{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:47AEURCGISTVGCYOVPHSD4GGRL","short_pith_number":"pith:47AEURCG","schema_version":"1.0","canonical_sha256":"e7c04a444644a7530b0eabcf21f0c68ad72039e082edfdf8e497849050275a9a","source":{"kind":"arxiv","id":"1906.02174","version":3},"attestation_state":"computed","paper":{"title":"Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Mingde Zhao, Sitao Luan, Xiao-Wen Chang","submitted_at":"2019-06-05T17:59:39Z","abstract_excerpt":"Recently, neural network based approaches have achieved significant improvement for solving large, complex, graph-structured problems. However, their bottlenecks still need to be addressed, and the advantages of multi-scale information and deep architectures have not been sufficiently exploited. In this paper, we theoretically analyze how existing Graph Convolutional Networks (GCNs) have limited expressive power due to the constraint of the activation functions and their architectures. We generalize spectral graph convolution and deep GCN in block Krylov subspace forms and devise two architect"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1906.02174","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-05T17:59:39Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6b643c9a04aa6eee06aa71ada5645b20a1b29d66db05acb993352cb2f9a74652","abstract_canon_sha256":"11a3e9c05225ea2602dd0cf778882a6828aae1c4d8b40ad059282ceca98b09e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:02:58.878454Z","signature_b64":"686joAClQ4s89S6qrF9gTBuo3wGjIgyvt8RcMpMAyXyC4nyHA/2tbbrp1Hko24UnXoALubx+YWg7eKHfQnq4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7c04a444644a7530b0eabcf21f0c68ad72039e082edfdf8e497849050275a9a","last_reissued_at":"2026-07-05T00:02:58.877942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:02:58.877942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Doina Precup, Mingde Zhao, Sitao Luan, Xiao-Wen Chang","submitted_at":"2019-06-05T17:59:39Z","abstract_excerpt":"Recently, neural network based approaches have achieved significant improvement for solving large, complex, graph-structured problems. However, their bottlenecks still need to be addressed, and the advantages of multi-scale information and deep architectures have not been sufficiently exploited. In this paper, we theoretically analyze how existing Graph Convolutional Networks (GCNs) have limited expressive power due to the constraint of the activation functions and their architectures. We generalize spectral graph convolution and deep GCN in block Krylov subspace forms and devise two architect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02174","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/1906.02174/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1906.02174","created_at":"2026-07-05T00:02:58.878000+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.02174v3","created_at":"2026-07-05T00:02:58.878000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02174","created_at":"2026-07-05T00:02:58.878000+00:00"},{"alias_kind":"pith_short_12","alias_value":"47AEURCGISTV","created_at":"2026-07-05T00:02:58.878000+00:00"},{"alias_kind":"pith_short_16","alias_value":"47AEURCGISTVGCYO","created_at":"2026-07-05T00:02:58.878000+00:00"},{"alias_kind":"pith_short_8","alias_value":"47AEURCG","created_at":"2026-07-05T00:02:58.878000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/47AEURCGISTVGCYOVPHSD4GGRL","json":"https://pith.science/pith/47AEURCGISTVGCYOVPHSD4GGRL.json","graph_json":"https://pith.science/api/pith-number/47AEURCGISTVGCYOVPHSD4GGRL/graph.json","events_json":"https://pith.science/api/pith-number/47AEURCGISTVGCYOVPHSD4GGRL/events.json","paper":"https://pith.science/paper/47AEURCG"},"agent_actions":{"view_html":"https://pith.science/pith/47AEURCGISTVGCYOVPHSD4GGRL","download_json":"https://pith.science/pith/47AEURCGISTVGCYOVPHSD4GGRL.json","view_paper":"https://pith.science/paper/47AEURCG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.02174&json=true","fetch_graph":"https://pith.science/api/pith-number/47AEURCGISTVGCYOVPHSD4GGRL/graph.json","fetch_events":"https://pith.science/api/pith-number/47AEURCGISTVGCYOVPHSD4GGRL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47AEURCGISTVGCYOVPHSD4GGRL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47AEURCGISTVGCYOVPHSD4GGRL/action/storage_attestation","attest_author":"https://pith.science/pith/47AEURCGISTVGCYOVPHSD4GGRL/action/author_attestation","sign_citation":"https://pith.science/pith/47AEURCGISTVGCYOVPHSD4GGRL/action/citation_signature","submit_replication":"https://pith.science/pith/47AEURCGISTVGCYOVPHSD4GGRL/action/replication_record"}},"created_at":"2026-07-05T00:02:58.878000+00:00","updated_at":"2026-07-05T00:02:58.878000+00:00"}