{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CA62T2KOW4WNHHDACK66HYXNBZ","short_pith_number":"pith:CA62T2KO","canonical_record":{"source":{"id":"2209.04766","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-11T01:39:29Z","cross_cats_sorted":[],"title_canon_sha256":"df238f5f374c6cb5c1cf385d161d13cdad25748254e02b244c5d3304a85741b9","abstract_canon_sha256":"9a9f03d61c115fdf600d1c4cc9b22943ba1c1813296f8c87d57415405eaa38cf"},"schema_version":"1.0"},"canonical_sha256":"103da9e94eb72cd39c6012bde3e2ed0e78f04f49c9bb34ff72e4333fa9bc3b99","source":{"kind":"arxiv","id":"2209.04766","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.04766","created_at":"2026-07-05T05:45:18Z"},{"alias_kind":"arxiv_version","alias_value":"2209.04766v3","created_at":"2026-07-05T05:45:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04766","created_at":"2026-07-05T05:45:18Z"},{"alias_kind":"pith_short_12","alias_value":"CA62T2KOW4WN","created_at":"2026-07-05T05:45:18Z"},{"alias_kind":"pith_short_16","alias_value":"CA62T2KOW4WNHHDA","created_at":"2026-07-05T05:45:18Z"},{"alias_kind":"pith_short_8","alias_value":"CA62T2KO","created_at":"2026-07-05T05:45:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CA62T2KOW4WNHHDACK66HYXNBZ","target":"record","payload":{"canonical_record":{"source":{"id":"2209.04766","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-11T01:39:29Z","cross_cats_sorted":[],"title_canon_sha256":"df238f5f374c6cb5c1cf385d161d13cdad25748254e02b244c5d3304a85741b9","abstract_canon_sha256":"9a9f03d61c115fdf600d1c4cc9b22943ba1c1813296f8c87d57415405eaa38cf"},"schema_version":"1.0"},"canonical_sha256":"103da9e94eb72cd39c6012bde3e2ed0e78f04f49c9bb34ff72e4333fa9bc3b99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:18.321254Z","signature_b64":"XqwbWuabEI8D4lNn4x099vNUzPXwWfsqEAR1ec26BhqR4iz8fzDEFJHZyUGZove9rpUgKBOkeBmWokpqynQ7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"103da9e94eb72cd39c6012bde3e2ed0e78f04f49c9bb34ff72e4333fa9bc3b99","last_reissued_at":"2026-07-05T05:45:18.320610Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:18.320610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.04766","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":"2026-07-05T05:45:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9sJMkb2sjGj2m2dnsvlxNq8++PdJZx/ya7jy4bG52/wHXAf3LPu3FTkUeCOVR9FWpAC9HP3YKeF3iH9DJRwuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:07:00.565242Z"},"content_sha256":"e073033e1a31abb14d56dafdb610a024d6333442a59725e9567edd345720e431","schema_version":"1.0","event_id":"sha256:e073033e1a31abb14d56dafdb610a024d6333442a59725e9567edd345720e431"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CA62T2KOW4WNHHDACK66HYXNBZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Sparsification of Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Caiwen Ding, Deniz Gurevin, Hongwu Peng, Omer Khan, Shaoyi Huang, Tong Geng, Weiwen Jiang","submitted_at":"2022-09-11T01:39:29Z","abstract_excerpt":"As real-world graphs expand in size, larger GNN models with billions of parameters are deployed. High parameter count in such models makes training and inference on graphs expensive and challenging. To reduce the computational and memory costs of GNNs, optimization methods such as pruning the redundant nodes and edges in input graphs have been commonly adopted. However, model compression, which directly targets the sparsification of model layers, has been mostly limited to traditional Deep Neural Networks (DNNs) used for tasks such as image classification and object detection. In this paper, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04766","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/2209.04766/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":"2026-07-05T05:45:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pUCgzEpG5FqF6Gqdk+pC4m/sLCI6hsFu78QIzvHhYjSGIGBLulV5zh8ldN8srD/4qW2Xdc0Xn5b8QND4NkuzAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:07:00.565644Z"},"content_sha256":"6186cec4e19874e7675b5be01ecddf2b38e3cfce6d06a909ca14b7d18d53a675","schema_version":"1.0","event_id":"sha256:6186cec4e19874e7675b5be01ecddf2b38e3cfce6d06a909ca14b7d18d53a675"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CA62T2KOW4WNHHDACK66HYXNBZ/bundle.json","state_url":"https://pith.science