{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3T62FUEGPPAESNZNATSOIRFA5H","short_pith_number":"pith:3T62FUEG","schema_version":"1.0","canonical_sha256":"dcfda2d0867bc049372d04e4e444a0e9fa9372a8c09661a2719c5f030bf30ef6","source":{"kind":"arxiv","id":"2302.12289","version":1},"attestation_state":"computed","paper":{"title":"Beyond Moments: Robustly Learning Affine Transformations with Asymptotically Optimal Error","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"He Jia, Pravesh K . Kothari, Santosh S. Vempala","submitted_at":"2023-02-23T19:13:30Z","abstract_excerpt":"We present a polynomial-time algorithm for robustly learning an unknown affine transformation of the standard hypercube from samples, an important and well-studied setting for independent component analysis (ICA). Specifically, given an $\\epsilon$-corrupted sample from a distribution $D$ obtained by applying an unknown affine transformation $x \\rightarrow Ax+s$ to the uniform distribution on a $d$-dimensional hypercube $[-1,1]^d$, our algorithm constructs $\\hat{A}, \\hat{s}$ such that the total variation distance of the distribution $\\hat{D}$ from $D$ is $O(\\epsilon)$ using poly$(d)$ time and s"},"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":"2302.12289","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2023-02-23T19:13:30Z","cross_cats_sorted":["cs.LG","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"7919225a05d4c24ce2ab0e703f74ff7341157dd474d5dfe4fb7e04ccc91ab1d4","abstract_canon_sha256":"620463aab80b7e1cbd1fe0ece40b8d302722997675434137c3457e0a8e0babc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:07.847851Z","signature_b64":"JBIBLNa5dHoLBlOH+FKQjUhWHx/06IQO8/RyPqjnH+lZrhVhjj0gB6Ck2WfhWOxRupk6/4IWO256EXAWlvVaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcfda2d0867bc049372d04e4e444a0e9fa9372a8c09661a2719c5f030bf30ef6","last_reissued_at":"2026-07-05T05:45:07.847293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:07.847293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Moments: Robustly Learning Affine Transformations with Asymptotically Optimal Error","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.DS","authors_text":"He Jia, Pravesh K . Kothari, Santosh S. Vempala","submitted_at":"2023-02-23T19:13:30Z","abstract_excerpt":"We present a polynomial-time algorithm for robustly learning an unknown affine transformation of the standard hypercube from samples, an important and well-studied setting for independent component analysis (ICA). Specifically, given an $\\epsilon$-corrupted sample from a distribution $D$ obtained by applying an unknown affine transformation $x \\rightarrow Ax+s$ to the uniform distribution on a $d$-dimensional hypercube $[-1,1]^d$, our algorithm constructs $\\hat{A}, \\hat{s}$ such that the total variation distance of the distribution $\\hat{D}$ from $D$ is $O(\\epsilon)$ using poly$(d)$ time and s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12289","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/2302.12289/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":"2302.12289","created_at":"2026-07-05T05:45:07.847377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12289v1","created_at":"2026-07-05T05:45:07.847377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12289","created_at":"2026-07-05T05:45:07.847377+00:00"},{"alias_kind":"pith_short_12","alias_value":"3T62FUEGPPAE","created_at":"2026-07-05T05:45:07.847377+00:00"},{"alias_kind":"pith_short_16","alias_value":"3T62FUEGPPAESNZN","created_at":"2026-07-05T05:45:07.847377+00:00"},{"alias_kind":"pith_short_8","alias_value":"3T62FUEG","created_at":"2026-07-05T05:45:07.847377+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05137","citing_title":"On the Learnability of Distribution Classes with Adaptive Adversaries","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3T62FUEGPPAESNZNATSOIRFA5H","json":"https://pith.science/pith/3T62FUEGPPAESNZNATSOIRFA5H.json","graph_json":"https://pith.science/api/pith-number/3T62FUEGPPAESNZNATSOIRFA5H/graph.json","events_json":"https://pith.science/api/pith-number/3T62FUEGPPAESNZNATSOIRFA5H/events.json","paper":"https://pith.science/paper/3T62FUEG"},"agent_actions":{"view_html":"https://pith.science/pith/3T62FUEGPPAESNZNATSOIRFA5H","download_json":"https://pith.science/pith/3T62FUEGPPAESNZNATSOIRFA5H.json","view_paper":"https://pith.science/paper/3T62FUEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12289&json=true","fetch_graph":"https://pith.science/api/pith-number/3T62FUEGPPAESNZNATSOIRFA5H/graph.json","fetch_events":"https://pith.science/api/pith-number/3T62FUEGPPAESNZNATSOIRFA5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3T62FUEGPPAESNZNATSOIRFA5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3T62FUEGPPAESNZNATSOIRFA5H/action/storage_attestation","attest_author":"https://pith.science/pith/3T62FUEGPPAESNZNATSOIRFA5H/action/author_attestation","sign_citation":"https://pith.science/pith/3T62FUEGPPAESNZNATSOIRFA5H/action/citation_signature","submit_replication":"https://pith.science/pith/3T62FUEGPPAESNZNATSOIRFA5H/action/replication_record"}},"created_at":"2026-07-05T05:45:07.847377+00:00","updated_at":"2026-07-05T05:45:07.847377+00:00"}