{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MVLF7JPIQTH7XGV4OCAAPXRSEO","short_pith_number":"pith:MVLF7JPI","schema_version":"1.0","canonical_sha256":"65565fa5e884cffb9abc708007de32239fafb115f2fb47e3d5f39fcc27ec3115","source":{"kind":"arxiv","id":"2405.08097","version":3},"attestation_state":"computed","paper":{"title":"A Galois theorem for machine learning: Functions on symmetric matrices and point clouds via lightweight invariant features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AC"],"primary_cat":"cs.LG","authors_text":"Ben Blum-Smith, Marco Cuturi, Ningyuan Huang, Soledad Villar","submitted_at":"2024-05-13T18:24:03Z","abstract_excerpt":"In this work, we present a mathematical formulation for machine learning of (1) functions on symmetric matrices that are invariant with respect to the action of permutations by conjugation, and (2) functions on point clouds that are invariant with respect to rotations, reflections, and permutations of the points. To achieve this, we provide a general construction of generically separating invariant features using ideas inspired by Galois theory. We construct $O(n^2)$ invariant features derived from generators for the field of rational functions on $n\\times n$ symmetric matrices that are invari"},"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":"2405.08097","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-13T18:24:03Z","cross_cats_sorted":["math.AC"],"title_canon_sha256":"e1f91a499459b9934f751234e9bfd163abab12b435c61c61a835424390b77ae7","abstract_canon_sha256":"1760703e53db8e650c4c8a7174119e9dbd9a6bc4cf6601365f0f17ac2934c5d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:39.980191Z","signature_b64":"kPql1KvXs5GffykLAbszXmRZCK/cR4vKrsbBfdkGSKr0RmS6wNzAfv8lsTlAzlsAri69T/U3E66eGQV6o9x9Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65565fa5e884cffb9abc708007de32239fafb115f2fb47e3d5f39fcc27ec3115","last_reissued_at":"2026-07-05T10:13:39.979742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:39.979742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Galois theorem for machine learning: Functions on symmetric matrices and point clouds via lightweight invariant features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.AC"],"primary_cat":"cs.LG","authors_text":"Ben Blum-Smith, Marco Cuturi, Ningyuan Huang, Soledad Villar","submitted_at":"2024-05-13T18:24:03Z","abstract_excerpt":"In this work, we present a mathematical formulation for machine learning of (1) functions on symmetric matrices that are invariant with respect to the action of permutations by conjugation, and (2) functions on point clouds that are invariant with respect to rotations, reflections, and permutations of the points. To achieve this, we provide a general construction of generically separating invariant features using ideas inspired by Galois theory. We construct $O(n^2)$ invariant features derived from generators for the field of rational functions on $n\\times n$ symmetric matrices that are invari"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.08097","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/2405.08097/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":"2405.08097","created_at":"2026-07-05T10:13:39.979794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.08097v3","created_at":"2026-07-05T10:13:39.979794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.08097","created_at":"2026-07-05T10:13:39.979794+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVLF7JPIQTH7","created_at":"2026-07-05T10:13:39.979794+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVLF7JPIQTH7XGV4","created_at":"2026-07-05T10:13:39.979794+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVLF7JPI","created_at":"2026-07-05T10:13:39.979794+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16035","citing_title":"Equivariant Eikonal Neural Networks: Grid-Free, Scalable Travel-Time Prediction on Homogeneous Spaces","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVLF7JPIQTH7XGV4OCAAPXRSEO","json":"https://pith.science/pith/MVLF7JPIQTH7XGV4OCAAPXRSEO.json","graph_json":"https://pith.science/api/pith-number/MVLF7JPIQTH7XGV4OCAAPXRSEO/graph.json","events_json":"https://pith.science/api/pith-number/MVLF7JPIQTH7XGV4OCAAPXRSEO/events.json","paper":"https://pith.science/paper/MVLF7JPI"},"agent_actions":{"view_html":"https://pith.science/pith/MVLF7JPIQTH7XGV4OCAAPXRSEO","download_json":"https://pith.science/pith/MVLF7JPIQTH7XGV4OCAAPXRSEO.json","view_paper":"https://pith.science/paper/MVLF7JPI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.08097&json=true","fetch_graph":"https://pith.science/api/pith-number/MVLF7JPIQTH7XGV4OCAAPXRSEO/graph.json","fetch_events":"https://pith.science/api/pith-number/MVLF7JPIQTH7XGV4OCAAPXRSEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVLF7JPIQTH7XGV4OCAAPXRSEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVLF7JPIQTH7XGV4OCAAPXRSEO/action/storage_attestation","attest_author":"https://pith.science/pith/MVLF7JPIQTH7XGV4OCAAPXRSEO/action/author_attestation","sign_citation":"https://pith.science/pith/MVLF7JPIQTH7XGV4OCAAPXRSEO/action/citation_signature","submit_replication":"https://pith.science/pith/MVLF7JPIQTH7XGV4OCAAPXRSEO/action/replication_record"}},"created_at":"2026-07-05T10:13:39.979794+00:00","updated_at":"2026-07-05T10:13:39.979794+00:00"}