{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:MNNKUY3MLSKJNT5EMTN5GTPSMH","short_pith_number":"pith:MNNKUY3M","schema_version":"1.0","canonical_sha256":"635aaa636c5c9496cfa464dbd34df261ee3278ba5db6703dec1ecbb5a5de412b","source":{"kind":"arxiv","id":"1704.02901","version":3},"attestation_state":"computed","paper":{"title":"Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Martin Simonovsky, Nikos Komodakis","submitted_at":"2017-04-10T15:18:54Z","abstract_excerpt":"A number of problems can be formulated as prediction on graph-structured data. In this work, we generalize the convolution operator from regular grids to arbitrary graphs while avoiding the spectral domain, which allows us to handle graphs of varying size and connectivity. To move beyond a simple diffusion, filter weights are conditioned on the specific edge labels in the neighborhood of a vertex. Together with the proper choice of graph coarsening, we explore constructing deep neural networks for graph classification. In particular, we demonstrate the generality of our formulation in point cl"},"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":"1704.02901","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-04-10T15:18:54Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"9a36ef54c2626b80efd1620e2457910eac8241f7586c74a379f67236160548de","abstract_canon_sha256":"daef9b2d91ec77e630bad673603bdc2edfda5238d48e8cf968c5f8e3a8030d8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:27.763517Z","signature_b64":"67jwQz1TLZJhIVH2kgT7r+4Unm4UETVwy7tuEbGtoHx2+JVK0KkBvFxuDOcJpgZU3dVier01Rvkbd7eD708qBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"635aaa636c5c9496cfa464dbd34df261ee3278ba5db6703dec1ecbb5a5de412b","last_reissued_at":"2026-05-18T00:38:27.762880Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:27.762880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cs.CV","authors_text":"Martin Simonovsky, Nikos Komodakis","submitted_at":"2017-04-10T15:18:54Z","abstract_excerpt":"A number of problems can be formulated as prediction on graph-structured data. In this work, we generalize the convolution operator from regular grids to arbitrary graphs while avoiding the spectral domain, which allows us to handle graphs of varying size and connectivity. To move beyond a simple diffusion, filter weights are conditioned on the specific edge labels in the neighborhood of a vertex. Together with the proper choice of graph coarsening, we explore constructing deep neural networks for graph classification. In particular, we demonstrate the generality of our formulation in point cl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.02901","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":""},"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":"1704.02901","created_at":"2026-05-18T00:38:27.762965+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.02901v3","created_at":"2026-05-18T00:38:27.762965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.02901","created_at":"2026-05-18T00:38:27.762965+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNNKUY3MLSKJ","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNNKUY3MLSKJNT5E","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNNKUY3M","created_at":"2026-05-18T12:31:31.346846+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/MNNKUY3MLSKJNT5EMTN5GTPSMH","json":"https://pith.science/pith/MNNKUY3MLSKJNT5EMTN5GTPSMH.json","graph_json":"https://pith.science/api/pith-number/MNNKUY3MLSKJNT5EMTN5GTPSMH/graph.json","events_json":"https://pith.science/api/pith-number/MNNKUY3MLSKJNT5EMTN5GTPSMH/events.json","paper":"https://pith.science/paper/MNNKUY3M"},"agent_actions":{"view_html":"https://pith.science/pith/MNNKUY3MLSKJNT5EMTN5GTPSMH","download_json":"https://pith.science/pith/MNNKUY3MLSKJNT5EMTN5GTPSMH.json","view_paper":"https://pith.science/paper/MNNKUY3M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.02901&json=true","fetch_graph":"https://pith.science/api/pith-number/MNNKUY3MLSKJNT5EMTN5GTPSMH/graph.json","fetch_events":"https://pith.science/api/pith-number/MNNKUY3MLSKJNT5EMTN5GTPSMH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNNKUY3MLSKJNT5EMTN5GTPSMH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNNKUY3MLSKJNT5EMTN5GTPSMH/action/storage_attestation","attest_author":"https://pith.science/pith/MNNKUY3MLSKJNT5EMTN5GTPSMH/action/author_attestation","sign_citation":"https://pith.science/pith/MNNKUY3MLSKJNT5EMTN5GTPSMH/action/citation_signature","submit_replication":"https://pith.science/pith/MNNKUY3MLSKJNT5EMTN5GTPSMH/action/replication_record"}},"created_at":"2026-05-18T00:38:27.762965+00:00","updated_at":"2026-05-18T00:38:27.762965+00:00"}