{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:INK3VDHD3XLJENGUPVY66V7UQO","short_pith_number":"pith:INK3VDHD","schema_version":"1.0","canonical_sha256":"4355ba8ce3ddd69234d47d71ef57f483a33a8c9f9822559f1aae3494f9c937d8","source":{"kind":"arxiv","id":"2404.13785","version":1},"attestation_state":"computed","paper":{"title":"How to Inverting the Leverage Score Distribution?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junze Yin, Weixin Wang, Zhao Song, Zheng Yu, Zhihang Li","submitted_at":"2024-04-21T21:36:42Z","abstract_excerpt":"Leverage score is a fundamental problem in machine learning and theoretical computer science. It has extensive applications in regression analysis, randomized algorithms, and neural network inversion. Despite leverage scores are widely used as a tool, in this paper, we study a novel problem, namely the inverting leverage score problem. We analyze to invert the leverage score distributions back to recover model parameters. Specifically, given a leverage score $\\sigma \\in \\mathbb{R}^n$, the matrix $A \\in \\mathbb{R}^{n \\times d}$, and the vector $b \\in \\mathbb{R}^n$, we analyze the non-convex opt"},"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":"2404.13785","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-21T21:36:42Z","cross_cats_sorted":[],"title_canon_sha256":"aa20d3ad2ef0dd18c3de5ff4cd25f9bf6e4c3bd6573fe675573767c4ec619bff","abstract_canon_sha256":"d42a19e7accf287663f4a6c7cdd00c8b06b20783a2bfa2cee1b3ddf76739830e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:10:37.250506Z","signature_b64":"dv0V+MlNcjNS1XbSnJQFn/EBeFeYMUEcF9m9islaYfyYVQdlXc9rBEbLRgltHvZaoTQCzh7gIfhnU6DgFo0ZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4355ba8ce3ddd69234d47d71ef57f483a33a8c9f9822559f1aae3494f9c937d8","last_reissued_at":"2026-07-05T08:10:37.249994Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:10:37.249994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Inverting the Leverage Score Distribution?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junze Yin, Weixin Wang, Zhao Song, Zheng Yu, Zhihang Li","submitted_at":"2024-04-21T21:36:42Z","abstract_excerpt":"Leverage score is a fundamental problem in machine learning and theoretical computer science. It has extensive applications in regression analysis, randomized algorithms, and neural network inversion. Despite leverage scores are widely used as a tool, in this paper, we study a novel problem, namely the inverting leverage score problem. We analyze to invert the leverage score distributions back to recover model parameters. Specifically, given a leverage score $\\sigma \\in \\mathbb{R}^n$, the matrix $A \\in \\mathbb{R}^{n \\times d}$, and the vector $b \\in \\mathbb{R}^n$, we analyze the non-convex opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.13785","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/2404.13785/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":"2404.13785","created_at":"2026-07-05T08:10:37.250055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.13785v1","created_at":"2026-07-05T08:10:37.250055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.13785","created_at":"2026-07-05T08:10:37.250055+00:00"},{"alias_kind":"pith_short_12","alias_value":"INK3VDHD3XLJ","created_at":"2026-07-05T08:10:37.250055+00:00"},{"alias_kind":"pith_short_16","alias_value":"INK3VDHD3XLJENGU","created_at":"2026-07-05T08:10:37.250055+00:00"},{"alias_kind":"pith_short_8","alias_value":"INK3VDHD","created_at":"2026-07-05T08:10:37.250055+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06167","citing_title":"Universal Approximation of Visual Autoregressive Transformers","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INK3VDHD3XLJENGUPVY66V7UQO","json":"https://pith.science/pith/INK3VDHD3XLJENGUPVY66V7UQO.json","graph_json":"https://pith.science/api/pith-number/INK3VDHD3XLJENGUPVY66V7UQO/graph.json","events_json":"https://pith.science/api/pith-number/INK3VDHD3XLJENGUPVY66V7UQO/events.json","paper":"https://pith.science/paper/INK3VDHD"},"agent_actions":{"view_html":"https://pith.science/pith/INK3VDHD3XLJENGUPVY66V7UQO","download_json":"https://pith.science/pith/INK3VDHD3XLJENGUPVY66V7UQO.json","view_paper":"https://pith.science/paper/INK3VDHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.13785&json=true","fetch_graph":"https://pith.science/api/pith-number/INK3VDHD3XLJENGUPVY66V7UQO/graph.json","fetch_events":"https://pith.science/api/pith-number/INK3VDHD3XLJENGUPVY66V7UQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INK3VDHD3XLJENGUPVY66V7UQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INK3VDHD3XLJENGUPVY66V7UQO/action/storage_attestation","attest_author":"https://pith.science/pith/INK3VDHD3XLJENGUPVY66V7UQO/action/author_attestation","sign_citation":"https://pith.science/pith/INK3VDHD3XLJENGUPVY66V7UQO/action/citation_signature","submit_replication":"https://pith.science/pith/INK3VDHD3XLJENGUPVY66V7UQO/action/replication_record"}},"created_at":"2026-07-05T08:10:37.250055+00:00","updated_at":"2026-07-05T08:10:37.250055+00:00"}