{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3NBW2D76CPUI4H3WPK6GCV7VW3","short_pith_number":"pith:3NBW2D76","canonical_record":{"source":{"id":"1906.00554","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T03:53:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3d8980557d874f28c5dab440bc8e1d68cdbb88185aef9da41fc4b0a266454008","abstract_canon_sha256":"ab5e02bc78a1c94002daa08e7f392431a1376fdff56a0f947acb93b8e6a9ef27"},"schema_version":"1.0"},"canonical_sha256":"db436d0ffe13e88e1f767abc6157f5b6dc04a1e42458c6d8fda29d2abd9d160c","source":{"kind":"arxiv","id":"1906.00554","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00554","created_at":"2026-05-17T23:44:24Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00554v1","created_at":"2026-05-17T23:44:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00554","created_at":"2026-05-17T23:44:24Z"},{"alias_kind":"pith_short_12","alias_value":"3NBW2D76CPUI","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"3NBW2D76CPUI4H3W","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"3NBW2D76","created_at":"2026-05-18T12:33:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3NBW2D76CPUI4H3WPK6GCV7VW3","target":"record","payload":{"canonical_record":{"source":{"id":"1906.00554","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T03:53:27Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3d8980557d874f28c5dab440bc8e1d68cdbb88185aef9da41fc4b0a266454008","abstract_canon_sha256":"ab5e02bc78a1c94002daa08e7f392431a1376fdff56a0f947acb93b8e6a9ef27"},"schema_version":"1.0"},"canonical_sha256":"db436d0ffe13e88e1f767abc6157f5b6dc04a1e42458c6d8fda29d2abd9d160c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:24.553096Z","signature_b64":"8NUFjSWwgh7SkyjW/7bJeZTVpukgXEr+TLiILVDp17b6i+o364JzjOFa1zDdkkDm+HdU7Z5db4iCxjHgxAbfDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db436d0ffe13e88e1f767abc6157f5b6dc04a1e42458c6d8fda29d2abd9d160c","last_reissued_at":"2026-05-17T23:44:24.552305Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:24.552305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.00554","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":"2026-05-17T23:44:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HvOj34o+fB2XwrbIMRCyjKEomv3njJjJZM8LONnkmNNPFG983GmrtIgrx/L45QLRSfwiU+8cyAbTXcELd0XSBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T14:24:22.865357Z"},"content_sha256":"65401b9fb79b8323face3dc3ca52295847a8580aacdb752ee5004349e47f8c38","schema_version":"1.0","event_id":"sha256:65401b9fb79b8323face3dc3ca52295847a8580aacdb752ee5004349e47f8c38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3NBW2D76CPUI4H3WPK6GCV7VW3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Factor Graph Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fan Wu, Wee Sun Lee, Zhen Zhang","submitted_at":"2019-06-03T03:53:27Z","abstract_excerpt":"Most of the successful deep neural network architectures are structured, often consisting of elements like convolutional neural networks and gated recurrent neural networks. Recently, graph neural networks have been successfully applied to graph structured data such as point cloud and molecular data. These networks often only consider pairwise dependencies, as they operate on a graph structure. We generalize the graph neural network into a factor graph neural network (FGNN) in order to capture higher order dependencies. We show that FGNN is able to represent Max-Product Belief Propagation, an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00554","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":""},"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":"2026-05-17T23:44:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jC5LtbkdZE9CKT7qQ7cs75zCwsqaseIi5/tQWM6tYYgsOHeLe3a7THg+/T2qzlR+3+fhrCwB9AMxQoTv6qfBAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T14:24:22.866122Z"},"content_sha256":"41681d1591b8c022a178b5b39e0eb9917198c23f7edd44b3423cc6b798dfc089","schema_version":"1.0","event_id":"sha256:41681d1591b8c022a178b5b39e0eb9917198c23f7edd44b3423cc6b798dfc089"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3NBW2D76CPUI4H3WPK6GCV7VW3/bundle.json