{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7UT6JQIQWUXX4PJYZLCTB65X7J","short_pith_number":"pith:7UT6JQIQ","schema_version":"1.0","canonical_sha256":"fd27e4c110b52f7e3d38cac530fbb7fa77ecadff12ee4def315696135fce559e","source":{"kind":"arxiv","id":"2410.15268","version":2},"attestation_state":"computed","paper":{"title":"GraphNarrator: Generating Textual Explanations for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Pan, Guanchen Wu, Liang Zhao, Yifei Zhang, Zheng Zhang, Zhen Xiong","submitted_at":"2024-10-20T03:55:46Z","abstract_excerpt":"Graph representation learning has garnered significant attention due to its broad applications in various domains, such as recommendation systems and social network analysis. Despite advancements in graph learning methods, challenges still remain in explainability when graphs are associated with semantic features. In this paper, we present GraphNarrator, the first method designed to generate natural language explanations for Graph Neural Networks. GraphNarrator employs a generative language model that maps input-output pairs to explanations reflecting the model's decision-making process. To ad"},"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":"2410.15268","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-20T03:55:46Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"6ab5d465bcee55cb6b1b832cb016f6325ae746b76a9016be6ca89d8a3c3cb319","abstract_canon_sha256":"d024d411f83900f65da630b38101ccb46865920454f608a1dfa4b9bb7587d87f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:36.277831Z","signature_b64":"4rmC7+y/KBLdEXU6GWwbOVKwyLtUPIrB5ytCWjpGv/59jSRfpD06sLRkrSs2Et4PxkQppwmGxH5DmgyK5Dq2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd27e4c110b52f7e3d38cac530fbb7fa77ecadff12ee4def315696135fce559e","last_reissued_at":"2026-07-05T11:11:36.277294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:36.277294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphNarrator: Generating Textual Explanations for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Pan, Guanchen Wu, Liang Zhao, Yifei Zhang, Zheng Zhang, Zhen Xiong","submitted_at":"2024-10-20T03:55:46Z","abstract_excerpt":"Graph representation learning has garnered significant attention due to its broad applications in various domains, such as recommendation systems and social network analysis. Despite advancements in graph learning methods, challenges still remain in explainability when graphs are associated with semantic features. In this paper, we present GraphNarrator, the first method designed to generate natural language explanations for Graph Neural Networks. GraphNarrator employs a generative language model that maps input-output pairs to explanations reflecting the model's decision-making process. To ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15268","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/2410.15268/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":"2410.15268","created_at":"2026-07-05T11:11:36.277368+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15268v2","created_at":"2026-07-05T11:11:36.277368+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15268","created_at":"2026-07-05T11:11:36.277368+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UT6JQIQWUXX","created_at":"2026-07-05T11:11:36.277368+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UT6JQIQWUXX4PJY","created_at":"2026-07-05T11:11:36.277368+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UT6JQIQ","created_at":"2026-07-05T11:11:36.277368+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28708","citing_title":"AnTenA: Actionable and Explainable Tensor Analysis System with Large Language Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2511.13658","citing_title":"Why is \"Chicago\" Predictive of Deceptive Reviews? Using LLMs to Discover Language Phenomena from Lexical Cues","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7UT6JQIQWUXX4PJYZLCTB65X7J","json":"https://pith.science/pith/7UT6JQIQWUXX4PJYZLCTB65X7J.json","graph_json":"https://pith.science/api/pith-number/7UT6JQIQWUXX4PJYZLCTB65X7J/graph.json","events_json":"https://pith.science/api/pith-number/7UT6JQIQWUXX4PJYZLCTB65X7J/events.json","paper":"https://pith.science/paper/7UT6JQIQ"},"agent_actions":{"view_html":"https://pith.science/pith/7UT6JQIQWUXX4PJYZLCTB65X7J","download_json":"https://pith.science/pith/7UT6JQIQWUXX4PJYZLCTB65X7J.json","view_paper":"https://pith.science/paper/7UT6JQIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15268&json=true","fetch_graph":"https://pith.science/api/pith-number/7UT6JQIQWUXX4PJYZLCTB65X7J/graph.json","fetch_events":"https://pith.science/api/pith-number/7UT6JQIQWUXX4PJYZLCTB65X7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UT6JQIQWUXX4PJYZLCTB65X7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UT6JQIQWUXX4PJYZLCTB65X7J/action/storage_attestation","attest_author":"https://pith.science/pith/7UT6JQIQWUXX4PJYZLCTB65X7J/action/author_attestation","sign_citation":"https://pith.science/pith/7UT6JQIQWUXX4PJYZLCTB65X7J/action/citation_signature","submit_replication":"https://pith.science/pith/7UT6JQIQWUXX4PJYZLCTB65X7J/action/replication_record"}},"created_at":"2026-07-05T11:11:36.277368+00:00","updated_at":"2026-07-05T11:11:36.277368+00:00"}