{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GDUGAG3V4VLOHHTNEXLLQES4KT","short_pith_number":"pith:GDUGAG3V","schema_version":"1.0","canonical_sha256":"30e8601b75e556e39e6d25d6b8125c54c6aef0b41f099b6a895a25783a01b163","source":{"kind":"arxiv","id":"2505.11346","version":1},"attestation_state":"computed","paper":{"title":"What Can We Learn From MIMO Graph Convolutions?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Roth, Thomas Liebig","submitted_at":"2025-05-16T15:13:09Z","abstract_excerpt":"Most graph neural networks (GNNs) utilize approximations of the general graph convolution derived in the graph Fourier domain. While GNNs are typically applied in the multi-input multi-output (MIMO) case, the approximations are performed in the single-input single-output (SISO) case. In this work, we first derive the MIMO graph convolution through the convolution theorem and approximate it directly in the MIMO case. We find the key MIMO-specific property of the graph convolution to be operating on multiple computational graphs, or equivalently, applying distinct feature transformations for eac"},"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":"2505.11346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T15:13:09Z","cross_cats_sorted":[],"title_canon_sha256":"db4b0ff72100ebacab7c3be79193b6b225b047015ed9288aae5faf925ca62d2c","abstract_canon_sha256":"f1889993994a80f56abe62c5f3b36751c2722d9905eddd2ce270520544139d0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:14.742584Z","signature_b64":"Qc2c7woR+2H4jPZwPOGfajKl9fbj9gXLiJcTo/BfXycteCjq3eH7bF27qM+9JkcJNGKHuo8Lluzox3FqqaVKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30e8601b75e556e39e6d25d6b8125c54c6aef0b41f099b6a895a25783a01b163","last_reissued_at":"2026-07-05T11:04:14.742047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:14.742047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Can We Learn From MIMO Graph Convolutions?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Roth, Thomas Liebig","submitted_at":"2025-05-16T15:13:09Z","abstract_excerpt":"Most graph neural networks (GNNs) utilize approximations of the general graph convolution derived in the graph Fourier domain. While GNNs are typically applied in the multi-input multi-output (MIMO) case, the approximations are performed in the single-input single-output (SISO) case. In this work, we first derive the MIMO graph convolution through the convolution theorem and approximate it directly in the MIMO case. We find the key MIMO-specific property of the graph convolution to be operating on multiple computational graphs, or equivalently, applying distinct feature transformations for eac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11346","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.11346/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":"2505.11346","created_at":"2026-07-05T11:04:14.742116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11346v1","created_at":"2026-07-05T11:04:14.742116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11346","created_at":"2026-07-05T11:04:14.742116+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDUGAG3V4VLO","created_at":"2026-07-05T11:04:14.742116+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDUGAG3V4VLOHHTN","created_at":"2026-07-05T11:04:14.742116+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDUGAG3V","created_at":"2026-07-05T11:04:14.742116+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/GDUGAG3V4VLOHHTNEXLLQES4KT","json":"https://pith.science/pith/GDUGAG3V4VLOHHTNEXLLQES4KT.json","graph_json":"https://pith.science/api/pith-number/GDUGAG3V4VLOHHTNEXLLQES4KT/graph.json","events_json":"https://pith.science/api/pith-number/GDUGAG3V4VLOHHTNEXLLQES4KT/events.json","paper":"https://pith.science/paper/GDUGAG3V"},"agent_actions":{"view_html":"https://pith.science/pith/GDUGAG3V4VLOHHTNEXLLQES4KT","download_json":"https://pith.science/pith/GDUGAG3V4VLOHHTNEXLLQES4KT.json","view_paper":"https://pith.science/paper/GDUGAG3V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11346&json=true","fetch_graph":"https://pith.science/api/pith-number/GDUGAG3V4VLOHHTNEXLLQES4KT/graph.json","fetch_events":"https://pith.science/api/pith-number/GDUGAG3V4VLOHHTNEXLLQES4KT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDUGAG3V4VLOHHTNEXLLQES4KT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDUGAG3V4VLOHHTNEXLLQES4KT/action/storage_attestation","attest_author":"https://pith.science/pith/GDUGAG3V4VLOHHTNEXLLQES4KT/action/author_attestation","sign_citation":"https://pith.science/pith/GDUGAG3V4VLOHHTNEXLLQES4KT/action/citation_signature","submit_replication":"https://pith.science/pith/GDUGAG3V4VLOHHTNEXLLQES4KT/action/replication_record"}},"created_at":"2026-07-05T11:04:14.742116+00:00","updated_at":"2026-07-05T11:04:14.742116+00:00"}