{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DLVEO3OKKAL3WDMZZO6KQE6AO4","short_pith_number":"pith:DLVEO3OK","schema_version":"1.0","canonical_sha256":"1aea476dca5017bb0d99cbbca813c0770174d8eebb8af76c2589b18ba9fef9eb","source":{"kind":"arxiv","id":"2506.08954","version":1},"attestation_state":"computed","paper":{"title":"Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.BM"],"primary_cat":"q-bio.QM","authors_text":"Aoi Otani, Debora Marks, Lood Van Niekerk, Pascal Notin, Peter M{\\o}rch Groth, Ruben Weitzman, Yarin Gal","submitted_at":"2025-06-10T16:24:09Z","abstract_excerpt":"Retrieving homologous protein sequences is essential for a broad range of protein modeling tasks such as fitness prediction, protein design, structure modeling, and protein-protein interactions. Traditional workflows have relied on a two-step process: first retrieving homologs via Multiple Sequence Alignments (MSA), then training models on one or more of these alignments. However, MSA-based retrieval is computationally expensive, struggles with highly divergent sequences or complex insertions & deletions patterns, and operates independently of the downstream modeling objective. We introduce Pr"},"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":"2506.08954","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.QM","submitted_at":"2025-06-10T16:24:09Z","cross_cats_sorted":["cs.LG","q-bio.BM"],"title_canon_sha256":"902c9dd69b12a1396a296d14d558126dc287a8786de7050ddcd58aefc88ed95b","abstract_canon_sha256":"8a6169692917d7a2062b040c4dac0296157e48879fee8e465b45612068795015"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:15.816430Z","signature_b64":"mQmmX5OBhWGlXXRx+b12khX6BiZO5VSBiISY/tcL3pyUGsDx0saDIHZN+NihCeNEhox++QjWKi6VSEWRuu+7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1aea476dca5017bb0d99cbbca813c0770174d8eebb8af76c2589b18ba9fef9eb","last_reissued_at":"2026-07-05T11:19:15.815905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:15.815905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Protriever: End-to-End Differentiable Protein Homology Search for Fitness Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.BM"],"primary_cat":"q-bio.QM","authors_text":"Aoi Otani, Debora Marks, Lood Van Niekerk, Pascal Notin, Peter M{\\o}rch Groth, Ruben Weitzman, Yarin Gal","submitted_at":"2025-06-10T16:24:09Z","abstract_excerpt":"Retrieving homologous protein sequences is essential for a broad range of protein modeling tasks such as fitness prediction, protein design, structure modeling, and protein-protein interactions. Traditional workflows have relied on a two-step process: first retrieving homologs via Multiple Sequence Alignments (MSA), then training models on one or more of these alignments. However, MSA-based retrieval is computationally expensive, struggles with highly divergent sequences or complex insertions & deletions patterns, and operates independently of the downstream modeling objective. We introduce Pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08954","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/2506.08954/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":"2506.08954","created_at":"2026-07-05T11:19:15.815966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08954v1","created_at":"2026-07-05T11:19:15.815966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08954","created_at":"2026-07-05T11:19:15.815966+00:00"},{"alias_kind":"pith_short_12","alias_value":"DLVEO3OKKAL3","created_at":"2026-07-05T11:19:15.815966+00:00"},{"alias_kind":"pith_short_16","alias_value":"DLVEO3OKKAL3WDMZ","created_at":"2026-07-05T11:19:15.815966+00:00"},{"alias_kind":"pith_short_8","alias_value":"DLVEO3OK","created_at":"2026-07-05T11:19:15.815966+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/DLVEO3OKKAL3WDMZZO6KQE6AO4","json":"https://pith.science/pith/DLVEO3OKKAL3WDMZZO6KQE6AO4.json","graph_json":"https://pith.science/api/pith-number/DLVEO3OKKAL3WDMZZO6KQE6AO4/graph.json","events_json":"https://pith.science/api/pith-number/DLVEO3OKKAL3WDMZZO6KQE6AO4/events.json","paper":"https://pith.science/paper/DLVEO3OK"},"agent_actions":{"view_html":"https://pith.science/pith/DLVEO3OKKAL3WDMZZO6KQE6AO4","download_json":"https://pith.science/pith/DLVEO3OKKAL3WDMZZO6KQE6AO4.json","view_paper":"https://pith.science/paper/DLVEO3OK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08954&json=true","fetch_graph":"https://pith.science/api/pith-number/DLVEO3OKKAL3WDMZZO6KQE6AO4/graph.json","fetch_events":"https://pith.science/api/pith-number/DLVEO3OKKAL3WDMZZO6KQE6AO4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DLVEO3OKKAL3WDMZZO6KQE6AO4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DLVEO3OKKAL3WDMZZO6KQE6AO4/action/storage_attestation","attest_author":"https://pith.science/pith/DLVEO3OKKAL3WDMZZO6KQE6AO4/action/author_attestation","sign_citation":"https://pith.science/pith/DLVEO3OKKAL3WDMZZO6KQE6AO4/action/citation_signature","submit_replication":"https://pith.science/pith/DLVEO3OKKAL3WDMZZO6KQE6AO4/action/replication_record"}},"created_at":"2026-07-05T11:19:15.815966+00:00","updated_at":"2026-07-05T11:19:15.815966+00:00"}