{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HCKDZ6YQQMTUTXZRFS5LBVDM4B","short_pith_number":"pith:HCKDZ6YQ","canonical_record":{"source":{"id":"2503.15438","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T17:19:07Z","cross_cats_sorted":["cs.AI","q-bio.QM"],"title_canon_sha256":"4bed01a04c16bdc036c1d80dbe8a294605cb690c517c25d585d03846b54f690e","abstract_canon_sha256":"bb672aaaa9c9e511f11d3c520c6190491796b1246d0f8d92fed472b56ae04f69"},"schema_version":"1.0"},"canonical_sha256":"38943cfb10832749df312cbab0d46ce046aaa29681428adf39636f5bb181dddb","source":{"kind":"arxiv","id":"2503.15438","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15438","created_at":"2026-07-05T10:35:26Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15438v1","created_at":"2026-07-05T10:35:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15438","created_at":"2026-07-05T10:35:26Z"},{"alias_kind":"pith_short_12","alias_value":"HCKDZ6YQQMTU","created_at":"2026-07-05T10:35:26Z"},{"alias_kind":"pith_short_16","alias_value":"HCKDZ6YQQMTUTXZR","created_at":"2026-07-05T10:35:26Z"},{"alias_kind":"pith_short_8","alias_value":"HCKDZ6YQ","created_at":"2026-07-05T10:35:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HCKDZ6YQQMTUTXZRFS5LBVDM4B","target":"record","payload":{"canonical_record":{"source":{"id":"2503.15438","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T17:19:07Z","cross_cats_sorted":["cs.AI","q-bio.QM"],"title_canon_sha256":"4bed01a04c16bdc036c1d80dbe8a294605cb690c517c25d585d03846b54f690e","abstract_canon_sha256":"bb672aaaa9c9e511f11d3c520c6190491796b1246d0f8d92fed472b56ae04f69"},"schema_version":"1.0"},"canonical_sha256":"38943cfb10832749df312cbab0d46ce046aaa29681428adf39636f5bb181dddb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:26.344720Z","signature_b64":"4kmjTZEC5fg7HvbLPMjh1N1n1p+iJvhXRUqrWwepX5sqS8bJiF0Mn5/c/KizliQoBPMKtfGdeq1KZncJRV1IAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38943cfb10832749df312cbab0d46ce046aaa29681428adf39636f5bb181dddb","last_reissued_at":"2026-07-05T10:35:26.343871Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:26.343871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.15438","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":"2026-07-05T10:35:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ckjEOcL9hQRFnz/+rTMCI1oBSyu4YBMB8ora+fvFT8UzOmQReNe7fxrLlQujw/eth4gYT95nU4x3KabOp2XSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:49:51.308630Z"},"content_sha256":"49675455b2538965d1c0f93e16c61262ebe5fe44239a9488339f94c516fb1c4d","schema_version":"1.0","event_id":"sha256:49675455b2538965d1c0f93e16c61262ebe5fe44239a9488339f94c516fb1c4d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HCKDZ6YQQMTUTXZRFS5LBVDM4B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VenusFactory: A Unified Platform for Protein Engineering Data Retrieval and Language Model Fine-Tuning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","q-bio.QM"],"primary_cat":"cs.CL","authors_text":"Banghao Wu, Bingxin Zhou, Chen Liu, Guisheng Fan, Huiqun Yu, Jingyuan Gao, Liang Hong, Lingrong Zhang, Mingchen Li, Ruilin Wang, Yang Tan","submitted_at":"2025-03-19T17:19:07Z","abstract_excerpt":"Natural language processing (NLP) has significantly influenced scientific domains beyond human language, including protein engineering, where pre-trained protein language models (PLMs) have demonstrated remarkable success. However, interdisciplinary adoption remains limited due to challenges in data collection, task benchmarking, and application. This work presents VenusFactory, a versatile engine that integrates biological data retrieval, standardized task benchmarking, and modular fine-tuning of PLMs. VenusFactory supports both computer science and biology communities with choices of both a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15438","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/2503.15438/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":"2026-07-05T10:35:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XUBFJ/+KXseF8jePcLkX9qS/poyOJVt2W/j+Qntz68kTiFrEFBrekfuO5lUFIokc3dMB4WCrq117FYAuNFCvCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:49:51.309024Z"},"content_sha256":"1356fe0c9dc75a05f634b26d5847e5e583ac525ef519a784b3cd648a337c7c2e","schema_version":"1.0","event_id":"sha256:1356fe0c9dc75a05f634b26d5847e5e583ac525ef519a784b3cd648a337c7c2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HCKDZ6YQQMTUTXZRFS5LBVDM4B/bundle.json","state_url":"https://pith.science