{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ONYVXMFX7QY743KKG3R5UNACS4","short_pith_number":"pith:ONYVXMFX","schema_version":"1.0","canonical_sha256":"73715bb0b7fc31fe6d4a36e3da340297046e8fef598e6d234303d692102679b6","source":{"kind":"arxiv","id":"2606.02624","version":1},"attestation_state":"computed","paper":{"title":"TadA-Bench: A Million-Variant Benchmark for Future-Round Discovery Toward Agentic Protein Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Dequan Wang, Dukun Zhao, Jiaqi Shen, Jin Gao, Junhao Shi, Juntu Zhao, Yuming Lu, Zirui Zeng","submitted_at":"2026-05-29T12:12:08Z","abstract_excerpt":"AI for scientific discovery is entering an agentic era, where protein-engineering systems are expected to prioritize future wet-lab experiments rather than merely fit static measurements. We introduce TadA-Bench, a million-variant wet-lab replay benchmark from 31 TadA directed-evolution rounds for future-round discovery toward agentic protein engineering. TadA-Bench preserves the campaign chronology and defines a fixed-data replay task: given earlier experimental rounds, models rank variants that appear only in later rounds. It provides aligned DNA, RNA, and protein views, and uses Seq2Graph, "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.02624","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2026-05-29T12:12:08Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ab3deddc56923b74279b29a870cc9b1f49e5cad5f2818c2714d5fda31d385971","abstract_canon_sha256":"5064fe006629cd9870f29a20bb6bbe360519dc4ea451178bbac25040e5e818d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T00:05:04.984671Z","signature_b64":"O4XXr25fM/6qz+x9j+hO7KApWjFgXE6vy++O7mmxDCNlP1MVORW3QYRRrRJdqMRk+n+DSdOyoLROLh6f7TRiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73715bb0b7fc31fe6d4a36e3da340297046e8fef598e6d234303d692102679b6","last_reissued_at":"2026-06-03T00:05:04.984234Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T00:05:04.984234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TadA-Bench: A Million-Variant Benchmark for Future-Round Discovery Toward Agentic Protein Engineering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.QM","authors_text":"Dequan Wang, Dukun Zhao, Jiaqi Shen, Jin Gao, Junhao Shi, Juntu Zhao, Yuming Lu, Zirui Zeng","submitted_at":"2026-05-29T12:12:08Z","abstract_excerpt":"AI for scientific discovery is entering an agentic era, where protein-engineering systems are expected to prioritize future wet-lab experiments rather than merely fit static measurements. We introduce TadA-Bench, a million-variant wet-lab replay benchmark from 31 TadA directed-evolution rounds for future-round discovery toward agentic protein engineering. TadA-Bench preserves the campaign chronology and defines a fixed-data replay task: given earlier experimental rounds, models rank variants that appear only in later rounds. It provides aligned DNA, RNA, and protein views, and uses Seq2Graph, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02624","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/2606.02624/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.02624","created_at":"2026-06-03T00:05:04.984291+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02624v1","created_at":"2026-06-03T00:05:04.984291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02624","created_at":"2026-06-03T00:05:04.984291+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONYVXMFX7QY7","created_at":"2026-06-03T00:05:04.984291+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONYVXMFX7QY743KK","created_at":"2026-06-03T00:05:04.984291+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONYVXMFX","created_at":"2026-06-03T00:05:04.984291+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ONYVXMFX7QY743KKG3R5UNACS4","json":"https://pith.science/pith/ONYVXMFX7QY743KKG3R5UNACS4.json","graph_json":"https://pith.science/api/pith-number/ONYVXMFX7QY743KKG3R5UNACS4/graph.json","events_json":"https://pith.science/api/pith-number/ONYVXMFX7QY743KKG3R5UNACS4/events.json","paper":"https://pith.science/paper/ONYVXMFX"},"agent_actions":{"view_html":"https://pith.science/pith/ONYVXMFX7QY743KKG3R5UNACS4","download_json":"https://pith.science/pith/ONYVXMFX7QY743KKG3R5UNACS4.json","view_paper":"https://pith.science/paper/ONYVXMFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02624&json=true","fetch_graph":"https://pith.science/api/pith-number/ONYVXMFX7QY743KKG3R5UNACS4/graph.json","fetch_events":"https://pith.science/api/pith-number/ONYVXMFX7QY743KKG3R5UNACS4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONYVXMFX7QY743KKG3R5UNACS4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONYVXMFX7QY743KKG3R5UNACS4/action/storage_attestation","attest_author":"https://pith.science/pith/ONYVXMFX7QY743KKG3R5UNACS4/action/author_attestation","sign_citation":"https://pith.science/pith/ONYVXMFX7QY743KKG3R5UNACS4/action/citation_signature","submit_replication":"https://pith.science/pith/ONYVXMFX7QY743KKG3R5UNACS4/action/replication_record"}},"created_at":"2026-06-03T00:05:04.984291+00:00","updated_at":"2026-06-03T00:05:04.984291+00:00"}