{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:YOWSBOSU2VTMDSADF7ZXDZVSOZ","short_pith_number":"pith:YOWSBOSU","canonical_record":{"source":{"id":"2202.08335","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-16T21:11:47Z","cross_cats_sorted":[],"title_canon_sha256":"d6119b3fe5b89313486af12e8ae7addfa302463cfeeeaf4a9ebdf8bab8aa8b88","abstract_canon_sha256":"f41131953a1afe0b05659201c1c25da6c34157064bbfdeb772d217ae92fc9637"},"schema_version":"1.0"},"canonical_sha256":"c3ad20ba54d566c1c8032ff371e6b2764861bb1917d57ea62a9c1d731d78181d","source":{"kind":"arxiv","id":"2202.08335","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.08335","created_at":"2026-07-05T05:00:26Z"},{"alias_kind":"arxiv_version","alias_value":"2202.08335v2","created_at":"2026-07-05T05:00:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.08335","created_at":"2026-07-05T05:00:26Z"},{"alias_kind":"pith_short_12","alias_value":"YOWSBOSU2VTM","created_at":"2026-07-05T05:00:26Z"},{"alias_kind":"pith_short_16","alias_value":"YOWSBOSU2VTMDSAD","created_at":"2026-07-05T05:00:26Z"},{"alias_kind":"pith_short_8","alias_value":"YOWSBOSU","created_at":"2026-07-05T05:00:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:YOWSBOSU2VTMDSADF7ZXDZVSOZ","target":"record","payload":{"canonical_record":{"source":{"id":"2202.08335","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-16T21:11:47Z","cross_cats_sorted":[],"title_canon_sha256":"d6119b3fe5b89313486af12e8ae7addfa302463cfeeeaf4a9ebdf8bab8aa8b88","abstract_canon_sha256":"f41131953a1afe0b05659201c1c25da6c34157064bbfdeb772d217ae92fc9637"},"schema_version":"1.0"},"canonical_sha256":"c3ad20ba54d566c1c8032ff371e6b2764861bb1917d57ea62a9c1d731d78181d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:00:26.367963Z","signature_b64":"Ron4Xn3kT4EInADPl2AVfbx+VoHpwP87s5lhtsXfsuUQQCV+zlLDTRNWqdVoa/TT4ZhwFzdjaGEB/7dLWv6+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3ad20ba54d566c1c8032ff371e6b2764861bb1917d57ea62a9c1d731d78181d","last_reissued_at":"2026-07-05T05:00:26.367504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:00:26.367504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.08335","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":"2026-07-05T05:00:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nJFj26u/kEtevCJIII1vkAeye134j5o9ohMk5LF/imTMPZhDDRAcX8EP9AIiZnPO3gJuH2LaggJesBZH8C20DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T23:07:39.370698Z"},"content_sha256":"d89bfcd3849d8234a9e4a8b6aaa3af46fe76985b3a5283e70b29d0bbfb83fb65","schema_version":"1.0","event_id":"sha256:d89bfcd3849d8234a9e4a8b6aaa3af46fe76985b3a5283e70b29d0bbfb83fb65"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:YOWSBOSU2VTMDSADF7ZXDZVSOZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task-Agnostic Graph Explanations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Edward Huang, Karthik Subbian, Nikhil Rao, Shuiwang Ji, Sumeet Katariya, Xianfeng Tang, Yaochen Xie","submitted_at":"2022-02-16T21:11:47Z","abstract_excerpt":"Graph Neural Networks (GNNs) have emerged as powerful tools to encode graph-structured data. Due to their broad applications, there is an increasing need to develop tools to explain how GNNs make decisions given graph-structured data. Existing learning-based GNN explanation approaches are task-specific in training and hence suffer from crucial drawbacks. Specifically, they are incapable of producing explanations for a multitask prediction model with a single explainer. They are also unable to provide explanations in cases where the GNN is trained in a self-supervised manner, and the resulting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.08335","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/2202.08335/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":"2026-07-05T05:00:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/qRDyNJH4/YaPKQqMSnlBokEN5sr9QoYT2+ncXI05FH4Qb9C3WTarqK6ViKAGB3ABFrGrheZ9cqrJRDEEB4fAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T23:07:39.371073Z"},"content_sha256":"7def22accfee5825e9e21a79f7c9ed31e191a7711a689291f2aecca979864966","schema_version":"1.0","event_id":"sha256:7def22accfee5825e9e21a79f7c9ed31e191a7711a689291f2aecca979864966"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YOWSBOSU2VTMDSADF7ZXDZVSOZ/bundle.json","state_url":"https://