{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JPQNABUVIYY7WAS256ZUJC5VJA","short_pith_number":"pith:JPQNABUV","canonical_record":{"source":{"id":"1910.11436","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-24T21:42:12Z","cross_cats_sorted":["math.SP","stat.ML"],"title_canon_sha256":"b8f10f604c75b4d4de1be0c72552fe133c6323f44a9c9a164714d12f2f24d1e0","abstract_canon_sha256":"d92c9ea230b4b71b5afc37a947a657e6448bd2296cffe6b6924d56c85beeaaf2"},"schema_version":"1.0"},"canonical_sha256":"4be0d006954631fb025aefb3448bb548285ac4575f5582049a676fd953fd22d8","source":{"kind":"arxiv","id":"1910.11436","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.11436","created_at":"2026-07-05T08:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"1910.11436v3","created_at":"2026-07-05T08:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.11436","created_at":"2026-07-05T08:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"JPQNABUVIYY7","created_at":"2026-07-05T08:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"JPQNABUVIYY7WAS2","created_at":"2026-07-05T08:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"JPQNABUV","created_at":"2026-07-05T08:10:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JPQNABUVIYY7WAS256ZUJC5VJA","target":"record","payload":{"canonical_record":{"source":{"id":"1910.11436","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-24T21:42:12Z","cross_cats_sorted":["math.SP","stat.ML"],"title_canon_sha256":"b8f10f604c75b4d4de1be0c72552fe133c6323f44a9c9a164714d12f2f24d1e0","abstract_canon_sha256":"d92c9ea230b4b71b5afc37a947a657e6448bd2296cffe6b6924d56c85beeaaf2"},"schema_version":"1.0"},"canonical_sha256":"4be0d006954631fb025aefb3448bb548285ac4575f5582049a676fd953fd22d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:08.531343Z","signature_b64":"hHXY5pQHrXgHH6DwVBmfzMe0nmCm6otNRL0unGeZPX677FHHYMo30no0KaSP7bnN95xgxWeIop2TJ4USC8ExBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4be0d006954631fb025aefb3448bb548285ac4575f5582049a676fd953fd22d8","last_reissued_at":"2026-07-05T08:10:08.530947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:08.530947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.11436","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:10:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BE0w6jJNoaxmrnceFM3eUHQ0nlfZ48yqIXNxSrv4K9I4rdm7cABX+cCT4Ix42K0HKWFnm3DHbb43vzYeXEooBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:01:04.031252Z"},"content_sha256":"b3aeb0a4bcf1fc006a24f3b471994a3c09a3e2900753d79cc38f74ef61d58be8","schema_version":"1.0","event_id":"sha256:b3aeb0a4bcf1fc006a24f3b471994a3c09a3e2900753d79cc38f74ef61d58be8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JPQNABUVIYY7WAS256ZUJC5VJA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.SP","stat.ML"],"primary_cat":"cs.LG","authors_text":"Cesare Alippi, Daniele Grattarola, Filippo Maria Bianchi, Lorenzo Livi","submitted_at":"2019-10-24T21:42:12Z","abstract_excerpt":"In graph neural networks (GNNs), pooling operators compute local summaries of input graphs to capture their global properties, and they are fundamental for building deep GNNs that learn hierarchical representations. In this work, we propose the Node Decimation Pooling (NDP), a pooling operator for GNNs that generates coarser graphs while preserving the overall graph topology. During training, the GNN learns new node representations and fits them to a pyramid of coarsened graphs, which is computed offline in a pre-processing stage. NDP consists of three steps. First, a node decimation procedure"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.11436","kind":"arxiv","version":3},"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/1910.11436/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":"2026-07-05T08:10:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tfl0TgLkL3z4sumZrN0P7AitsH2AM0CO4O5Q1lE3y86MbSHdwlcgU0ZnZjyDj8W+lg4lfWeme8ZRf1aa3+u6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T08:01:04.031635Z"},"content_sha256":"9e38b606fa52a9f483f56bfb5c261c29225c236cf14843dd8389eee34a305f26","schema_version":"1.0","event_id":"sha256:9e38b606fa52a9f483f56bfb5c261c29225c236cf14843dd8389eee34a305f26"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JPQNABUVIYY7WAS256ZUJC5VJA/bundle.json","state_url":"https://pith.science/pith/JPQNABUVIYY7WAS256ZUJC5VJA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JPQNABUVIYY7WAS256ZUJC5VJA/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":"2026-08-13T08:01:04Z","links":{"resolver":"https://pith.science/pith/JPQNABUVIYY7WAS256ZUJC5VJA","bundle":"https://pith.science/pith/JPQNABUVIYY7WAS256ZUJC5VJA/bundle.json","state":"https://pith.science/pith/JPQNABUVIYY7WAS256ZUJC5VJA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JPQNABUVIYY7WAS256ZUJC5VJA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JPQNABUVIYY7WAS256ZUJC5VJA","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":"d92c9ea230b4b71b5afc37a947a657e6448bd2296cffe6b6924d56c85beeaaf2","cross_cats_sorted":["math.SP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-24T21:42:12Z","title_canon_sha256":"b8f10f604c75b4d4de1be0c72552fe133c6323f44a9c9a164714d12f2f24d1e0"},"schema_version":"1.0","source":{"id":"1910.11436","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.11436","created_at":"2026-07-05T08:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"1910.11436v3","created_at":"2026-07-05T08:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.11436","created_at":"2026-07-05T08:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"JPQNABUVIYY7","created_at":"2026-07-05T08:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"JPQNABUVIYY7WAS2","created_at":"2026-07-05T08:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"JPQNABUV","created_at":"2026-07-05T08:10:08Z"}],"graph_snapshots":[{"event_id":"sha256:9e38b606fa52a9f483f56bfb5c261c29225c236cf14843dd8389eee34a305f26","target":"graph","created_at":"2026-07-05T08:10:08Z","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/1910.11436/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In graph neural networks (GNNs), pooling operators compute local summaries of input graphs to capture their global properties, and they are fundamental for building deep GNNs that learn hierarchical representations. In this work, we propose the Node Decimation Pooling (NDP), a pooling operator for GNNs that generates coarser graphs while preserving the overall graph topology. During training, the GNN learns new node representations and fits them to a pyramid of coarsened graphs, which is computed offline in a pre-processing stage. NDP consists of three steps. First, a node decimation procedure","authors_text":"Cesare Alippi, Daniele Grattarola, Filippo Maria Bianchi, Lorenzo Livi","cross_cats":["math.SP","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-24T21:42:12Z","title":"Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.11436","kind":"arxiv","version":3},"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:b3aeb0a4bcf1fc006a24f3b471994a3c09a3e2900753d79cc38f74ef61d58be8","target":"record","created_at":"2026-07-05T08:10:08Z","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":"d92c9ea230b4b71b5afc37a947a657e6448bd2296cffe6b6924d56c85beeaaf2","cross_cats_sorted":["math.SP","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-24T21:42:12Z","title_canon_sha256":"b8f10f604c75b4d4de1be0c72552fe133c6323f44a9c9a164714d12f2f24d1e0"},"schema_version":"1.0","source":{"id":"1910.11436","kind":"arxiv","version":3}},"canonical_sha256":"4be0d006954631fb025aefb3448bb548285ac4575f5582049a676fd953fd22d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4be0d006954631fb025aefb3448bb548285ac4575f5582049a676fd953fd22d8","first_computed_at":"2026-07-05T08:10:08.530947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:10:08.530947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hHXY5pQHrXgHH6DwVBmfzMe0nmCm6otNRL0unGeZPX677FHHYMo30no0KaSP7bnN95xgxWeIop2TJ4USC8ExBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:10:08.531343Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.11436","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3aeb0a4bcf1fc006a24f3b471994a3c09a3e2900753d79cc38f74ef61d58be8","sha256:9e38b606fa52a9f483f56bfb5c261c29225c236cf14843dd8389eee34a305f26"],"state_sha256":"854205a423b2e4f89b82af2b5a2789655bd658a3b68efe15f9ffbd7b18416702"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kChFvauW6CSyKqjNpoOg6g8ldT0esYSklyH9CMPNd3Pv6IRWFevKENWQKUT+AzjmBrUEm/B/EcUsjqDGZAvUAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T08:01:04.034444Z","bundle_sha256":"71184e6c9ce349dadd4d75ed6eebb70f9740cf8ec7cafe974fa1a3e41dbee344"}}