{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZOTMKBFVYL22HAMLUB6LNPI66Z","short_pith_number":"pith:ZOTMKBFV","canonical_record":{"source":{"id":"2501.06271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-01-10T01:43:05Z","cross_cats_sorted":["cs.AI","cs.CE"],"title_canon_sha256":"160cda118e6bdfaa39377f5a287f8b703ada6151449821170bd9a946a8311067","abstract_canon_sha256":"878a8690f9658271fb4b852261d79dfa05e63c77afdce592ebafada1b36bb91e"},"schema_version":"1.0"},"canonical_sha256":"cba6c504b5c2f5a3818ba07cb6bd1ef649f32e396fe54ea42b6cf37bedf44ace","source":{"kind":"arxiv","id":"2501.06271","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06271","created_at":"2026-07-05T10:00:00Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06271v1","created_at":"2026-07-05T10:00:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06271","created_at":"2026-07-05T10:00:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZOTMKBFVYL22","created_at":"2026-07-05T10:00:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZOTMKBFVYL22HAML","created_at":"2026-07-05T10:00:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZOTMKBFV","created_at":"2026-07-05T10:00:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZOTMKBFVYL22HAMLUB6LNPI66Z","target":"record","payload":{"canonical_record":{"source":{"id":"2501.06271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-01-10T01:43:05Z","cross_cats_sorted":["cs.AI","cs.CE"],"title_canon_sha256":"160cda118e6bdfaa39377f5a287f8b703ada6151449821170bd9a946a8311067","abstract_canon_sha256":"878a8690f9658271fb4b852261d79dfa05e63c77afdce592ebafada1b36bb91e"},"schema_version":"1.0"},"canonical_sha256":"cba6c504b5c2f5a3818ba07cb6bd1ef649f32e396fe54ea42b6cf37bedf44ace","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:00.395373Z","signature_b64":"SEhuDziN0z0lg5RevwH6BUMBCSCFy/Yt06nvz1AMplka5HV9+x5hf9Fuo/3XNdZxXj3eUV0VcQwa3bvEqc9qAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cba6c504b5c2f5a3818ba07cb6bd1ef649f32e396fe54ea42b6cf37bedf44ace","last_reissued_at":"2026-07-05T10:00:00.394878Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:00.394878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.06271","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":"2026-07-05T10:00:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RnHEt4DFTi6+t7nDtdc/sidrSfzBweCPZhlPT+3skd/14+HL6mf13MkHyALNpeH8S7a7C8gwD0UYBMnvJGcIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:17:12.816719Z"},"content_sha256":"d7cdf84163a0cee74436c573279a2fd27623d35a23be806b82bcdb991d37b8b0","schema_version":"1.0","event_id":"sha256:d7cdf84163a0cee74436c573279a2fd27623d35a23be806b82bcdb991d37b8b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZOTMKBFVYL22HAMLUB6LNPI66Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models for Bioinformatics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE"],"primary_cat":"q-bio.QM","authors_text":"Andrea Sikora, Chao Huang, Dajiang Zhu, Gang Li, Hanqi Jiang, Hongtu Zhu, Jianli Zhang, Jiazhang Cai, Jingyuan Chen, Jing Zhang, Jin Lu, Junhao Chen, Kenan Song, Lifang He, Lin Zhao, Luyang Fang, Lu Zhang, Peilong Wang, Peng Shu, Ping Ma, Qi Gan, Quanzheng Li, Rongjie Liu, Shang Gao, Shizhe Liang, Shuo Yu, Tao Wang, Terry Ma, Tianming Liu, Wei Liu, Wei Ruan, Wei Zhang, Wenxuan Zhong, Xiang Li, Xianqiao Wang, Xinyu Gong, Yajun Yan, Yang Ge, Yanjun Lyu, Yao Lu, Ye Shen, Yingfeng Wang, Yi Pan, Yiwei Li, Yohannes Abate, Yuan Dou, Yuanxin Qian, Yue Wang, Yufang Liu, Yusong Zou, Zebang Chen, Zhengliang Liu, Zhenyuan Yang, Zihao Wu, Ziyu Liu","submitted_at":"2025-01-10T01:43:05Z","abstract_excerpt":"With the rapid advancements in large language model (LLM) technology and the emergence of bioinformatics-specific language models (BioLMs), there is a growing need for a comprehensive analysis of the current landscape, computational characteristics, and diverse applications. This survey aims to address this need by providing a thorough review of BioLMs, focusing on their evolution, classification, and distinguishing features, alongside a detailed examination of training methodologies, datasets, and evaluation frameworks. We explore the wide-ranging applications of BioLMs in critical areas