{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NAICUIUGZ22TUCJXUPYCHARPFS","short_pith_number":"pith:NAICUIUG","schema_version":"1.0","canonical_sha256":"68102a2286ceb53a0937a3f023822f2c8f6ca9338c4ea5f30ce908b68174b931","source":{"kind":"arxiv","id":"2605.21502","version":1},"attestation_state":"computed","paper":{"title":"Graph neural network explanations reveal a topological signature of disease-associated hubs in biological networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.MN","authors_text":"Dennis Veselkov, Ivan Laponogov, Kirill Veselkov, Kyle Higgins","submitted_at":"2026-05-08T15:29:36Z","abstract_excerpt":"Graph neural networks (GNNs) are increasingly used to model biological systems, yet the reliability of post-hoc explanation methods for recovering meaningful molecular mechanisms remains unclear. Here, we systematically evaluate four widely used approaches: Saliency Attribution (SA), Integrated Gradients (IG), GNNExplainer, and Layer-wise Relevance Propagation (LRP) for identifying disease-relevant structure in breast cancer RNA-seq data projected onto a protein-protein interaction network. Using synthetic benchmarks with known ground-truth motifs, we show that explanation methods recover dist"},"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":"2605.21502","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.MN","submitted_at":"2026-05-08T15:29:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4dd9de0e9c9e0a6b907d650c66cdef19d70a7b1d109836abe5681cbd1a6940ca","abstract_canon_sha256":"33a751a0d2a89ec80d0b202d9e3f9f8d7a1ce7ee3b0fcbcae9455240a9cd9712"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T00:02:27.115674Z","signature_b64":"Hi1ZjLVSXQdD88klR0WPObzNJ6oLXxpzUC97s303WklcH8bMNskAKPfHZpxuDxr3YKcJ62jfyVXFD2zf9kwDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68102a2286ceb53a0937a3f023822f2c8f6ca9338c4ea5f30ce908b68174b931","last_reissued_at":"2026-05-22T00:02:27.115184Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T00:02:27.115184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph neural network explanations reveal a topological signature of disease-associated hubs in biological networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"q-bio.MN","authors_text":"Dennis Veselkov, Ivan Laponogov, Kirill Veselkov, Kyle Higgins","submitted_at":"2026-05-08T15:29:36Z","abstract_excerpt":"Graph neural networks (GNNs) are increasingly used to model biological systems, yet the reliability of post-hoc explanation methods for recovering meaningful molecular mechanisms remains unclear. Here, we systematically evaluate four widely used approaches: Saliency Attribution (SA), Integrated Gradients (IG), GNNExplainer, and Layer-wise Relevance Propagation (LRP) for identifying disease-relevant structure in breast cancer RNA-seq data projected onto a protein-protein interaction network. Using synthetic benchmarks with known ground-truth motifs, we show that explanation methods recover dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21502","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/2605.21502/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":"2605.21502","created_at":"2026-05-22T00:02:27.115243+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21502v1","created_at":"2026-05-22T00:02:27.115243+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21502","created_at":"2026-05-22T00:02:27.115243+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAICUIUGZ22T","created_at":"2026-05-22T00:02:27.115243+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAICUIUGZ22TUCJX","created_at":"2026-05-22T00:02:27.115243+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAICUIUG","created_at":"2026-05-22T00:02:27.115243+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NAICUIUGZ22TUCJXUPYCHARPFS","json":"https://pith.science/pith/NAICUIUGZ22TUCJXUPYCHARPFS.json","graph_json":"https://pith.science/api/pith-number/NAICUIUGZ22TUCJXUPYCHARPFS/graph.json","events_json":"https://pith.science/api/pith-number/NAICUIUGZ22TUCJXUPYCHARPFS/events.json","paper":"https://pith.science/paper/NAICUIUG"},"agent_actions":{"view_html":"https://pith.science/pith/NAICUIUGZ22TUCJXUPYCHARPFS","download_json":"https://pith.science/pith/NAICUIUGZ22TUCJXUPYCHARPFS.json","view_paper":"https://pith.science/paper/NAICUIUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21502&json=true","fetch_graph":"https://pith.science/api/pith-number/NAICUIUGZ22TUCJXUPYCHARPFS/graph.json","fetch_events":"https://pith.science/api/pith-number/NAICUIUGZ22TUCJXUPYCHARPFS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAICUIUGZ22TUCJXUPYCHARPFS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAICUIUGZ22TUCJXUPYCHARPFS/action/storage_attestation","attest_author":"https://pith.science/pith/NAICUIUGZ22TUCJXUPYCHARPFS/action/author_attestation","sign_citation":"https://pith.science/pith/NAICUIUGZ22TUCJXUPYCHARPFS/action/citation_signature","submit_replication":"https://pith.science/pith/NAICUIUGZ22TUCJXUPYCHARPFS/action/replication_record"}},"created_at":"2026-05-22T00:02:27.115243+00:00","updated_at":"2026-05-22T00:02:27.115243+00:00"}