{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VEKQZK3DEJ5WXLQ2UT4BGSDUSC","short_pith_number":"pith:VEKQZK3D","schema_version":"1.0","canonical_sha256":"a9150cab63227b6bae1aa4f813487490963575b61c0561fe6557f9e20731ed90","source":{"kind":"arxiv","id":"2305.19523","version":5},"attestation_state":"computed","paper":{"title":"Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Perold, Bryan Hooi, Thomas Laurent, Xavier Bresson, Xiaoxin He, Yann LeCun","submitted_at":"2023-05-31T03:18:03Z","abstract_excerpt":"Representation learning on text-attributed graphs (TAGs) has become a critical research problem in recent years. A typical example of a TAG is a paper citation graph, where the text of each paper serves as node attributes. Initial graph neural network (GNN) pipelines handled these text attributes by transforming them into shallow or hand-crafted features, such as skip-gram or bag-of-words features. Recent efforts have focused on enhancing these pipelines with language models (LMs), which typically demand intricate designs and substantial computational resources. With the advent of powerful lar"},"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":"2305.19523","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T03:18:03Z","cross_cats_sorted":[],"title_canon_sha256":"6f4a74c2b597480393f0dbf9b2a930553942570d998ff25830e0352acc3a6d64","abstract_canon_sha256":"3d6c05bd03ffe82c91724ae237769e1f171b369806b1587572eec166a69134ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:08.492859Z","signature_b64":"QwLvB8/ZuT5DB15XbGItXJ/6V/yLm6tiwV17n5oQb+oDPSzcde8P3XbtPmhg0RCHU3qt3ABp+alc3CD6wg4dAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a9150cab63227b6bae1aa4f813487490963575b61c0561fe6557f9e20731ed90","last_reissued_at":"2026-07-05T07:53:08.492386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:08.492386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Perold, Bryan Hooi, Thomas Laurent, Xavier Bresson, Xiaoxin He, Yann LeCun","submitted_at":"2023-05-31T03:18:03Z","abstract_excerpt":"Representation learning on text-attributed graphs (TAGs) has become a critical research problem in recent years. A typical example of a TAG is a paper citation graph, where the text of each paper serves as node attributes. Initial graph neural network (GNN) pipelines handled these text attributes by transforming them into shallow or hand-crafted features, such as skip-gram or bag-of-words features. Recent efforts have focused on enhancing these pipelines with language models (LMs), which typically demand intricate designs and substantial computational resources. With the advent of powerful lar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19523","kind":"arxiv","version":5},"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/2305.19523/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":"2305.19523","created_at":"2026-07-05T07:53:08.492448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.19523v5","created_at":"2026-07-05T07:53:08.492448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19523","created_at":"2026-07-05T07:53:08.492448+00:00"},{"alias_kind":"pith_short_12","alias_value":"VEKQZK3DEJ5W","created_at":"2026-07-05T07:53:08.492448+00:00"},{"alias_kind":"pith_short_16","alias_value":"VEKQZK3DEJ5WXLQ2","created_at":"2026-07-05T07:53:08.492448+00:00"},{"alias_kind":"pith_short_8","alias_value":"VEKQZK3D","created_at":"2026-07-05T07:53:08.492448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17579","citing_title":"LLM Features Can Hurt GNNs: Concatenation Interference on Homophilous Graph Benchmarks","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11583","citing_title":"Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01873","citing_title":"G2LoRA: Gradient Orthogonal Low-Rank Adaptation Framework for Graph Continual Learning on Text-Attributed Graphs","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27913","citing_title":"Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMs","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2603.02938","citing_title":"Beyond One-Size-Fits-All: Adaptive Subgraph Denoising for Zero-Shot Graph Learning with Large Language Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18579","citing_title":"S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18579","citing_title":"S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08952","citing_title":"When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2511.02135","citing_title":"Graph-Based Alternatives to LLMs for Human Simulation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12814","citing_title":"Linking Extreme Discourse to Structural Polarization in Signed Interaction Networks","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07361","citing_title":"BLEG: LLM Functions as Powerful fMRI Graph-Enhancer for Brain Network Analysis","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2410.05779","citing_title":"LightRAG: Simple and Fast Retrieval-Augmented Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06073","citing_title":"PRISM: Iterative Cross-Modal Posterior Refinement for Dynamic Text-Attributed Graphs","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17411","citing_title":"DuConTE: Dual-Granularity Text Encoder with Topology-Constrained Attention for Text-attributed Graphs","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17897","citing_title":"LoReC: Rethinking Large Language Models for Graph Data Analysis","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VEKQZK3DEJ5WXLQ2UT4BGSDUSC","json":"https://pith.science/pith/VEKQZK3DEJ5WXLQ2UT4BGSDUSC.json","graph_json":"https://pith.science/api/pith-number/VEKQZK3DEJ5WXLQ2UT4BGSDUSC/graph.json","events_json":"https://pith.science/api/pith-number/VEKQZK3DEJ5WXLQ2UT4BGSDUSC/events.json","paper":"https://pith.science/paper/VEKQZK3D"},"agent_actions":{"view_html":"https://pith.science/pith/VEKQZK3DEJ5WXLQ2UT4BGSDUSC","download_json":"https://pith.science/pith/VEKQZK3DEJ5WXLQ2UT4BGSDUSC.json","view_paper":"https://pith.science/paper/VEKQZK3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.19523&json=true","fetch_graph":"https://pith.science/api/pith-number/VEKQZK3DEJ5WXLQ2UT4BGSDUSC/graph.json","fetch_events":"https://pith.science/api/pith-number/VEKQZK3DEJ5WXLQ2UT4BGSDUSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VEKQZK3DEJ5WXLQ2UT4BGSDUSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VEKQZK3DEJ5WXLQ2UT4BGSDUSC/action/storage_attestation","attest_author":"https://pith.science/pith/VEKQZK3DEJ5WXLQ2UT4BGSDUSC/action/author_attestation","sign_citation":"https://pith.science/pith/VEKQZK3DEJ5WXLQ2UT4BGSDUSC/action/citation_signature","submit_replication":"https://pith.science/pith/VEKQZK3DEJ5WXLQ2UT4BGSDUSC/action/replication_record"}},"created_at":"2026-07-05T07:53:08.492448+00:00","updated_at":"2026-07-05T07:53:08.492448+00:00"}