{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GVFKCEZBFTID2IYINYJC4I5EWS","short_pith_number":"pith:GVFKCEZB","schema_version":"1.0","canonical_sha256":"354aa113212cd03d23086e122e23a4b4b778895889ed9196ac5bcbfe3f28c01e","source":{"kind":"arxiv","id":"2208.04222","version":1},"attestation_state":"computed","paper":{"title":"GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Fabrizio Silvestri, Gabriele Tolomei, Hongshik Ahn, Jia Wang, Yongfeng Zhang, Zhenhua Huang, Ziheng Chen","submitted_at":"2022-08-04T09:13:00Z","abstract_excerpt":"Recently, graph neural networks (GNNs) have been widely used to develop successful recommender systems. Although powerful, it is very difficult for a GNN-based recommender system to attach tangible explanations of why a specific item ends up in the list of suggestions for a given user. Indeed, explaining GNN-based recommendations is unique, and existing GNN explanation methods are inappropriate for two reasons. First, traditional GNN explanation methods are designed for node, edge, or graph classification tasks rather than ranking, as in recommender systems. Second, standard machine learning e"},"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":"2208.04222","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-08-04T09:13:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e85c8566ba4261091d79759624cd9db2ebbee44fd939a09c443447bbb8c9363a","abstract_canon_sha256":"f691847de7ba85c50d41e9b3d6cfb016c42504322a1eaa871f6469248bf655ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:48.858920Z","signature_b64":"zrb+9ZeB/affVTRm93unvNaMJpvvWT8mwgpP70G1Wy0cZKnUn6TBmUspE5UQS9szYxdSs5PKsC/0CLUs+Q7UDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"354aa113212cd03d23086e122e23a4b4b778895889ed9196ac5bcbfe3f28c01e","last_reissued_at":"2026-07-05T04:46:48.858515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:48.858515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Fabrizio Silvestri, Gabriele Tolomei, Hongshik Ahn, Jia Wang, Yongfeng Zhang, Zhenhua Huang, Ziheng Chen","submitted_at":"2022-08-04T09:13:00Z","abstract_excerpt":"Recently, graph neural networks (GNNs) have been widely used to develop successful recommender systems. Although powerful, it is very difficult for a GNN-based recommender system to attach tangible explanations of why a specific item ends up in the list of suggestions for a given user. Indeed, explaining GNN-based recommendations is unique, and existing GNN explanation methods are inappropriate for two reasons. First, traditional GNN explanation methods are designed for node, edge, or graph classification tasks rather than ranking, as in recommender systems. Second, standard machine learning e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.04222","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/2208.04222/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":"2208.04222","created_at":"2026-07-05T04:46:48.858576+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.04222v1","created_at":"2026-07-05T04:46:48.858576+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.04222","created_at":"2026-07-05T04:46:48.858576+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVFKCEZBFTID","created_at":"2026-07-05T04:46:48.858576+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVFKCEZBFTID2IYI","created_at":"2026-07-05T04:46:48.858576+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVFKCEZB","created_at":"2026-07-05T04:46:48.858576+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.13724","citing_title":"Heterogeneous Graph Neural Networks with Post-hoc Explanations for Multi-modal and Explainable Land Use Inference","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19663","citing_title":"From Top-1 to Top-K: A Reproducibility Study and Benchmarking of Counterfactual Explanations for Recommender Systems","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVFKCEZBFTID2IYINYJC4I5EWS","json":"https://pith.science/pith/GVFKCEZBFTID2IYINYJC4I5EWS.json","graph_json":"https://pith.science/api/pith-number/GVFKCEZBFTID2IYINYJC4I5EWS/graph.json","events_json":"https://pith.science/api/pith-number/GVFKCEZBFTID2IYINYJC4I5EWS/events.json","paper":"https://pith.science/paper/GVFKCEZB"},"agent_actions":{"view_html":"https://pith.science/pith/GVFKCEZBFTID2IYINYJC4I5EWS","download_json":"https://pith.science/pith/GVFKCEZBFTID2IYINYJC4I5EWS.json","view_paper":"https://pith.science/paper/GVFKCEZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.04222&json=true","fetch_graph":"https://pith.science/api/pith-number/GVFKCEZBFTID2IYINYJC4I5EWS/graph.json","fetch_events":"https://pith.science/api/pith-number/GVFKCEZBFTID2IYINYJC4I5EWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVFKCEZBFTID2IYINYJC4I5EWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVFKCEZBFTID2IYINYJC4I5EWS/action/storage_attestation","attest_author":"https://pith.science/pith/GVFKCEZBFTID2IYINYJC4I5EWS/action/author_attestation","sign_citation":"https://pith.science/pith/GVFKCEZBFTID2IYINYJC4I5EWS/action/citation_signature","submit_replication":"https://pith.science/pith/GVFKCEZBFTID2IYINYJC4I5EWS/action/replication_record"}},"created_at":"2026-07-05T04:46:48.858576+00:00","updated_at":"2026-07-05T04:46:48.858576+00:00"}