{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N3C45PCPQZYXWE2CZM2EWP7W45","short_pith_number":"pith:N3C45PCP","schema_version":"1.0","canonical_sha256":"6ec5cebc4f86717b1342cb344b3ff6e7620512eead478d6c1ccd658cd860dc4f","source":{"kind":"arxiv","id":"2605.17285","version":1},"attestation_state":"computed","paper":{"title":"UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Geonhee Han, Hogun Park, Hyunju Kang","submitted_at":"2026-05-17T06:48:16Z","abstract_excerpt":"Node representation learning, such as Graph Neural Networks (GNNs), has emerged as a pivotal method in machine learning. The demand for reliable explanation generation surges, yet unsupervised models remain underexplored. To bridge this gap, we introduce a method for generating counterfactual (CF) explanations in unsupervised node representation learning. We identify the most important subgraphs that cause a significant change in the k-nearest neighbors of a node of interest in the learned embedding space upon perturbation. The k-nearest neighbor-based CF explanation method provides simple, ye"},"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":"2605.17285","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-17T06:48:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f1b4af197208d94ac3e4c8ce3cf16f42e8e9fe6312ac269fbc8a1899d8de2011","abstract_canon_sha256":"1cc8b6cfbd807ad7869cb839fd4db3911dff2ba97ca75e637dc83cf0bfff83f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:49.850189Z","signature_b64":"4hVswjZ8kdV5hvx6KzMEXqXRd0f6H6N4VlN5bJTuAjjgOvFNYnNvNmnGPf8ULvklMCGDsFo4zrF7NGSjCuLgDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ec5cebc4f86717b1342cb344b3ff6e7620512eead478d6c1ccd658cd860dc4f","last_reissued_at":"2026-05-20T00:03:49.849474Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:49.849474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Geonhee Han, Hogun Park, Hyunju Kang","submitted_at":"2026-05-17T06:48:16Z","abstract_excerpt":"Node representation learning, such as Graph Neural Networks (GNNs), has emerged as a pivotal method in machine learning. The demand for reliable explanation generation surges, yet unsupervised models remain underexplored. To bridge this gap, we introduce a method for generating counterfactual (CF) explanations in unsupervised node representation learning. We identify the most important subgraphs that cause a significant change in the k-nearest neighbors of a node of interest in the learned embedding space upon perturbation. The k-nearest neighbor-based CF explanation method provides simple, ye"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17285","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/2605.17285/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T22:01:57.821997Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.769696Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"540bffbc994eaf84d932fc63b851e234c531dc035fcbea86e36a8c816723082d"},"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":"2605.17285","created_at":"2026-05-20T00:03:49.849581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17285v1","created_at":"2026-05-20T00:03:49.849581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17285","created_at":"2026-05-20T00:03:49.849581+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3C45PCPQZYX","created_at":"2026-05-20T00:03:49.849581+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3C45PCPQZYXWE2C","created_at":"2026-05-20T00:03:49.849581+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3C45PCP","created_at":"2026-05-20T00:03:49.849581+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/N3C45PCPQZYXWE2CZM2EWP7W45","json":"https://pith.science/pith/N3C45PCPQZYXWE2CZM2EWP7W45.json","graph_json":"https://pith.science/api/pith-number/N3C45PCPQZYXWE2CZM2EWP7W45/graph.json","events_json":"https://pith.science/api/pith-number/N3C45PCPQZYXWE2CZM2EWP7W45/events.json","paper":"https://pith.science/paper/N3C45PCP"},"agent_actions":{"view_html":"https://pith.science/pith/N3C45PCPQZYXWE2CZM2EWP7W45","download_json":"https://pith.science/pith/N3C45PCPQZYXWE2CZM2EWP7W45.json","view_paper":"https://pith.science/paper/N3C45PCP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17285&json=true","fetch_graph":"https://pith.science/api/pith-number/N3C45PCPQZYXWE2CZM2EWP7W45/graph.json","fetch_events":"https://pith.science/api/pith-number/N3C45PCPQZYXWE2CZM2EWP7W45/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3C45PCPQZYXWE2CZM2EWP7W45/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3C45PCPQZYXWE2CZM2EWP7W45/action/storage_attestation","attest_author":"https://pith.science/pith/N3C45PCPQZYXWE2CZM2EWP7W45/action/author_attestation","sign_citation":"https://pith.science/pith/N3C45PCPQZYXWE2CZM2EWP7W45/action/citation_signature","submit_replication":"https://pith.science/pith/N3C45PCPQZYXWE2CZM2EWP7W45/action/replication_record"}},"created_at":"2026-05-20T00:03:49.849581+00:00","updated_at":"2026-05-20T00:03:49.849581+00:00"}