{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:M6MDIV4UD4IQZLI6ZRCZQC7PAO","short_pith_number":"pith:M6MDIV4U","schema_version":"1.0","canonical_sha256":"67983457941f110cad1ecc45980bef03ba5ccbdd364341e2ae107264b39644c6","source":{"kind":"arxiv","id":"2010.11925","version":3},"attestation_state":"computed","paper":{"title":"The Polynomial Method is Universal for Distribution-Free Correlational SQ Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Adam Klivans, Aravind Gollakota, Sushrut Karmalkar","submitted_at":"2020-10-22T17:55:26Z","abstract_excerpt":"We consider the problem of distribution-free learning for Boolean function classes in the PAC and agnostic models. Generalizing a beautiful work of Malach and Shalev-Shwartz (2022) that gave tight correlational SQ (CSQ) lower bounds for learning DNF formulas, we give new proofs that lower bounds on the threshold or approximate degree of any function class directly imply CSQ lower bounds for PAC or agnostic learning respectively. While such bounds implicitly follow by combining prior results by Feldman (2008, 2012) and Sherstov (2008, 2011), to our knowledge the precise statements we give had n"},"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":"2010.11925","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2020-10-22T17:55:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e225528a8d8f1f2fc9841d9fa759139a03d95826b2a5e539d07527924160a08d","abstract_canon_sha256":"b3b39cfb63fdecf125884712dc691dadd2f5c8f12908c3b49e2e22a541cd1048"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:18.033115Z","signature_b64":"N2A7wIiLOuvdjmCHDBdSq7Vd9ognO/2/byqK5aIG0sCvJL3+ywcFEAQIvbWvtyjVzG6Kx4D74dIKNmjcap8WCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67983457941f110cad1ecc45980bef03ba5ccbdd364341e2ae107264b39644c6","last_reissued_at":"2026-07-05T06:44:18.032590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:18.032590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Polynomial Method is Universal for Distribution-Free Correlational SQ Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"Adam Klivans, Aravind Gollakota, Sushrut Karmalkar","submitted_at":"2020-10-22T17:55:26Z","abstract_excerpt":"We consider the problem of distribution-free learning for Boolean function classes in the PAC and agnostic models. Generalizing a beautiful work of Malach and Shalev-Shwartz (2022) that gave tight correlational SQ (CSQ) lower bounds for learning DNF formulas, we give new proofs that lower bounds on the threshold or approximate degree of any function class directly imply CSQ lower bounds for PAC or agnostic learning respectively. While such bounds implicitly follow by combining prior results by Feldman (2008, 2012) and Sherstov (2008, 2011), to our knowledge the precise statements we give had n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11925","kind":"arxiv","version":3},"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/2010.11925/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":"2010.11925","created_at":"2026-07-05T06:44:18.032656+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.11925v3","created_at":"2026-07-05T06:44:18.032656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11925","created_at":"2026-07-05T06:44:18.032656+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6MDIV4UD4IQ","created_at":"2026-07-05T06:44:18.032656+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6MDIV4UD4IQZLI6","created_at":"2026-07-05T06:44:18.032656+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6MDIV4U","created_at":"2026-07-05T06:44:18.032656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06109","citing_title":"Learning $\\mathsf{AC}^0$ Under Graphical Models","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6MDIV4UD4IQZLI6ZRCZQC7PAO","json":"https://pith.science/pith/M6MDIV4UD4IQZLI6ZRCZQC7PAO.json","graph_json":"https://pith.science/api/pith-number/M6MDIV4UD4IQZLI6ZRCZQC7PAO/graph.json","events_json":"https://pith.science/api/pith-number/M6MDIV4UD4IQZLI6ZRCZQC7PAO/events.json","paper":"https://pith.science/paper/M6MDIV4U"},"agent_actions":{"view_html":"https://pith.science/pith/M6MDIV4UD4IQZLI6ZRCZQC7PAO","download_json":"https://pith.science/pith/M6MDIV4UD4IQZLI6ZRCZQC7PAO.json","view_paper":"https://pith.science/paper/M6MDIV4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.11925&json=true","fetch_graph":"https://pith.science/api/pith-number/M6MDIV4UD4IQZLI6ZRCZQC7PAO/graph.json","fetch_events":"https://pith.science/api/pith-number/M6MDIV4UD4IQZLI6ZRCZQC7PAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6MDIV4UD4IQZLI6ZRCZQC7PAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6MDIV4UD4IQZLI6ZRCZQC7PAO/action/storage_attestation","attest_author":"https://pith.science/pith/M6MDIV4UD4IQZLI6ZRCZQC7PAO/action/author_attestation","sign_citation":"https://pith.science/pith/M6MDIV4UD4IQZLI6ZRCZQC7PAO/action/citation_signature","submit_replication":"https://pith.science/pith/M6MDIV4UD4IQZLI6ZRCZQC7PAO/action/replication_record"}},"created_at":"2026-07-05T06:44:18.032656+00:00","updated_at":"2026-07-05T06:44:18.032656+00:00"}