{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UNAS5IBPZ3JINXBHT7LQW4YVP7","short_pith_number":"pith:UNAS5IBP","canonical_record":{"source":{"id":"2208.03559","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-06T18:26:30Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"029880b5839577f21ea6df266542e9ebb04aea5f85638f85a571f20e6b0af651","abstract_canon_sha256":"7c0db6bb0e801560e32a1799aafed0b26bc963be3e43342cffaaf8ef7471cf05"},"schema_version":"1.0"},"canonical_sha256":"a3412ea02fced286dc279fd70b73157ff501076c226d284c4ac717f6eefffab6","source":{"kind":"arxiv","id":"2208.03559","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.03559","created_at":"2026-07-05T04:46:42Z"},{"alias_kind":"arxiv_version","alias_value":"2208.03559v1","created_at":"2026-07-05T04:46:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.03559","created_at":"2026-07-05T04:46:42Z"},{"alias_kind":"pith_short_12","alias_value":"UNAS5IBPZ3JI","created_at":"2026-07-05T04:46:42Z"},{"alias_kind":"pith_short_16","alias_value":"UNAS5IBPZ3JINXBH","created_at":"2026-07-05T04:46:42Z"},{"alias_kind":"pith_short_8","alias_value":"UNAS5IBP","created_at":"2026-07-05T04:46:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UNAS5IBPZ3JINXBHT7LQW4YVP7","target":"record","payload":{"canonical_record":{"source":{"id":"2208.03559","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-06T18:26:30Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"029880b5839577f21ea6df266542e9ebb04aea5f85638f85a571f20e6b0af651","abstract_canon_sha256":"7c0db6bb0e801560e32a1799aafed0b26bc963be3e43342cffaaf8ef7471cf05"},"schema_version":"1.0"},"canonical_sha256":"a3412ea02fced286dc279fd70b73157ff501076c226d284c4ac717f6eefffab6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:42.040751Z","signature_b64":"2rzDTJiQXdgrFCa/F9o4t+DRVtc8FZ2amA39cq1xjRcyawEZUFcEGBf/69p18kJmLp2pz4UBlFd+vIGzux2mAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3412ea02fced286dc279fd70b73157ff501076c226d284c4ac717f6eefffab6","last_reissued_at":"2026-07-05T04:46:42.040307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:42.040307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.03559","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":"2026-07-05T04:46:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OcTs0SHJq6HSnAhdWrJ7u3PC9t8GtksC0udH9EBPFvMCsWzOhuXGEpOSkiql6PfSEZZuJJeYLWC80Od9vxPrAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:05:35.910091Z"},"content_sha256":"ba83fd77120f90a713f01f2e37e0a7a3041ec81750f1416ebc8fb26d33d687a4","schema_version":"1.0","event_id":"sha256:ba83fd77120f90a713f01f2e37e0a7a3041ec81750f1416ebc8fb26d33d687a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UNAS5IBPZ3JINXBHT7LQW4YVP7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Triple Sparsification of Graph Convolutional Networks without Sacrificing the Accuracy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Ariful Azad, Md. Khaledur Rahman","submitted_at":"2022-08-06T18:26:30Z","abstract_excerpt":"Graph Neural Networks (GNNs) are widely used to perform different machine learning tasks on graphs. As the size of the graphs grows, and the GNNs get deeper, training and inference time become costly in addition to the memory requirement. Thus, without sacrificing accuracy, graph sparsification, or model compression becomes a viable approach for graph learning tasks. A few existing techniques only study the sparsification of graphs and GNN models. In this paper, we develop a SparseGCN pipeline to study all possible sparsification in GNN. We provide a theoretical analysis and empirically show t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.03559","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/2208.03559/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":"2026-07-05T04:46:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zk/9LPtteOlpUda6CGyDvIKt68+ZbYyT71RZSFwbROTt+pS0/Y9NlVpVkERQ9/GHaIWA0DMJrzTdo34ZFKgyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:05:35.910490Z"},"content_sha256":"b063c8561b3668b3a9a8c78d49422377e41223aa5a8cd02dd35ead3ddf4cfb89","schema_version":"1.0","event_id":"sha256:b063c8561b3668b3a9a8c78d49422377e41223aa5a8cd02dd35ead3ddf4cfb89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UNAS5IBPZ3JINXBHT7LQW4YVP7/bundle.json","state_url":"https://pith.science/pith/UNAS5IBPZ3JINXBHT7LQW4YVP7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UNAS5IBPZ3JINXBHT7LQW4YVP7/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":"2026-07-06T19:05:35Z","links":{"resolver":"https://pith.science/pith/UNAS5IBPZ3JINXBHT7LQW4YVP7","bundle":"https://pith.science/pith/UNAS5IBPZ3JINXBHT7LQW4YVP7/bundle.json","state":"https://pith.science/pith/UNAS5IBPZ3JINXBHT7LQW4YVP7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UNAS5IBPZ3JINXBHT7LQW4YVP7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UNAS5IBPZ3JINXBHT7LQW4YVP7","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":"7c0db6bb0e801560e32a1799aafed0b26bc963be3e43342cffaaf8ef7471cf05","cross_cats_sorted":["cs.PF"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-06T18:26:30Z","title_canon_sha256":"029880b5839577f21ea6df266542e9ebb04aea5f85638f85a571f20e6b0af651"},"schema_version":"1.0","source":{"id":"2208.03559","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.03559","created_at":"2026-07-05T04:46:42Z"},{"alias_kind":"arxiv_version","alias_value":"2208.03559v1","created_at":"2026-07-05T04:46:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.03559","created_at":"2026-07-05T04:46:42Z"},{"alias_kind":"pith_short_12","alias_value":"UNAS5IBPZ3JI","created_at":"2026-07-05T04:46:42Z"},{"alias_kind":"pith_short_16","alias_value":"UNAS5IBPZ3JINXBH","created_at":"2026-07-05T04:46:42Z"},{"alias_kind":"pith_short_8","alias_value":"UNAS5IBP","created_at":"2026-07-05T04:46:42Z"}],"graph_snapshots":[{"event_id":"sha256:b063c8561b3668b3a9a8c78d49422377e41223aa5a8cd02dd35ead3ddf4cfb89","target":"graph","created_at":"2026-07-05T04:46:42Z","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/2208.03559/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Graph Neural Networks (GNNs) are widely used to perform different machine learning tasks on graphs. As the size of the graphs grows, and the GNNs get deeper, training and inference time become costly in addition to the memory requirement. Thus, without sacrificing accuracy, graph sparsification, or model compression becomes a viable approach for graph learning tasks. A few existing techniques only study the sparsification of graphs and GNN models. In this paper, we develop a SparseGCN pipeline to study all possible sparsification in GNN. We provide a theoretical analysis and empirically show t","authors_text":"Ariful Azad, Md. Khaledur Rahman","cross_cats":["cs.PF"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-06T18:26:30Z","title":"Triple Sparsification of Graph Convolutional Networks without Sacrificing the Accuracy"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.03559","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:ba83fd77120f90a713f01f2e37e0a7a3041ec81750f1416ebc8fb26d33d687a4","target":"record","created_at":"2026-07-05T04:46:42Z","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":"7c0db6bb0e801560e32a1799aafed0b26bc963be3e43342cffaaf8ef7471cf05","cross_cats_sorted":["cs.PF"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-06T18:26:30Z","title_canon_sha256":"029880b5839577f21ea6df266542e9ebb04aea5f85638f85a571f20e6b0af651"},"schema_version":"1.0","source":{"id":"2208.03559","kind":"arxiv","version":1}},"canonical_sha256":"a3412ea02fced286dc279fd70b73157ff501076c226d284c4ac717f6eefffab6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3412ea02fced286dc279fd70b73157ff501076c226d284c4ac717f6eefffab6","first_computed_at":"2026-07-05T04:46:42.040307Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:42.040307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2rzDTJiQXdgrFCa/F9o4t+DRVtc8FZ2amA39cq1xjRcyawEZUFcEGBf/69p18kJmLp2pz4UBlFd+vIGzux2mAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:42.040751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.03559","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba83fd77120f90a713f01f2e37e0a7a3041ec81750f1416ebc8fb26d33d687a4","sha256:b063c8561b3668b3a9a8c78d49422377e41223aa5a8cd02dd35ead3ddf4cfb89"],"state_sha256":"bdd3e404143add54784859da79c701c71eea69e11c2273e638c863c387587743"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0cUYtMkmJBuS3gNWo7T6cEXpWX03uMr3elLHRJlRHnyYBB+5DtMBo+TgRucLrQBZW3IZ3eOgHHnbyY4+kA26CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:05:35.912644Z","bundle_sha256":"58b5219069ea7417a3e3008c087ef0b0e23e145a6ca283148cbb96e71a14b93f"}}