{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CJ466OVKK3UVR6E6VVKZZ7TJRA","short_pith_number":"pith:CJ466OVK","schema_version":"1.0","canonical_sha256":"1279ef3aaa56e958f89ead559cfe698833ca2d7802c0caa1ac6e0ca338e1052b","source":{"kind":"arxiv","id":"2107.11889","version":1},"attestation_state":"computed","paper":{"title":"GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dmitry Kazhdan, Lucie Charlotte Magister, Pietro Li\\`o, Vikash Singh","submitted_at":"2021-07-25T20:52:48Z","abstract_excerpt":"While graph neural networks (GNNs) have been shown to perform well on graph-based data from a variety of fields, they suffer from a lack of transparency and accountability, which hinders trust and consequently the deployment of such models in high-stake and safety-critical scenarios. Even though recent research has investigated methods for explaining GNNs, these methods are limited to single-instance explanations, also known as local explanations. Motivated by the aim of providing global explanations, we adapt the well-known Automated Concept-based Explanation approach (Ghorbani et al., 2019) "},"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":"2107.11889","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-25T20:52:48Z","cross_cats_sorted":[],"title_canon_sha256":"bd00f61d12b8bad7f7bce839880d44781457fc2f3db58a14bc56baa0dd02aaa9","abstract_canon_sha256":"70606dd71b7f1a7c4579a2af906a3e8a927a9badc83d9395cd5c5402c022da90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:38.414126Z","signature_b64":"zNNfkzxuS5HEs+BsEG+1cEi0IVXb2MdLw2ss4f4/d1OBpBrVkbObg4x/5MZZd38M9qXzJD1JNEwRbhh4YD7/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1279ef3aaa56e958f89ead559cfe698833ca2d7802c0caa1ac6e0ca338e1052b","last_reissued_at":"2026-07-05T03:00:38.413630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:38.413630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dmitry Kazhdan, Lucie Charlotte Magister, Pietro Li\\`o, Vikash Singh","submitted_at":"2021-07-25T20:52:48Z","abstract_excerpt":"While graph neural networks (GNNs) have been shown to perform well on graph-based data from a variety of fields, they suffer from a lack of transparency and accountability, which hinders trust and consequently the deployment of such models in high-stake and safety-critical scenarios. Even though recent research has investigated methods for explaining GNNs, these methods are limited to single-instance explanations, also known as local explanations. Motivated by the aim of providing global explanations, we adapt the well-known Automated Concept-based Explanation approach (Ghorbani et al., 2019) "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.11889","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/2107.11889/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":"2107.11889","created_at":"2026-07-05T03:00:38.413685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.11889v1","created_at":"2026-07-05T03:00:38.413685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.11889","created_at":"2026-07-05T03:00:38.413685+00:00"},{"alias_kind":"pith_short_12","alias_value":"CJ466OVKK3UV","created_at":"2026-07-05T03:00:38.413685+00:00"},{"alias_kind":"pith_short_16","alias_value":"CJ466OVKK3UVR6E6","created_at":"2026-07-05T03:00:38.413685+00:00"},{"alias_kind":"pith_short_8","alias_value":"CJ466OVK","created_at":"2026-07-05T03:00:38.413685+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10669","citing_title":"In Defense of Information Leakage in Concept-based Models","ref_index":219,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01698","citing_title":"Learning Label-Efficient Interpretable Medical Image Diagnosis via Semi-supervised Hypergraph Concept Bottleneck Model","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14884","citing_title":"AIMing for Standardised Explainability Evaluation in GNNs: A Framework and Case Study on Graph Kernel Networks","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18868","citing_title":"Subgraph Concept Networks: Concept Levels in Graph Classification","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20082","citing_title":"Concept Graph Convolutions: Message Passing in the Concept Space","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CJ466OVKK3UVR6E6VVKZZ7TJRA","json":"https://pith.science/pith/CJ466OVKK3UVR6E6VVKZZ7TJRA.json","graph_json":"https://pith.science/api/pith-number/CJ466OVKK3UVR6E6VVKZZ7TJRA/graph.json","events_json":"https://pith.science/api/pith-number/CJ466OVKK3UVR6E6VVKZZ7TJRA/events.json","paper":"https://pith.science/paper/CJ466OVK"},"agent_actions":{"view_html":"https://pith.science/pith/CJ466OVKK3UVR6E6VVKZZ7TJRA","download_json":"https://pith.science/pith/CJ466OVKK3UVR6E6VVKZZ7TJRA.json","view_paper":"https://pith.science/paper/CJ466OVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.11889&json=true","fetch_graph":"https://pith.science/api/pith-number/CJ466OVKK3UVR6E6VVKZZ7TJRA/graph.json","fetch_events":"https://pith.science/api/pith-number/CJ466OVKK3UVR6E6VVKZZ7TJRA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CJ466OVKK3UVR6E6VVKZZ7TJRA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CJ466OVKK3UVR6E6VVKZZ7TJRA/action/storage_attestation","attest_author":"https://pith.science/pith/CJ466OVKK3UVR6E6VVKZZ7TJRA/action/author_attestation","sign_citation":"https://pith.science/pith/CJ466OVKK3UVR6E6VVKZZ7TJRA/action/citation_signature","submit_replication":"https://pith.science/pith/CJ466OVKK3UVR6E6VVKZZ7TJRA/action/replication_record"}},"created_at":"2026-07-05T03:00:38.413685+00:00","updated_at":"2026-07-05T03:00:38.413685+00:00"}