{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NELYTL5QR6DGERTDMDGDDS4SBN","short_pith_number":"pith:NELYTL5Q","schema_version":"1.0","canonical_sha256":"691789afb08f8662466360cc31cb920b52c8fcb1cde329152478fb3673de7d4d","source":{"kind":"arxiv","id":"2502.01886","version":1},"attestation_state":"computed","paper":{"title":"Invariant Kernels: Rank Stabilization and Generalization Across Dimensions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.RT","stat.ML"],"primary_cat":"math.OC","authors_text":"Dmitriy Drusvyatskiy, Jack Kendrick, Mateo D\\'iaz, Rekha R. Thomas","submitted_at":"2025-02-03T23:37:43Z","abstract_excerpt":"Symmetry arises often when learning from high dimensional data. For example, data sets consisting of point clouds, graphs, and unordered sets appear routinely in contemporary applications, and exhibit rich underlying symmetries. Understanding the benefits of symmetry on the statistical and numerical efficiency of learning algorithms is an active area of research. In this work, we show that symmetry has a pronounced impact on the rank of kernel matrices. Specifically, we compute the rank of a polynomial kernel of fixed degree that is invariant under various groups acting independently on its tw"},"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":"2502.01886","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-02-03T23:37:43Z","cross_cats_sorted":["math.RT","stat.ML"],"title_canon_sha256":"621ca757c1abe5573539189fbfc707037896f77b49f788d855dc6047ababde2f","abstract_canon_sha256":"5a3083ebbe6a16323eb25339c5418e9777b4ea1371c94a20d65c77b0e3b0d3f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:52.786103Z","signature_b64":"rR5dQGbLjl+iKqRWXp8VgEM/WZzAop3pfti9rYlqccHVVNwv1HrL/A18Pbsz1+rifB32W/CTp5zs3BABv3CdAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"691789afb08f8662466360cc31cb920b52c8fcb1cde329152478fb3673de7d4d","last_reissued_at":"2026-07-05T10:09:52.785705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:52.785705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Invariant Kernels: Rank Stabilization and Generalization Across Dimensions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.RT","stat.ML"],"primary_cat":"math.OC","authors_text":"Dmitriy Drusvyatskiy, Jack Kendrick, Mateo D\\'iaz, Rekha R. Thomas","submitted_at":"2025-02-03T23:37:43Z","abstract_excerpt":"Symmetry arises often when learning from high dimensional data. For example, data sets consisting of point clouds, graphs, and unordered sets appear routinely in contemporary applications, and exhibit rich underlying symmetries. Understanding the benefits of symmetry on the statistical and numerical efficiency of learning algorithms is an active area of research. In this work, we show that symmetry has a pronounced impact on the rank of kernel matrices. Specifically, we compute the rank of a polynomial kernel of fixed degree that is invariant under various groups acting independently on its tw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01886","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/2502.01886/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":"2502.01886","created_at":"2026-07-05T10:09:52.785757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.01886v1","created_at":"2026-07-05T10:09:52.785757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01886","created_at":"2026-07-05T10:09:52.785757+00:00"},{"alias_kind":"pith_short_12","alias_value":"NELYTL5QR6DG","created_at":"2026-07-05T10:09:52.785757+00:00"},{"alias_kind":"pith_short_16","alias_value":"NELYTL5QR6DGERTD","created_at":"2026-07-05T10:09:52.785757+00:00"},{"alias_kind":"pith_short_8","alias_value":"NELYTL5Q","created_at":"2026-07-05T10:09:52.785757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07680","citing_title":"Any-Dimensional Learning by Sampling","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24418","citing_title":"Data Augmentation: A Fourier Analysis Perspective","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23156","citing_title":"Any-Dimensional Invariant Universality","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NELYTL5QR6DGERTDMDGDDS4SBN","json":"https://pith.science/pith/NELYTL5QR6DGERTDMDGDDS4SBN.json","graph_json":"https://pith.science/api/pith-number/NELYTL5QR6DGERTDMDGDDS4SBN/graph.json","events_json":"https://pith.science/api/pith-number/NELYTL5QR6DGERTDMDGDDS4SBN/events.json","paper":"https://pith.science/paper/NELYTL5Q"},"agent_actions":{"view_html":"https://pith.science/pith/NELYTL5QR6DGERTDMDGDDS4SBN","download_json":"https://pith.science/pith/NELYTL5QR6DGERTDMDGDDS4SBN.json","view_paper":"https://pith.science/paper/NELYTL5Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.01886&json=true","fetch_graph":"https://pith.science/api/pith-number/NELYTL5QR6DGERTDMDGDDS4SBN/graph.json","fetch_events":"https://pith.science/api/pith-number/NELYTL5QR6DGERTDMDGDDS4SBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NELYTL5QR6DGERTDMDGDDS4SBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NELYTL5QR6DGERTDMDGDDS4SBN/action/storage_attestation","attest_author":"https://pith.science/pith/NELYTL5QR6DGERTDMDGDDS4SBN/action/author_attestation","sign_citation":"https://pith.science/pith/NELYTL5QR6DGERTDMDGDDS4SBN/action/citation_signature","submit_replication":"https://pith.science/pith/NELYTL5QR6DGERTDMDGDDS4SBN/action/replication_record"}},"created_at":"2026-07-05T10:09:52.785757+00:00","updated_at":"2026-07-05T10:09:52.785757+00:00"}