/pith/CA62T2KOW4WNHHDACK66HYXNBZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CA62T2KOW4WNHHDACK66HYXNBZ/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":"2026-07-06T18:07:00Z","links":{"resolver":"https://pith.science/pith/CA62T2KOW4WNHHDACK66HYXNBZ","bundle":"https://pith.science/pith/CA62T2KOW4WNHHDACK66HYXNBZ/bundle.json","state":"https://pith.science/pith/CA62T2KOW4WNHHDACK66HYXNBZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CA62T2KOW4WNHHDACK66HYXNBZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CA62T2KOW4WNHHDACK66HYXNBZ","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":"9a9f03d61c115fdf600d1c4cc9b22943ba1c1813296f8c87d57415405eaa38cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-11T01:39:29Z","title_canon_sha256":"df238f5f374c6cb5c1cf385d161d13cdad25748254e02b244c5d3304a85741b9"},"schema_version":"1.0","source":{"id":"2209.04766","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.04766","created_at":"2026-07-05T05:45:18Z"},{"alias_kind":"arxiv_version","alias_value":"2209.04766v3","created_at":"2026-07-05T05:45:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04766","created_at":"2026-07-05T05:45:18Z"},{"alias_kind":"pith_short_12","alias_value":"CA62T2KOW4WN","created_at":"2026-07-05T05:45:18Z"},{"alias_kind":"pith_short_16","alias_value":"CA62T2KOW4WNHHDA","created_at":"2026-07-05T05:45:18Z"},{"alias_kind":"pith_short_8","alias_value":"CA62T2KO","created_at":"2026-07-05T05:45:18Z"}],"graph_snapshots":[{"event_id":"sha256:6186cec4e19874e7675b5be01ecddf2b38e3cfce6d06a909ca14b7d18d53a675","target":"graph","created_at":"2026-07-05T05:45:18Z","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/2209.04766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As real-world graphs expand in size, larger GNN models with billions of parameters are deployed. High parameter count in such models makes training and inference on graphs expensive and challenging. To reduce the computational and memory costs of GNNs, optimization methods such as pruning the redundant nodes and edges in input graphs have been commonly adopted. However, model compression, which directly targets the sparsification of model layers, has been mostly limited to traditional Deep Neural Networks (DNNs) used for tasks such as image classification and object detection. In this paper, w","authors_text":"Caiwen Ding, Deniz Gurevin, Hongwu Peng, Omer Khan, Shaoyi Huang, Tong Geng, Weiwen Jiang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-11T01:39:29Z","title":"Towards Sparsification of Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04766","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:e073033e1a31abb14d56dafdb610a024d6333442a59725e9567edd345720e431","target":"record","created_at":"2026-07-05T05:45:18Z","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":"9a9f03d61c115fdf600d1c4cc9b22943ba1c1813296f8c87d57415405eaa38cf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-09-11T01:39:29Z","title_canon_sha256":"df238f5f374c6cb5c1cf385d161d13cdad25748254e02b244c5d3304a85741b9"},"schema_version":"1.0","source":{"id":"2209.04766","kind":"arxiv","version":3}},"canonical_sha256":"103da9e94eb72cd39c6012bde3e2ed0e78f04f49c9bb34ff72e4333fa9bc3b99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"103da9e94eb72cd39c6012bde3e2ed0e78f04f49c9bb34ff72e4333fa9bc3b99","first_computed_at":"2026-07-05T05:45:18.320610Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:45:18.320610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XqwbWuabEI8D4lNn4x099vNUzPXwWfsqEAR1ec26BhqR4iz8fzDEFJHZyUGZove9rpUgKBOkeBmWokpqynQ7DA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:45:18.321254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.04766","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e073033e1a31abb14d56dafdb610a024d6333442a59725e9567edd345720e431","sha256:6186cec4e19874e7675b5be01ecddf2b38e3cfce6d06a909ca14b7d18d53a675"],"state_sha256":"f16192f249347da8483ca040bae25420e520b21610d53b340b870aa51af0ef94"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ne9oK2vdvpOjKNF0U9RPdz0qdm/4ppkMZBEeZUVC/gPpre1ePdpfsdgB5/FteddRpBcDk2kZiEiRUjSUpZHqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:07:00.567762Z","bundle_sha256":"82839bb87d213aea0dfdf872041737890bcf2f79bd9bed4fedf40096baf28e5e"}}