{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PFDTQWPRGFFX6FCJ7LYR4MUVI2","short_pith_number":"pith:PFDTQWPR","schema_version":"1.0","canonical_sha256":"79473859f1314b7f1449faf11e329546b648993547f42261cf20c24a819eef7c","source":{"kind":"arxiv","id":"2010.03633","version":2},"attestation_state":"computed","paper":{"title":"Simplicial Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gard Spreemann, Micha\\\"el Defferrard, Stefania Ebli","submitted_at":"2020-10-07T20:15:01Z","abstract_excerpt":"We present simplicial neural networks (SNNs), a generalization of graph neural networks to data that live on a class of topological spaces called simplicial complexes. These are natural multi-dimensional extensions of graphs that encode not only pairwise relationships but also higher-order interactions between vertices - allowing us to consider richer data, including vector fields and $n$-fold collaboration networks. We define an appropriate notion of convolution that we leverage to construct the desired convolutional neural networks. We test the SNNs on the task of imputing missing data on co"},"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":"2010.03633","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-07T20:15:01Z","cross_cats_sorted":["math.AT","stat.ML"],"title_canon_sha256":"e05165a928cc97df691139ad2eb15ad5c89b69015565a292367a9913dd6c7029","abstract_canon_sha256":"8dde353a02a9f1aec6583136254802dfa5d03da4a3c5b197dce0308e0aba5261"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:02:06.862639Z","signature_b64":"3Jclis2eClEx+twXkrViflQ08sx9ENCCU309glnwxhb/49Di7o50rehAqsviIaBxJkt5UTAFCrGm1DccxRYwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79473859f1314b7f1449faf11e329546b648993547f42261cf20c24a819eef7c","last_reissued_at":"2026-07-05T02:02:06.862226Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:02:06.862226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simplicial Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gard Spreemann, Micha\\\"el Defferrard, Stefania Ebli","submitted_at":"2020-10-07T20:15:01Z","abstract_excerpt":"We present simplicial neural networks (SNNs), a generalization of graph neural networks to data that live on a class of topological spaces called simplicial complexes. These are natural multi-dimensional extensions of graphs that encode not only pairwise relationships but also higher-order interactions between vertices - allowing us to consider richer data, including vector fields and $n$-fold collaboration networks. We define an appropriate notion of convolution that we leverage to construct the desired convolutional neural networks. We test the SNNs on the task of imputing missing data on co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.03633","kind":"arxiv","version":2},"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/2010.03633/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":"2010.03633","created_at":"2026-07-05T02:02:06.862282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.03633v2","created_at":"2026-07-05T02:02:06.862282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.03633","created_at":"2026-07-05T02:02:06.862282+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFDTQWPRGFFX","created_at":"2026-07-05T02:02:06.862282+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFDTQWPRGFFX6FCJ","created_at":"2026-07-05T02:02:06.862282+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFDTQWPR","created_at":"2026-07-05T02:02:06.862282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23517","citing_title":"Collapsed Effective Operators for Higher-order Structures","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00937","citing_title":"Cellular Sheaf Neural Operators for Structure-Preserving Surrogate Modeling of Constrained PDEs","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13834","citing_title":"Topology-Preserving Neural Operator Learning via Hodge Decomposition","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22853","citing_title":"Topological Signal Processing: An Application-Oriented Tutorial","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13997","citing_title":"HodgeCover: Higher-Order Topological Coverage Drives Compression of Sparse Mixture-of-Experts","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13834","citing_title":"Topology-Preserving Neural Operator Learning via Hodge Decomposition","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15833","citing_title":"Modern Structure-Aware Simplicial Spatiotemporal Neural Network","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PFDTQWPRGFFX6FCJ7LYR4MUVI2","json":"https://pith.science/pith/PFDTQWPRGFFX6FCJ7LYR4MUVI2.json","graph_json":"https://pith.science/api/pith-number/PFDTQWPRGFFX6FCJ7LYR4MUVI2/graph.json","events_json":"https://pith.science/api/pith-number/PFDTQWPRGFFX6FCJ7LYR4MUVI2/events.json","paper":"https://pith.science/paper/PFDTQWPR"},"agent_actions":{"view_html":"https://pith.science/pith/PFDTQWPRGFFX6FCJ7LYR4MUVI2","download_json":"https://pith.science/pith/PFDTQWPRGFFX6FCJ7LYR4MUVI2.json","view_paper":"https://pith.science/paper/PFDTQWPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.03633&json=true","fetch_graph":"https://pith.science/api/pith-number/PFDTQWPRGFFX6FCJ7LYR4MUVI2/graph.json","fetch_events":"https://pith.science/api/pith-number/PFDTQWPRGFFX6FCJ7LYR4MUVI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFDTQWPRGFFX6FCJ7LYR4MUVI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFDTQWPRGFFX6FCJ7LYR4MUVI2/action/storage_attestation","attest_author":"https://pith.science/pith/PFDTQWPRGFFX6FCJ7LYR4MUVI2/action/author_attestation","sign_citation":"https://pith.science/pith/PFDTQWPRGFFX6FCJ7LYR4MUVI2/action/citation_signature","submit_replication":"https://pith.science/pith/PFDTQWPRGFFX6FCJ7LYR4MUVI2/action/replication_record"}},"created_at":"2026-07-05T02:02:06.862282+00:00","updated_at":"2026-07-05T02:02:06.862282+00:00"}