{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z6JZUDD3GINH676Q7564ZQH5OU","short_pith_number":"pith:Z6JZUDD3","schema_version":"1.0","canonical_sha256":"cf939a0c7b321a7f7fd0ff7dccc0fd75351b668d6cba41777d9c7a35330e0be3","source":{"kind":"arxiv","id":"2406.10685","version":2},"attestation_state":"computed","paper":{"title":"Scale Equivariant Graph Metanetworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Giorgos Bouritsas, Ioannis Kalogeropoulos, Yannis Panagakis","submitted_at":"2024-06-15T16:41:04Z","abstract_excerpt":"This paper pertains to an emerging machine learning paradigm: learning higher-order functions, i.e. functions whose inputs are functions themselves, $\\textit{particularly when these inputs are Neural Networks (NNs)}$. With the growing interest in architectures that process NNs, a recurring design principle has permeated the field: adhering to the permutation symmetries arising from the connectionist structure of NNs. $\\textit{However, are these the sole symmetries present in NN parameterizations}$? Zooming into most practical activation functions (e.g. sine, ReLU, tanh) answers this question n"},"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":"2406.10685","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-15T16:41:04Z","cross_cats_sorted":[],"title_canon_sha256":"38fe42cafbbb76f3bb76b22d248d18cab95cb6b4e78a3045b81fb6cdd0885ffc","abstract_canon_sha256":"7557233646239b4558f9813dd862a21e6c60ac1d573023266f11a4252086fddf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:32.224851Z","signature_b64":"liy0UBEkAW/LDQl9DpnV9dAsyJeX/m9p5Kz9AyVvJVkLqpo6FwVwXxfJ6r8L8VRQwqO8WIs76x0wtjEdp+vHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf939a0c7b321a7f7fd0ff7dccc0fd75351b668d6cba41777d9c7a35330e0be3","last_reissued_at":"2026-07-05T09:28:32.224333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:32.224333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scale Equivariant Graph Metanetworks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Giorgos Bouritsas, Ioannis Kalogeropoulos, Yannis Panagakis","submitted_at":"2024-06-15T16:41:04Z","abstract_excerpt":"This paper pertains to an emerging machine learning paradigm: learning higher-order functions, i.e. functions whose inputs are functions themselves, $\\textit{particularly when these inputs are Neural Networks (NNs)}$. With the growing interest in architectures that process NNs, a recurring design principle has permeated the field: adhering to the permutation symmetries arising from the connectionist structure of NNs. $\\textit{However, are these the sole symmetries present in NN parameterizations}$? Zooming into most practical activation functions (e.g. sine, ReLU, tanh) answers this question n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10685","kind":"arxiv","version":2},"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/2406.10685/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":"2406.10685","created_at":"2026-07-05T09:28:32.224398+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.10685v2","created_at":"2026-07-05T09:28:32.224398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10685","created_at":"2026-07-05T09:28:32.224398+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6JZUDD3GINH","created_at":"2026-07-05T09:28:32.224398+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6JZUDD3GINH676Q","created_at":"2026-07-05T09:28:32.224398+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6JZUDD3","created_at":"2026-07-05T09:28:32.224398+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09619","citing_title":"Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z6JZUDD3GINH676Q7564ZQH5OU","json":"https://pith.science/pith/Z6JZUDD3GINH676Q7564ZQH5OU.json","graph_json":"https://pith.science/api/pith-number/Z6JZUDD3GINH676Q7564ZQH5OU/graph.json","events_json":"https://pith.science/api/pith-number/Z6JZUDD3GINH676Q7564ZQH5OU/events.json","paper":"https://pith.science/paper/Z6JZUDD3"},"agent_actions":{"view_html":"https://pith.science/pith/Z6JZUDD3GINH676Q7564ZQH5OU","download_json":"https://pith.science/pith/Z6JZUDD3GINH676Q7564ZQH5OU.json","view_paper":"https://pith.science/paper/Z6JZUDD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.10685&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6JZUDD3GINH676Q7564ZQH5OU/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6JZUDD3GINH676Q7564ZQH5OU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6JZUDD3GINH676Q7564ZQH5OU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6JZUDD3GINH676Q7564ZQH5OU/action/storage_attestation","attest_author":"https://pith.science/pith/Z6JZUDD3GINH676Q7564ZQH5OU/action/author_attestation","sign_citation":"https://pith.science/pith/Z6JZUDD3GINH676Q7564ZQH5OU/action/citation_signature","submit_replication":"https://pith.science/pith/Z6JZUDD3GINH676Q7564ZQH5OU/action/replication_record"}},"created_at":"2026-07-05T09:28:32.224398+00:00","updated_at":"2026-07-05T09:28:32.224398+00:00"}