{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2OPBJGZUOGE4Y3W46I2UJXMCDD","short_pith_number":"pith:2OPBJGZU","schema_version":"1.0","canonical_sha256":"d39e149b347189cc6edcf23544dd8218d8b2a3d524f2bba37ef0ec45eed74cf2","source":{"kind":"arxiv","id":"2202.13013","version":4},"attestation_state":"computed","paper":{"title":"Sign and Basis Invariant Networks for Spectral Graph Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Derek Lim, Haggai Maron, Joshua Robinson, Lingxiao Zhao, Stefanie Jegelka, Suvrit Sra, Tess Smidt","submitted_at":"2022-02-25T23:11:59Z","abstract_excerpt":"We introduce SignNet and BasisNet -- new neural architectures that are invariant to two key symmetries displayed by eigenvectors: (i) sign flips, since if $v$ is an eigenvector then so is $-v$; and (ii) more general basis symmetries, which occur in higher dimensional eigenspaces with infinitely many choices of basis eigenvectors. We prove that under certain conditions our networks are universal, i.e., they can approximate any continuous function of eigenvectors with the desired invariances. When used with Laplacian eigenvectors, our networks are provably more expressive than existing spectral "},"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":"2202.13013","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-25T23:11:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e2151d4bb0ce6fa219b2392bca8bbbe9bf1278f06398c6af56faafbfd803106d","abstract_canon_sha256":"d6862d13e6dce59e89beec844981439e5f3fe6750879b49f2429f1fa6c57e350"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:24.632798Z","signature_b64":"e05wL63bBjBwHT04UCCFLr8YubyvVZiLNx6fjBDH+lFJ531NuesogOOXbqg+4kHB+LYJ987zf/bshm1l1NbvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d39e149b347189cc6edcf23544dd8218d8b2a3d524f2bba37ef0ec45eed74cf2","last_reissued_at":"2026-07-05T05:02:24.632302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:24.632302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sign and Basis Invariant Networks for Spectral Graph Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Derek Lim, Haggai Maron, Joshua Robinson, Lingxiao Zhao, Stefanie Jegelka, Suvrit Sra, Tess Smidt","submitted_at":"2022-02-25T23:11:59Z","abstract_excerpt":"We introduce SignNet and BasisNet -- new neural architectures that are invariant to two key symmetries displayed by eigenvectors: (i) sign flips, since if $v$ is an eigenvector then so is $-v$; and (ii) more general basis symmetries, which occur in higher dimensional eigenspaces with infinitely many choices of basis eigenvectors. We prove that under certain conditions our networks are universal, i.e., they can approximate any continuous function of eigenvectors with the desired invariances. When used with Laplacian eigenvectors, our networks are provably more expressive than existing spectral "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.13013","kind":"arxiv","version":4},"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/2202.13013/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":"2202.13013","created_at":"2026-07-05T05:02:24.632377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.13013v4","created_at":"2026-07-05T05:02:24.632377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.13013","created_at":"2026-07-05T05:02:24.632377+00:00"},{"alias_kind":"pith_short_12","alias_value":"2OPBJGZUOGE4","created_at":"2026-07-05T05:02:24.632377+00:00"},{"alias_kind":"pith_short_16","alias_value":"2OPBJGZUOGE4Y3W4","created_at":"2026-07-05T05:02:24.632377+00:00"},{"alias_kind":"pith_short_8","alias_value":"2OPBJGZU","created_at":"2026-07-05T05:02:24.632377+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.06546","citing_title":"Graph Convolutional Attention: A Spectral Perspective on Graph Denoising and Diffusion","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06224","citing_title":"Canopy: A Heterograph Foundation Model for Metabolic Engineering","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2606.01891","citing_title":"MidSurfNet: Learnable Face Pairing and Interference Implicit Fields for Generalized Mid-surface Abstraction","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29828","citing_title":"When Do Graph Foundation Models Transfer? A Data-Centric Theory","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21000","citing_title":"Feature Augmentation of GNNs for ILPs: Local Uniqueness Suffices","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24886","citing_title":"Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10247","citing_title":"Teaching LLMs to See Graphs: Unifying Text and Structural Reasoning","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2OPBJGZUOGE4Y3W46I2UJXMCDD","json":"https://pith.science/pith/2OPBJGZUOGE4Y3W46I2UJXMCDD.json","graph_json":"https://pith.science/api/pith-number/2OPBJGZUOGE4Y3W46I2UJXMCDD/graph.json","events_json":"https://pith.science/api/pith-number/2OPBJGZUOGE4Y3W46I2UJXMCDD/events.json","paper":"https://pith.science/paper/2OPBJGZU"},"agent_actions":{"view_html":"https://pith.science/pith/2OPBJGZUOGE4Y3W46I2UJXMCDD","download_json":"https://pith.science/pith/2OPBJGZUOGE4Y3W46I2UJXMCDD.json","view_paper":"https://pith.science/paper/2OPBJGZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.13013&json=true","fetch_graph":"https://pith.science/api/pith-number/2OPBJGZUOGE4Y3W46I2UJXMCDD/graph.json","fetch_events":"https://pith.science/api/pith-number/2OPBJGZUOGE4Y3W46I2UJXMCDD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2OPBJGZUOGE4Y3W46I2UJXMCDD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2OPBJGZUOGE4Y3W46I2UJXMCDD/action/storage_attestation","attest_author":"https://pith.science/pith/2OPBJGZUOGE4Y3W46I2UJXMCDD/action/author_attestation","sign_citation":"https://pith.science/pith/2OPBJGZUOGE4Y3W46I2UJXMCDD/action/citation_signature","submit_replication":"https://pith.science/pith/2OPBJGZUOGE4Y3W46I2UJXMCDD/action/replication_record"}},"created_at":"2026-07-05T05:02:24.632377+00:00","updated_at":"2026-07-05T05:02:24.632377+00:00"}