{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4NRVQ5VFS2KRC3UMKJCH3RHADP","short_pith_number":"pith:4NRVQ5VF","schema_version":"1.0","canonical_sha256":"e3635876a59695116e8c52447dc4e01bf44c1a97901cdab4277199f79ab636ca","source":{"kind":"arxiv","id":"2602.00511","version":2},"attestation_state":"computed","paper":{"title":"Partition of Unity Neural Networks for Interpretable Classification with Explicit Class Regions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Akram Aldroubi","submitted_at":"2026-01-31T04:40:11Z","abstract_excerpt":"Despite their empirical success, neural network classifiers remain difficult to interpret. In softmax-based models, class regions are defined implicitly as solutions to systems of inequalities among logits, making them difficult to extract and visualize. We introduce Partition of Unity Neural Networks (PUNN), an architecture in which class probabilities arise directly from a learned partition of unity, without requiring a softmax layer.\n  PUNN constructs $k$ nonnegative functions $h_1, \\ldots, h_k$ satisfying $\\sum_i h_i(x) = 1$, where each $h_i(x)$ directly represents $P(\\text{class } i \\mid "},"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":"2602.00511","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-31T04:40:11Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"4bd236869ab5cca8e7ec7c3395573ff6e66a5a570cce0664070f144b91b25967","abstract_canon_sha256":"ca5ff973bb3e6584b2143ffd01a2daf2f40f2ea4c079e9b0d0a94c5377a6a344"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:24.065929Z","signature_b64":"N+mJYbNi1+tIFOW/fXjSmKDTOIqdb3Fj16hXj+8xw3oQSWBbPZJ5lsX0pq3zpoXJ1TlzH0ScvBOBa6reZ47FBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3635876a59695116e8c52447dc4e01bf44c1a97901cdab4277199f79ab636ca","last_reissued_at":"2026-05-26T01:03:24.064955Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:24.064955Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Partition of Unity Neural Networks for Interpretable Classification with Explicit Class Regions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Akram Aldroubi","submitted_at":"2026-01-31T04:40:11Z","abstract_excerpt":"Despite their empirical success, neural network classifiers remain difficult to interpret. In softmax-based models, class regions are defined implicitly as solutions to systems of inequalities among logits, making them difficult to extract and visualize. We introduce Partition of Unity Neural Networks (PUNN), an architecture in which class probabilities arise directly from a learned partition of unity, without requiring a softmax layer.\n  PUNN constructs $k$ nonnegative functions $h_1, \\ldots, h_k$ satisfying $\\sum_i h_i(x) = 1$, where each $h_i(x)$ directly represents $P(\\text{class } i \\mid "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.00511","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/2602.00511/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":"2602.00511","created_at":"2026-05-26T01:03:24.065092+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.00511v2","created_at":"2026-05-26T01:03:24.065092+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.00511","created_at":"2026-05-26T01:03:24.065092+00:00"},{"alias_kind":"pith_short_12","alias_value":"4NRVQ5VFS2KR","created_at":"2026-05-26T01:03:24.065092+00:00"},{"alias_kind":"pith_short_16","alias_value":"4NRVQ5VFS2KRC3UM","created_at":"2026-05-26T01:03:24.065092+00:00"},{"alias_kind":"pith_short_8","alias_value":"4NRVQ5VF","created_at":"2026-05-26T01:03:24.065092+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/4NRVQ5VFS2KRC3UMKJCH3RHADP","json":"https://pith.science/pith/4NRVQ5VFS2KRC3UMKJCH3RHADP.json","graph_json":"https://pith.science/api/pith-number/4NRVQ5VFS2KRC3UMKJCH3RHADP/graph.json","events_json":"https://pith.science/api/pith-number/4NRVQ5VFS2KRC3UMKJCH3RHADP/events.json","paper":"https://pith.science/paper/4NRVQ5VF"},"agent_actions":{"view_html":"https://pith.science/pith/4NRVQ5VFS2KRC3UMKJCH3RHADP","download_json":"https://pith.science/pith/4NRVQ5VFS2KRC3UMKJCH3RHADP.json","view_paper":"https://pith.science/paper/4NRVQ5VF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.00511&json=true","fetch_graph":"https://pith.science/api/pith-number/4NRVQ5VFS2KRC3UMKJCH3RHADP/graph.json","fetch_events":"https://pith.science/api/pith-number/4NRVQ5VFS2KRC3UMKJCH3RHADP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4NRVQ5VFS2KRC3UMKJCH3RHADP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4NRVQ5VFS2KRC3UMKJCH3RHADP/action/storage_attestation","attest_author":"https://pith.science/pith/4NRVQ5VFS2KRC3UMKJCH3RHADP/action/author_attestation","sign_citation":"https://pith.science/pith/4NRVQ5VFS2KRC3UMKJCH3RHADP/action/citation_signature","submit_replication":"https://pith.science/pith/4NRVQ5VFS2KRC3UMKJCH3RHADP/action/replication_record"}},"created_at":"2026-05-26T01:03:24.065092+00:00","updated_at":"2026-05-26T01:03:24.065092+00:00"}