{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WMUPM3DI7ZNMC5RVM3UDRHCT3D","short_pith_number":"pith:WMUPM3DI","schema_version":"1.0","canonical_sha256":"b328f66c68fe5ac1763566e8389c53d8f5a1c1b669ff34f9fb43441ec3dfa01c","source":{"kind":"arxiv","id":"2601.19683","version":2},"attestation_state":"computed","paper":{"title":"SharpNet: Enhancing MLPs to Represent Functions with Controlled Non-differentiability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Hou, Hanting Niu, Junkai Deng, Wencheng Wang, Ying He","submitted_at":"2026-01-27T15:01:11Z","abstract_excerpt":"Multi-layer perceptrons (MLPs) are a standard tool for learning and function approximation, but they inherently produce globally smooth outputs. Consequently, they struggle to represent functions that are continuous yet intentionally non-differentiable (i.e., functions with prescribed $C^0$ sharp features) without ad hoc post-processing. We present SharpNet, a modified MLP architecture that encodes user-specified sharp features by augmenting the network with an auxiliary feature function defined as the solution to Poisson's equation with jump Neumann boundary conditions. This feature function "},"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":"2601.19683","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-01-27T15:01:11Z","cross_cats_sorted":[],"title_canon_sha256":"93666eb945ce0b5dd722594a3fb0c7af72fc3072c31b8d7f254c7133459fdf62","abstract_canon_sha256":"b2abd850cba03c2ed0d52a5a3a8d07c84d1af92be6ad4e4d7d6b9d7b9bc7244e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:40.559412Z","signature_b64":"fKXy+w7U8HmDVbd5aY+TI5gh/xvuwdo1gtduoofCcjC2LOODStbeiOsu7bSx06k1G/f9ygyK/kfalbbIs3bxCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b328f66c68fe5ac1763566e8389c53d8f5a1c1b669ff34f9fb43441ec3dfa01c","last_reissued_at":"2026-06-04T01:08:40.558839Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:40.558839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SharpNet: Enhancing MLPs to Represent Functions with Controlled Non-differentiability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Hou, Hanting Niu, Junkai Deng, Wencheng Wang, Ying He","submitted_at":"2026-01-27T15:01:11Z","abstract_excerpt":"Multi-layer perceptrons (MLPs) are a standard tool for learning and function approximation, but they inherently produce globally smooth outputs. Consequently, they struggle to represent functions that are continuous yet intentionally non-differentiable (i.e., functions with prescribed $C^0$ sharp features) without ad hoc post-processing. We present SharpNet, a modified MLP architecture that encodes user-specified sharp features by augmenting the network with an auxiliary feature function defined as the solution to Poisson's equation with jump Neumann boundary conditions. This feature function "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.19683","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/2601.19683/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":"2601.19683","created_at":"2026-06-04T01:08:40.558912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.19683v2","created_at":"2026-06-04T01:08:40.558912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.19683","created_at":"2026-06-04T01:08:40.558912+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMUPM3DI7ZNM","created_at":"2026-06-04T01:08:40.558912+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMUPM3DI7ZNMC5RV","created_at":"2026-06-04T01:08:40.558912+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMUPM3DI","created_at":"2026-06-04T01:08:40.558912+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/WMUPM3DI7ZNMC5RVM3UDRHCT3D","json":"https://pith.science/pith/WMUPM3DI7ZNMC5RVM3UDRHCT3D.json","graph_json":"https://pith.science/api/pith-number/WMUPM3DI7ZNMC5RVM3UDRHCT3D/graph.json","events_json":"https://pith.science/api/pith-number/WMUPM3DI7ZNMC5RVM3UDRHCT3D/events.json","paper":"https://pith.science/paper/WMUPM3DI"},"agent_actions":{"view_html":"https://pith.science/pith/WMUPM3DI7ZNMC5RVM3UDRHCT3D","download_json":"https://pith.science/pith/WMUPM3DI7ZNMC5RVM3UDRHCT3D.json","view_paper":"https://pith.science/paper/WMUPM3DI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.19683&json=true","fetch_graph":"https://pith.science/api/pith-number/WMUPM3DI7ZNMC5RVM3UDRHCT3D/graph.json","fetch_events":"https://pith.science/api/pith-number/WMUPM3DI7ZNMC5RVM3UDRHCT3D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMUPM3DI7ZNMC5RVM3UDRHCT3D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMUPM3DI7ZNMC5RVM3UDRHCT3D/action/storage_attestation","attest_author":"https://pith.science/pith/WMUPM3DI7ZNMC5RVM3UDRHCT3D/action/author_attestation","sign_citation":"https://pith.science/pith/WMUPM3DI7ZNMC5RVM3UDRHCT3D/action/citation_signature","submit_replication":"https://pith.science/pith/WMUPM3DI7ZNMC5RVM3UDRHCT3D/action/replication_record"}},"created_at":"2026-06-04T01:08:40.558912+00:00","updated_at":"2026-06-04T01:08:40.558912+00:00"}