{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4ZJWYI3OIS5HNBXRPE4X4F7YSC","short_pith_number":"pith:4ZJWYI3O","schema_version":"1.0","canonical_sha256":"e6536c236e44ba7686f179397e17f8909ccafef801acf379a1470b836e1bbeae","source":{"kind":"arxiv","id":"2310.02117","version":1},"attestation_state":"computed","paper":{"title":"Symmetric Single Index Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron Zweig, Joan Bruna","submitted_at":"2023-10-03T14:59:00Z","abstract_excerpt":"Few neural architectures lend themselves to provable learning with gradient based methods. One popular model is the single-index model, in which labels are produced by composing an unknown linear projection with a possibly unknown scalar link function. Learning this model with SGD is relatively well-understood, whereby the so-called information exponent of the link function governs a polynomial sample complexity rate. However, extending this analysis to deeper or more complicated architectures remains challenging.\n  In this work, we consider single index learning in the setting of symmetric ne"},"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":"2310.02117","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-03T14:59:00Z","cross_cats_sorted":[],"title_canon_sha256":"9e28ab9c9a0fcbc75cd41137a3ba3d1f97513681a1c63d59299d2a3e3a3d7acc","abstract_canon_sha256":"4c358046e1b541880b49a0f3e8c29d80deffd5fb2ae636eadd741564b35f0a7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:56:50.276463Z","signature_b64":"ZnzmsDItMAEBEgwaa8ougYxA5L6R6yitVP+/zgmXOsTMsPj0gouz0vNXqX1/m1Y57glksz7+Bin5fGjIkLPPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6536c236e44ba7686f179397e17f8909ccafef801acf379a1470b836e1bbeae","last_reissued_at":"2026-07-05T06:56:50.276009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:56:50.276009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symmetric Single Index Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron Zweig, Joan Bruna","submitted_at":"2023-10-03T14:59:00Z","abstract_excerpt":"Few neural architectures lend themselves to provable learning with gradient based methods. One popular model is the single-index model, in which labels are produced by composing an unknown linear projection with a possibly unknown scalar link function. Learning this model with SGD is relatively well-understood, whereby the so-called information exponent of the link function governs a polynomial sample complexity rate. However, extending this analysis to deeper or more complicated architectures remains challenging.\n  In this work, we consider single index learning in the setting of symmetric ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02117","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/2310.02117/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":"2310.02117","created_at":"2026-07-05T06:56:50.276077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02117v1","created_at":"2026-07-05T06:56:50.276077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02117","created_at":"2026-07-05T06:56:50.276077+00:00"},{"alias_kind":"pith_short_12","alias_value":"4ZJWYI3OIS5H","created_at":"2026-07-05T06:56:50.276077+00:00"},{"alias_kind":"pith_short_16","alias_value":"4ZJWYI3OIS5HNBXR","created_at":"2026-07-05T06:56:50.276077+00:00"},{"alias_kind":"pith_short_8","alias_value":"4ZJWYI3O","created_at":"2026-07-05T06:56:50.276077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21336","citing_title":"Joint Learning in the Gaussian Single Index Model","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4ZJWYI3OIS5HNBXRPE4X4F7YSC","json":"https://pith.science/pith/4ZJWYI3OIS5HNBXRPE4X4F7YSC.json","graph_json":"https://pith.science/api/pith-number/4ZJWYI3OIS5HNBXRPE4X4F7YSC/graph.json","events_json":"https://pith.science/api/pith-number/4ZJWYI3OIS5HNBXRPE4X4F7YSC/events.json","paper":"https://pith.science/paper/4ZJWYI3O"},"agent_actions":{"view_html":"https://pith.science/pith/4ZJWYI3OIS5HNBXRPE4X4F7YSC","download_json":"https://pith.science/pith/4ZJWYI3OIS5HNBXRPE4X4F7YSC.json","view_paper":"https://pith.science/paper/4ZJWYI3O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02117&json=true","fetch_graph":"https://pith.science/api/pith-number/4ZJWYI3OIS5HNBXRPE4X4F7YSC/graph.json","fetch_events":"https://pith.science/api/pith-number/4ZJWYI3OIS5HNBXRPE4X4F7YSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4ZJWYI3OIS5HNBXRPE4X4F7YSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4ZJWYI3OIS5HNBXRPE4X4F7YSC/action/storage_attestation","attest_author":"https://pith.science/pith/4ZJWYI3OIS5HNBXRPE4X4F7YSC/action/author_attestation","sign_citation":"https://pith.science/pith/4ZJWYI3OIS5HNBXRPE4X4F7YSC/action/citation_signature","submit_replication":"https://pith.science/pith/4ZJWYI3OIS5HNBXRPE4X4F7YSC/action/replication_record"}},"created_at":"2026-07-05T06:56:50.276077+00:00","updated_at":"2026-07-05T06:56:50.276077+00:00"}