","state_url":"https://pith.science/pith/3NBW2D76CPUI4H3WPK6GCV7VW3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3NBW2D76CPUI4H3WPK6GCV7VW3/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":"2026-05-25T14:24:22Z","links":{"resolver":"https://pith.science/pith/3NBW2D76CPUI4H3WPK6GCV7VW3","bundle":"https://pith.science/pith/3NBW2D76CPUI4H3WPK6GCV7VW3/bundle.json","state":"https://pith.science/pith/3NBW2D76CPUI4H3WPK6GCV7VW3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3NBW2D76CPUI4H3WPK6GCV7VW3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3NBW2D76CPUI4H3WPK6GCV7VW3","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":"ab5e02bc78a1c94002daa08e7f392431a1376fdff56a0f947acb93b8e6a9ef27","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T03:53:27Z","title_canon_sha256":"3d8980557d874f28c5dab440bc8e1d68cdbb88185aef9da41fc4b0a266454008"},"schema_version":"1.0","source":{"id":"1906.00554","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00554","created_at":"2026-05-17T23:44:24Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00554v1","created_at":"2026-05-17T23:44:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00554","created_at":"2026-05-17T23:44:24Z"},{"alias_kind":"pith_short_12","alias_value":"3NBW2D76CPUI","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"3NBW2D76CPUI4H3W","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"3NBW2D76","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:41681d1591b8c022a178b5b39e0eb9917198c23f7edd44b3423cc6b798dfc089","target":"graph","created_at":"2026-05-17T23:44:24Z","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"},"paper":{"abstract_excerpt":"Most of the successful deep neural network architectures are structured, often consisting of elements like convolutional neural networks and gated recurrent neural networks. Recently, graph neural networks have been successfully applied to graph structured data such as point cloud and molecular data. These networks often only consider pairwise dependencies, as they operate on a graph structure. We generalize the graph neural network into a factor graph neural network (FGNN) in order to capture higher order dependencies. We show that FGNN is able to represent Max-Product Belief Propagation, an ","authors_text":"Fan Wu, Wee Sun Lee, Zhen Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T03:53:27Z","title":"Factor Graph Neural Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00554","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":"sha256:65401b9fb79b8323face3dc3ca52295847a8580aacdb752ee5004349e47f8c38","target":"record","created_at":"2026-05-17T23:44:24Z","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":"ab5e02bc78a1c94002daa08e7f392431a1376fdff56a0f947acb93b8e6a9ef27","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T03:53:27Z","title_canon_sha256":"3d8980557d874f28c5dab440bc8e1d68cdbb88185aef9da41fc4b0a266454008"},"schema_version":"1.0","source":{"id":"1906.00554","kind":"arxiv","version":1}},"canonical_sha256":"db436d0ffe13e88e1f767abc6157f5b6dc04a1e42458c6d8fda29d2abd9d160c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db436d0ffe13e88e1f767abc6157f5b6dc04a1e42458c6d8fda29d2abd9d160c","first_computed_at":"2026-05-17T23:44:24.552305Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:24.552305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8NUFjSWwgh7SkyjW/7bJeZTVpukgXEr+TLiILVDp17b6i+o364JzjOFa1zDdkkDm+HdU7Z5db4iCxjHgxAbfDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:24.553096Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.00554","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65401b9fb79b8323face3dc3ca52295847a8580aacdb752ee5004349e47f8c38","sha256:41681d1591b8c022a178b5b39e0eb9917198c23f7edd44b3423cc6b798dfc089"],"state_sha256":"9a08382c9d831065b95908eff2c0ba35048f6aaff505525337318fa53c3feac3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6qVDKiwnKJAIwRzpxyF8Mn0V0WjParhwWi/dnl2C9mi9dn7o3sWy7k5uam5V7bbqDBe5jfAyO1pwJQj1Fbj0CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T14:24:22.870288Z","bundle_sha256":"28df31670895004f66ea939b1226386f4f5005b673aa223c9843d54f4935e23e"}}