{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PT5VHBMQRHFSDCFFY5OZFU7SRU","short_pith_number":"pith:PT5VHBMQ","schema_version":"1.0","canonical_sha256":"7cfb53859089cb2188a5c75d92d3f28d3054f978440f6b1ab8b707d17a81b48a","source":{"kind":"arxiv","id":"2602.04360","version":2},"attestation_state":"computed","paper":{"title":"Counterfactual Explanations for Hypergraph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"Fabiano Veglianti, Gabriele Tolomei, Lorenzo Antonelli","submitted_at":"2026-02-04T09:34:03Z","abstract_excerpt":"Hypergraph neural networks (HGNNs) effectively model higher-order interactions in many real-world systems but remain difficult to interpret, limiting their deployment in high-stakes settings. We introduce CF-HyperGNNExplainer, a counterfactual explanation method for HGNNs that identifies the minimal structural changes required to alter a model's prediction. The method generates counterfactual hypergraphs using actionable edits limited to removing node-hyperedge incidences or deleting hyperedges, producing concise and structurally meaningful explanations. Extensive experiments on hypergraph ben"},"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":"2602.04360","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T09:34:03Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"1bdc9855024070d41b8e0a5758170e28e51e3a2cba7f4a76b5a0e83f40facb86","abstract_canon_sha256":"a8a5e48bf1eb0e822287962d0f2b85b498bc8f971324bb48e8c724faa65ba1f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:24.520814Z","signature_b64":"NQzQWfPxWyRCDiNT40fOjw1N7xgYO+DvsToNuFUUjiU86UkKBnpy9CBLCwTDN9nH7Yk6UxA3B5DtOrR3imenBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cfb53859089cb2188a5c75d92d3f28d3054f978440f6b1ab8b707d17a81b48a","last_reissued_at":"2026-05-26T01:03:24.520279Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:24.520279Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Counterfactual Explanations for Hypergraph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.LG","authors_text":"Fabiano Veglianti, Gabriele Tolomei, Lorenzo Antonelli","submitted_at":"2026-02-04T09:34:03Z","abstract_excerpt":"Hypergraph neural networks (HGNNs) effectively model higher-order interactions in many real-world systems but remain difficult to interpret, limiting their deployment in high-stakes settings. We introduce CF-HyperGNNExplainer, a counterfactual explanation method for HGNNs that identifies the minimal structural changes required to alter a model's prediction. The method generates counterfactual hypergraphs using actionable edits limited to removing node-hyperedge incidences or deleting hyperedges, producing concise and structurally meaningful explanations. Extensive experiments on hypergraph ben"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.04360","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/2602.04360/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":"2602.04360","created_at":"2026-05-26T01:03:24.520349+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.04360v2","created_at":"2026-05-26T01:03:24.520349+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04360","created_at":"2026-05-26T01:03:24.520349+00:00"},{"alias_kind":"pith_short_12","alias_value":"PT5VHBMQRHFS","created_at":"2026-05-26T01:03:24.520349+00:00"},{"alias_kind":"pith_short_16","alias_value":"PT5VHBMQRHFSDCFF","created_at":"2026-05-26T01:03:24.520349+00:00"},{"alias_kind":"pith_short_8","alias_value":"PT5VHBMQ","created_at":"2026-05-26T01:03:24.520349+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/PT5VHBMQRHFSDCFFY5OZFU7SRU","json":"https://pith.science/pith/PT5VHBMQRHFSDCFFY5OZFU7SRU.json","graph_json":"https://pith.science/api/pith-number/PT5VHBMQRHFSDCFFY5OZFU7SRU/graph.json","events_json":"https://pith.science/api/pith-number/PT5VHBMQRHFSDCFFY5OZFU7SRU/events.json","paper":"https://pith.science/paper/PT5VHBMQ"},"agent_actions":{"view_html":"https://pith.science/pith/PT5VHBMQRHFSDCFFY5OZFU7SRU","download_json":"https://pith.science/pith/PT5VHBMQRHFSDCFFY5OZFU7SRU.json","view_paper":"https://pith.science/paper/PT5VHBMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.04360&json=true","fetch_graph":"https://pith.science/api/pith-number/PT5VHBMQRHFSDCFFY5OZFU7SRU/graph.json","fetch_events":"https://pith.science/api/pith-number/PT5VHBMQRHFSDCFFY5OZFU7SRU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PT5VHBMQRHFSDCFFY5OZFU7SRU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PT5VHBMQRHFSDCFFY5OZFU7SRU/action/storage_attestation","attest_author":"https://pith.science/pith/PT5VHBMQRHFSDCFFY5OZFU7SRU/action/author_attestation","sign_citation":"https://pith.science/pith/PT5VHBMQRHFSDCFFY5OZFU7SRU/action/citation_signature","submit_replication":"https://pith.science/pith/PT5VHBMQRHFSDCFFY5OZFU7SRU/action/replication_record"}},"created_at":"2026-05-26T01:03:24.520349+00:00","updated_at":"2026-05-26T01:03:24.520349+00:00"}