{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4LPQPEGJRA3M7JK7ZTCWZP7VE2","short_pith_number":"pith:4LPQPEGJ","schema_version":"1.0","canonical_sha256":"e2df0790c98836cfa55fccc56cbff526b0bdb41f3a4b5643d3a1e4941121121d","source":{"kind":"arxiv","id":"2405.13902","version":2},"attestation_state":"computed","paper":{"title":"LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiarong Xu, Qing He, Xiang Ao, Xiaoqian Sun, Yang Liu, Yiran Qiao","submitted_at":"2024-05-22T18:17:20Z","abstract_excerpt":"Recent prevailing works on graph machine learning typically follow a similar methodology that involves designing advanced variants of graph neural networks (GNNs) to maintain the superior performance of GNNs on different graphs. In this paper, we aim to streamline the GNN design process and leverage the advantages of Large Language Models (LLMs) to improve the performance of GNNs on downstream tasks. We formulate a new paradigm, coined \"LLMs-as-Consultants,\" which integrates LLMs with GNNs in an interactive manner. A framework named LOGIN (LLM Consulted GNN training) is instantiated, empowerin"},"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":"2405.13902","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-22T18:17:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e19f55c0f144617157c40d06a84178459ea97f8065526e3ae02c00be724df154","abstract_canon_sha256":"bb8b4fc041062ceef4927e9a7f8d0e6081c8e0ed5b7ba38fafd85631d17b6424"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:10.301536Z","signature_b64":"F6qkk2dV1xjwyaVtH2jamLF2AEvo+2Gx5hRJEmF9FG7vVgd0gnM49/ufJBejJ2/WBRG0VB474MLlCbsBJcJnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2df0790c98836cfa55fccc56cbff526b0bdb41f3a4b5643d3a1e4941121121d","last_reissued_at":"2026-07-05T08:28:10.300974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:10.300974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiarong Xu, Qing He, Xiang Ao, Xiaoqian Sun, Yang Liu, Yiran Qiao","submitted_at":"2024-05-22T18:17:20Z","abstract_excerpt":"Recent prevailing works on graph machine learning typically follow a similar methodology that involves designing advanced variants of graph neural networks (GNNs) to maintain the superior performance of GNNs on different graphs. In this paper, we aim to streamline the GNN design process and leverage the advantages of Large Language Models (LLMs) to improve the performance of GNNs on downstream tasks. We formulate a new paradigm, coined \"LLMs-as-Consultants,\" which integrates LLMs with GNNs in an interactive manner. A framework named LOGIN (LLM Consulted GNN training) is instantiated, empowerin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13902","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/2405.13902/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":"2405.13902","created_at":"2026-07-05T08:28:10.301033+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13902v2","created_at":"2026-07-05T08:28:10.301033+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13902","created_at":"2026-07-05T08:28:10.301033+00:00"},{"alias_kind":"pith_short_12","alias_value":"4LPQPEGJRA3M","created_at":"2026-07-05T08:28:10.301033+00:00"},{"alias_kind":"pith_short_16","alias_value":"4LPQPEGJRA3M7JK7","created_at":"2026-07-05T08:28:10.301033+00:00"},{"alias_kind":"pith_short_8","alias_value":"4LPQPEGJ","created_at":"2026-07-05T08:28:10.301033+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.02130","citing_title":"Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4LPQPEGJRA3M7JK7ZTCWZP7VE2","json":"https://pith.science/pith/4LPQPEGJRA3M7JK7ZTCWZP7VE2.json","graph_json":"https://pith.science/api/pith-number/4LPQPEGJRA3M7JK7ZTCWZP7VE2/graph.json","events_json":"https://pith.science/api/pith-number/4LPQPEGJRA3M7JK7ZTCWZP7VE2/events.json","paper":"https://pith.science/paper/4LPQPEGJ"},"agent_actions":{"view_html":"https://pith.science/pith/4LPQPEGJRA3M7JK7ZTCWZP7VE2","download_json":"https://pith.science/pith/4LPQPEGJRA3M7JK7ZTCWZP7VE2.json","view_paper":"https://pith.science/paper/4LPQPEGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13902&json=true","fetch_graph":"https://pith.science/api/pith-number/4LPQPEGJRA3M7JK7ZTCWZP7VE2/graph.json","fetch_events":"https://pith.science/api/pith-number/4LPQPEGJRA3M7JK7ZTCWZP7VE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4LPQPEGJRA3M7JK7ZTCWZP7VE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4LPQPEGJRA3M7JK7ZTCWZP7VE2/action/storage_attestation","attest_author":"https://pith.science/pith/4LPQPEGJRA3M7JK7ZTCWZP7VE2/action/author_attestation","sign_citation":"https://pith.science/pith/4LPQPEGJRA3M7JK7ZTCWZP7VE2/action/citation_signature","submit_replication":"https://pith.science/pith/4LPQPEGJRA3M7JK7ZTCWZP7VE2/action/replication_record"}},"created_at":"2026-07-05T08:28:10.301033+00:00","updated_at":"2026-07-05T08:28:10.301033+00:00"}