{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TEII2DSKILP2FA7GZE3MXMW7GO","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":"214e3b5aa772fb8b247822f77a662ed403eca3d64791b3ff24a9ebc40264378c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-07-10T08:41:08Z","title_canon_sha256":"335ac8c9b28488e5dacf85ffa2ed2d4ff04602ab63cece0dfb7a5044fdb47233"},"schema_version":"1.0","source":{"id":"2507.07547","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07547","created_at":"2026-07-05T11:35:00Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07547v1","created_at":"2026-07-05T11:35:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07547","created_at":"2026-07-05T11:35:00Z"},{"alias_kind":"pith_short_12","alias_value":"TEII2DSKILP2","created_at":"2026-07-05T11:35:00Z"},{"alias_kind":"pith_short_16","alias_value":"TEII2DSKILP2FA7G","created_at":"2026-07-05T11:35:00Z"},{"alias_kind":"pith_short_8","alias_value":"TEII2DSK","created_at":"2026-07-05T11:35:00Z"}],"graph_snapshots":[{"event_id":"sha256:ee89abc1e13a125c559ffade382c9c8f2ea81961d3f4dd3ba17b79c941e61a90","target":"graph","created_at":"2026-07-05T11:35:00Z","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/2507.07547/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data-driven modeling based on Machine Learning (ML) is becoming a central component of protein engineering workflows. This perspective presents the elements necessary to develop effective, reliable, and reproducible ML models, and a set of guidelines for ML developments for protein engineering. This includes a critical discussion of software engineering good practices for development and evaluation of ML-based protein engineering projects, emphasizing supervised learning. These guidelines cover all the necessary steps for ML development, from data acquisition to model deployment. Additionally,","authors_text":"David Medina-Ortiz, Fabian Mauz, Fabio Herrera-Rocha, Juergen Pleiss, Mehdi D. Davari","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-07-10T08:41:08Z","title":"Best Practices for Machine Learning-Assisted Protein Engineering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07547","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:a2aaa52702a242bd361575ae7b2baa7c8f4c197880a83ac6b0041fba980e7f59","target":"record","created_at":"2026-07-05T11:35:00Z","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":"214e3b5aa772fb8b247822f77a662ed403eca3d64791b3ff24a9ebc40264378c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-07-10T08:41:08Z","title_canon_sha256":"335ac8c9b28488e5dacf85ffa2ed2d4ff04602ab63cece0dfb7a5044fdb47233"},"schema_version":"1.0","source":{"id":"2507.07547","kind":"arxiv","version":1}},"canonical_sha256":"99108d0e4a42dfa283e6c936cbb2df33b3d0cb5a76f00bcdf65572cb5661ba6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99108d0e4a42dfa283e6c936cbb2df33b3d0cb5a76f00bcdf65572cb5661ba6f","first_computed_at":"2026-07-05T11:35:00.374810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:00.374810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+ytkuGcLSMGzSjJtIZWyYuYxh2JsbKYU1E1H2negdnwJBi1ltl9nwuJ/cJW6JBBa1l6mawy79seFy3nVvKbUCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:00.375307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07547","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2aaa52702a242bd361575ae7b2baa7c8f4c197880a83ac6b0041fba980e7f59","sha256:ee89abc1e13a125c559ffade382c9c8f2ea81961d3f4dd3ba17b79c941e61a90"],"state_sha256":"5ae3156d84631e60c7f7d859b4614a163b0b0e6bc420f35be91472a1e17eaaaa"}