{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XKSXN5PAVISEWMYS4SWEYIMIV7","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":"63fe2da4f6df63822bf8c7e736b7a8c7543d605166fe6d5376ddab526d8eef07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T19:36:54Z","title_canon_sha256":"8284f8b73f9910ffe3fea71820f0ee1f44b24ceee1319913f0e57029c3fe6a01"},"schema_version":"1.0","source":{"id":"2605.16581","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16581","created_at":"2026-05-20T00:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16581v1","created_at":"2026-05-20T00:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16581","created_at":"2026-05-20T00:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"XKSXN5PAVISE","created_at":"2026-05-20T00:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"XKSXN5PAVISEWMYS","created_at":"2026-05-20T00:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"XKSXN5PA","created_at":"2026-05-20T00:02:30Z"}],"graph_snapshots":[{"event_id":"sha256:04ed8eda8b66d624ccd305b787506354ead6b63330d01853a4a51d2abe38908c","target":"graph","created_at":"2026-05-20T00:02:30Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T19:21:56.851195Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.613430Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.16581/integrity.json","findings":[],"snapshot_sha256":"929b0445dbf758b1406ba17c3d9a386e721c240179a6ca2234996a25f39d4b5e","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Masked language modeling (MLM) is the standard objective for training protein language models, typically implemented by randomly masking individual residues at a fixed rate (e.g., 15%). This practice implicitly assumes that all sequence positions contribute equally to representation learning. In downstream fitness prediction tasks, however, protein sequences are governed by three-dimensional structural dependencies and long-range residue contacts that induce strong nonlocal couplings between residues. We introduce Bucket Masking, a structure-aware masking strategy that selects groups of residu","authors_text":"Amirali Aghazadeh, Ayan Goel, Thomas Walton","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T19:36:54Z","title":"Structure-Aware Masking for Protein Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16581","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":"sha256:3c1f9df1da9c66222e0aae570069c53a4312ada0883a32fd2acf90eaee3226a9","target":"record","created_at":"2026-05-20T00:02:30Z","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":"63fe2da4f6df63822bf8c7e736b7a8c7543d605166fe6d5376ddab526d8eef07","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T19:36:54Z","title_canon_sha256":"8284f8b73f9910ffe3fea71820f0ee1f44b24ceee1319913f0e57029c3fe6a01"},"schema_version":"1.0","source":{"id":"2605.16581","kind":"arxiv","version":1}},"canonical_sha256":"baa576f5e0aa244b3312e4ac4c2188afdce12fa24f93bd15fd8e43a6ff598700","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"baa576f5e0aa244b3312e4ac4c2188afdce12fa24f93bd15fd8e43a6ff598700","first_computed_at":"2026-05-20T00:02:30.865136Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:30.865136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IVbhkHHqLgNgGzhcy/NCvaueGHP/XpoBhDE/J+Nq0IIdXL2Y4ZA2yLSVYm0G1Y2dfv6SdBxsj9LFPbZSO4pADw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:30.865917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16581","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3c1f9df1da9c66222e0aae570069c53a4312ada0883a32fd2acf90eaee3226a9","sha256:04ed8eda8b66d624ccd305b787506354ead6b63330d01853a4a51d2abe38908c"],"state_sha256":"d6aa304aa8ceb329773d3da94aa19a13a4a020272410056d2192998a44b5a014"}