{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:PB6NUAPNFBY2AD2SZJBFPQ5EVM","short_pith_number":"pith:PB6NUAPN","canonical_record":{"source":{"id":"2003.13663","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T17:48:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c2cd9a051c1d1012253e514195a14c655aad2faefa52746924f5644abeb2e803","abstract_canon_sha256":"6c72269453cef82107f0b3480aa76e31ebb5db4c8e3ad06bb32a90873ef83a32"},"schema_version":"1.0"},"canonical_sha256":"787cda01ed2871a00f52ca4257c3a4ab18c6bdeea7e3e0e6524a8a79d553bb61","source":{"kind":"arxiv","id":"2003.13663","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.13663","created_at":"2026-07-05T01:11:13Z"},{"alias_kind":"arxiv_version","alias_value":"2003.13663v5","created_at":"2026-07-05T01:11:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13663","created_at":"2026-07-05T01:11:13Z"},{"alias_kind":"pith_short_12","alias_value":"PB6NUAPNFBY2","created_at":"2026-07-05T01:11:13Z"},{"alias_kind":"pith_short_16","alias_value":"PB6NUAPNFBY2AD2S","created_at":"2026-07-05T01:11:13Z"},{"alias_kind":"pith_short_8","alias_value":"PB6NUAPN","created_at":"2026-07-05T01:11:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:PB6NUAPNFBY2AD2SZJBFPQ5EVM","target":"record","payload":{"canonical_record":{"source":{"id":"2003.13663","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T17:48:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c2cd9a051c1d1012253e514195a14c655aad2faefa52746924f5644abeb2e803","abstract_canon_sha256":"6c72269453cef82107f0b3480aa76e31ebb5db4c8e3ad06bb32a90873ef83a32"},"schema_version":"1.0"},"canonical_sha256":"787cda01ed2871a00f52ca4257c3a4ab18c6bdeea7e3e0e6524a8a79d553bb61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:11:13.224536Z","signature_b64":"HIknaEPIkX40Gn6Yu7xzUByRZejU5gbTjdHVGOMKXlRrFPecbcFGjnQ9Y9yaTw82mdhG1IWSyVqr5z/bXrCDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"787cda01ed2871a00f52ca4257c3a4ab18c6bdeea7e3e0e6524a8a79d553bb61","last_reissued_at":"2026-07-05T01:11:13.224036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:11:13.224036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.13663","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:11:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bLKP0fi5p1OwCj1Okysnj64cZ1670vPdq74kEiQO0Hvnozf+Tapj7PC3nb8tYoNatbXtAo0ygT4dwPXlDdRsBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:45:41.325380Z"},"content_sha256":"ac7800ad77dae9bde87756fdbb21a0ce176d2daf88c71062ab3a286f12497c01","schema_version":"1.0","event_id":"sha256:ac7800ad77dae9bde87756fdbb21a0ce176d2daf88c71062ab3a286f12497c01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:PB6NUAPNFBY2AD2SZJBFPQ5EVM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting Over-smoothing in Deep GCNs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chaoqi Yang, Ruijie Wang, Shengzhong Liu, Shuochao Yao, Tarek Abdelzaher","submitted_at":"2020-03-30T17:48:04Z","abstract_excerpt":"Oversmoothing has been assumed to be the major cause of performance drop in deep graph convolutional networks (GCNs). In this paper, we propose a new view that deep GCNs can actually learn to anti-oversmooth during training. This work interprets a standard GCN architecture as layerwise integration of a Multi-layer Perceptron (MLP) and graph regularization. We analyze and conclude that before training, the final representation of a deep GCN does over-smooth, however, it learns anti-oversmoothing during training. Based on the conclusion, the paper further designs a cheap but effective trick to i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13663","kind":"arxiv","version":5},"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/2003.13663/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":"2026-07-05T01:11:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AMcbDMtEttGbTFFSyfB4eIK/o6avcNZSKA815/Y8FoTSzs9RJ4fzFCMqyrCTLTQwlbfTTfpdv8pBJRLPTBSsCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:45:41.325770Z"},"content_sha256":"38e5267c05d4f7348ddd8ece2ffd70f9abff3f712590197cb58f55dbe15dab54","schema_version":"1.0","event_id":"sha256:38e5267c05d4f7348ddd8ece2ffd70f9abff3f712590197cb58f55dbe15dab54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PB6NUAPNFBY2AD2SZJBFPQ5EVM/bundle.json","state_url":"https://pith.science