{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BBJS5234SL3UTOPICRGQ62AHDI","short_pith_number":"pith:BBJS5234","schema_version":"1.0","canonical_sha256":"08532eeb7c92f749b9e8144d0f68071a2572973495273661cf51bbd2c79b0c0c","source":{"kind":"arxiv","id":"2505.00110","version":1},"attestation_state":"computed","paper":{"title":"On the expressivity of deep Heaviside networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"stat.ML","authors_text":"Insung Kong, Johannes Schmidt-Hieber, Juntong Chen, Sophie Langer","submitted_at":"2025-04-30T18:25:05Z","abstract_excerpt":"We show that deep Heaviside networks (DHNs) have limited expressiveness but that this can be overcome by including either skip connections or neurons with linear activation. We provide lower and upper bounds for the Vapnik-Chervonenkis (VC) dimensions and approximation rates of these network classes. As an application, we derive statistical convergence rates for DHN fits in the nonparametric regression model."},"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":"2505.00110","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-04-30T18:25:05Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA"],"title_canon_sha256":"4b763349c8aaebd64940684494c6a65a3a5eaf4387a5b302d2c0bf769f4cf86d","abstract_canon_sha256":"30c6fa77f44a005992f8825ab061d68d468727167da3af276a092e48b7e6c182"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:41.917935Z","signature_b64":"8Ncx992crBiSJM3dxrfxhPWbr4PKboYT6YXHBtJIperLE6bX1AR6G/sO8FAQwc3IzcTpeoTvDMoxJS+8S6iTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08532eeb7c92f749b9e8144d0f68071a2572973495273661cf51bbd2c79b0c0c","last_reissued_at":"2026-07-05T10:56:41.917478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:41.917478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the expressivity of deep Heaviside networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA"],"primary_cat":"stat.ML","authors_text":"Insung Kong, Johannes Schmidt-Hieber, Juntong Chen, Sophie Langer","submitted_at":"2025-04-30T18:25:05Z","abstract_excerpt":"We show that deep Heaviside networks (DHNs) have limited expressiveness but that this can be overcome by including either skip connections or neurons with linear activation. We provide lower and upper bounds for the Vapnik-Chervonenkis (VC) dimensions and approximation rates of these network classes. As an application, we derive statistical convergence rates for DHN fits in the nonparametric regression model."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00110","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/2505.00110/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":"2505.00110","created_at":"2026-07-05T10:56:41.917532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00110v1","created_at":"2026-07-05T10:56:41.917532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00110","created_at":"2026-07-05T10:56:41.917532+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBJS5234SL3U","created_at":"2026-07-05T10:56:41.917532+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBJS5234SL3UTOPI","created_at":"2026-07-05T10:56:41.917532+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBJS5234","created_at":"2026-07-05T10:56:41.917532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11558","citing_title":"A Composite Activation Function for Learning Stable Binary Representations","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBJS5234SL3UTOPICRGQ62AHDI","json":"https://pith.science/pith/BBJS5234SL3UTOPICRGQ62AHDI.json","graph_json":"https://pith.science/api/pith-number/BBJS5234SL3UTOPICRGQ62AHDI/graph.json","events_json":"https://pith.science/api/pith-number/BBJS5234SL3UTOPICRGQ62AHDI/events.json","paper":"https://pith.science/paper/BBJS5234"},"agent_actions":{"view_html":"https://pith.science/pith/BBJS5234SL3UTOPICRGQ62AHDI","download_json":"https://pith.science/pith/BBJS5234SL3UTOPICRGQ62AHDI.json","view_paper":"https://pith.science/paper/BBJS5234","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00110&json=true","fetch_graph":"https://pith.science/api/pith-number/BBJS5234SL3UTOPICRGQ62AHDI/graph.json","fetch_events":"https://pith.science/api/pith-number/BBJS5234SL3UTOPICRGQ62AHDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBJS5234SL3UTOPICRGQ62AHDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBJS5234SL3UTOPICRGQ62AHDI/action/storage_attestation","attest_author":"https://pith.science/pith/BBJS5234SL3UTOPICRGQ62AHDI/action/author_attestation","sign_citation":"https://pith.science/pith/BBJS5234SL3UTOPICRGQ62AHDI/action/citation_signature","submit_replication":"https://pith.science/pith/BBJS5234SL3UTOPICRGQ62AHDI/action/replication_record"}},"created_at":"2026-07-05T10:56:41.917532+00:00","updated_at":"2026-07-05T10:56:41.917532+00:00"}