{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EYTGYLE4D6HPKZMXH6S7EU4T3Z","short_pith_number":"pith:EYTGYLE4","schema_version":"1.0","canonical_sha256":"26266c2c9c1f8ef565973fa5f25393de5eed165eef97b2b1742ba9ebaa3ab1fc","source":{"kind":"arxiv","id":"2409.11697","version":3},"attestation_state":"computed","paper":{"title":"Monomial Matrix Group Equivariant Neural Functional Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"An T. Nguyen, Tan M. Nguyen, Thieu N. Vo, Tho H. Tran, Viet-Hoang Tran","submitted_at":"2024-09-18T04:36:05Z","abstract_excerpt":"Neural functional networks (NFNs) have recently gained significant attention due to their diverse applications, ranging from predicting network generalization and network editing to classifying implicit neural representation. Previous NFN designs often depend on permutation symmetries in neural networks' weights, which traditionally arise from the unordered arrangement of neurons in hidden layers. However, these designs do not take into account the weight scaling symmetries of $\\ReLU$ networks, and the weight sign flipping symmetries of $\\sin$ or $\\Tanh$ networks. In this paper, we extend the "},"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":"2409.11697","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-18T04:36:05Z","cross_cats_sorted":[],"title_canon_sha256":"9718d7d6228b795af0bb143033d9256349c659a98300bbb3524ac703f2b21873","abstract_canon_sha256":"2b70265925eda2d82822d62e3d6c98e4589a4ba45c0500b2ddb7de1489b88ee7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:23.067560Z","signature_b64":"qUIE5Du0OitfQyaIh0ClAGgdeGdjQZKsbo1RuW1c1jJumr0fmoCP5eqmrgJsXiCiDsi/zsrWR0qVsgV/3/9PAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26266c2c9c1f8ef565973fa5f25393de5eed165eef97b2b1742ba9ebaa3ab1fc","last_reissued_at":"2026-07-05T10:30:23.066642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:23.066642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monomial Matrix Group Equivariant Neural Functional Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"An T. Nguyen, Tan M. Nguyen, Thieu N. Vo, Tho H. Tran, Viet-Hoang Tran","submitted_at":"2024-09-18T04:36:05Z","abstract_excerpt":"Neural functional networks (NFNs) have recently gained significant attention due to their diverse applications, ranging from predicting network generalization and network editing to classifying implicit neural representation. Previous NFN designs often depend on permutation symmetries in neural networks' weights, which traditionally arise from the unordered arrangement of neurons in hidden layers. However, these designs do not take into account the weight scaling symmetries of $\\ReLU$ networks, and the weight sign flipping symmetries of $\\sin$ or $\\Tanh$ networks. In this paper, we extend the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11697","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/2409.11697/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":"2409.11697","created_at":"2026-07-05T10:30:23.066780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11697v3","created_at":"2026-07-05T10:30:23.066780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11697","created_at":"2026-07-05T10:30:23.066780+00:00"},{"alias_kind":"pith_short_12","alias_value":"EYTGYLE4D6HP","created_at":"2026-07-05T10:30:23.066780+00:00"},{"alias_kind":"pith_short_16","alias_value":"EYTGYLE4D6HPKZMX","created_at":"2026-07-05T10:30:23.066780+00:00"},{"alias_kind":"pith_short_8","alias_value":"EYTGYLE4","created_at":"2026-07-05T10:30:23.066780+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/EYTGYLE4D6HPKZMXH6S7EU4T3Z","json":"https://pith.science/pith/EYTGYLE4D6HPKZMXH6S7EU4T3Z.json","graph_json":"https://pith.science/api/pith-number/EYTGYLE4D6HPKZMXH6S7EU4T3Z/graph.json","events_json":"https://pith.science/api/pith-number/EYTGYLE4D6HPKZMXH6S7EU4T3Z/events.json","paper":"https://pith.science/paper/EYTGYLE4"},"agent_actions":{"view_html":"https://pith.science/pith/EYTGYLE4D6HPKZMXH6S7EU4T3Z","download_json":"https://pith.science/pith/EYTGYLE4D6HPKZMXH6S7EU4T3Z.json","view_paper":"https://pith.science/paper/EYTGYLE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11697&json=true","fetch_graph":"https://pith.science/api/pith-number/EYTGYLE4D6HPKZMXH6S7EU4T3Z/graph.json","fetch_events":"https://pith.science/api/pith-number/EYTGYLE4D6HPKZMXH6S7EU4T3Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EYTGYLE4D6HPKZMXH6S7EU4T3Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EYTGYLE4D6HPKZMXH6S7EU4T3Z/action/storage_attestation","attest_author":"https://pith.science/pith/EYTGYLE4D6HPKZMXH6S7EU4T3Z/action/author_attestation","sign_citation":"https://pith.science/pith/EYTGYLE4D6HPKZMXH6S7EU4T3Z/action/citation_signature","submit_replication":"https://pith.science/pith/EYTGYLE4D6HPKZMXH6S7EU4T3Z/action/replication_record"}},"created_at":"2026-07-05T10:30:23.066780+00:00","updated_at":"2026-07-05T10:30:23.066780+00:00"}