{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YFRRWTZUZYXRPUEJQ4VU5TW6EU","short_pith_number":"pith:YFRRWTZU","canonical_record":{"source":{"id":"2403.06425","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T04:26:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7eb0cfd71f6b03d78987bacc6c1a21ce4f3e28f2ecae9eb04cc643e3cea139cc","abstract_canon_sha256":"477f928031a2d4bdea12b4aa5e71e333d978a7c922aed300c63802e6a0447eb2"},"schema_version":"1.0"},"canonical_sha256":"c1631b4f34ce2f17d089872b4ecede252933ffd7e7db0f8fd9eb67c06e81ffa2","source":{"kind":"arxiv","id":"2403.06425","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06425","created_at":"2026-07-05T07:54:37Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06425v1","created_at":"2026-07-05T07:54:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06425","created_at":"2026-07-05T07:54:37Z"},{"alias_kind":"pith_short_12","alias_value":"YFRRWTZUZYXR","created_at":"2026-07-05T07:54:37Z"},{"alias_kind":"pith_short_16","alias_value":"YFRRWTZUZYXRPUEJ","created_at":"2026-07-05T07:54:37Z"},{"alias_kind":"pith_short_8","alias_value":"YFRRWTZU","created_at":"2026-07-05T07:54:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YFRRWTZUZYXRPUEJQ4VU5TW6EU","target":"record","payload":{"canonical_record":{"source":{"id":"2403.06425","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T04:26:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7eb0cfd71f6b03d78987bacc6c1a21ce4f3e28f2ecae9eb04cc643e3cea139cc","abstract_canon_sha256":"477f928031a2d4bdea12b4aa5e71e333d978a7c922aed300c63802e6a0447eb2"},"schema_version":"1.0"},"canonical_sha256":"c1631b4f34ce2f17d089872b4ecede252933ffd7e7db0f8fd9eb67c06e81ffa2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:37.906857Z","signature_b64":"wOg2eCXDAaN9q2GzJUAStOCOuUjvYUaVjXjTLi+g+WLambCK8EyAKNNHgOWy31jxk/xZ1zRRtCoYC03yd/Y+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1631b4f34ce2f17d089872b4ecede252933ffd7e7db0f8fd9eb67c06e81ffa2","last_reissued_at":"2026-07-05T07:54:37.906327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:37.906327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.06425","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":"2026-07-05T07:54:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9dioAH3X4qpQIfUmYcrid8GvCXGpVJz1VTb+0KZqf2MfzQYOYfGJeQb/05TepiQAxJ87/d6LsYWYF9GkWKgADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:56:03.612124Z"},"content_sha256":"785ecdc36167dfbd88a30b51ef8e18a3c75d86e84b5fcca7435c417f0910aa9a","schema_version":"1.0","event_id":"sha256:785ecdc36167dfbd88a30b51ef8e18a3c75d86e84b5fcca7435c417f0910aa9a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YFRRWTZUZYXRPUEJQ4VU5TW6EU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Differential Geometric View and Explainability of GNN on Evolving Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Sihong Xie, Xi Zhang, Yazheng Liu","submitted_at":"2024-03-11T04:26:18Z","abstract_excerpt":"Graphs are ubiquitous in social networks and biochemistry, where Graph Neural Networks (GNN) are the state-of-the-art models for prediction. Graphs can be evolving and it is vital to formally model and understand how a trained GNN responds to graph evolution. We propose a smooth parameterization of the GNN predicted distributions using axiomatic attribution, where the distributions are on a low-dimensional manifold within a high-dimensional embedding space. We exploit the differential geometric viewpoint to model distributional evolution as smooth curves on the manifold. We reparameterize fami"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06425","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/2403.06425/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":"2026-07-05T07:54:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dZ/2cevWaGeXlxTHC6tn7EnDveAG6b/fD2PBf0m6kcJiN+VE2GkxAIh4xuVPq9/k62dzSlNkykfFe98w7SflBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T06:56:03.612633Z"},"content_sha256":"1cb4c3d26f050f8ef405602c67942af17d60bd864d2446779df87371b5ed116e","schema_version":"1.0","event_id":"sha256:1cb4c3d26f050f8ef405602c67942af17d60bd864d2446779df87371b5ed116e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YFRRWTZUZYXRPUEJQ4VU5TW6EU/bundle.json","state_url":"https://pith.science/pith/YFRRWTZUZYXRPUEJQ4VU5TW6EU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YFRRWTZUZYXRPUEJQ4VU5TW6EU/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":"2026-08-17T06:56:03Z","links":{"resolver":"https://pith.science/pith/YFRRWTZUZYXRPUEJQ4VU5TW6EU","bundle":"https://pith.science/pith/YFRRWTZUZYXRPUEJQ4VU5TW6EU/bundle.json","state":"https://pith.science/pith/YFRRWTZUZYXRPUEJQ4VU5TW6EU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YFRRWTZUZYXRPUEJQ4VU5TW6EU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YFRRWTZUZYXRPUEJQ4VU5TW6EU","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":"477f928031a2d4bdea12b4aa5e71e333d978a7c922aed300c63802e6a0447eb2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T04:26:18Z","title_canon_sha256":"7eb0cfd71f6b03d78987bacc6c1a21ce4f3e28f2ecae9eb04cc643e3cea139cc"},"schema_version":"1.0","source":{"id":"2403.06425","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06425","created_at":"2026-07-05T07:54:37Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06425v1","created_at":"2026-07-05T07:54:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06425","created_at":"2026-07-05T07:54:37Z"},{"alias_kind":"pith_short_12","alias_value":"YFRRWTZUZYXR","created_at":"2026-07-05T07:54:37Z"},{"alias_kind":"pith_short_16","alias_value":"YFRRWTZUZYXRPUEJ","created_at":"2026-07-05T07:54:37Z"},{"alias_kind":"pith_short_8","alias_value":"YFRRWTZU","created_at":"2026-07-05T07:54:37Z"}],"graph_snapshots":[{"event_id":"sha256:1cb4c3d26f050f8ef405602c67942af17d60bd864d2446779df87371b5ed116e","target":"graph","created_at":"2026-07-05T07:54:37Z","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/2403.06425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graphs are ubiquitous in social networks and biochemistry, where Graph Neural Networks (GNN) are the state-of-the-art models for prediction. Graphs can be evolving and it is vital to formally model and understand how a trained GNN responds to graph evolution. We propose a smooth parameterization of the GNN predicted distributions using axiomatic attribution, where the distributions are on a low-dimensional manifold within a high-dimensional embedding space. We exploit the differential geometric viewpoint to model distributional evolution as smooth curves on the manifold. We reparameterize fami","authors_text":"Sihong Xie, Xi Zhang, Yazheng Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T04:26:18Z","title":"A Differential Geometric View and Explainability of GNN on Evolving Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06425","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":"sha256:785ecdc36167dfbd88a30b51ef8e18a3c75d86e84b5fcca7435c417f0910aa9a","target":"record","created_at":"2026-07-05T07:54:37Z","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":"477f928031a2d4bdea12b4aa5e71e333d978a7c922aed300c63802e6a0447eb2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-11T04:26:18Z","title_canon_sha256":"7eb0cfd71f6b03d78987bacc6c1a21ce4f3e28f2ecae9eb04cc643e3cea139cc"},"schema_version":"1.0","source":{"id":"2403.06425","kind":"arxiv","version":1}},"canonical_sha256":"c1631b4f34ce2f17d089872b4ecede252933ffd7e7db0f8fd9eb67c06e81ffa2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1631b4f34ce2f17d089872b4ecede252933ffd7e7db0f8fd9eb67c06e81ffa2","first_computed_at":"2026-07-05T07:54:37.906327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:37.906327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wOg2eCXDAaN9q2GzJUAStOCOuUjvYUaVjXjTLi+g+WLambCK8EyAKNNHgOWy31jxk/xZ1zRRtCoYC03yd/Y+Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:37.906857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06425","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:785ecdc36167dfbd88a30b51ef8e18a3c75d86e84b5fcca7435c417f0910aa9a","sha256:1cb4c3d26f050f8ef405602c67942af17d60bd864d2446779df87371b5ed116e"],"state_sha256":"9d6e53e657be9ef855a0910ee41abfa124d50f3285b39015eecf834a90b9e459"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bW7w8wam4AAr5+rFjqDePp5e72GaDNGY6ImbGFF2Qgo1upYTfeEppUROfMH04wj2sUFC8f1O3+Uk1YIgMC52Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T06:56:03.618247Z","bundle_sha256":"2b384c56c1283052efee81c3f5b9e80b081c12067b8ccb7e5200a9de019d59cb"}}