{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6LXCYT7FKYE76NGIZ4Q3PMF4EV","short_pith_number":"pith:6LXCYT7F","canonical_record":{"source":{"id":"1802.09405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-02-26T15:36:56Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"6c7d8b1e2bfcf28f98efbea507ca155f98b9bfebfb54ebc3fb41c7f41cf9c1b1","abstract_canon_sha256":"41c2c06f7b1b6900d827db1c9da2cded4d366129ac7051f5dd6bdfc10a60230f"},"schema_version":"1.0"},"canonical_sha256":"f2ee2c4fe55609ff34c8cf21b7b0bc256e33aa37453e080f1c0e9c8a892f6342","source":{"kind":"arxiv","id":"1802.09405","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09405","created_at":"2026-05-18T00:22:33Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09405v1","created_at":"2026-05-18T00:22:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09405","created_at":"2026-05-18T00:22:33Z"},{"alias_kind":"pith_short_12","alias_value":"6LXCYT7FKYE7","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"6LXCYT7FKYE76NGI","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"6LXCYT7F","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6LXCYT7FKYE76NGIZ4Q3PMF4EV","target":"record","payload":{"canonical_record":{"source":{"id":"1802.09405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-02-26T15:36:56Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"6c7d8b1e2bfcf28f98efbea507ca155f98b9bfebfb54ebc3fb41c7f41cf9c1b1","abstract_canon_sha256":"41c2c06f7b1b6900d827db1c9da2cded4d366129ac7051f5dd6bdfc10a60230f"},"schema_version":"1.0"},"canonical_sha256":"f2ee2c4fe55609ff34c8cf21b7b0bc256e33aa37453e080f1c0e9c8a892f6342","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:33.780463Z","signature_b64":"pCcyfs314qMKQMeShUH/N0coBiNltGxux175jTtwwrCuNckD/hH8yliovNWrdlZJQu4Fg5U6cfdAIC0MJ6ENDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2ee2c4fe55609ff34c8cf21b7b0bc256e33aa37453e080f1c0e9c8a892f6342","last_reissued_at":"2026-05-18T00:22:33.780029Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:33.780029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.09405","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":"2026-05-18T00:22:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kQP3/hSH0sWcYvKaOlYHeaCh3Mc6P36rw5m0a2wpTeKLTNLg7ZsbW5B8tz4AH/5X+CfbkwRfVyyEtdxFlVRECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:21:31.950722Z"},"content_sha256":"5a19aa1de16a8ab93666bc0e2676b01b35cbe04a321d08b80bdf27e3bc2245e1","schema_version":"1.0","event_id":"sha256:5a19aa1de16a8ab93666bc0e2676b01b35cbe04a321d08b80bdf27e3bc2245e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6LXCYT7FKYE76NGIZ4Q3PMF4EV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Graph Convolutional Networks with Non-Parametric Activation Functions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Aurelio Uncini, Danilo Comminiello, Simone Scardapane, Steven Van Vaerenbergh","submitted_at":"2018-02-26T15:36:56Z","abstract_excerpt":"Graph neural networks (GNNs) are a class of neural networks that allow to efficiently perform inference on data that is associated to a graph structure, such as, e.g., citation networks or knowledge graphs. While several variants of GNNs have been proposed, they only consider simple nonlinear activation functions in their layers, such as rectifiers or squashing functions. In this paper, we investigate the use of graph convolutional networks (GCNs) when combined with more complex activation functions, able to adapt from the training data. More specifically, we extend the recently proposed kerne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09405","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":"2026-05-18T00:22:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GW2cVg7Xv8iqhHVXdWkney1FkICOL+SfzFzZFKSw0fdxjOF37tXTp97pJPVit1Tbmo4j37paHM1n65pdzjHhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:21:31.951072Z"},"content_sha256":"20720fb9509439a7c9f5fb4de6796e3233a2c173bb137139dc10ec45b2af773a","schema_version":"1.0","event_id":"sha256:20720fb9509439a7c9f5fb4de6796e3233a2c173bb137139dc10ec45b2af773a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6LXCYT7FKYE76NGIZ4Q3PMF4EV/bundle.json","state_url":"https://pith.science/pith