{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FZAEOBS2Y7XIMWIDTKSMGVCMIK","short_pith_number":"pith:FZAEOBS2","canonical_record":{"source":{"id":"2501.09274","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T03:44:16Z","cross_cats_sorted":["cs.AI","q-bio.QM"],"title_canon_sha256":"6570c877050baf4b3d0182b6bca5db0d460ea138c9410b2c4e9cb06069ba3b86","abstract_canon_sha256":"e226ac4c661b257588a1203507ec203d0bb9484a455631af00ba84554fedbfab"},"schema_version":"1.0"},"canonical_sha256":"2e4047065ac7ee8659039aa4c3544c42a7987a6538612d7af986d0e544421d24","source":{"kind":"arxiv","id":"2501.09274","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09274","created_at":"2026-07-05T10:02:10Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09274v2","created_at":"2026-07-05T10:02:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09274","created_at":"2026-07-05T10:02:10Z"},{"alias_kind":"pith_short_12","alias_value":"FZAEOBS2Y7XI","created_at":"2026-07-05T10:02:10Z"},{"alias_kind":"pith_short_16","alias_value":"FZAEOBS2Y7XIMWID","created_at":"2026-07-05T10:02:10Z"},{"alias_kind":"pith_short_8","alias_value":"FZAEOBS2","created_at":"2026-07-05T10:02:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FZAEOBS2Y7XIMWIDTKSMGVCMIK","target":"record","payload":{"canonical_record":{"source":{"id":"2501.09274","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T03:44:16Z","cross_cats_sorted":["cs.AI","q-bio.QM"],"title_canon_sha256":"6570c877050baf4b3d0182b6bca5db0d460ea138c9410b2c4e9cb06069ba3b86","abstract_canon_sha256":"e226ac4c661b257588a1203507ec203d0bb9484a455631af00ba84554fedbfab"},"schema_version":"1.0"},"canonical_sha256":"2e4047065ac7ee8659039aa4c3544c42a7987a6538612d7af986d0e544421d24","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:10.184785Z","signature_b64":"bwJ8tWyC+Fk7E9tNtwpjvvUm3GI6CoQaqF34szMrNXYSo5fgY85bBIu8biK8kHGB7US/iB+NS9VZzJCUpjShBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e4047065ac7ee8659039aa4c3544c42a7987a6538612d7af986d0e544421d24","last_reissued_at":"2026-07-05T10:02:10.184364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:10.184364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.09274","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":"2026-07-05T10:02:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gIWhgTwDKqT5SJY9icMO47zwzd+/qztOmJY9A3z89s9YRqygcwJ+RqPC/ttPP7lZE8cnW5VzTjpL/n8oIxI9CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T13:49:31.662672Z"},"content_sha256":"1a3547ee16fd6f5375c0a191b2a96182d40e8adf9a86c955182b948d2dc4395d","schema_version":"1.0","event_id":"sha256:1a3547ee16fd6f5375c0a191b2a96182d40e8adf9a86c955182b948d2dc4395d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FZAEOBS2Y7XIMWIDTKSMGVCMIK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Model is Secretly a Protein Sequence Optimizer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","q-bio.QM"],"primary_cat":"cs.LG","authors_text":"Jianan Canal Li, Jiaxing He, Li-Ping Liu, Soha Hassoun, Xiaohui Chen, Xiaolin Xu, Yinkai Wang, Yuanqi Du","submitted_at":"2025-01-16T03:44:16Z","abstract_excerpt":"We consider the protein sequence engineering problem, which aims to find protein sequences with high fitness levels, starting from a given wild-type sequence. Directed evolution has been a dominating paradigm in this field which has an iterative process to generate variants and select via experimental feedback. We demonstrate large language models (LLMs), despite being trained on massive texts, are secretly protein sequence optimizers. With a directed evolutionary method, LLM can perform protein engineering through Pareto and experiment-budget constrained optimization, demonstrating success on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09274","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/2501.09274/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":"2026-07-05T10:02:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UGTZ1CFHVYgXVt8TgxGr/Sq7Dk1NVv9AHL2nr5EdgqxXu3Uz+iD4cMPmv51Qk5A6nw4eJ57IGh+iLoVwLYFvBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T13:49:31.664169Z"},"content_sha256":"07c7fbed5f9964b9910cebeed0d7146e6ee75613f0790aa64169571ff5fcd89a","schema_version":"1.0","event_id":"sha256:07c7fbed5f9964b9910cebeed0d7146e6ee75613f0790aa64169571ff5fcd89a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FZAEOBS2Y7XIMWIDTKSMGVCMIK/bundle.json","state_url":"https://pith.science