{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7UCDCCYLBVF54M2X6CZTOH7OIH","short_pith_number":"pith:7UCDCCYL","schema_version":"1.0","canonical_sha256":"fd04310b0b0d4bde3357f0b3371fee41fa0c1c7a5270d46ac51e6cd4e5280839","source":{"kind":"arxiv","id":"2107.03066","version":1},"attestation_state":"computed","paper":{"title":"Probabilistic partition of unity networks: clustering based deep approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andy Huang, Kookjin Lee, Mamikon Gulian, Nat Trask","submitted_at":"2021-07-07T08:02:00Z","abstract_excerpt":"Partition of unity networks (POU-Nets) have been shown capable of realizing algebraic convergence rates for regression and solution of PDEs, but require empirical tuning of training parameters. We enrich POU-Nets with a Gaussian noise model to obtain a probabilistic generalization amenable to gradient-based minimization of a maximum likelihood loss. The resulting architecture provides spatial representations of both noiseless and noisy data as Gaussian mixtures with closed form expressions for variance which provides an estimator of local error. The training process yields remarkably sharp par"},"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":"2107.03066","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-07T08:02:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"40ea137032e9e65217ec9b5af5c369100b8e46ed45f66eb1aa8a14f856a9f1c0","abstract_canon_sha256":"4b1b18047b57cd5e0140c673d9f1003fea57facf9d76e5ebe1716406927cb699"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:55:59.808010Z","signature_b64":"zoSOO/OUHslNFQci7J6/4C/kNwGllyEUx9ULMyGo2o5jav8KbtkTQpZNaq6Rzh4XYLPPZ52MbnesFVTeJZt1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd04310b0b0d4bde3357f0b3371fee41fa0c1c7a5270d46ac51e6cd4e5280839","last_reissued_at":"2026-07-05T02:55:59.807596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:55:59.807596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic partition of unity networks: clustering based deep approximation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andy Huang, Kookjin Lee, Mamikon Gulian, Nat Trask","submitted_at":"2021-07-07T08:02:00Z","abstract_excerpt":"Partition of unity networks (POU-Nets) have been shown capable of realizing algebraic convergence rates for regression and solution of PDEs, but require empirical tuning of training parameters. We enrich POU-Nets with a Gaussian noise model to obtain a probabilistic generalization amenable to gradient-based minimization of a maximum likelihood loss. The resulting architecture provides spatial representations of both noiseless and noisy data as Gaussian mixtures with closed form expressions for variance which provides an estimator of local error. The training process yields remarkably sharp par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.03066","kind":"arxiv","version":1},"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/2107.03066/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":"2107.03066","created_at":"2026-07-05T02:55:59.807651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.03066v1","created_at":"2026-07-05T02:55:59.807651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.03066","created_at":"2026-07-05T02:55:59.807651+00:00"},{"alias_kind":"pith_short_12","alias_value":"7UCDCCYLBVF5","created_at":"2026-07-05T02:55:59.807651+00:00"},{"alias_kind":"pith_short_16","alias_value":"7UCDCCYLBVF54M2X","created_at":"2026-07-05T02:55:59.807651+00:00"},{"alias_kind":"pith_short_8","alias_value":"7UCDCCYL","created_at":"2026-07-05T02:55:59.807651+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/7UCDCCYLBVF54M2X6CZTOH7OIH","json":"https://pith.science/pith/7UCDCCYLBVF54M2X6CZTOH7OIH.json","graph_json":"https://pith.science/api/pith-number/7UCDCCYLBVF54M2X6CZTOH7OIH/graph.json","events_json":"https://pith.science/api/pith-number/7UCDCCYLBVF54M2X6CZTOH7OIH/events.json","paper":"https://pith.science/paper/7UCDCCYL"},"agent_actions":{"view_html":"https://pith.science/pith/7UCDCCYLBVF54M2X6CZTOH7OIH","download_json":"https://pith.science/pith/7UCDCCYLBVF54M2X6CZTOH7OIH.json","view_paper":"https://pith.science/paper/7UCDCCYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.03066&json=true","fetch_graph":"https://pith.science/api/pith-number/7UCDCCYLBVF54M2X6CZTOH7OIH/graph.json","fetch_events":"https://pith.science/api/pith-number/7UCDCCYLBVF54M2X6CZTOH7OIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7UCDCCYLBVF54M2X6CZTOH7OIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7UCDCCYLBVF54M2X6CZTOH7OIH/action/storage_attestation","attest_author":"https://pith.science/pith/7UCDCCYLBVF54M2X6CZTOH7OIH/action/author_attestation","sign_citation":"https://pith.science/pith/7UCDCCYLBVF54M2X6CZTOH7OIH/action/citation_signature","submit_replication":"https://pith.science/pith/7UCDCCYLBVF54M2X6CZTOH7OIH/action/replication_record"}},"created_at":"2026-07-05T02:55:59.807651+00:00","updated_at":"2026-07-05T02:55:59.807651+00:00"}