{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:SE3BH2EVQLTD7JDVPHJ7WNUDOP","short_pith_number":"pith:SE3BH2EV","schema_version":"1.0","canonical_sha256":"913613e89582e63fa47579d3fb368373d418a7ab7582e8404fd1ae48427285c7","source":{"kind":"arxiv","id":"1506.05163","version":1},"attestation_state":"computed","paper":{"title":"Deep Convolutional Networks on Graph-Structured Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Joan Bruna, Mikael Henaff, Yann LeCun","submitted_at":"2015-06-16T22:31:09Z","abstract_excerpt":"Deep Learning's recent successes have mostly relied on Convolutional Networks, which exploit fundamental statistical properties of images, sounds and video data: the local stationarity and multi-scale compositional structure, that allows expressing long range interactions in terms of shorter, localized interactions. However, there exist other important examples, such as text documents or bioinformatic data, that may lack some or all of these strong statistical regularities.\n  In this paper we consider the general question of how to construct deep architectures with small learning complexity on"},"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":"1506.05163","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-16T22:31:09Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"4e9226ee6bac3744e4abc9ec09c390ecf5d7632131241951e31efdfd4ef2310e","abstract_canon_sha256":"db198ec7b557178cbec5de7240bf1b63c1860c0496ac22293bfa070e79c6c048"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:46:12.909095Z","signature_b64":"ZAV7QXPqlGEsfO4x24ImRW06R86nmBMsQbQgffnPTqTGXRcEiK7G0R/9v+zd5Sg4s7slvftYj1w3MLDDFLTcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"913613e89582e63fa47579d3fb368373d418a7ab7582e8404fd1ae48427285c7","last_reissued_at":"2026-05-18T01:46:12.908487Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:46:12.908487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Convolutional Networks on Graph-Structured Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Joan Bruna, Mikael Henaff, Yann LeCun","submitted_at":"2015-06-16T22:31:09Z","abstract_excerpt":"Deep Learning's recent successes have mostly relied on Convolutional Networks, which exploit fundamental statistical properties of images, sounds and video data: the local stationarity and multi-scale compositional structure, that allows expressing long range interactions in terms of shorter, localized interactions. However, there exist other important examples, such as text documents or bioinformatic data, that may lack some or all of these strong statistical regularities.\n  In this paper we consider the general question of how to construct deep architectures with small learning complexity on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.05163","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":""},"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":"1506.05163","created_at":"2026-05-18T01:46:12.908612+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.05163v1","created_at":"2026-05-18T01:46:12.908612+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.05163","created_at":"2026-05-18T01:46:12.908612+00:00"},{"alias_kind":"pith_short_12","alias_value":"SE3BH2EVQLTD","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"SE3BH2EVQLTD7JDV","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"SE3BH2EV","created_at":"2026-05-18T12:29:39.896362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"1907.06356","citing_title":"Motorway Traffic Flow Prediction using Advanced Deep Learning","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"1907.08990","citing_title":"Spectral-based Graph Convolutional Network for Directed Graphs","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"1907.09000","citing_title":"Image Classification with Hierarchical Multigraph Networks","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"1908.05387","citing_title":"HONEM: Learning Embedding for Higher Order Networks","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11705","citing_title":"Low-Rank Matrix Completion: A Contemporary Survey","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2511.06443","citing_title":"How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2512.06356","citing_title":"Mitigating Structural Overfitting: A Distribution-Aware Rectification Framework for Missing Feature Imputation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"1710.10903","citing_title":"Graph Attention Networks","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SE3BH2EVQLTD7JDVPHJ7WNUDOP","json":"https://pith.science/pith/SE3BH2EVQLTD7JDVPHJ7WNUDOP.json","graph_json":"https://pith.science/api/pith-number/SE3BH2EVQLTD7JDVPHJ7WNUDOP/graph.json","events_json":"https://pith.science/api/pith-number/SE3BH2EVQLTD7JDVPHJ7WNUDOP/events.json","paper":"https://pith.science/paper/SE3BH2EV"},"agent_actions":{"view_html":"https://pith.science/pith/SE3BH2EVQLTD7JDVPHJ7WNUDOP","download_json":"https://pith.science/pith/SE3BH2EVQLTD7JDVPHJ7WNUDOP.json","view_paper":"https://pith.science/paper/SE3BH2EV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.05163&json=true","fetch_graph":"https://pith.science/api/pith-number/SE3BH2EVQLTD7JDVPHJ7WNUDOP/graph.json","fetch_events":"https://pith.science/api/pith-number/SE3BH2EVQLTD7JDVPHJ7WNUDOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SE3BH2EVQLTD7JDVPHJ7WNUDOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SE3BH2EVQLTD7JDVPHJ7WNUDOP/action/storage_attestation","attest_author":"https://pith.science/pith/SE3BH2EVQLTD7JDVPHJ7WNUDOP/action/author_attestation","sign_citation":"https://pith.science/pith/SE3BH2EVQLTD7JDVPHJ7WNUDOP/action/citation_signature","submit_replication":"https://pith.science/pith/SE3BH2EVQLTD7JDVPHJ7WNUDOP/action/replication_record"}},"created_at":"2026-05-18T01:46:12.908612+00:00","updated_at":"2026-05-18T01:46:12.908612+00:00"}