/pith/HCKDZ6YQQMTUTXZRFS5LBVDM4B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HCKDZ6YQQMTUTXZRFS5LBVDM4B/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":"2026-08-04T16:49:51Z","links":{"resolver":"https://pith.science/pith/HCKDZ6YQQMTUTXZRFS5LBVDM4B","bundle":"https://pith.science/pith/HCKDZ6YQQMTUTXZRFS5LBVDM4B/bundle.json","state":"https://pith.science/pith/HCKDZ6YQQMTUTXZRFS5LBVDM4B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HCKDZ6YQQMTUTXZRFS5LBVDM4B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HCKDZ6YQQMTUTXZRFS5LBVDM4B","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":"bb672aaaa9c9e511f11d3c520c6190491796b1246d0f8d92fed472b56ae04f69","cross_cats_sorted":["cs.AI","q-bio.QM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T17:19:07Z","title_canon_sha256":"4bed01a04c16bdc036c1d80dbe8a294605cb690c517c25d585d03846b54f690e"},"schema_version":"1.0","source":{"id":"2503.15438","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15438","created_at":"2026-07-05T10:35:26Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15438v1","created_at":"2026-07-05T10:35:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15438","created_at":"2026-07-05T10:35:26Z"},{"alias_kind":"pith_short_12","alias_value":"HCKDZ6YQQMTU","created_at":"2026-07-05T10:35:26Z"},{"alias_kind":"pith_short_16","alias_value":"HCKDZ6YQQMTUTXZR","created_at":"2026-07-05T10:35:26Z"},{"alias_kind":"pith_short_8","alias_value":"HCKDZ6YQ","created_at":"2026-07-05T10:35:26Z"}],"graph_snapshots":[{"event_id":"sha256:1356fe0c9dc75a05f634b26d5847e5e583ac525ef519a784b3cd648a337c7c2e","target":"graph","created_at":"2026-07-05T10:35:26Z","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/2503.15438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural language processing (NLP) has significantly influenced scientific domains beyond human language, including protein engineering, where pre-trained protein language models (PLMs) have demonstrated remarkable success. However, interdisciplinary adoption remains limited due to challenges in data collection, task benchmarking, and application. This work presents VenusFactory, a versatile engine that integrates biological data retrieval, standardized task benchmarking, and modular fine-tuning of PLMs. VenusFactory supports both computer science and biology communities with choices of both a ","authors_text":"Banghao Wu, Bingxin Zhou, Chen Liu, Guisheng Fan, Huiqun Yu, Jingyuan Gao, Liang Hong, Lingrong Zhang, Mingchen Li, Ruilin Wang, Yang Tan","cross_cats":["cs.AI","q-bio.QM"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T17:19:07Z","title":"VenusFactory: A Unified Platform for Protein Engineering Data Retrieval and Language Model Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15438","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":"sha256:49675455b2538965d1c0f93e16c61262ebe5fe44239a9488339f94c516fb1c4d","target":"record","created_at":"2026-07-05T10:35:26Z","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":"bb672aaaa9c9e511f11d3c520c6190491796b1246d0f8d92fed472b56ae04f69","cross_cats_sorted":["cs.AI","q-bio.QM"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T17:19:07Z","title_canon_sha256":"4bed01a04c16bdc036c1d80dbe8a294605cb690c517c25d585d03846b54f690e"},"schema_version":"1.0","source":{"id":"2503.15438","kind":"arxiv","version":1}},"canonical_sha256":"38943cfb10832749df312cbab0d46ce046aaa29681428adf39636f5bb181dddb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38943cfb10832749df312cbab0d46ce046aaa29681428adf39636f5bb181dddb","first_computed_at":"2026-07-05T10:35:26.343871Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:26.343871Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4kmjTZEC5fg7HvbLPMjh1N1n1p+iJvhXRUqrWwepX5sqS8bJiF0Mn5/c/KizliQoBPMKtfGdeq1KZncJRV1IAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:26.344720Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15438","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49675455b2538965d1c0f93e16c61262ebe5fe44239a9488339f94c516fb1c4d","sha256:1356fe0c9dc75a05f634b26d5847e5e583ac525ef519a784b3cd648a337c7c2e"],"state_sha256":"264a4c2265089ba7a6db125b69339e1794290906e7c6b89b76b2bee3d01df2e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gUlBweEXzX9K2DRNUsKx3WsJMRk/TVZPzi0e2M0OT+tzrefG9ItC8pfR/doTiZ5DzTaG5M+Z1iIbpWtpw9Q4Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:49:51.312162Z","bundle_sha256":"f387ab532b58376e9ffda9074296428da24529eb7fcf957e2da737e3c52826c8"}}