{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FYLMUCP5TST75VE6R2RQGODSIJ","short_pith_number":"pith:FYLMUCP5","canonical_record":{"source":{"id":"2502.17504","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-02-21T19:22:10Z","cross_cats_sorted":["cs.AI","cs.CE","cs.CL","cs.LG"],"title_canon_sha256":"fe9e46ae20e4439615a9e3475fe95d1bf993e91a9849b2993dbcad8257ad969d","abstract_canon_sha256":"b5841d5f61dec155a3a5ba1c8c63e14a0e4f4b7fa96bfb3818df7d0a75555b47"},"schema_version":"1.0"},"canonical_sha256":"2e16ca09fd9ca7fed49e8ea303387242496baadc08750fc2da0ec515e7bbab4c","source":{"kind":"arxiv","id":"2502.17504","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17504","created_at":"2026-07-05T10:25:18Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17504v2","created_at":"2026-07-05T10:25:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17504","created_at":"2026-07-05T10:25:18Z"},{"alias_kind":"pith_short_12","alias_value":"FYLMUCP5TST7","created_at":"2026-07-05T10:25:18Z"},{"alias_kind":"pith_short_16","alias_value":"FYLMUCP5TST75VE6","created_at":"2026-07-05T10:25:18Z"},{"alias_kind":"pith_short_8","alias_value":"FYLMUCP5","created_at":"2026-07-05T10:25:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FYLMUCP5TST75VE6R2RQGODSIJ","target":"record","payload":{"canonical_record":{"source":{"id":"2502.17504","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-02-21T19:22:10Z","cross_cats_sorted":["cs.AI","cs.CE","cs.CL","cs.LG"],"title_canon_sha256":"fe9e46ae20e4439615a9e3475fe95d1bf993e91a9849b2993dbcad8257ad969d","abstract_canon_sha256":"b5841d5f61dec155a3a5ba1c8c63e14a0e4f4b7fa96bfb3818df7d0a75555b47"},"schema_version":"1.0"},"canonical_sha256":"2e16ca09fd9ca7fed49e8ea303387242496baadc08750fc2da0ec515e7bbab4c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:18.366905Z","signature_b64":"ogZUHzZk8afqjTN7urHsLnAy3XHOH1EKsePyOAihJIMvYth/XjOItRYWed/f3idNYEixunJhCiTP3epGvxGpAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e16ca09fd9ca7fed49e8ea303387242496baadc08750fc2da0ec515e7bbab4c","last_reissued_at":"2026-07-05T10:25:18.366301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:18.366301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.17504","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:25:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lYEp/w8taD10ngeU7beIFFX69srOQjqF7rfRQFIeP01Qrmy7BVRUwTW3eXCgqzT2cHGHGEC9SXBPQWC00FvjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:40:51.534187Z"},"content_sha256":"1a021a7fec298a9fec34e427049fabff0f90fa3b5c7e891bdf848be73cec38de","schema_version":"1.0","event_id":"sha256:1a021a7fec298a9fec34e427049fabff0f90fa3b5c7e891bdf848be73cec38de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FYLMUCP5TST75VE6R2RQGODSIJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Protein Large Language Models: A Comprehensive Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.CL","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Guancheng Wan, Haixin Wang, Han Zhang, James Zou, Junkai Zhang, Pan Lu, Renliang Sun, Wanjia Zhao, Wei Wang, Xiao Luo, Yijia Xiao, Yiqiao Jin, Yizhou Sun, Yu Zhang, Zhicheng Ren","submitted_at":"2025-02-21T19:22:10Z","abstract_excerpt":"Protein-specific large language models (Protein LLMs) are revolutionizing protein science by enabling more efficient protein structure prediction, function annotation, and design. While existing surveys focus on specific aspects or applications, this work provides the first comprehensive overview of Protein LLMs, covering their architectures, training datasets, evaluation metrics, and diverse applications. Through a systematic analysis of over 100 articles, we propose a structured taxonomy of state-of-the-art Protein LLMs, analyze how they leverage large-scale protein sequence data for improve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17504","kind":"arxiv","version":2},"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/2502.17504/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":"2026-07-05T10:25:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QzzAakJvLZ4DFmth3PhEOBVPLEUpPNgmurNSGZxyDrKmNwrcc9yj8gz3coee2k6xD3BsCphbrbj4mCZgShEWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:40:51.534573Z"},"content_sha256":"1c6aca78218e1c14363a93dcac9e66291071d09e69840293375d552e0c75828b","schema_version":"1.0","event_id":"sha256:1c6aca78218e1c14363a93dcac9e66291071d09e69840293375d552e0c75828b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FYLMUCP5TST75VE6R2RQGODSIJ/bundle.json","state_url":"https://pith.science