{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YXRUPWHI7D2CLCZU3G7BBD3ZAL","short_pith_number":"pith:YXRUPWHI","canonical_record":{"source":{"id":"2605.04118","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2026-05-05T11:48:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"29ff778fc392f8d1cc0d4cccd4cc6a6ff4f34f38282127e94d7386357ab61d32","abstract_canon_sha256":"9bc5302669094ee96b4db6b9698023741e2216b324eb8f9eafe8add32dfaabc2"},"schema_version":"1.0"},"canonical_sha256":"c5e347d8e8f8f4258b34d9be108f7902c3754fa0392a20e7f11152d771719371","source":{"kind":"arxiv","id":"2605.04118","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.04118","created_at":"2026-05-25T02:02:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.04118v2","created_at":"2026-05-25T02:02:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.04118","created_at":"2026-05-25T02:02:16Z"},{"alias_kind":"pith_short_12","alias_value":"YXRUPWHI7D2C","created_at":"2026-05-25T02:02:16Z"},{"alias_kind":"pith_short_16","alias_value":"YXRUPWHI7D2CLCZU","created_at":"2026-05-25T02:02:16Z"},{"alias_kind":"pith_short_8","alias_value":"YXRUPWHI","created_at":"2026-05-25T02:02:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YXRUPWHI7D2CLCZU3G7BBD3ZAL","target":"record","payload":{"canonical_record":{"source":{"id":"2605.04118","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2026-05-05T11:48:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"29ff778fc392f8d1cc0d4cccd4cc6a6ff4f34f38282127e94d7386357ab61d32","abstract_canon_sha256":"9bc5302669094ee96b4db6b9698023741e2216b324eb8f9eafe8add32dfaabc2"},"schema_version":"1.0"},"canonical_sha256":"c5e347d8e8f8f4258b34d9be108f7902c3754fa0392a20e7f11152d771719371","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:16.241791Z","signature_b64":"U3FC9CenPMFp3dO9hwwoCHwLXGdTsg3PnBxye+dxF6Ks0GQtFPp0CbetlL+LhbrCU37ALdYZtka4dBo89eKDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5e347d8e8f8f4258b34d9be108f7902c3754fa0392a20e7f11152d771719371","last_reissued_at":"2026-05-25T02:02:16.241048Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:16.241048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.04118","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":"2026-05-25T02:02:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"47Nl7qMeUmtMHJ8UAn887PSZITFcO92sS85Whvt1YYSUNcS1RJDAZwVcciGqReVoTtUGMM/+w1R7t0zv1ai7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:19:28.171997Z"},"content_sha256":"b38b39d44863282150b301ee5e90c0e4d12d97e4f62f6c97523c56486f8c1be8","schema_version":"1.0","event_id":"sha256:b38b39d44863282150b301ee5e90c0e4d12d97e4f62f6c97523c56486f8c1be8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YXRUPWHI7D2CLCZU3G7BBD3ZAL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProtDBench: A Unified Benchmark of Protein Binder Design and Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A new benchmark for protein binder design shows that common structure prediction models disagree substantially on which designs succeed under identical rules.","cross_cats":["cs.AI"],"primary_cat":"q-bio.QM","authors_text":"Chengyue Gong, Cong Liu, Jiaqi Guan, Jinyuan Sun, Milong Ren, Wenzhi Xiao, Xinshi Chen","submitted_at":"2026-05-05T11:48:59Z","abstract_excerpt":"Recent advances in de novo protein binder design have enabled increasing experimental validation, yet reported in silico metrics remain difficult to interpret or compare across studies due to non-standardized evaluation protocols. We introduce ProtDBench, a standardized and throughput-aware evaluation framework for protein binder design. ProtDBench defines unified benchmark tasks, evaluation protocols, and success criteria, enabling systematic analysis of how evaluation design influences observed performance. Using a large wet-lab annotated dataset, we analyze commonly used structure predictio"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Using a large wet-lab annotated dataset, we analyze commonly used structure prediction models as evaluation verifiers, revealing substantial verifier-dependent bias and limited agreement under identical filtering protocols. ... Overall, ProtDBench provides a fair and reproducible evaluation pipeline that supports systematic and controlled comparison of protein binder design methods under realistic evaluation settings.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the defined success criteria, filtering protocols, and wet-lab annotated dataset accurately reflect real experimental binder performance and provide a representative basis for benchmarking.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ProtDBench standardizes protein binder design evaluation using wet-lab data, exposing verifier biases, metric dependencies, and trade-offs between success rate, speed, and structural diversity.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A new benchmark for protein binder design shows that common structure prediction models disagree substantially on which designs succeed under identical rules.