pith.science/pith/YOWSBOSU2VTMDSADF7ZXDZVSOZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YOWSBOSU2VTMDSADF7ZXDZVSOZ/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":"2026-07-09T23:07:39Z","links":{"resolver":"https://pith.science/pith/YOWSBOSU2VTMDSADF7ZXDZVSOZ","bundle":"https://pith.science/pith/YOWSBOSU2VTMDSADF7ZXDZVSOZ/bundle.json","state":"https://pith.science/pith/YOWSBOSU2VTMDSADF7ZXDZVSOZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YOWSBOSU2VTMDSADF7ZXDZVSOZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YOWSBOSU2VTMDSADF7ZXDZVSOZ","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":"f41131953a1afe0b05659201c1c25da6c34157064bbfdeb772d217ae92fc9637","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-16T21:11:47Z","title_canon_sha256":"d6119b3fe5b89313486af12e8ae7addfa302463cfeeeaf4a9ebdf8bab8aa8b88"},"schema_version":"1.0","source":{"id":"2202.08335","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.08335","created_at":"2026-07-05T05:00:26Z"},{"alias_kind":"arxiv_version","alias_value":"2202.08335v2","created_at":"2026-07-05T05:00:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.08335","created_at":"2026-07-05T05:00:26Z"},{"alias_kind":"pith_short_12","alias_value":"YOWSBOSU2VTM","created_at":"2026-07-05T05:00:26Z"},{"alias_kind":"pith_short_16","alias_value":"YOWSBOSU2VTMDSAD","created_at":"2026-07-05T05:00:26Z"},{"alias_kind":"pith_short_8","alias_value":"YOWSBOSU","created_at":"2026-07-05T05:00:26Z"}],"graph_snapshots":[{"event_id":"sha256:7def22accfee5825e9e21a79f7c9ed31e191a7711a689291f2aecca979864966","target":"graph","created_at":"2026-07-05T05:00:26Z","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/2202.08335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph Neural Networks (GNNs) have emerged as powerful tools to encode graph-structured data. Due to their broad applications, there is an increasing need to develop tools to explain how GNNs make decisions given graph-structured data. Existing learning-based GNN explanation approaches are task-specific in training and hence suffer from crucial drawbacks. Specifically, they are incapable of producing explanations for a multitask prediction model with a single explainer. They are also unable to provide explanations in cases where the GNN is trained in a self-supervised manner, and the resulting ","authors_text":"Edward Huang, Karthik Subbian, Nikhil Rao, Shuiwang Ji, Sumeet Katariya, Xianfeng Tang, Yaochen Xie","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-16T21:11:47Z","title":"Task-Agnostic Graph Explanations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.08335","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:d89bfcd3849d8234a9e4a8b6aaa3af46fe76985b3a5283e70b29d0bbfb83fb65","target":"record","created_at":"2026-07-05T05:00:26Z","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":"f41131953a1afe0b05659201c1c25da6c34157064bbfdeb772d217ae92fc9637","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-16T21:11:47Z","title_canon_sha256":"d6119b3fe5b89313486af12e8ae7addfa302463cfeeeaf4a9ebdf8bab8aa8b88"},"schema_version":"1.0","source":{"id":"2202.08335","kind":"arxiv","version":2}},"canonical_sha256":"c3ad20ba54d566c1c8032ff371e6b2764861bb1917d57ea62a9c1d731d78181d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3ad20ba54d566c1c8032ff371e6b2764861bb1917d57ea62a9c1d731d78181d","first_computed_at":"2026-07-05T05:00:26.367504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:00:26.367504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ron4Xn3kT4EInADPl2AVfbx+VoHpwP87s5lhtsXfsuUQQCV+zlLDTRNWqdVoa/TT4ZhwFzdjaGEB/7dLWv6+DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:00:26.367963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.08335","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d89bfcd3849d8234a9e4a8b6aaa3af46fe76985b3a5283e70b29d0bbfb83fb65","sha256:7def22accfee5825e9e21a79f7c9ed31e191a7711a689291f2aecca979864966"],"state_sha256":"59e9a7f9b78e8489ac404c4a60d9a919bcd1319bd6c97a77446cb1c9096437fb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B7z48j1F8TzdNSSUeilO4Ptn3rU4omiAfrh2EuaYC+2CDH1VUCja3dSqJaHXYfV2W+5tLZSc1GA842c6SRwXCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T23:07:39.373118Z","bundle_sha256":"74bca7a6a1d61a83a070288ee20fa707554a98d804deadab4e1d454c6e9038d4"}}