{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:WBLPV7OYU5QZCF7N6TP7KNAGIQ","short_pith_number":"pith:WBLPV7OY","canonical_record":{"source":{"id":"2209.14402","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T20:03:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a8f632bd4c63a8fe653cb1c0c50f336c57a3795c077bb1a91b94f0b0ec25c740","abstract_canon_sha256":"0a09dd58276a9282fd381d3a77eb77f4befc02c54a63c549e096f0a24aeaa9e6"},"schema_version":"1.0"},"canonical_sha256":"b056fafdd8a7619117edf4dff534064418d48707327306935b26d0ea12c15a45","source":{"kind":"arxiv","id":"2209.14402","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14402","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14402v4","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14402","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"pith_short_12","alias_value":"WBLPV7OYU5QZ","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"pith_short_16","alias_value":"WBLPV7OYU5QZCF7N","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"pith_short_8","alias_value":"WBLPV7OY","created_at":"2026-07-05T08:31:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:WBLPV7OYU5QZCF7N6TP7KNAGIQ","target":"record","payload":{"canonical_record":{"source":{"id":"2209.14402","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T20:03:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a8f632bd4c63a8fe653cb1c0c50f336c57a3795c077bb1a91b94f0b0ec25c740","abstract_canon_sha256":"0a09dd58276a9282fd381d3a77eb77f4befc02c54a63c549e096f0a24aeaa9e6"},"schema_version":"1.0"},"canonical_sha256":"b056fafdd8a7619117edf4dff534064418d48707327306935b26d0ea12c15a45","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:38.256534Z","signature_b64":"hGUGDGtpeq4m3TuaE5pDHpyk+/61SbFiiKNDSj/WHsCJp01sp8bhQA8G/FZbguyNAv6N0EBkPU6qaA0Q+JNnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b056fafdd8a7619117edf4dff534064418d48707327306935b26d0ea12c15a45","last_reissued_at":"2026-07-05T08:31:38.256119Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:38.256119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.14402","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:31:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B3MLu54F4ga0oSUmOuWUaJ53CgZzGPYE8SeqZfcpvzuNwgFC+fD65HQ5CUMLlehoatD221TJJzn+WkhrDhMTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:47:57.924613Z"},"content_sha256":"a8da26db4f70ea847461736a1b10bd1f7679cf24a49da07583987e2c9ceec4de","schema_version":"1.0","event_id":"sha256:a8da26db4f70ea847461736a1b10bd1f7679cf24a49da07583987e2c9ceec4de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:WBLPV7OYU5QZCF7N6TP7KNAGIQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"L2XGNN: Learning to Explain Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Giuseppe Serra, Mathias Niepert","submitted_at":"2022-09-28T20:03:57Z","abstract_excerpt":"Graph Neural Networks (GNNs) are a popular class of machine learning models. Inspired by the learning to explain (L2X) paradigm, we propose L2XGNN, a framework for explainable GNNs which provides faithful explanations by design. L2XGNN learns a mechanism for selecting explanatory subgraphs (motifs) which are exclusively used in the GNNs message-passing operations. L2XGNN is able to select, for each input graph, a subgraph with specific properties such as being sparse and connected. Imposing such constraints on the motifs often leads to more interpretable and effective explanations. Experiments"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14402","kind":"arxiv","version":4},"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/2209.14402/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:31:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZIWNS0UNXEw02p38hwlQHoilZaDARPAFZk2cJVrbuHSIPoLJlr+ZNL9IEyZraCKAeUM+CVJ4qE/zP55Yg55HBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T06:47:57.925143Z"},"content_sha256":"2497e6accff6941946b3abc55d57584e01aa9138804af7e691c0bcb1b38ccaaf","schema_version":"1.0","event_id":"sha256:2497e6accff6941946b3abc55d57584e01aa9138804af7e691c0bcb1b38ccaaf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WBLPV7OYU5QZCF7N6TP7KNAGIQ/bundle.json","state_url":"https://pith.science/pith/WBLPV7OYU5QZCF7N6TP7KNAGIQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WBLPV7OYU5QZCF7N6TP7KNAGIQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-20T06:47:57Z","links":{"resolver":"https://pith.science/pith/WBLPV7OYU5QZCF7N6TP7KNAGIQ","bundle":"https://pith.science/pith/WBLPV7OYU5QZCF7N6TP7KNAGIQ/bundle.json","state":"https://pith.science/pith/WBLPV7OYU5QZCF7N6TP7KNAGIQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WBLPV7OYU5QZCF7N6TP7KNAGIQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:WBLPV7OYU5QZCF7N6TP7KNAGIQ","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":"0a09dd58276a9282fd381d3a77eb77f4befc02c54a63c549e096f0a24aeaa9e6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T20:03:57Z","title_canon_sha256":"a8f632bd4c63a8fe653cb1c0c50f336c57a3795c077bb1a91b94f0b0ec25c740"},"schema_version":"1.0","source":{"id":"2209.14402","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.14402","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"arxiv_version","alias_value":"2209.14402v4","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14402","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"pith_short_12","alias_value":"WBLPV7OYU5QZ","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"pith_short_16","alias_value":"WBLPV7OYU5QZCF7N","created_at":"2026-07-05T08:31:38Z"},{"alias_kind":"pith_short_8","alias_value":"WBLPV7OY","created_at":"2026-07-05T08:31:38Z"}],"graph_snapshots":[{"event_id":"sha256:2497e6accff6941946b3abc55d57584e01aa9138804af7e691c0bcb1b38ccaaf","target":"graph","created_at":"2026-07-05T08:31:38Z","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/2209.14402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph Neural Networks (GNNs) are a popular class of machine learning models. Inspired by the learning to explain (L2X) paradigm, we propose L2XGNN, a framework for explainable GNNs which provides faithful explanations by design. L2XGNN learns a mechanism for selecting explanatory subgraphs (motifs) which are exclusively used in the GNNs message-passing operations. L2XGNN is able to select, for each input graph, a subgraph with specific properties such as being sparse and connected. Imposing such constraints on the motifs often leads to more interpretable and effective explanations. Experiments","authors_text":"Giuseppe Serra, Mathias Niepert","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T20:03:57Z","title":"L2XGNN: Learning to Explain Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14402","kind":"arxiv","version":4},"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:a8da26db4f70ea847461736a1b10bd1f7679cf24a49da07583987e2c9ceec4de","target":"record","created_at":"2026-07-05T08:31:38Z","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":"0a09dd58276a9282fd381d3a77eb77f4befc02c54a63c549e096f0a24aeaa9e6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T20:03:57Z","title_canon_sha256":"a8f632bd4c63a8fe653cb1c0c50f336c57a3795c077bb1a91b94f0b0ec25c740"},"schema_version":"1.0","source":{"id":"2209.14402","kind":"arxiv","version":4}},"canonical_sha256":"b056fafdd8a7619117edf4dff534064418d48707327306935b26d0ea12c15a45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b056fafdd8a7619117edf4dff534064418d48707327306935b26d0ea12c15a45","first_computed_at":"2026-07-05T08:31:38.256119Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:38.256119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hGUGDGtpeq4m3TuaE5pDHpyk+/61SbFiiKNDSj/WHsCJp01sp8bhQA8G/FZbguyNAv6N0EBkPU6qaA0Q+JNnDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:38.256534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.14402","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8da26db4f70ea847461736a1b10bd1f7679cf24a49da07583987e2c9ceec4de","sha256:2497e6accff6941946b3abc55d57584e01aa9138804af7e691c0bcb1b38ccaaf"],"state_sha256":"ff370a2726c465375c464102815643ff5644b23aaec3d37da2107cd806110414"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sgjVksghRAE3ZtqLBbEz4yxTAmHTcx5Pb9fDdCCbN80lEoBSmfB/wDJb4nKXVyY6VD10u9aIfKSbznzq4WT+AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T06:47:57.928892Z","bundle_sha256":"35490859abb919df3c0d1b52268f0d6eb4296ec361599e8d3789fa90895d955a"}}