such"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06271","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/2501.06271/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":"2026-07-05T10:00:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zrR15lt3m4ZzYsO8/PemTWeBxEWoFlskHCo5o4LmWUV3AtEhMzVQ5IqcLflBIW/8Y8G4Jna9BKmoD1vidcw3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:17:12.817104Z"},"content_sha256":"248887da83876037954bed622306803bca943a76e0ea41db42af7131785cccb7","schema_version":"1.0","event_id":"sha256:248887da83876037954bed622306803bca943a76e0ea41db42af7131785cccb7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZOTMKBFVYL22HAMLUB6LNPI66Z/bundle.json","state_url":"https://pith.science/pith/ZOTMKBFVYL22HAMLUB6LNPI66Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZOTMKBFVYL22HAMLUB6LNPI66Z/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":"2026-07-06T20:17:12Z","links":{"resolver":"https://pith.science/pith/ZOTMKBFVYL22HAMLUB6LNPI66Z","bundle":"https://pith.science/pith/ZOTMKBFVYL22HAMLUB6LNPI66Z/bundle.json","state":"https://pith.science/pith/ZOTMKBFVYL22HAMLUB6LNPI66Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZOTMKBFVYL22HAMLUB6LNPI66Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZOTMKBFVYL22HAMLUB6LNPI66Z","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"878a8690f9658271fb4b852261d79dfa05e63c77afdce592ebafada1b36bb91e","cross_cats_sorted":["cs.AI","cs.CE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-01-10T01:43:05Z","title_canon_sha256":"160cda118e6bdfaa39377f5a287f8b703ada6151449821170bd9a946a8311067"},"schema_version":"1.0","source":{"id":"2501.06271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06271","created_at":"2026-07-05T10:00:00Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06271v1","created_at":"2026-07-05T10:00:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06271","created_at":"2026-07-05T10:00:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZOTMKBFVYL22","created_at":"2026-07-05T10:00:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZOTMKBFVYL22HAML","created_at":"2026-07-05T10:00:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZOTMKBFV","created_at":"2026-07-05T10:00:00Z"}],"graph_snapshots":[{"event_id":"sha256:248887da83876037954bed622306803bca943a76e0ea41db42af7131785cccb7","target":"graph","created_at":"2026-07-05T10:00:00Z","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/2501.06271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rapid advancements in large language model (LLM) technology and the emergence of bioinformatics-specific language models (BioLMs), there is a growing need for a comprehensive analysis of the current landscape, computational characteristics, and diverse applications. This survey aims to address this need by providing a thorough review of BioLMs, focusing on their evolution, classification, and distinguishing features, alongside a detailed examination of training methodologies, datasets, and evaluation frameworks. We explore the wide-ranging applications of BioLMs in critical areas such","authors_text":"Andrea Sikora, Chao Huang, Dajiang Zhu, Gang Li, Hanqi Jiang, Hongtu Zhu, Jianli Zhang, Jiazhang Cai, Jingyuan Chen, Jing Zhang, Jin Lu, Junhao Chen, Kenan Song, Lifang He, Lin Zhao, Luyang Fang, Lu Zhang, Peilong Wang, Peng Shu, Ping Ma, Qi Gan, Quanzheng Li, Rongjie Liu, Shang Gao, Shizhe Liang, Shuo Yu, Tao Wang, Terry Ma, Tianming Liu, Wei Liu, Wei Ruan, Wei Zhang, Wenxuan Zhong, Xiang Li, Xianqiao Wang, Xinyu Gong, Yajun Yan, Yang Ge, Yanjun Lyu, Yao Lu, Ye Shen, Yingfeng Wang, Yi Pan, Yiwei Li, Yohannes Abate, Yuan Dou, Yuanxin Qian, Yue Wang, Yufang Liu, Yusong Zou, Zebang Chen, Zhengliang Liu, Zhenyuan Yang, Zihao Wu, Ziyu Liu","cross_cats":["cs.AI","cs.CE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-01-10T01:43:05Z","title":"Large Language Models for Bioinformatics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06271","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:d7cdf84163a0cee74436c573279a2fd27623d35a23be806b82bcdb991d37b8b0","target":"record","created_at":"2026-07-05T10:00:00Z","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":"878a8690f9658271fb4b852261d79dfa05e63c77afdce592ebafada1b36bb91e","cross_cats_sorted":["cs.AI","cs.CE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-01-10T01:43:05Z","title_canon_sha256":"160cda118e6bdfaa39377f5a287f8b703ada6151449821170bd9a946a8311067"},"schema_version":"1.0","source":{"id":"2501.06271","kind":"arxiv","version":1}},"canonical_sha256":"cba6c504b5c2f5a3818ba07cb6bd1ef649f32e396fe54ea42b6cf37bedf44ace","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cba6c504b5c2f5a3818ba07cb6bd1ef649f32e396fe54ea42b6cf37bedf44ace","first_computed_at":"2026-07-05T10:00:00.394878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:00.394878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SEhuDziN0z0lg5RevwH6BUMBCSCFy/Yt06nvz1AMplka5HV9+x5hf9Fuo/3XNdZxXj3eUV0VcQwa3bvEqc9qAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:00.395373Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7cdf84163a0cee74436c573279a2fd27623d35a23be806b82bcdb991d37b8b0","sha256:248887da83876037954bed622306803bca943a76e0ea41db42af7131785cccb7"],"state_sha256":"fcc107c14c1a8de2e1c6b9d321a25614f6b716307f376223624b54b5355bcdab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZxV05scIhxk6AFGmdVI7iv7ur+sF616wGmIfkkjyhcDhUPCYsZXPm/sBgarLtKkBYggeyxarIWj10i0PJdFbAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:17:12.819105Z","bundle_sha256":"a42774a7349732c7042d77b2de0d36f64b6a97dcafde2aa638e4aeed45e5cb38"}}