{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:V6XXG3KH5CGYSVSUTFX7OJTLRY","short_pith_number":"pith:V6XXG3KH","canonical_record":{"source":{"id":"2010.05788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-12T15:33:13Z","cross_cats_sorted":[],"title_canon_sha256":"8416976e96a33d76b53d9d70d84cbfeb1d2bccc5f8bde63a226502e889fa53ec","abstract_canon_sha256":"0acc1326dfcc013a1156aeef387b2ca5f2d3d5b637ab9ac171a475954bead636"},"schema_version":"1.0"},"canonical_sha256":"afaf736d47e88d895654996ff7266b8e0896570beee3c8a9ad26ba7cac607242","source":{"kind":"arxiv","id":"2010.05788","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.05788","created_at":"2026-07-05T01:42:10Z"},{"alias_kind":"arxiv_version","alias_value":"2010.05788v1","created_at":"2026-07-05T01:42:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.05788","created_at":"2026-07-05T01:42:10Z"},{"alias_kind":"pith_short_12","alias_value":"V6XXG3KH5CGY","created_at":"2026-07-05T01:42:10Z"},{"alias_kind":"pith_short_16","alias_value":"V6XXG3KH5CGYSVSU","created_at":"2026-07-05T01:42:10Z"},{"alias_kind":"pith_short_8","alias_value":"V6XXG3KH","created_at":"2026-07-05T01:42:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:V6XXG3KH5CGYSVSUTFX7OJTLRY","target":"record","payload":{"canonical_record":{"source":{"id":"2010.05788","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-12T15:33:13Z","cross_cats_sorted":[],"title_canon_sha256":"8416976e96a33d76b53d9d70d84cbfeb1d2bccc5f8bde63a226502e889fa53ec","abstract_canon_sha256":"0acc1326dfcc013a1156aeef387b2ca5f2d3d5b637ab9ac171a475954bead636"},"schema_version":"1.0"},"canonical_sha256":"afaf736d47e88d895654996ff7266b8e0896570beee3c8a9ad26ba7cac607242","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:42:10.747430Z","signature_b64":"DOLkuGiDFu0ArVd0A8rW2plj5RS5YOj3oi+DzJwawg22UQvf1MEPPwfJvsMT1kOyaZkw6xCKitAgZIrt5HRsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afaf736d47e88d895654996ff7266b8e0896570beee3c8a9ad26ba7cac607242","last_reissued_at":"2026-07-05T01:42:10.746994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:42:10.746994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.05788","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:42:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bgExncSU4cXuJjej0cPcVaEgi05hvOUKHKgqBT4nkkZ1rzLgevUjcYrybw/pnH68FUIKX2cc6FP3GFLkiJ7PCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:05:52.625225Z"},"content_sha256":"1aa589fe27cd7e24351a04271f4d5daff09a9d54f20090e74ebf4efe8af3fa8d","schema_version":"1.0","event_id":"sha256:1aa589fe27cd7e24351a04271f4d5daff09a9d54f20090e74ebf4efe8af3fa8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:V6XXG3KH5CGYSVSUTFX7OJTLRY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Minh N. Vu, My T. Thai","submitted_at":"2020-10-12T15:33:13Z","abstract_excerpt":"In Graph Neural Networks (GNNs), the graph structure is incorporated into the learning of node representations. This complex structure makes explaining GNNs' predictions become much more challenging. In this paper, we propose PGM-Explainer, a Probabilistic Graphical Model (PGM) model-agnostic explainer for GNNs. Given a prediction to be explained, PGM-Explainer identifies crucial graph components and generates an explanation in form of a PGM approximating that prediction. Different from existing explainers for GNNs where the explanations are drawn from a set of linear functions of explained fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.05788","kind":"arxiv","version":1},"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/2010.05788/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":"2026-07-05T01:42:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JU1GPyoUL9sMAE9fGqa1ZLeASTghqOOy+lD3DcacSDiM4Skhnh+TtsMnWWeSZsBU+XNG+GfzxeXmgMl4Bfr0DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:05:52.625874Z"},"content_sha256":"f0c6ae3fa6326b2fcdfcad25712160de8fbb61d8541ff43a09c60c5358a96af9","schema_version":"1.0","event_id":"sha256:f0c6ae3fa6326b2fcdfcad25712160de8fbb61d8541ff43a09c60c5358a96af9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V6XXG3KH5CGYSVSUTFX7OJTLRY/bundle.json","state_url":"https://pith.science/pith/V6XXG3KH5CGYSVSUTFX7OJTLRY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V6XXG3KH5CGYSVSUTFX7OJTLRY/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":"2026-08-09T13:05:52Z","links":{"resolver":"https://pith.science/pith/V6XXG3KH5CGYSVSUTFX7OJTLRY","bundle":"https://pith.science/pith/V6XXG3KH5CGYSVSUTFX7OJTLRY/bundle.json","state":"https://pith.science/pith/V6XXG3KH5CGYSVSUTFX7OJTLRY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V6XXG3KH5CGYSVSUTFX7OJTLRY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:V6XXG3KH5CGYSVSUTFX7OJTLRY","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":"0acc1326dfcc013a1156aeef387b2ca5f2d3d5b637ab9ac171a475954bead636","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-12T15:33:13Z","title_canon_sha256":"8416976e96a33d76b53d9d70d84cbfeb1d2bccc5f8bde63a226502e889fa53ec"},"schema_version":"1.0","source":{"id":"2010.05788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.05788","created_at":"2026-07-05T01:42:10Z"},{"alias_kind":"arxiv_version","alias_value":"2010.05788v1","created_at":"2026-07-05T01:42:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.05788","created_at":"2026-07-05T01:42:10Z"},{"alias_kind":"pith_short_12","alias_value":"V6XXG3KH5CGY","created_at":"2026-07-05T01:42:10Z"},{"alias_kind":"pith_short_16","alias_value":"V6XXG3KH5CGYSVSU","created_at":"2026-07-05T01:42:10Z"},{"alias_kind":"pith_short_8","alias_value":"V6XXG3KH","created_at":"2026-07-05T01:42:10Z"}],"graph_snapshots":[{"event_id":"sha256:f0c6ae3fa6326b2fcdfcad25712160de8fbb61d8541ff43a09c60c5358a96af9","target":"graph","created_at":"2026-07-05T01:42:10Z","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/2010.05788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Graph Neural Networks (GNNs), the graph structure is incorporated into the learning of node representations. This complex structure makes explaining GNNs' predictions become much more challenging. In this paper, we propose PGM-Explainer, a Probabilistic Graphical Model (PGM) model-agnostic explainer for GNNs. Given a prediction to be explained, PGM-Explainer identifies crucial graph components and generates an explanation in form of a PGM approximating that prediction. Different from existing explainers for GNNs where the explanations are drawn from a set of linear functions of explained fe","authors_text":"Minh N. Vu, My T. Thai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-12T15:33:13Z","title":"PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.05788","kind":"arxiv","version":1},"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":"sha256:1aa589fe27cd7e24351a04271f4d5daff09a9d54f20090e74ebf4efe8af3fa8d","target":"record","created_at":"2026-07-05T01:42:10Z","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":"0acc1326dfcc013a1156aeef387b2ca5f2d3d5b637ab9ac171a475954bead636","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-12T15:33:13Z","title_canon_sha256":"8416976e96a33d76b53d9d70d84cbfeb1d2bccc5f8bde63a226502e889fa53ec"},"schema_version":"1.0","source":{"id":"2010.05788","kind":"arxiv","version":1}},"canonical_sha256":"afaf736d47e88d895654996ff7266b8e0896570beee3c8a9ad26ba7cac607242","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afaf736d47e88d895654996ff7266b8e0896570beee3c8a9ad26ba7cac607242","first_computed_at":"2026-07-05T01:42:10.746994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:42:10.746994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DOLkuGiDFu0ArVd0A8rW2plj5RS5YOj3oi+DzJwawg22UQvf1MEPPwfJvsMT1kOyaZkw6xCKitAgZIrt5HRsBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:42:10.747430Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.05788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1aa589fe27cd7e24351a04271f4d5daff09a9d54f20090e74ebf4efe8af3fa8d","sha256:f0c6ae3fa6326b2fcdfcad25712160de8fbb61d8541ff43a09c60c5358a96af9"],"state_sha256":"3a0b2f1eb73cfa855a7edd0af9db80890b88cd93ab257a9c77bdc7b3d17a1ac4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hmfyj8mAlBpkcbO6TeoE4kVVH4T2Q8XKKb2zff+WTvMLPkKpsVBbEz1RPW1B0iPe14ZL1RDdAWKZy30Fcr8xAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:05:52.632723Z","bundle_sha256":"7cf7b959e29a0f064d9e86deafd3c8f3e8ce92298ab1b868d01401f2f849135c"}}