{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ARLP5QA33XRL3DNCSTJMSQFTKK","short_pith_number":"pith:ARLP5QA3","schema_version":"1.0","canonical_sha256":"0456fec01bdde2bd8da294d2c940b35293f6671bd480301fe37ff61c06598997","source":{"kind":"arxiv","id":"2411.05316","version":2},"attestation_state":"computed","paper":{"title":"Aligning Large Language Models and Geometric Deep Models for Protein Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Bingbing Duan, Dong Shu, Jiliang Tang, Kai Guo, Kaixiong Zhou, Mengnan Du","submitted_at":"2024-11-08T04:15:08Z","abstract_excerpt":"Latent representation alignment has become a foundational technique for constructing multimodal large language models (MLLM) by mapping embeddings from different modalities into a shared space, often aligned with the embedding space of large language models (LLMs) to enable effective cross-modal understanding. While preliminary protein-focused MLLMs have emerged, they have predominantly relied on heuristic approaches, lacking a fundamental understanding of optimal alignment practices across representations. In this study, we explore the alignment of multimodal representations between LLMs and "},"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":"2411.05316","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-08T04:15:08Z","cross_cats_sorted":["cs.AI","cs.CE","q-bio.BM"],"title_canon_sha256":"8aec1b9224f9228a3e84a15f3d75efdaf62d8d992dda77f4c127dcb161766e51","abstract_canon_sha256":"0663f972dd3c3c6b9b1a13c71ce9f03438c2004de7275d1cac19ebb5470402fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:27.238773Z","signature_b64":"GNFXBXMPzHrLlJNWoS3cnSL4KsBNawy62lccn3VioCnhzGfXplGtp6EmrWMleMxQX0g0ViRmz3tJdAGhOuKjDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0456fec01bdde2bd8da294d2c940b35293f6671bd480301fe37ff61c06598997","last_reissued_at":"2026-07-05T10:24:27.237916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:27.237916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning Large Language Models and Geometric Deep Models for Protein Representation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Bingbing Duan, Dong Shu, Jiliang Tang, Kai Guo, Kaixiong Zhou, Mengnan Du","submitted_at":"2024-11-08T04:15:08Z","abstract_excerpt":"Latent representation alignment has become a foundational technique for constructing multimodal large language models (MLLM) by mapping embeddings from different modalities into a shared space, often aligned with the embedding space of large language models (LLMs) to enable effective cross-modal understanding. While preliminary protein-focused MLLMs have emerged, they have predominantly relied on heuristic approaches, lacking a fundamental understanding of optimal alignment practices across representations. In this study, we explore the alignment of multimodal representations between LLMs and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05316","kind":"arxiv","version":2},"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/2411.05316/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":"2411.05316","created_at":"2026-07-05T10:24:27.238081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.05316v2","created_at":"2026-07-05T10:24:27.238081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05316","created_at":"2026-07-05T10:24:27.238081+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARLP5QA33XRL","created_at":"2026-07-05T10:24:27.238081+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARLP5QA33XRL3DNC","created_at":"2026-07-05T10:24:27.238081+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARLP5QA3","created_at":"2026-07-05T10:24:27.238081+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/ARLP5QA33XRL3DNCSTJMSQFTKK","json":"https://pith.science/pith/ARLP5QA33XRL3DNCSTJMSQFTKK.json","graph_json":"https://pith.science/api/pith-number/ARLP5QA33XRL3DNCSTJMSQFTKK/graph.json","events_json":"https://pith.science/api/pith-number/ARLP5QA33XRL3DNCSTJMSQFTKK/events.json","paper":"https://pith.science/paper/ARLP5QA3"},"agent_actions":{"view_html":"https://pith.science/pith/ARLP5QA33XRL3DNCSTJMSQFTKK","download_json":"https://pith.science/pith/ARLP5QA33XRL3DNCSTJMSQFTKK.json","view_paper":"https://pith.science/paper/ARLP5QA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.05316&json=true","fetch_graph":"https://pith.science/api/pith-number/ARLP5QA33XRL3DNCSTJMSQFTKK/graph.json","fetch_events":"https://pith.science/api/pith-number/ARLP5QA33XRL3DNCSTJMSQFTKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARLP5QA33XRL3DNCSTJMSQFTKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARLP5QA33XRL3DNCSTJMSQFTKK/action/storage_attestation","attest_author":"https://pith.science/pith/ARLP5QA33XRL3DNCSTJMSQFTKK/action/author_attestation","sign_citation":"https://pith.science/pith/ARLP5QA33XRL3DNCSTJMSQFTKK/action/citation_signature","submit_replication":"https://pith.science/pith/ARLP5QA33XRL3DNCSTJMSQFTKK/action/replication_record"}},"created_at":"2026-07-05T10:24:27.238081+00:00","updated_at":"2026-07-05T10:24:27.238081+00:00"}