{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3GO5JLHKUPNBEEE53SRDEOMTTR","short_pith_number":"pith:3GO5JLHK","schema_version":"1.0","canonical_sha256":"d99dd4aceaa3da12109ddca23239939c44ac3bbee116a22e2865c56ce177d97e","source":{"kind":"arxiv","id":"2104.06643","version":2},"attestation_state":"computed","paper":{"title":"Generative Causal Explanations for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baochun Li, Hao Lan, Wanyu Lin","submitted_at":"2021-04-14T06:22:21Z","abstract_excerpt":"This paper presents Gem, a model-agnostic approach for providing interpretable explanations for any GNNs on various graph learning tasks. Specifically, we formulate the problem of providing explanations for the decisions of GNNs as a causal learning task. Then we train a causal explanation model equipped with a loss function based on Granger causality. Different from existing explainers for GNNs, Gem explains GNNs on graph-structured data from a causal perspective. It has better generalization ability as it has no requirements on the internal structure of the GNNs or prior knowledge on the gra"},"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":"2104.06643","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-14T06:22:21Z","cross_cats_sorted":[],"title_canon_sha256":"5666720141fb9cf8c1d327acfeb9ffc07ff62f057aa0f5bf563cf564baa2544f","abstract_canon_sha256":"ab1d0adc5c53746a468eecabb2b4955e573cff9361c884bccf119cc763cdbd86"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:27.497578Z","signature_b64":"7aE8uCaUPp4Zf1HioMhYn6cGQIxEYm/xAwa5RIg4dwgTi1XkeVxW6cYgs3Bw07AJmRiluxmBZOoeN72fM3cRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d99dd4aceaa3da12109ddca23239939c44ac3bbee116a22e2865c56ce177d97e","last_reissued_at":"2026-07-05T02:46:27.497063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:27.497063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Causal Explanations for Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Baochun Li, Hao Lan, Wanyu Lin","submitted_at":"2021-04-14T06:22:21Z","abstract_excerpt":"This paper presents Gem, a model-agnostic approach for providing interpretable explanations for any GNNs on various graph learning tasks. Specifically, we formulate the problem of providing explanations for the decisions of GNNs as a causal learning task. Then we train a causal explanation model equipped with a loss function based on Granger causality. Different from existing explainers for GNNs, Gem explains GNNs on graph-structured data from a causal perspective. It has better generalization ability as it has no requirements on the internal structure of the GNNs or prior knowledge on the gra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06643","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/2104.06643/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":"2104.06643","created_at":"2026-07-05T02:46:27.497128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06643v2","created_at":"2026-07-05T02:46:27.497128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06643","created_at":"2026-07-05T02:46:27.497128+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GO5JLHKUPNB","created_at":"2026-07-05T02:46:27.497128+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GO5JLHKUPNBEEE5","created_at":"2026-07-05T02:46:27.497128+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GO5JLHK","created_at":"2026-07-05T02:46:27.497128+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/3GO5JLHKUPNBEEE53SRDEOMTTR","json":"https://pith.science/pith/3GO5JLHKUPNBEEE53SRDEOMTTR.json","graph_json":"https://pith.science/api/pith-number/3GO5JLHKUPNBEEE53SRDEOMTTR/graph.json","events_json":"https://pith.science/api/pith-number/3GO5JLHKUPNBEEE53SRDEOMTTR/events.json","paper":"https://pith.science/paper/3GO5JLHK"},"agent_actions":{"view_html":"https://pith.science/pith/3GO5JLHKUPNBEEE53SRDEOMTTR","download_json":"https://pith.science/pith/3GO5JLHKUPNBEEE53SRDEOMTTR.json","view_paper":"https://pith.science/paper/3GO5JLHK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06643&json=true","fetch_graph":"https://pith.science/api/pith-number/3GO5JLHKUPNBEEE53SRDEOMTTR/graph.json","fetch_events":"https://pith.science/api/pith-number/3GO5JLHKUPNBEEE53SRDEOMTTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GO5JLHKUPNBEEE53SRDEOMTTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GO5JLHKUPNBEEE53SRDEOMTTR/action/storage_attestation","attest_author":"https://pith.science/pith/3GO5JLHKUPNBEEE53SRDEOMTTR/action/author_attestation","sign_citation":"https://pith.science/pith/3GO5JLHKUPNBEEE53SRDEOMTTR/action/citation_signature","submit_replication":"https://pith.science/pith/3GO5JLHKUPNBEEE53SRDEOMTTR/action/replication_record"}},"created_at":"2026-07-05T02:46:27.497128+00:00","updated_at":"2026-07-05T02:46:27.497128+00:00"}