{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NUEFTB6ZBC4WHIX2J3JVTKEMCE","short_pith_number":"pith:NUEFTB6Z","schema_version":"1.0","canonical_sha256":"6d085987d908b963a2fa4ed359a88c1110ba7b581cf4dea6151508cc79747a12","source":{"kind":"arxiv","id":"2607.25200","version":1},"attestation_state":"computed","paper":{"title":"Algorithmic Separation between Constant-Depth and Logarithmic-Depth Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jason D. Lee, Yunwei Ren, Zihao Wang","submitted_at":"2026-07-28T02:13:30Z","abstract_excerpt":"Despite the empirical advantages of deep networks over shallow ones, theoretical depth separations largely concern approximation power, while algorithmic results are mostly limited to comparisons between two- and three-layer networks. In this work, we prove the first algorithmic separation between constant-depth and logarithmic-depth networks.\n  Specifically, we identify a class of Boolean functions with hierarchically structured Fourier spectra that logarithmic-depth networks can learn efficiently using layerwise coordinate descent by reconstructing the spectra hierarchically and adaptively. "},"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":"2607.25200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-28T02:13:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d25b05b37531ee61a9aaaacf6177b16a972a2cc3f2a13ae80d5e90f8a2520dd0","abstract_canon_sha256":"6ac996143598ad0b53c10f2758699dc315ec7619b448577ea3a864cf95ecdc4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:25:08.156709Z","signature_b64":"e7d/qOGZBvnyZ+FTRrnMYi/IBMC1ePySFBJCmYbIeFzjgE8ej4f6W0Zvw7LZzxqa0m5Utym7nI1vqUdTEyw3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d085987d908b963a2fa4ed359a88c1110ba7b581cf4dea6151508cc79747a12","last_reissued_at":"2026-07-29T00:25:08.155842Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:25:08.155842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Algorithmic Separation between Constant-Depth and Logarithmic-Depth Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jason D. Lee, Yunwei Ren, Zihao Wang","submitted_at":"2026-07-28T02:13:30Z","abstract_excerpt":"Despite the empirical advantages of deep networks over shallow ones, theoretical depth separations largely concern approximation power, while algorithmic results are mostly limited to comparisons between two- and three-layer networks. In this work, we prove the first algorithmic separation between constant-depth and logarithmic-depth networks.\n  Specifically, we identify a class of Boolean functions with hierarchically structured Fourier spectra that logarithmic-depth networks can learn efficiently using layerwise coordinate descent by reconstructing the spectra hierarchically and adaptively. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25200","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/2607.25200/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":"2607.25200","created_at":"2026-07-29T00:25:08.156283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.25200v1","created_at":"2026-07-29T00:25:08.156283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25200","created_at":"2026-07-29T00:25:08.156283+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUEFTB6ZBC4W","created_at":"2026-07-29T00:25:08.156283+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUEFTB6ZBC4WHIX2","created_at":"2026-07-29T00:25:08.156283+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUEFTB6Z","created_at":"2026-07-29T00:25:08.156283+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/NUEFTB6ZBC4WHIX2J3JVTKEMCE","json":"https://pith.science/pith/NUEFTB6ZBC4WHIX2J3JVTKEMCE.json","graph_json":"https://pith.science/api/pith-number/NUEFTB6ZBC4WHIX2J3JVTKEMCE/graph.json","events_json":"https://pith.science/api/pith-number/NUEFTB6ZBC4WHIX2J3JVTKEMCE/events.json","paper":"https://pith.science/paper/NUEFTB6Z"},"agent_actions":{"view_html":"https://pith.science/pith/NUEFTB6ZBC4WHIX2J3JVTKEMCE","download_json":"https://pith.science/pith/NUEFTB6ZBC4WHIX2J3JVTKEMCE.json","view_paper":"https://pith.science/paper/NUEFTB6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.25200&json=true","fetch_graph":"https://pith.science/api/pith-number/NUEFTB6ZBC4WHIX2J3JVTKEMCE/graph.json","fetch_events":"https://pith.science/api/pith-number/NUEFTB6ZBC4WHIX2J3JVTKEMCE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUEFTB6ZBC4WHIX2J3JVTKEMCE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUEFTB6ZBC4WHIX2J3JVTKEMCE/action/storage_attestation","attest_author":"https://pith.science/pith/NUEFTB6ZBC4WHIX2J3JVTKEMCE/action/author_attestation","sign_citation":"https://pith.science/pith/NUEFTB6ZBC4WHIX2J3JVTKEMCE/action/citation_signature","submit_replication":"https://pith.science/pith/NUEFTB6ZBC4WHIX2J3JVTKEMCE/action/replication_record"}},"created_at":"2026-07-29T00:25:08.156283+00:00","updated_at":"2026-07-29T00:25:08.156283+00:00"}