{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CV44LP64SY274H4LBCEU7UAJHZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"75a8851b06b6812a740544fdcb746c26415c5a34746014cd5e5e228203a0a465","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T11:09:10Z","title_canon_sha256":"f14606379b4e706642904d292792af5a10a11665bd63ed6d72ab1d5c952f60ca"},"schema_version":"1.0","source":{"id":"2109.09426","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09426","created_at":"2026-07-05T05:26:34Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09426v2","created_at":"2026-07-05T05:26:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09426","created_at":"2026-07-05T05:26:34Z"},{"alias_kind":"pith_short_12","alias_value":"CV44LP64SY27","created_at":"2026-07-05T05:26:34Z"},{"alias_kind":"pith_short_16","alias_value":"CV44LP64SY274H4L","created_at":"2026-07-05T05:26:34Z"},{"alias_kind":"pith_short_8","alias_value":"CV44LP64","created_at":"2026-07-05T05:26:34Z"}],"graph_snapshots":[{"event_id":"sha256:bee42de1c89e4daf217a7ae49de2b70c98d53c0c941d22abbf036937d0e23411","target":"graph","created_at":"2026-07-05T05:26:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2109.09426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we investigate the degree of explainability of graph neural networks (GNNs). Existing explainers work by finding global/local subgraphs to explain a prediction, but they are applied after a GNN has already been trained. Here, we propose a meta-learning framework for improving the level of explainability of a GNN directly at training time, by steering the optimization procedure towards what we call `interpretable minima'. Our framework (called MATE, MetA-Train to Explain) jointly trains a model to solve the original task, e.g., node classification, and to provide easily processab","authors_text":"Aurelio Uncini, Indro Spinelli, Simone Scardapane","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T11:09:10Z","title":"A Meta-Learning Approach for Training Explainable Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09426","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3e68539bc230f36968f382db485d7044bdb75b01690632c5106f384106a62f4d","target":"record","created_at":"2026-07-05T05:26:34Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"75a8851b06b6812a740544fdcb746c26415c5a34746014cd5e5e228203a0a465","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T11:09:10Z","title_canon_sha256":"f14606379b4e706642904d292792af5a10a11665bd63ed6d72ab1d5c952f60ca"},"schema_version":"1.0","source":{"id":"2109.09426","kind":"arxiv","version":2}},"canonical_sha256":"1579c5bfdc9635fe1f8b08894fd0093e44d0f88c1fef5ae9ca426421cd58fa22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1579c5bfdc9635fe1f8b08894fd0093e44d0f88c1fef5ae9ca426421cd58fa22","first_computed_at":"2026-07-05T05:26:34.745224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:26:34.745224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"krh5nIVBvOwbYrwh65v6eI3Euzmth+zU5yrXxSePvi4rK1U4lsvac/YJAywzwBYUShTwrrL9wJawn+yLnuVyDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:26:34.745719Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.09426","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e68539bc230f36968f382db485d7044bdb75b01690632c5106f384106a62f4d","sha256:bee42de1c89e4daf217a7ae49de2b70c98d53c0c941d22abbf036937d0e23411"],"state_sha256":"6fe824b1ca402ccf10a19bef42d098fd3d2dcdaeddacc9a77774fcb00e365963"}