{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JOIDKBFVJTSYWHYBEFO7ZGDADY","short_pith_number":"pith:JOIDKBFV","schema_version":"1.0","canonical_sha256":"4b903504b54ce58b1f01215dfc98601e06c2df8fed9b8010d45b69474d7c3d9c","source":{"kind":"arxiv","id":"2406.04640","version":1},"attestation_state":"computed","paper":{"title":"LinkGPT: Teaching Large Language Models To Predict Missing Links","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Danai Koutra, Jing Zhu, Joyce Chai, Shengyi Qian, Zhongmou He","submitted_at":"2024-06-07T04:54:36Z","abstract_excerpt":"Large Language Models (LLMs) have shown promising results on various language and vision tasks. Recently, there has been growing interest in applying LLMs to graph-based tasks, particularly on Text-Attributed Graphs (TAGs). However, most studies have focused on node classification, while the use of LLMs for link prediction (LP) remains understudied. In this work, we propose a new task on LLMs, where the objective is to leverage LLMs to predict missing links between nodes in a graph. This task evaluates an LLM's ability to reason over structured data and infer new facts based on learned pattern"},"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":"2406.04640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-07T04:54:36Z","cross_cats_sorted":[],"title_canon_sha256":"a97212f9b975fddde1ee952ad9807336547ea3cb70752792004907fd610c6c7f","abstract_canon_sha256":"b96e28e54ad8b21cbbfb6d941d954e4759f365ec89cf769ac0dd0fca37ad9538"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:46.912420Z","signature_b64":"uE3lvwSEnrsd6KZU/rNE4o6X0y7M7cR0Qqe9KRHQLrW/dDD/n350sqJpq3z9P/Lu4/ClGWbioIPkpOwQM2SsDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b903504b54ce58b1f01215dfc98601e06c2df8fed9b8010d45b69474d7c3d9c","last_reissued_at":"2026-07-05T08:28:46.912024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:46.912024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LinkGPT: Teaching Large Language Models To Predict Missing Links","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Danai Koutra, Jing Zhu, Joyce Chai, Shengyi Qian, Zhongmou He","submitted_at":"2024-06-07T04:54:36Z","abstract_excerpt":"Large Language Models (LLMs) have shown promising results on various language and vision tasks. Recently, there has been growing interest in applying LLMs to graph-based tasks, particularly on Text-Attributed Graphs (TAGs). However, most studies have focused on node classification, while the use of LLMs for link prediction (LP) remains understudied. In this work, we propose a new task on LLMs, where the objective is to leverage LLMs to predict missing links between nodes in a graph. This task evaluates an LLM's ability to reason over structured data and infer new facts based on learned pattern"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04640","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/2406.04640/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":"2406.04640","created_at":"2026-07-05T08:28:46.912079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04640v1","created_at":"2026-07-05T08:28:46.912079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04640","created_at":"2026-07-05T08:28:46.912079+00:00"},{"alias_kind":"pith_short_12","alias_value":"JOIDKBFVJTSY","created_at":"2026-07-05T08:28:46.912079+00:00"},{"alias_kind":"pith_short_16","alias_value":"JOIDKBFVJTSYWHYB","created_at":"2026-07-05T08:28:46.912079+00:00"},{"alias_kind":"pith_short_8","alias_value":"JOIDKBFV","created_at":"2026-07-05T08:28:46.912079+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30291","citing_title":"PromptGNN-sim: Deep Fusion and Alignment of GNN and LLMs for Text-Attributed Graph Learning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21522","citing_title":"Protein Thoughts: Interpretable Reasoning with Tree of Thoughts and Embedding-Space Flow Matching for Protein-Protein Interaction Discovery","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":148,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12651","citing_title":"Learning Chain Of Thoughts Prompts for Predicting Entities, Relations, and even Literals on Knowledge Graphs","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JOIDKBFVJTSYWHYBEFO7ZGDADY","json":"https://pith.science/pith/JOIDKBFVJTSYWHYBEFO7ZGDADY.json","graph_json":"https://pith.science/api/pith-number/JOIDKBFVJTSYWHYBEFO7ZGDADY/graph.json","events_json":"https://pith.science/api/pith-number/JOIDKBFVJTSYWHYBEFO7ZGDADY/events.json","paper":"https://pith.science/paper/JOIDKBFV"},"agent_actions":{"view_html":"https://pith.science/pith/JOIDKBFVJTSYWHYBEFO7ZGDADY","download_json":"https://pith.science/pith/JOIDKBFVJTSYWHYBEFO7ZGDADY.json","view_paper":"https://pith.science/paper/JOIDKBFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04640&json=true","fetch_graph":"https://pith.science/api/pith-number/JOIDKBFVJTSYWHYBEFO7ZGDADY/graph.json","fetch_events":"https://pith.science/api/pith-number/JOIDKBFVJTSYWHYBEFO7ZGDADY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JOIDKBFVJTSYWHYBEFO7ZGDADY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JOIDKBFVJTSYWHYBEFO7ZGDADY/action/storage_attestation","attest_author":"https://pith.science/pith/JOIDKBFVJTSYWHYBEFO7ZGDADY/action/author_attestation","sign_citation":"https://pith.science/pith/JOIDKBFVJTSYWHYBEFO7ZGDADY/action/citation_signature","submit_replication":"https://pith.science/pith/JOIDKBFVJTSYWHYBEFO7ZGDADY/action/replication_record"}},"created_at":"2026-07-05T08:28:46.912079+00:00","updated_at":"2026-07-05T08:28:46.912079+00:00"}