/pith/FYLMUCP5TST75VE6R2RQGODSIJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FYLMUCP5TST75VE6R2RQGODSIJ/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":"2026-07-07T13:40:51Z","links":{"resolver":"https://pith.science/pith/FYLMUCP5TST75VE6R2RQGODSIJ","bundle":"https://pith.science/pith/FYLMUCP5TST75VE6R2RQGODSIJ/bundle.json","state":"https://pith.science/pith/FYLMUCP5TST75VE6R2RQGODSIJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FYLMUCP5TST75VE6R2RQGODSIJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FYLMUCP5TST75VE6R2RQGODSIJ","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":"b5841d5f61dec155a3a5ba1c8c63e14a0e4f4b7fa96bfb3818df7d0a75555b47","cross_cats_sorted":["cs.AI","cs.CE","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-02-21T19:22:10Z","title_canon_sha256":"fe9e46ae20e4439615a9e3475fe95d1bf993e91a9849b2993dbcad8257ad969d"},"schema_version":"1.0","source":{"id":"2502.17504","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17504","created_at":"2026-07-05T10:25:18Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17504v2","created_at":"2026-07-05T10:25:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17504","created_at":"2026-07-05T10:25:18Z"},{"alias_kind":"pith_short_12","alias_value":"FYLMUCP5TST7","created_at":"2026-07-05T10:25:18Z"},{"alias_kind":"pith_short_16","alias_value":"FYLMUCP5TST75VE6","created_at":"2026-07-05T10:25:18Z"},{"alias_kind":"pith_short_8","alias_value":"FYLMUCP5","created_at":"2026-07-05T10:25:18Z"}],"graph_snapshots":[{"event_id":"sha256:1c6aca78218e1c14363a93dcac9e66291071d09e69840293375d552e0c75828b","target":"graph","created_at":"2026-07-05T10:25:18Z","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/2502.17504/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Protein-specific large language models (Protein LLMs) are revolutionizing protein science by enabling more efficient protein structure prediction, function annotation, and design. While existing surveys focus on specific aspects or applications, this work provides the first comprehensive overview of Protein LLMs, covering their architectures, training datasets, evaluation metrics, and diverse applications. Through a systematic analysis of over 100 articles, we propose a structured taxonomy of state-of-the-art Protein LLMs, analyze how they leverage large-scale protein sequence data for improve","authors_text":"Guancheng Wan, Haixin Wang, Han Zhang, James Zou, Junkai Zhang, Pan Lu, Renliang Sun, Wanjia Zhao, Wei Wang, Xiao Luo, Yijia Xiao, Yiqiao Jin, Yizhou Sun, Yu Zhang, Zhicheng Ren","cross_cats":["cs.AI","cs.CE","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-02-21T19:22:10Z","title":"Protein Large Language Models: A Comprehensive Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17504","kind":"arxiv","version":2},"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":"sha256:1a021a7fec298a9fec34e427049fabff0f90fa3b5c7e891bdf848be73cec38de","target":"record","created_at":"2026-07-05T10:25:18Z","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":"b5841d5f61dec155a3a5ba1c8c63e14a0e4f4b7fa96bfb3818df7d0a75555b47","cross_cats_sorted":["cs.AI","cs.CE","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-02-21T19:22:10Z","title_canon_sha256":"fe9e46ae20e4439615a9e3475fe95d1bf993e91a9849b2993dbcad8257ad969d"},"schema_version":"1.0","source":{"id":"2502.17504","kind":"arxiv","version":2}},"canonical_sha256":"2e16ca09fd9ca7fed49e8ea303387242496baadc08750fc2da0ec515e7bbab4c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e16ca09fd9ca7fed49e8ea303387242496baadc08750fc2da0ec515e7bbab4c","first_computed_at":"2026-07-05T10:25:18.366301Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:18.366301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ogZUHzZk8afqjTN7urHsLnAy3XHOH1EKsePyOAihJIMvYth/XjOItRYWed/f3idNYEixunJhCiTP3epGvxGpAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:18.366905Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.17504","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a021a7fec298a9fec34e427049fabff0f90fa3b5c7e891bdf848be73cec38de","sha256:1c6aca78218e1c14363a93dcac9e66291071d09e69840293375d552e0c75828b"],"state_sha256":"c01b066e8f732391398bbb11c8742d00e2ef71185e81ea8753b26678722fc513"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NmIMf/JpKWwEAWa29V60/Q2S9idWxg5Kfa0CzIUNU3hNomewsH+qgr+4a2sBGqeQmYmh+CUw1rkswjax8/EUDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:40:51.536576Z","bundle_sha256":"d751d90e9101c061fbe358847850d8008e1abcbb59a5c69f07d5a1d41c579a23"}}