/pith/FZAEOBS2Y7XIMWIDTKSMGVCMIK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FZAEOBS2Y7XIMWIDTKSMGVCMIK/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":"2026-08-20T13:49:31Z","links":{"resolver":"https://pith.science/pith/FZAEOBS2Y7XIMWIDTKSMGVCMIK","bundle":"https://pith.science/pith/FZAEOBS2Y7XIMWIDTKSMGVCMIK/bundle.json","state":"https://pith.science/pith/FZAEOBS2Y7XIMWIDTKSMGVCMIK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FZAEOBS2Y7XIMWIDTKSMGVCMIK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FZAEOBS2Y7XIMWIDTKSMGVCMIK","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":"e226ac4c661b257588a1203507ec203d0bb9484a455631af00ba84554fedbfab","cross_cats_sorted":["cs.AI","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T03:44:16Z","title_canon_sha256":"6570c877050baf4b3d0182b6bca5db0d460ea138c9410b2c4e9cb06069ba3b86"},"schema_version":"1.0","source":{"id":"2501.09274","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09274","created_at":"2026-07-05T10:02:10Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09274v2","created_at":"2026-07-05T10:02:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09274","created_at":"2026-07-05T10:02:10Z"},{"alias_kind":"pith_short_12","alias_value":"FZAEOBS2Y7XI","created_at":"2026-07-05T10:02:10Z"},{"alias_kind":"pith_short_16","alias_value":"FZAEOBS2Y7XIMWID","created_at":"2026-07-05T10:02:10Z"},{"alias_kind":"pith_short_8","alias_value":"FZAEOBS2","created_at":"2026-07-05T10:02:10Z"}],"graph_snapshots":[{"event_id":"sha256:07c7fbed5f9964b9910cebeed0d7146e6ee75613f0790aa64169571ff5fcd89a","target":"graph","created_at":"2026-07-05T10:02:10Z","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/2501.09274/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the protein sequence engineering problem, which aims to find protein sequences with high fitness levels, starting from a given wild-type sequence. Directed evolution has been a dominating paradigm in this field which has an iterative process to generate variants and select via experimental feedback. We demonstrate large language models (LLMs), despite being trained on massive texts, are secretly protein sequence optimizers. With a directed evolutionary method, LLM can perform protein engineering through Pareto and experiment-budget constrained optimization, demonstrating success on","authors_text":"Jianan Canal Li, Jiaxing He, Li-Ping Liu, Soha Hassoun, Xiaohui Chen, Xiaolin Xu, Yinkai Wang, Yuanqi Du","cross_cats":["cs.AI","q-bio.QM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T03:44:16Z","title":"Large Language Model is Secretly a Protein Sequence Optimizer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09274","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":"sha256:1a3547ee16fd6f5375c0a191b2a96182d40e8adf9a86c955182b948d2dc4395d","target":"record","created_at":"2026-07-05T10:02:10Z","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":"e226ac4c661b257588a1203507ec203d0bb9484a455631af00ba84554fedbfab","cross_cats_sorted":["cs.AI","q-bio.QM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-16T03:44:16Z","title_canon_sha256":"6570c877050baf4b3d0182b6bca5db0d460ea138c9410b2c4e9cb06069ba3b86"},"schema_version":"1.0","source":{"id":"2501.09274","kind":"arxiv","version":2}},"canonical_sha256":"2e4047065ac7ee8659039aa4c3544c42a7987a6538612d7af986d0e544421d24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e4047065ac7ee8659039aa4c3544c42a7987a6538612d7af986d0e544421d24","first_computed_at":"2026-07-05T10:02:10.184364Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:10.184364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bwJ8tWyC+Fk7E9tNtwpjvvUm3GI6CoQaqF34szMrNXYSo5fgY85bBIu8biK8kHGB7US/iB+NS9VZzJCUpjShBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:10.184785Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09274","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a3547ee16fd6f5375c0a191b2a96182d40e8adf9a86c955182b948d2dc4395d","sha256:07c7fbed5f9964b9910cebeed0d7146e6ee75613f0790aa64169571ff5fcd89a"],"state_sha256":"eb5eb94f5999c875a32ae31be04db26e70e325ada349333ccbb58480a33fea22"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mGCWcg3VQWYn2SWUrctJ3C8k0cZTcb0WUFoLOh/IItH8KvC5hlBIXxZjcS4hD5a/BiZb5/UMDAb5ZLQAS+IxDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T13:49:31.671167Z","bundle_sha256":"abfc508af1f15db6ec0513bd98bff190a35e7b38c6f959a69f46d5b76d77d814"}}