{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JZX2HUFID5RZJ32XZJHRCUEGUY","short_pith_number":"pith:JZX2HUFI","schema_version":"1.0","canonical_sha256":"4e6fa3d0a81f6394ef57ca4f115086a611335d466f936acd049b8cd641643cdf","source":{"kind":"arxiv","id":"2406.08966","version":3},"attestation_state":"computed","paper":{"title":"Separation Power of Equivariant Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bruno Lepri, Gabriele Santin, Marco Pacini, Xiaowen Dong","submitted_at":"2024-06-13T09:52:44Z","abstract_excerpt":"The separation power of a machine learning model refers to its ability to distinguish between different inputs and is often used as a proxy for its expressivity. Indeed, knowing the separation power of a family of models is a necessary condition to obtain fine-grained universality results. In this paper, we analyze the separation power of equivariant neural networks, such as convolutional and permutation-invariant networks. We first present a complete characterization of inputs indistinguishable by models derived by a given architecture. From this results, we derive how separability is influen"},"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":"2406.08966","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-13T09:52:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db017d029cc348e51202aa8fb441319856d06d725390ea65ac23c42142b48f65","abstract_canon_sha256":"763977903d25d34f97a4385165f602f43f6c1547a3c7478fb75cbfcb939c9fc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:11.453784Z","signature_b64":"rpw9m3pIhiczUwLMt/JtEav6IMDuquLZiSbl4yTvKtvxqa+OTOuREwupl6jw2KW0c2mGVnez3kF5BORWWsXRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e6fa3d0a81f6394ef57ca4f115086a611335d466f936acd049b8cd641643cdf","last_reissued_at":"2026-06-05T01:15:11.453295Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:11.453295Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Separation Power of Equivariant Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bruno Lepri, Gabriele Santin, Marco Pacini, Xiaowen Dong","submitted_at":"2024-06-13T09:52:44Z","abstract_excerpt":"The separation power of a machine learning model refers to its ability to distinguish between different inputs and is often used as a proxy for its expressivity. Indeed, knowing the separation power of a family of models is a necessary condition to obtain fine-grained universality results. In this paper, we analyze the separation power of equivariant neural networks, such as convolutional and permutation-invariant networks. We first present a complete characterization of inputs indistinguishable by models derived by a given architecture. From this results, we derive how separability is influen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08966","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/2406.08966/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":"2406.08966","created_at":"2026-06-05T01:15:11.453357+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08966v3","created_at":"2026-06-05T01:15:11.453357+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08966","created_at":"2026-06-05T01:15:11.453357+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZX2HUFID5RZ","created_at":"2026-06-05T01:15:11.453357+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZX2HUFID5RZJ32X","created_at":"2026-06-05T01:15:11.453357+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZX2HUFI","created_at":"2026-06-05T01:15:11.453357+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/JZX2HUFID5RZJ32XZJHRCUEGUY","json":"https://pith.science/pith/JZX2HUFID5RZJ32XZJHRCUEGUY.json","graph_json":"https://pith.science/api/pith-number/JZX2HUFID5RZJ32XZJHRCUEGUY/graph.json","events_json":"https://pith.science/api/pith-number/JZX2HUFID5RZJ32XZJHRCUEGUY/events.json","paper":"https://pith.science/paper/JZX2HUFI"},"agent_actions":{"view_html":"https://pith.science/pith/JZX2HUFID5RZJ32XZJHRCUEGUY","download_json":"https://pith.science/pith/JZX2HUFID5RZJ32XZJHRCUEGUY.json","view_paper":"https://pith.science/paper/JZX2HUFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08966&json=true","fetch_graph":"https://pith.science/api/pith-number/JZX2HUFID5RZJ32XZJHRCUEGUY/graph.json","fetch_events":"https://pith.science/api/pith-number/JZX2HUFID5RZJ32XZJHRCUEGUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZX2HUFID5RZJ32XZJHRCUEGUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZX2HUFID5RZJ32XZJHRCUEGUY/action/storage_attestation","attest_author":"https://pith.science/pith/JZX2HUFID5RZJ32XZJHRCUEGUY/action/author_attestation","sign_citation":"https://pith.science/pith/JZX2HUFID5RZJ32XZJHRCUEGUY/action/citation_signature","submit_replication":"https://pith.science/pith/JZX2HUFID5RZJ32XZJHRCUEGUY/action/replication_record"}},"created_at":"2026-06-05T01:15:11.453357+00:00","updated_at":"2026-06-05T01:15:11.453357+00:00"}