{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TNIUFWDSSD52VA2IBK6BG5ZWEC","short_pith_number":"pith:TNIUFWDS","canonical_record":{"source":{"id":"2403.16846","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-25T15:07:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f661bc7bfc08d015f56454d4017620f17efed3cef22fac06855bcded2da2f4a","abstract_canon_sha256":"ea6978c2204b85c26a239276282168740b5e9402c88746a8d8a1d42bcdd382d9"},"schema_version":"1.0"},"canonical_sha256":"9b5142d87290fbaa83480abc137736209ecec0134220a3121eeb4de98e88ea90","source":{"kind":"arxiv","id":"2403.16846","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16846","created_at":"2026-07-05T11:33:14Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16846v2","created_at":"2026-07-05T11:33:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16846","created_at":"2026-07-05T11:33:14Z"},{"alias_kind":"pith_short_12","alias_value":"TNIUFWDSSD52","created_at":"2026-07-05T11:33:14Z"},{"alias_kind":"pith_short_16","alias_value":"TNIUFWDSSD52VA2I","created_at":"2026-07-05T11:33:14Z"},{"alias_kind":"pith_short_8","alias_value":"TNIUFWDS","created_at":"2026-07-05T11:33:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TNIUFWDSSD52VA2IBK6BG5ZWEC","target":"record","payload":{"canonical_record":{"source":{"id":"2403.16846","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-25T15:07:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f661bc7bfc08d015f56454d4017620f17efed3cef22fac06855bcded2da2f4a","abstract_canon_sha256":"ea6978c2204b85c26a239276282168740b5e9402c88746a8d8a1d42bcdd382d9"},"schema_version":"1.0"},"canonical_sha256":"9b5142d87290fbaa83480abc137736209ecec0134220a3121eeb4de98e88ea90","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:14.218760Z","signature_b64":"iQ0dxKjt9Gz1f5QEwfX7HaQvJazQYZJltWttrAZJY/coE32lXfAX90SmP5/reTTTwSPcb6et+6dzTKul2BY2BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b5142d87290fbaa83480abc137736209ecec0134220a3121eeb4de98e88ea90","last_reissued_at":"2026-07-05T11:33:14.218296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:14.218296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.16846","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":"2026-07-05T11:33:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O/GwT2mgrnP5klFD63auCQqiFT4NoACquYGpsDmzLEMp9WJ8bvvZ0JpfZf2aIFZFpv+Q2GRVJ3aeFvstcv11AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:14:48.734247Z"},"content_sha256":"51802ea7191f1de224b6d9d1663328fd39154805cd55278f8df1a2895c8ad3ac","schema_version":"1.0","event_id":"sha256:51802ea7191f1de224b6d9d1663328fd39154805cd55278f8df1a2895c8ad3ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TNIUFWDSSD52VA2IBK6BG5ZWEC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoDy: Counterfactual Explainers for Dynamic Graphs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniel Gomm, Michael F\\\"arber, Zhan Qu","submitted_at":"2024-03-25T15:07:50Z","abstract_excerpt":"Temporal Graph Neural Networks (TGNNs) are widely used to model dynamic systems where relationships and features evolve over time. Although TGNNs demonstrate strong predictive capabilities in these domains, their complex architectures pose significant challenges for explainability. Counterfactual explanation methods provide a promising solution by illustrating how modifications to input graphs can influence model predictions. To address this challenge, we present CoDy, Counterfactual Explainer for Dynamic Graphs, a model-agnostic, instance-level explanation approach that identifies counterfact"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16846","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/2403.16846/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":"2026-07-05T11:33:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0nJI7NIL85GiFWyjwH4pJu6h18Hyafw4R9gHbXb2ZAg8arkPvvatRoNrZDGizq06mwbdbBrPcawaa4vOW0jLAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:14:48.735182Z"},"content_sha256":"a8929048aec5a305a0c54f16ecf9b9ac35bfc8ca52c82082faa874ed17d2784d","schema_version":"1.0","event_id":"sha256:a8929048aec5a305a0c54f16ecf9b9ac35bfc8ca52c82082faa874ed17d2784d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TNIUFWDSSD52VA2IBK6BG5ZWEC/bundle.json","state_url":"https://pith.science