{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:OBAMRXRU2D4LP3O37LWA2F6GEF","short_pith_number":"pith:OBAMRXRU","canonical_record":{"source":{"id":"2104.10482","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-18T10:40:37Z","cross_cats_sorted":[],"title_canon_sha256":"7bad62cac3b64a54e83b8d4248a54b789ebf704c0e21dd204225b6d328878461","abstract_canon_sha256":"a2492a7fab8128eaef2b895233ba34bec8fb07baa4d796d7ddd65b897354afd8"},"schema_version":"1.0"},"canonical_sha256":"7040c8de34d0f8b7eddbfaec0d17c62179874260097becb62a0cc12f0c36910d","source":{"kind":"arxiv","id":"2104.10482","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.10482","created_at":"2026-07-05T02:57:19Z"},{"alias_kind":"arxiv_version","alias_value":"2104.10482v2","created_at":"2026-07-05T02:57:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.10482","created_at":"2026-07-05T02:57:19Z"},{"alias_kind":"pith_short_12","alias_value":"OBAMRXRU2D4L","created_at":"2026-07-05T02:57:19Z"},{"alias_kind":"pith_short_16","alias_value":"OBAMRXRU2D4LP3O3","created_at":"2026-07-05T02:57:19Z"},{"alias_kind":"pith_short_8","alias_value":"OBAMRXRU","created_at":"2026-07-05T02:57:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:OBAMRXRU2D4LP3O37LWA2F6GEF","target":"record","payload":{"canonical_record":{"source":{"id":"2104.10482","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-18T10:40:37Z","cross_cats_sorted":[],"title_canon_sha256":"7bad62cac3b64a54e83b8d4248a54b789ebf704c0e21dd204225b6d328878461","abstract_canon_sha256":"a2492a7fab8128eaef2b895233ba34bec8fb07baa4d796d7ddd65b897354afd8"},"schema_version":"1.0"},"canonical_sha256":"7040c8de34d0f8b7eddbfaec0d17c62179874260097becb62a0cc12f0c36910d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:57:19.732947Z","signature_b64":"R510Vo4hhbKBNGYl/Pg5pm2FZy39KMcp6gJPiQwqb6Lp79AcVMjYtcH3lFfs3nO3/aqefCwDvSfSIumEGZJODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7040c8de34d0f8b7eddbfaec0d17c62179874260097becb62a0cc12f0c36910d","last_reissued_at":"2026-07-05T02:57:19.732430Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:57:19.732430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.10482","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:57:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WpUXvPjfxT2W3YE/Es1zacv88UkWOfVcIhU83SIJrZXF1ohO8MkLJQW6wXZd9WOEDy/C2KHCfV9uY2dN//mfDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:55:17.877682Z"},"content_sha256":"e20a77a1f6884dcd7b2ef020735e53ca974245e4dcef2e80bb5d9605d76fe772","schema_version":"1.0","event_id":"sha256:e20a77a1f6884dcd7b2ef020735e53ca974245e4dcef2e80bb5d9605d76fe772"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:OBAMRXRU2D4LP3O37LWA2F6GEF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GraphSVX: Shapley Value Explanations for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandre Duval, Fragkiskos D. Malliaros","submitted_at":"2021-04-18T10:40:37Z","abstract_excerpt":"Graph Neural Networks (GNNs) achieve significant performance for various learning tasks on geometric data due to the incorporation of graph structure into the learning of node representations, which renders their comprehension challenging. In this paper, we first propose a unified framework satisfied by most existing GNN explainers. Then, we introduce GraphSVX, a post hoc local model-agnostic explanation method specifically designed for GNNs. GraphSVX is a decomposition technique that captures the \"fair\" contribution of each feature and node towards the explained prediction by constructing a s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.10482","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/2104.10482/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":"2026-07-05T02:57:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tXffunazBiO3VHdjQnRL/PFmuKR8KBWYhDWtV91rgrWzqa89nWcROi7d3PC6ne26KdbV1bqeB5EZVG7mQkKmBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:55:17.878465Z"},"content_sha256":"26a9e5dc8dce4124a951680d0d9a3a2b8c9e61a17220a3297f0cd94f7325d70f","schema_version":"1.0","event_id":"sha256:26a9e5dc8dce4124a951680d0d9a3a2b8c9e61a17220a3297f0cd94f7325d70f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OBAMRXRU2D4LP3O37LWA2F6GEF/bundle.json","state_url":"https://pith.science