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"75e6ef31d6837543ba092d650fe111d71d724b28c36cea7f8a9cd14f537e5132"},"source":{"id":"2605.04118","kind":"arxiv","version":2},"verdict":{"id":"f144bf74-40b8-4ca1-88b0-b1ae56f84e27","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T18:09:03.659188Z","strongest_claim":"Using a large wet-lab annotated dataset, we analyze commonly used structure prediction models as evaluation verifiers, revealing substantial verifier-dependent bias and limited agreement under identical filtering protocols. ... Overall, ProtDBench provides a fair and reproducible evaluation pipeline that supports systematic and controlled comparison of protein binder design methods under realistic evaluation settings.","one_line_summary":"ProtDBench standardizes protein binder design evaluation using wet-lab data, exposing verifier biases, metric dependencies, and trade-offs between success rate, speed, and structural diversity.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the defined success criteria, filtering protocols, and wet-lab annotated dataset accurately reflect real experimental binder performance and provide a representative basis for benchmarking.","pith_extraction_headline":"A new benchmark for protein binder design shows that common structure prediction models disagree substantially on which designs succeed under identical rules."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.04118/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T13:36:39.248387Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T00:31:21.665980Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T15:07:27.199343Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9522f94c1f930f5201dea4bd8886f4758b5b7e2598cc6a2a986b8e861c421d81"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":3,"snapshot_sha256":"ff35b7430ce1419199860890142a12cc8dd08fe311b31a58b6e9832801aa4498"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"f144bf74-40b8-4ca1-88b0-b1ae56f84e27"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-25T02:02:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rwc02gH/RuVOsqo4NhexmPlgJ5Zi5q0ZAoR4am5gyMUi8KyZj4i1SH48gmyoMw60eWUzwpzhi9H6s1FRLqhTDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T17:19:28.173138Z"},"content_sha256":"f0ca3aff194a867ac6a10d16512275a9e0c7dcf3d6fa78435da584ecc9ffcf9a","schema_version":"1.0","event_id":"sha256:f0ca3aff194a867ac6a10d16512275a9e0c7dcf3d6fa78435da584ecc9ffcf9a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YXRUPWHI7D2CLCZU3G7BBD3ZAL/bundle.json","state_url":"https://pith.science/pith/YXRUPWHI7D2CLCZU3G7BBD3ZAL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YXRUPWHI7D2CLCZU3G7BBD3ZAL/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":"2026-05-30T17:19:28Z","links":{"resolver":"https://pith.science/pith/YXRUPWHI7D2CLCZU3G7BBD3ZAL","bundle":"https://pith.science/pith/YXRUPWHI7D2CLCZU3G7BBD3ZAL/bundle.json","state":"https://pith.science/pith/YXRUPWHI7D2CLCZU3G7BBD3ZAL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YXRUPWHI7D2CLCZU3G7BBD3ZAL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YXRUPWHI7D2CLCZU3G7BBD3ZAL","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":"9bc5302669094ee96b4db6b9698023741e2216b324eb8f9eafe8add32dfaabc2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2026-05-05T11:48:59Z","title_canon_sha256":"29ff778fc392f8d1cc0d4cccd4cc6a6ff4f34f38282127e94d7386357ab61d32"},"schema_version":"1.0","source":{"id":"2605.04118","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.04118","created_at":"2026-05-25T02:02:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.04118v2","created_at":"2026-05-25T02:02:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.04118","created_at":"2026-05-25T02:02:16Z"},{"alias_kind":"pith_short_12","alias_value":"YXRUPWHI7D2C","created_at":"2026-05-25T02:02:16Z"},{"alias_kind":"pith_short_16","alias_value":"YXRUPWHI7D2CLCZU","created_at":"2026-05-25T02:02:16Z"},{"alias_kind":"pith_short_8","alias_value":"YXRUPWHI","created_at":"2026-05-25T02:02:16Z"}],"graph_snapshots":[{"event_id":"sha256:f0ca3aff194a867ac6a10d16512275a9e0c7dcf3d6fa78435da584ecc9ffcf9a","target":"graph","created_at":"2026-05-25T02:02:16Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Using a large wet-lab annotated dataset, we analyze commonly used structure prediction models as evaluation verifiers, revealing substantial verifier-dependent bias and limited agreement under identical filtering protocols. ... Overall, ProtDBench provides a fair and reproducible evaluation pipeline that supports systematic and controlled comparison of protein binder design methods under realistic evaluation settings."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the defined success criteria, filtering protocols, and wet-lab annotated dataset accurately reflect real experimental binder performance and provide a representative basis for benchmarking."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ProtDBench standardizes protein binder design evaluation using wet-lab data, exposing verifier biases, metric dependencies, and trade-offs between success rate, speed, and structural diversity."