{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O5Z2JGDZFE7ZEWU2SACEAXUIDR","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":"a365f3af5f89a5a8846dbe950b0e32d45d7f7550b1b3ff01826020d68998c7f4","cross_cats_sorted":["cs.AI","cs.CE","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-05-27T08:13:08Z","title_canon_sha256":"0da33e7205b2525232930124a175279b9e250c42f98355946f638303d3f493a3"},"schema_version":"1.0","source":{"id":"2506.08023","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.08023","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"arxiv_version","alias_value":"2506.08023v1","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08023","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_12","alias_value":"O5Z2JGDZFE7Z","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_16","alias_value":"O5Z2JGDZFE7ZEWU2","created_at":"2026-07-05T11:18:43Z"},{"alias_kind":"pith_short_8","alias_value":"O5Z2JGDZ","created_at":"2026-07-05T11:18:43Z"}],"graph_snapshots":[{"event_id":"sha256:7e235606924d67996d5c16cad9fc9b6d0dc09e015f63b2757348896c0dcbd9af","target":"graph","created_at":"2026-07-05T11:18:43Z","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/2506.08023/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper aims to retrieve proteins with similar structures and semantics from large-scale protein dataset, facilitating the functional interpretation of protein structures derived by structural determination methods like cryo-Electron Microscopy (cryo-EM). Motivated by the recent progress of vision-language models (VLMs), we propose a CLIP-style framework for aligning 3D protein structures with functional annotations using contrastive learning. For model training, we propose a large-scale dataset of approximately 200,000 protein-caption pairs with rich functional descriptors. We evaluate our","authors_text":"Daisuke Kihara, Han Zhu, Min Xu, Qifeng Wu, Yizhou Zhao, Zhengzhe Liu","cross_cats":["cs.AI","cs.CE","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-05-27T08:13:08Z","title":"Aligning Proteins and Language: A Foundation Model for Protein Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08023","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:d7b755bb63f47edc0adb26067b4d9065a31b5ad52beb5d5c40511ddded60506a","target":"record","created_at":"2026-07-05T11:18:43Z","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":"a365f3af5f89a5a8846dbe950b0e32d45d7f7550b1b3ff01826020d68998c7f4","cross_cats_sorted":["cs.AI","cs.CE","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-05-27T08:13:08Z","title_canon_sha256":"0da33e7205b2525232930124a175279b9e250c42f98355946f638303d3f493a3"},"schema_version":"1.0","source":{"id":"2506.08023","kind":"arxiv","version":1}},"canonical_sha256":"7773a49879293f925a9a9004405e881c48b0c8c0fa802cb3b88a53d34591396a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7773a49879293f925a9a9004405e881c48b0c8c0fa802cb3b88a53d34591396a","first_computed_at":"2026-07-05T11:18:43.826650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:43.826650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U5TuqFWe6fI8rwq7HQOz5ZBnLYWGVvnKqnzVgii1CK2mt5cch/OatqOZPX7YNF2zQrTg0u/hcvGtIXHa7y0jBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:43.827029Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.08023","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7b755bb63f47edc0adb26067b4d9065a31b5ad52beb5d5c40511ddded60506a","sha256:7e235606924d67996d5c16cad9fc9b6d0dc09e015f63b2757348896c0dcbd9af"],"state_sha256":"223c77e030fdd2e8f33b6cb88a22689f87c5b195fccdaf05949cbc4832aa4b48"}