{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XTXYPEMTIDQLJW4CBADC3QXVHT","short_pith_number":"pith:XTXYPEMT","schema_version":"1.0","canonical_sha256":"bcef87919340e0b4db8208062dc2f53ceafc410e54175993a6e33f0be277951b","source":{"kind":"arxiv","id":"2210.15651","version":1},"attestation_state":"computed","paper":{"title":"Learning Single-Index Models with Shallow Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alberto Bietti, Clayton Sanford, Joan Bruna, Min Jae Song","submitted_at":"2022-10-27T17:52:58Z","abstract_excerpt":"Single-index models are a class of functions given by an unknown univariate ``link'' function applied to an unknown one-dimensional projection of the input. These models are particularly relevant in high dimension, when the data might present low-dimensional structure that learning algorithms should adapt to. While several statistical aspects of this model, such as the sample complexity of recovering the relevant (one-dimensional) subspace, are well-understood, they rely on tailored algorithms that exploit the specific structure of the target function. In this work, we introduce a natural clas"},"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":"2210.15651","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-27T17:52:58Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"b3de89dac991e7726ca341d29314e0c03d18565c17fbacfbc86d59d950fdd610","abstract_canon_sha256":"2ef9836b5c67677358de9120897fe48298fd5721fa49b409be546584c1cc1268"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:08.415547Z","signature_b64":"nBDJHLSiK7BBzKhCqeXv0mnm4Ppsp3wsMYnBuCMSKxu0cJ9XGLbhV7ZHojoskUywGKNSLpqRqBWySk3mn3wTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcef87919340e0b4db8208062dc2f53ceafc410e54175993a6e33f0be277951b","last_reissued_at":"2026-07-05T05:11:08.415065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:08.415065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Single-Index Models with Shallow Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alberto Bietti, Clayton Sanford, Joan Bruna, Min Jae Song","submitted_at":"2022-10-27T17:52:58Z","abstract_excerpt":"Single-index models are a class of functions given by an unknown univariate ``link'' function applied to an unknown one-dimensional projection of the input. These models are particularly relevant in high dimension, when the data might present low-dimensional structure that learning algorithms should adapt to. While several statistical aspects of this model, such as the sample complexity of recovering the relevant (one-dimensional) subspace, are well-understood, they rely on tailored algorithms that exploit the specific structure of the target function. In this work, we introduce a natural clas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.15651","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/2210.15651/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":"2210.15651","created_at":"2026-07-05T05:11:08.415126+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.15651v1","created_at":"2026-07-05T05:11:08.415126+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.15651","created_at":"2026-07-05T05:11:08.415126+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTXYPEMTIDQL","created_at":"2026-07-05T05:11:08.415126+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTXYPEMTIDQLJW4C","created_at":"2026-07-05T05:11:08.415126+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTXYPEMT","created_at":"2026-07-05T05:11:08.415126+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.14473","citing_title":"Sharp convergence rates for Spectral methods via the feature space decomposition method","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XTXYPEMTIDQLJW4CBADC3QXVHT","json":"https://pith.science/pith/XTXYPEMTIDQLJW4CBADC3QXVHT.json","graph_json":"https://pith.science/api/pith-number/XTXYPEMTIDQLJW4CBADC3QXVHT/graph.json","events_json":"https://pith.science/api/pith-number/XTXYPEMTIDQLJW4CBADC3QXVHT/events.json","paper":"https://pith.science/paper/XTXYPEMT"},"agent_actions":{"view_html":"https://pith.science/pith/XTXYPEMTIDQLJW4CBADC3QXVHT","download_json":"https://pith.science/pith/XTXYPEMTIDQLJW4CBADC3QXVHT.json","view_paper":"https://pith.science/paper/XTXYPEMT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.15651&json=true","fetch_graph":"https://pith.science/api/pith-number/XTXYPEMTIDQLJW4CBADC3QXVHT/graph.json","fetch_events":"https://pith.science/api/pith-number/XTXYPEMTIDQLJW4CBADC3QXVHT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTXYPEMTIDQLJW4CBADC3QXVHT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTXYPEMTIDQLJW4CBADC3QXVHT/action/storage_attestation","attest_author":"https://pith.science/pith/XTXYPEMTIDQLJW4CBADC3QXVHT/action/author_attestation","sign_citation":"https://pith.science/pith/XTXYPEMTIDQLJW4CBADC3QXVHT/action/citation_signature","submit_replication":"https://pith.science/pith/XTXYPEMTIDQLJW4CBADC3QXVHT/action/replication_record"}},"created_at":"2026-07-05T05:11:08.415126+00:00","updated_at":"2026-07-05T05:11:08.415126+00:00"}