{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3ZVGEVTATG45WOBJDSG4EV2HXP","short_pith_number":"pith:3ZVGEVTA","schema_version":"1.0","canonical_sha256":"de6a62566099b9db38291c8dc25747bbc9517007f5387e84e38566535cf6e87b","source":{"kind":"arxiv","id":"2312.15237","version":1},"attestation_state":"computed","paper":{"title":"Towards Fine-Grained Explainability for Heterogeneous Graph Neural Network","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Caleb Chen Cao, Jiale Deng, Luyu Qiu, Tong Li, Yanyan Shen, Yongxiang Huang","submitted_at":"2023-12-23T12:13:23Z","abstract_excerpt":"Heterogeneous graph neural networks (HGNs) are prominent approaches to node classification tasks on heterogeneous graphs. Despite the superior performance, insights about the predictions made from HGNs are obscure to humans. Existing explainability techniques are mainly proposed for GNNs on homogeneous graphs. They focus on highlighting salient graph objects to the predictions whereas the problem of how these objects affect the predictions remains unsolved. Given heterogeneous graphs with complex structures and rich semantics, it is imperative that salient objects can be accompanied with their"},"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":"2312.15237","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-23T12:13:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6238d960e648017e40ccdf947dc2c7d1253b3157197104a643b3c35d70678140","abstract_canon_sha256":"03d608762265a3b830e9d24b8f1948e9deac8924179c88e2619b00eb389e6510"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:32.573880Z","signature_b64":"3dlPCCmP7hlHXOHNgjeULRz3wli4a4hwKT5m/8vCa9A3mfuW3AG1yZCtw69lByOwpU59fHVCcgQtNYc7OyuECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de6a62566099b9db38291c8dc25747bbc9517007f5387e84e38566535cf6e87b","last_reissued_at":"2026-07-05T07:27:32.573460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:32.573460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Fine-Grained Explainability for Heterogeneous Graph Neural Network","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Caleb Chen Cao, Jiale Deng, Luyu Qiu, Tong Li, Yanyan Shen, Yongxiang Huang","submitted_at":"2023-12-23T12:13:23Z","abstract_excerpt":"Heterogeneous graph neural networks (HGNs) are prominent approaches to node classification tasks on heterogeneous graphs. Despite the superior performance, insights about the predictions made from HGNs are obscure to humans. Existing explainability techniques are mainly proposed for GNNs on homogeneous graphs. They focus on highlighting salient graph objects to the predictions whereas the problem of how these objects affect the predictions remains unsolved. Given heterogeneous graphs with complex structures and rich semantics, it is imperative that salient objects can be accompanied with their"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15237","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/2312.15237/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":"2312.15237","created_at":"2026-07-05T07:27:32.573514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.15237v1","created_at":"2026-07-05T07:27:32.573514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15237","created_at":"2026-07-05T07:27:32.573514+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZVGEVTATG45","created_at":"2026-07-05T07:27:32.573514+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZVGEVTATG45WOBJ","created_at":"2026-07-05T07:27:32.573514+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZVGEVTA","created_at":"2026-07-05T07:27:32.573514+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/3ZVGEVTATG45WOBJDSG4EV2HXP","json":"https://pith.science/pith/3ZVGEVTATG45WOBJDSG4EV2HXP.json","graph_json":"https://pith.science/api/pith-number/3ZVGEVTATG45WOBJDSG4EV2HXP/graph.json","events_json":"https://pith.science/api/pith-number/3ZVGEVTATG45WOBJDSG4EV2HXP/events.json","paper":"https://pith.science/paper/3ZVGEVTA"},"agent_actions":{"view_html":"https://pith.science/pith/3ZVGEVTATG45WOBJDSG4EV2HXP","download_json":"https://pith.science/pith/3ZVGEVTATG45WOBJDSG4EV2HXP.json","view_paper":"https://pith.science/paper/3ZVGEVTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.15237&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZVGEVTATG45WOBJDSG4EV2HXP/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZVGEVTATG45WOBJDSG4EV2HXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZVGEVTATG45WOBJDSG4EV2HXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZVGEVTATG45WOBJDSG4EV2HXP/action/storage_attestation","attest_author":"https://pith.science/pith/3ZVGEVTATG45WOBJDSG4EV2HXP/action/author_attestation","sign_citation":"https://pith.science/pith/3ZVGEVTATG45WOBJDSG4EV2HXP/action/citation_signature","submit_replication":"https://pith.science/pith/3ZVGEVTATG45WOBJDSG4EV2HXP/action/replication_record"}},"created_at":"2026-07-05T07:27:32.573514+00:00","updated_at":"2026-07-05T07:27:32.573514+00:00"}