/pith/OBAMRXRU2D4LP3O37LWA2F6GEF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OBAMRXRU2D4LP3O37LWA2F6GEF/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":"2026-08-05T08:55:17Z","links":{"resolver":"https://pith.science/pith/OBAMRXRU2D4LP3O37LWA2F6GEF","bundle":"https://pith.science/pith/OBAMRXRU2D4LP3O37LWA2F6GEF/bundle.json","state":"https://pith.science/pith/OBAMRXRU2D4LP3O37LWA2F6GEF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OBAMRXRU2D4LP3O37LWA2F6GEF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OBAMRXRU2D4LP3O37LWA2F6GEF","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":"a2492a7fab8128eaef2b895233ba34bec8fb07baa4d796d7ddd65b897354afd8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-18T10:40:37Z","title_canon_sha256":"7bad62cac3b64a54e83b8d4248a54b789ebf704c0e21dd204225b6d328878461"},"schema_version":"1.0","source":{"id":"2104.10482","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.10482","created_at":"2026-07-05T02:57:19Z"},{"alias_kind":"arxiv_version","alias_value":"2104.10482v2","created_at":"2026-07-05T02:57:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.10482","created_at":"2026-07-05T02:57:19Z"},{"alias_kind":"pith_short_12","alias_value":"OBAMRXRU2D4L","created_at":"2026-07-05T02:57:19Z"},{"alias_kind":"pith_short_16","alias_value":"OBAMRXRU2D4LP3O3","created_at":"2026-07-05T02:57:19Z"},{"alias_kind":"pith_short_8","alias_value":"OBAMRXRU","created_at":"2026-07-05T02:57:19Z"}],"graph_snapshots":[{"event_id":"sha256:26a9e5dc8dce4124a951680d0d9a3a2b8c9e61a17220a3297f0cd94f7325d70f","target":"graph","created_at":"2026-07-05T02:57:19Z","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/2104.10482/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph Neural Networks (GNNs) achieve significant performance for various learning tasks on geometric data due to the incorporation of graph structure into the learning of node representations, which renders their comprehension challenging. In this paper, we first propose a unified framework satisfied by most existing GNN explainers. Then, we introduce GraphSVX, a post hoc local model-agnostic explanation method specifically designed for GNNs. GraphSVX is a decomposition technique that captures the \"fair\" contribution of each feature and node towards the explained prediction by constructing a s","authors_text":"Alexandre Duval, Fragkiskos D. Malliaros","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-18T10:40:37Z","title":"GraphSVX: Shapley Value Explanations for Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.10482","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:e20a77a1f6884dcd7b2ef020735e53ca974245e4dcef2e80bb5d9605d76fe772","target":"record","created_at":"2026-07-05T02:57:19Z","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":"a2492a7fab8128eaef2b895233ba34bec8fb07baa4d796d7ddd65b897354afd8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-18T10:40:37Z","title_canon_sha256":"7bad62cac3b64a54e83b8d4248a54b789ebf704c0e21dd204225b6d328878461"},"schema_version":"1.0","source":{"id":"2104.10482","kind":"arxiv","version":2}},"canonical_sha256":"7040c8de34d0f8b7eddbfaec0d17c62179874260097becb62a0cc12f0c36910d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7040c8de34d0f8b7eddbfaec0d17c62179874260097becb62a0cc12f0c36910d","first_computed_at":"2026-07-05T02:57:19.732430Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:57:19.732430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R510Vo4hhbKBNGYl/Pg5pm2FZy39KMcp6gJPiQwqb6Lp79AcVMjYtcH3lFfs3nO3/aqefCwDvSfSIumEGZJODQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:57:19.732947Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.10482","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e20a77a1f6884dcd7b2ef020735e53ca974245e4dcef2e80bb5d9605d76fe772","sha256:26a9e5dc8dce4124a951680d0d9a3a2b8c9e61a17220a3297f0cd94f7325d70f"],"state_sha256":"381a26dc264c91e833dbe0e63d3d391dfe5233e409570da1a74bcc77552952d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YG8Ka4DdO+FyRFd87SQPDhqLJSXfn7/8hykMlIS6IzUhhLavl+xrqyjyvJpSdDXzWYhW3S+2NHeiVw851fDrCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:55:17.884602Z","bundle_sha256":"6c708dd31912117a798b946b934f9b13913b520553a74fff529215cfdd6be8c4"}}