{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OSNZN53MDZ5XPZCHSDUGFBHEDC","short_pith_number":"pith:OSNZN53M","schema_version":"1.0","canonical_sha256":"749b96f76c1e7b77e44790e86284e418b05284288a9d70b61d1c32b2e13e722b","source":{"kind":"arxiv","id":"2205.02956","version":3},"attestation_state":"computed","paper":{"title":"Low Dimensional Invariant Embeddings for Universal Geometric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AG"],"primary_cat":"cs.LG","authors_text":"Nadav Dym, Steven J. Gortler","submitted_at":"2022-05-05T22:56:19Z","abstract_excerpt":"This paper studies separating invariants: mappings on $D$ dimensional domains which are invariant to an appropriate group action, and which separate orbits. The motivation for this study comes from the usefulness of separating invariants in proving universality of equivariant neural network architectures.\n  We observe that in several cases the cardinality of separating invariants proposed in the machine learning literature is much larger than the dimension $D$. As a result, the theoretical universal constructions based on these separating invariants is unrealistically large. Our goal in this p"},"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":"2205.02956","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-05T22:56:19Z","cross_cats_sorted":["math.AG"],"title_canon_sha256":"e54b8f3b39f39a78685a7c2c9bb1c938d822cfc4c5cfd774a23533c83d4ae770","abstract_canon_sha256":"fa6153447f66ce893ad6c22dec6877b26f2fe6b83499dbdf6347227545efce81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:50.119128Z","signature_b64":"naflKSWptrXOpl2pOd7EqAmpsnwyseM4QI3cNIhaCqg5c8QHN8aM74/d+xmSm5eIbI//MgtZkagvXRtAGSoSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"749b96f76c1e7b77e44790e86284e418b05284288a9d70b61d1c32b2e13e722b","last_reissued_at":"2026-07-05T07:14:50.118630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:50.118630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low Dimensional Invariant Embeddings for Universal Geometric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AG"],"primary_cat":"cs.LG","authors_text":"Nadav Dym, Steven J. Gortler","submitted_at":"2022-05-05T22:56:19Z","abstract_excerpt":"This paper studies separating invariants: mappings on $D$ dimensional domains which are invariant to an appropriate group action, and which separate orbits. The motivation for this study comes from the usefulness of separating invariants in proving universality of equivariant neural network architectures.\n  We observe that in several cases the cardinality of separating invariants proposed in the machine learning literature is much larger than the dimension $D$. As a result, the theoretical universal constructions based on these separating invariants is unrealistically large. Our goal in this p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02956","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.02956/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":"2205.02956","created_at":"2026-07-05T07:14:50.118688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.02956v3","created_at":"2026-07-05T07:14:50.118688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02956","created_at":"2026-07-05T07:14:50.118688+00:00"},{"alias_kind":"pith_short_12","alias_value":"OSNZN53MDZ5X","created_at":"2026-07-05T07:14:50.118688+00:00"},{"alias_kind":"pith_short_16","alias_value":"OSNZN53MDZ5XPZCH","created_at":"2026-07-05T07:14:50.118688+00:00"},{"alias_kind":"pith_short_8","alias_value":"OSNZN53M","created_at":"2026-07-05T07:14:50.118688+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.02508","citing_title":"Fermi Sets: Universal and interpretable neural architectures for fermions","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OSNZN53MDZ5XPZCHSDUGFBHEDC","json":"https://pith.science/pith/OSNZN53MDZ5XPZCHSDUGFBHEDC.json","graph_json":"https://pith.science/api/pith-number/OSNZN53MDZ5XPZCHSDUGFBHEDC/graph.json","events_json":"https://pith.science/api/pith-number/OSNZN53MDZ5XPZCHSDUGFBHEDC/events.json","paper":"https://pith.science/paper/OSNZN53M"},"agent_actions":{"view_html":"https://pith.science/pith/OSNZN53MDZ5XPZCHSDUGFBHEDC","download_json":"https://pith.science/pith/OSNZN53MDZ5XPZCHSDUGFBHEDC.json","view_paper":"https://pith.science/paper/OSNZN53M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.02956&json=true","fetch_graph":"https://pith.science/api/pith-number/OSNZN53MDZ5XPZCHSDUGFBHEDC/graph.json","fetch_events":"https://pith.science/api/pith-number/OSNZN53MDZ5XPZCHSDUGFBHEDC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OSNZN53MDZ5XPZCHSDUGFBHEDC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OSNZN53MDZ5XPZCHSDUGFBHEDC/action/storage_attestation","attest_author":"https://pith.science/pith/OSNZN53MDZ5XPZCHSDUGFBHEDC/action/author_attestation","sign_citation":"https://pith.science/pith/OSNZN53MDZ5XPZCHSDUGFBHEDC/action/citation_signature","submit_replication":"https://pith.science/pith/OSNZN53MDZ5XPZCHSDUGFBHEDC/action/replication_record"}},"created_at":"2026-07-05T07:14:50.118688+00:00","updated_at":"2026-07-05T07:14:50.118688+00:00"}