053b7cc39e30d3e5d6a3a445422035a478c25872d"],"state_sha256":"0fae37ffe330b9a768bfbb55701f2cfb0e92abdc89d0db5177f8a42d32146bd3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pew1t2q5IJuw7x4J4q6TTx1yi32fBOrhOUS9y+blvhHODIIINha+0mtnwJ5HTwTHUB0DNhlEW1ujqysAcvLtCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T08:48:14.906912Z","bundle_sha256":"0c526513c796311cc5701ffb60b3de282d15bc5984885f260c65c24d2ff8fc38"}}