{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XKSXN5PAVISEWMYS4SWEYIMIV7","short_pith_number":"pith:XKSXN5PA","schema_version":"1.0","canonical_sha256":"baa576f5e0aa244b3312e4ac4c2188afdce12fa24f93bd15fd8e43a6ff598700","source":{"kind":"arxiv","id":"2605.16581","version":1},"attestation_state":"computed","paper":{"title":"Structure-Aware Masking for Protein Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amirali Aghazadeh, Ayan Goel, Thomas Walton","submitted_at":"2026-05-15T19:36:54Z","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"},"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":"2605.16581","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T19:36:54Z","cross_cats_sorted":[],"title_canon_sha256":"8284f8b73f9910ffe3fea71820f0ee1f44b24ceee1319913f0e57029c3fe6a01","abstract_canon_sha256":"63fe2da4f6df63822bf8c7e736b7a8c7543d605166fe6d5376ddab526d8eef07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:30.865917Z","signature_b64":"IVbhkHHqLgNgGzhcy/NCvaueGHP/XpoBhDE/J+Nq0IIdXL2Y4ZA2yLSVYm0G1Y2dfv6SdBxsj9LFPbZSO4pADw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"baa576f5e0aa244b3312e4ac4c2188afdce12fa24f93bd15fd8e43a6ff598700","last_reissued_at":"2026-05-20T00:02:30.865136Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:30.865136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structure-Aware Masking for Protein Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amirali Aghazadeh, Ayan Goel, Thomas Walton","submitted_at":"2026-05-15T19:36:54Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16581","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/2605.16581/integrity.json","findings":[],"available":true,"detectors_run":[{"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","findings_count":0}],"snapshot_sha256":"929b0445dbf758b1406ba17c3d9a386e721c240179a6ca2234996a25f39d4b5e"},"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":"2605.16581","created_at":"2026-05-20T00:02:30.865261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16581v1","created_at":"2026-05-20T00:02:30.865261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16581","created_at":"2026-05-20T00:02:30.865261+00:00"},{"alias_kind":"pith_short_12","alias_value":"XKSXN5PAVISE","created_at":"2026-05-20T00:02:30.865261+00:00"},{"alias_kind":"pith_short_16","alias_value":"XKSXN5PAVISEWMYS","created_at":"2026-05-20T00:02:30.865261+00:00"},{"alias_kind":"pith_short_8","alias_value":"XKSXN5PA","created_at":"2026-05-20T00:02:30.865261+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/XKSXN5PAVISEWMYS4SWEYIMIV7","json":"https://pith.science/pith/XKSXN5PAVISEWMYS4SWEYIMIV7.json","graph_json":"https://pith.science/api/pith-number/XKSXN5PAVISEWMYS4SWEYIMIV7/graph.json","events_json":"https://pith.science/api/pith-number/XKSXN5PAVISEWMYS4SWEYIMIV7/events.json","paper":"https://pith.science/paper/XKSXN5PA"},"agent_actions":{"view_html":"https://pith.science/pith/XKSXN5PAVISEWMYS4SWEYIMIV7","download_json":"https://pith.science/pith/XKSXN5PAVISEWMYS4SWEYIMIV7.json","view_paper":"https://pith.science/paper/XKSXN5PA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16581&json=true","fetch_graph":"https://pith.science/api/pith-number/XKSXN5PAVISEWMYS4SWEYIMIV7/graph.json","fetch_events":"https://pith.science/api/pith-number/XKSXN5PAVISEWMYS4SWEYIMIV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XKSXN5PAVISEWMYS4SWEYIMIV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XKSXN5PAVISEWMYS4SWEYIMIV7/action/storage_attestation","attest_author":"https://pith.science/pith/XKSXN5PAVISEWMYS4SWEYIMIV7/action/author_attestation","sign_citation":"https://pith.science/pith/XKSXN5PAVISEWMYS4SWEYIMIV7/action/citation_signature","submit_replication":"https://pith.science/pith/XKSXN5PAVISEWMYS4SWEYIMIV7/action/replication_record"}},"created_at":"2026-05-20T00:02:30.865261+00:00","updated_at":"2026-05-20T00:02:30.865261+00:00"}