/pith/PB6NUAPNFBY2AD2SZJBFPQ5EVM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PB6NUAPNFBY2AD2SZJBFPQ5EVM/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":"2026-07-06T17:45:41Z","links":{"resolver":"https://pith.science/pith/PB6NUAPNFBY2AD2SZJBFPQ5EVM","bundle":"https://pith.science/pith/PB6NUAPNFBY2AD2SZJBFPQ5EVM/bundle.json","state":"https://pith.science/pith/PB6NUAPNFBY2AD2SZJBFPQ5EVM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PB6NUAPNFBY2AD2SZJBFPQ5EVM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PB6NUAPNFBY2AD2SZJBFPQ5EVM","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":"6c72269453cef82107f0b3480aa76e31ebb5db4c8e3ad06bb32a90873ef83a32","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T17:48:04Z","title_canon_sha256":"c2cd9a051c1d1012253e514195a14c655aad2faefa52746924f5644abeb2e803"},"schema_version":"1.0","source":{"id":"2003.13663","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.13663","created_at":"2026-07-05T01:11:13Z"},{"alias_kind":"arxiv_version","alias_value":"2003.13663v5","created_at":"2026-07-05T01:11:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.13663","created_at":"2026-07-05T01:11:13Z"},{"alias_kind":"pith_short_12","alias_value":"PB6NUAPNFBY2","created_at":"2026-07-05T01:11:13Z"},{"alias_kind":"pith_short_16","alias_value":"PB6NUAPNFBY2AD2S","created_at":"2026-07-05T01:11:13Z"},{"alias_kind":"pith_short_8","alias_value":"PB6NUAPN","created_at":"2026-07-05T01:11:13Z"}],"graph_snapshots":[{"event_id":"sha256:38e5267c05d4f7348ddd8ece2ffd70f9abff3f712590197cb58f55dbe15dab54","target":"graph","created_at":"2026-07-05T01:11:13Z","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/2003.13663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Oversmoothing has been assumed to be the major cause of performance drop in deep graph convolutional networks (GCNs). In this paper, we propose a new view that deep GCNs can actually learn to anti-oversmooth during training. This work interprets a standard GCN architecture as layerwise integration of a Multi-layer Perceptron (MLP) and graph regularization. We analyze and conclude that before training, the final representation of a deep GCN does over-smooth, however, it learns anti-oversmoothing during training. Based on the conclusion, the paper further designs a cheap but effective trick to i","authors_text":"Chaoqi Yang, Ruijie Wang, Shengzhong Liu, Shuochao Yao, Tarek Abdelzaher","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T17:48:04Z","title":"Revisiting Over-smoothing in Deep GCNs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.13663","kind":"arxiv","version":5},"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:ac7800ad77dae9bde87756fdbb21a0ce176d2daf88c71062ab3a286f12497c01","target":"record","created_at":"2026-07-05T01:11:13Z","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":"6c72269453cef82107f0b3480aa76e31ebb5db4c8e3ad06bb32a90873ef83a32","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T17:48:04Z","title_canon_sha256":"c2cd9a051c1d1012253e514195a14c655aad2faefa52746924f5644abeb2e803"},"schema_version":"1.0","source":{"id":"2003.13663","kind":"arxiv","version":5}},"canonical_sha256":"787cda01ed2871a00f52ca4257c3a4ab18c6bdeea7e3e0e6524a8a79d553bb61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"787cda01ed2871a00f52ca4257c3a4ab18c6bdeea7e3e0e6524a8a79d553bb61","first_computed_at":"2026-07-05T01:11:13.224036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:11:13.224036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HIknaEPIkX40Gn6Yu7xzUByRZejU5gbTjdHVGOMKXlRrFPecbcFGjnQ9Y9yaTw82mdhG1IWSyVqr5z/bXrCDCA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:11:13.224536Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.13663","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac7800ad77dae9bde87756fdbb21a0ce176d2daf88c71062ab3a286f12497c01","sha256:38e5267c05d4f7348ddd8ece2ffd70f9abff3f712590197cb58f55dbe15dab54"],"state_sha256":"0b80c68958b388274054c6e7a694022a970ae38278dcffbecd505cbb61395275"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uEkfhcp7CPn8STXbkvdVhAOt5dt1iTPvifyXiCwURdd3MPb139wPvDxMXIYrh8/3vyVYVxj11CXwWAr1FHjpAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:45:41.327742Z","bundle_sha256":"c8d44eccd5f956d722d50e438a9157073caf21c025d30e4fe11e7eea78d67c32"}}