/pith/TNIUFWDSSD52VA2IBK6BG5ZWEC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TNIUFWDSSD52VA2IBK6BG5ZWEC/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":"2026-08-05T06:14:48Z","links":{"resolver":"https://pith.science/pith/TNIUFWDSSD52VA2IBK6BG5ZWEC","bundle":"https://pith.science/pith/TNIUFWDSSD52VA2IBK6BG5ZWEC/bundle.json","state":"https://pith.science/pith/TNIUFWDSSD52VA2IBK6BG5ZWEC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TNIUFWDSSD52VA2IBK6BG5ZWEC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TNIUFWDSSD52VA2IBK6BG5ZWEC","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":"ea6978c2204b85c26a239276282168740b5e9402c88746a8d8a1d42bcdd382d9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-25T15:07:50Z","title_canon_sha256":"7f661bc7bfc08d015f56454d4017620f17efed3cef22fac06855bcded2da2f4a"},"schema_version":"1.0","source":{"id":"2403.16846","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.16846","created_at":"2026-07-05T11:33:14Z"},{"alias_kind":"arxiv_version","alias_value":"2403.16846v2","created_at":"2026-07-05T11:33:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16846","created_at":"2026-07-05T11:33:14Z"},{"alias_kind":"pith_short_12","alias_value":"TNIUFWDSSD52","created_at":"2026-07-05T11:33:14Z"},{"alias_kind":"pith_short_16","alias_value":"TNIUFWDSSD52VA2I","created_at":"2026-07-05T11:33:14Z"},{"alias_kind":"pith_short_8","alias_value":"TNIUFWDS","created_at":"2026-07-05T11:33:14Z"}],"graph_snapshots":[{"event_id":"sha256:a8929048aec5a305a0c54f16ecf9b9ac35bfc8ca52c82082faa874ed17d2784d","target":"graph","created_at":"2026-07-05T11:33:14Z","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/2403.16846/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Temporal Graph Neural Networks (TGNNs) are widely used to model dynamic systems where relationships and features evolve over time. Although TGNNs demonstrate strong predictive capabilities in these domains, their complex architectures pose significant challenges for explainability. Counterfactual explanation methods provide a promising solution by illustrating how modifications to input graphs can influence model predictions. To address this challenge, we present CoDy, Counterfactual Explainer for Dynamic Graphs, a model-agnostic, instance-level explanation approach that identifies counterfact","authors_text":"Daniel Gomm, Michael F\\\"arber, Zhan Qu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-25T15:07:50Z","title":"CoDy: Counterfactual Explainers for Dynamic Graphs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16846","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":"sha256:51802ea7191f1de224b6d9d1663328fd39154805cd55278f8df1a2895c8ad3ac","target":"record","created_at":"2026-07-05T11:33:14Z","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":"ea6978c2204b85c26a239276282168740b5e9402c88746a8d8a1d42bcdd382d9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-25T15:07:50Z","title_canon_sha256":"7f661bc7bfc08d015f56454d4017620f17efed3cef22fac06855bcded2da2f4a"},"schema_version":"1.0","source":{"id":"2403.16846","kind":"arxiv","version":2}},"canonical_sha256":"9b5142d87290fbaa83480abc137736209ecec0134220a3121eeb4de98e88ea90","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b5142d87290fbaa83480abc137736209ecec0134220a3121eeb4de98e88ea90","first_computed_at":"2026-07-05T11:33:14.218296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:14.218296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iQ0dxKjt9Gz1f5QEwfX7HaQvJazQYZJltWttrAZJY/coE32lXfAX90SmP5/reTTTwSPcb6et+6dzTKul2BY2BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:14.218760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.16846","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51802ea7191f1de224b6d9d1663328fd39154805cd55278f8df1a2895c8ad3ac","sha256:a8929048aec5a305a0c54f16ecf9b9ac35bfc8ca52c82082faa874ed17d2784d"],"state_sha256":"afd93bfd8eae813638ff0c1f211900847bb1e49290120fae1158cbb3b59a3d33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UYc/hrpNioD1AS6JbrkoqrnoHWT5t8CCG5hhWGnMSvtB6y+UFnfMSncK8nMF9rkaTnDP+GD3Cd9Squk5VwYPCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:14:48.740389Z","bundle_sha256":"926d5a59800d1f726e6224256854bfa086317f1fad5110ca6538e777f7459ed7"}}