{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RBVAPGP2MIS4ZFWZY7NMFM7LNO","short_pith_number":"pith:RBVAPGP2","schema_version":"1.0","canonical_sha256":"886a0799fa6225cc96d9c7dac2b3eb6bb17b8f55ae26921519c095b1a69098b7","source":{"kind":"arxiv","id":"2410.11235","version":2},"attestation_state":"computed","paper":{"title":"GT2Vec: Large Language Models as Multi-Modal Encoders for Text and Graph-Structured Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Danai Koutra, Edward W Huang, Haoyu Han, Jiacheng Lin, Jimeng Sun, Karthik Subbian, Kun Qian, Nurendra Choudhary, Sahika Genc, Sheng Wang, Tianxin Wei, Zhongruo Wang","submitted_at":"2024-10-15T03:40:20Z","abstract_excerpt":"Graph-structured information offers rich contextual information that can enhance language models by providing structured relationships and hierarchies, leading to more expressive embeddings for various applications such as retrieval, question answering, and classification. However, existing methods for integrating graph and text embeddings, often based on Multi-layer Perceptrons (MLPs) or shallow transformers, are limited in their ability to fully exploit the heterogeneous nature of these modalities. To overcome this, we propose GT2Vec, a simple yet effective framework that leverages Large Lan"},"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":"2410.11235","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-15T03:40:20Z","cross_cats_sorted":[],"title_canon_sha256":"6587a05f010eccd91cd6b40a7d6a1b789ae0d5f2b2ae1ea8a439356a3aca2afc","abstract_canon_sha256":"803c04a9b1d32aadf1bd5be8641c02b08491ef18fdff2ce4cb4d5ef0a268b871"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:21.319289Z","signature_b64":"di5tr+Nmbc2LT6u7gqE6lF9utJ0QMvGTIqSAf1405QMYpj4FFbxIL0axIpUNqID9dqAJCHdhQebFt2xbQCvNAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"886a0799fa6225cc96d9c7dac2b3eb6bb17b8f55ae26921519c095b1a69098b7","last_reissued_at":"2026-07-05T10:12:21.318838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:21.318838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GT2Vec: Large Language Models as Multi-Modal Encoders for Text and Graph-Structured Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Danai Koutra, Edward W Huang, Haoyu Han, Jiacheng Lin, Jimeng Sun, Karthik Subbian, Kun Qian, Nurendra Choudhary, Sahika Genc, Sheng Wang, Tianxin Wei, Zhongruo Wang","submitted_at":"2024-10-15T03:40:20Z","abstract_excerpt":"Graph-structured information offers rich contextual information that can enhance language models by providing structured relationships and hierarchies, leading to more expressive embeddings for various applications such as retrieval, question answering, and classification. However, existing methods for integrating graph and text embeddings, often based on Multi-layer Perceptrons (MLPs) or shallow transformers, are limited in their ability to fully exploit the heterogeneous nature of these modalities. To overcome this, we propose GT2Vec, a simple yet effective framework that leverages Large Lan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11235","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/2410.11235/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":"2410.11235","created_at":"2026-07-05T10:12:21.318896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11235v2","created_at":"2026-07-05T10:12:21.318896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11235","created_at":"2026-07-05T10:12:21.318896+00:00"},{"alias_kind":"pith_short_12","alias_value":"RBVAPGP2MIS4","created_at":"2026-07-05T10:12:21.318896+00:00"},{"alias_kind":"pith_short_16","alias_value":"RBVAPGP2MIS4ZFWZ","created_at":"2026-07-05T10:12:21.318896+00:00"},{"alias_kind":"pith_short_8","alias_value":"RBVAPGP2","created_at":"2026-07-05T10:12:21.318896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00142","citing_title":"Enhancing Few-Shot Vision-Language Classification with Large Multimodal Model Features","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RBVAPGP2MIS4ZFWZY7NMFM7LNO","json":"https://pith.science/pith/RBVAPGP2MIS4ZFWZY7NMFM7LNO.json","graph_json":"https://pith.science/api/pith-number/RBVAPGP2MIS4ZFWZY7NMFM7LNO/graph.json","events_json":"https://pith.science/api/pith-number/RBVAPGP2MIS4ZFWZY7NMFM7LNO/events.json","paper":"https://pith.science/paper/RBVAPGP2"},"agent_actions":{"view_html":"https://pith.science/pith/RBVAPGP2MIS4ZFWZY7NMFM7LNO","download_json":"https://pith.science/pith/RBVAPGP2MIS4ZFWZY7NMFM7LNO.json","view_paper":"https://pith.science/paper/RBVAPGP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11235&json=true","fetch_graph":"https://pith.science/api/pith-number/RBVAPGP2MIS4ZFWZY7NMFM7LNO/graph.json","fetch_events":"https://pith.science/api/pith-number/RBVAPGP2MIS4ZFWZY7NMFM7LNO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RBVAPGP2MIS4ZFWZY7NMFM7LNO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RBVAPGP2MIS4ZFWZY7NMFM7LNO/action/storage_attestation","attest_author":"https://pith.science/pith/RBVAPGP2MIS4ZFWZY7NMFM7LNO/action/author_attestation","sign_citation":"https://pith.science/pith/RBVAPGP2MIS4ZFWZY7NMFM7LNO/action/citation_signature","submit_replication":"https://pith.science/pith/RBVAPGP2MIS4ZFWZY7NMFM7LNO/action/replication_record"}},"created_at":"2026-07-05T10:12:21.318896+00:00","updated_at":"2026-07-05T10:12:21.318896+00:00"}