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A new benchmark for protein binder design shows that common structure prediction models disagree substantially on which designs succeed under identical rules."}],"snapshot_sha256":"75e6ef31d6837543ba092d650fe111d71d724b28c36cea7f8a9cd14f537e5132"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"ff35b7430ce1419199860890142a12cc8dd08fe311b31a58b6e9832801aa4498"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T13:36:39.248387Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T00:31:21.665980Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T15:07:27.199343Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.04118/integrity.json","findings":[],"snapshot_sha256":"9522f94c1f930f5201dea4bd8886f4758b5b7e2598cc6a2a986b8e861c421d81","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in de novo protein binder design have enabled increasing experimental validation, yet reported in silico metrics remain difficult to interpret or compare across studies due to non-standardized evaluation protocols. We introduce ProtDBench, a standardized and throughput-aware evaluation framework for protein binder design. ProtDBench defines unified benchmark tasks, evaluation protocols, and success criteria, enabling systematic analysis of how evaluation design influences observed performance. Using a large wet-lab annotated dataset, we analyze commonly used structure predictio","authors_text":"Chengyue Gong, Cong Liu, Jiaqi Guan, Jinyuan Sun, Milong Ren, Wenzhi Xiao, Xinshi Chen","cross_cats":["cs.AI"],"headline":"A new benchmark for protein binder design shows that common structure prediction models disagree substantially on which designs succeed under identical rules.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2026-05-05T11:48:59Z","title":"ProtDBench: A Unified Benchmark of Protein Binder Design and Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.04118","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T18:09:03.659188Z","id":"f144bf74-40b8-4ca1-88b0-b1ae56f84e27","model_set":{"reader":"grok-4.3"},"one_line_summary":"ProtDBench standardizes protein binder design evaluation using wet-lab data, exposing verifier biases, metric dependencies, and trade-offs between success rate, speed, and structural diversity.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A new benchmark for protein binder design shows that common structure prediction models disagree substantially on which designs succeed under identical rules.","strongest_claim":"Using a large wet-lab annotated dataset, we analyze commonly used structure prediction models as evaluation verifiers, revealing substantial verifier-dependent bias and limited agreement under identical filtering protocols. ... Overall, ProtDBench provides a fair and reproducible evaluation pipeline that supports systematic and controlled comparison of protein binder design methods under realistic evaluation settings.","weakest_assumption":"That the defined success criteria, filtering protocols, and wet-lab annotated dataset accurately reflect real experimental binder performance and provide a representative basis for benchmarking."}},"verdict_id":"f144bf74-40b8-4ca1-88b0-b1ae56f84e27"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b38b39d44863282150b301ee5e90c0e4d12d97e4f62f6c97523c56486f8c1be8","target":"record","created_at":"2026-05-25T02:02:16Z","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":"9bc5302669094ee96b4db6b9698023741e2216b324eb8f9eafe8add32dfaabc2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.QM","submitted_at":"2026-05-05T11:48:59Z","title_canon_sha256":"29ff778fc392f8d1cc0d4cccd4cc6a6ff4f34f38282127e94d7386357ab61d32"},"schema_version":"1.0","source":{"id":"2605.04118","kind":"arxiv","version":2}},"canonical_sha256":"c5e347d8e8f8f4258b34d9be108f7902c3754fa0392a20e7f11152d771719371","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5e347d8e8f8f4258b34d9be108f7902c3754fa0392a20e7f11152d771719371","first_computed_at":"2026-05-25T02:02:16.241048Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:16.241048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U3FC9CenPMFp3dO9hwwoCHwLXGdTsg3PnBxye+dxF6Ks0GQtFPp0CbetlL+LhbrCU37ALdYZtka4dBo89eKDDg==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:16.241791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.04118","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b38b39d44863282150b301ee5e90c0e4d12d97e4f62f6c97523c56486f8c1be8","sha256:f0ca3aff194a867ac6a10d16512275a9e0c7dcf3d6fa78435da584ecc9ffcf9a"],"state_sha256":"d1644fef38c6184afb82d65cfb74c4a6862e71348cd6b15a42e1299ab072ac4f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nrMsGY5qjFika+t6Zj9X0TXe6lCfIdKtXRlJUCeefgWji4CUZ+8l6euue8uyyN5HdvujOQrnr4d1H/c4F9ODAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T17:19:28.178226Z","bundle_sha256":"5d81889f38ae1266200250986259dbbb9c45b97760cdc276a81727565694ebd4"}}