/6LXCYT7FKYE76NGIZ4Q3PMF4EV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6LXCYT7FKYE76NGIZ4Q3PMF4EV/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":"2026-05-28T14:21:31Z","links":{"resolver":"https://pith.science/pith/6LXCYT7FKYE76NGIZ4Q3PMF4EV","bundle":"https://pith.science/pith/6LXCYT7FKYE76NGIZ4Q3PMF4EV/bundle.json","state":"https://pith.science/pith/6LXCYT7FKYE76NGIZ4Q3PMF4EV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6LXCYT7FKYE76NGIZ4Q3PMF4EV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6LXCYT7FKYE76NGIZ4Q3PMF4EV","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":"41c2c06f7b1b6900d827db1c9da2cded4d366129ac7051f5dd6bdfc10a60230f","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-02-26T15:36:56Z","title_canon_sha256":"6c7d8b1e2bfcf28f98efbea507ca155f98b9bfebfb54ebc3fb41c7f41cf9c1b1"},"schema_version":"1.0","source":{"id":"1802.09405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09405","created_at":"2026-05-18T00:22:33Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09405v1","created_at":"2026-05-18T00:22:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09405","created_at":"2026-05-18T00:22:33Z"},{"alias_kind":"pith_short_12","alias_value":"6LXCYT7FKYE7","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"6LXCYT7FKYE76NGI","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"6LXCYT7F","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:20720fb9509439a7c9f5fb4de6796e3233a2c173bb137139dc10ec45b2af773a","target":"graph","created_at":"2026-05-18T00:22:33Z","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":"Graph neural networks (GNNs) are a class of neural networks that allow to efficiently perform inference on data that is associated to a graph structure, such as, e.g., citation networks or knowledge graphs. While several variants of GNNs have been proposed, they only consider simple nonlinear activation functions in their layers, such as rectifiers or squashing functions. In this paper, we investigate the use of graph convolutional networks (GCNs) when combined with more complex activation functions, able to adapt from the training data. More specifically, we extend the recently proposed kerne","authors_text":"Aurelio Uncini, Danilo Comminiello, Simone Scardapane, Steven Van Vaerenbergh","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-02-26T15:36:56Z","title":"Improving Graph Convolutional Networks with Non-Parametric Activation Functions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09405","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":"sha256:5a19aa1de16a8ab93666bc0e2676b01b35cbe04a321d08b80bdf27e3bc2245e1","target":"record","created_at":"2026-05-18T00:22:33Z","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":"41c2c06f7b1b6900d827db1c9da2cded4d366129ac7051f5dd6bdfc10a60230f","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-02-26T15:36:56Z","title_canon_sha256":"6c7d8b1e2bfcf28f98efbea507ca155f98b9bfebfb54ebc3fb41c7f41cf9c1b1"},"schema_version":"1.0","source":{"id":"1802.09405","kind":"arxiv","version":1}},"canonical_sha256":"f2ee2c4fe55609ff34c8cf21b7b0bc256e33aa37453e080f1c0e9c8a892f6342","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2ee2c4fe55609ff34c8cf21b7b0bc256e33aa37453e080f1c0e9c8a892f6342","first_computed_at":"2026-05-18T00:22:33.780029Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:33.780029Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pCcyfs314qMKQMeShUH/N0coBiNltGxux175jTtwwrCuNckD/hH8yliovNWrdlZJQu4Fg5U6cfdAIC0MJ6ENDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:33.780463Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.09405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a19aa1de16a8ab93666bc0e2676b01b35cbe04a321d08b80bdf27e3bc2245e1","sha256:20720fb9509439a7c9f5fb4de6796e3233a2c173bb137139dc10ec45b2af773a"],"state_sha256":"9505f84bc31287ce8929fe30860a49b66677ba64820fc2ed96be56aad2420f1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h8678D2ZXgDEIfsLLFtqp+e0yC3Wt9VKX/qZHxryzVFE484rQclYJGoGT82joE7AAjSpE2wXZuZzl5CN0hrpCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T14:21:31.953300Z","bundle_sha256":"f20be2a094f07c535ef07d35bcf03c8d0441e0fcc098bfb9c3713386889ac637"}}