{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RFBXY45YDQJLAZA2EKT4ZDTKOD","short_pith_number":"pith:RFBXY45Y","schema_version":"1.0","canonical_sha256":"89437c73b81c12b0641a22a7cc8e6a70f1eb0a4b0f83c112c6e6f3d4dd4c1800","source":{"kind":"arxiv","id":"2606.17215","version":1},"attestation_state":"computed","paper":{"title":"Sum-of-Squares Degree Barriers for the Reweighted-Hinge Method in Robust Halfspace Learning: A Christoffel-Function Characterization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Xiaoyu Li","submitted_at":"2026-06-15T18:56:27Z","abstract_excerpt":"A certificate that removes outliers sees the data only through its low-degree moments, and an adversary exploits exactly this, hiding corruption where the clean data already looks typical, in the blind spot no bounded-degree test resolves. That blind spot turns out to have an exact size: the Christoffel function of the clean marginal, the very quantity modern data analysis thresholds to detect outliers, here read from the adversary's side as the corruption a bounded-degree certificate cannot remove. We turn this inversion into the organizing principle of the reweighted-hinge approach to robust"},"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":"2606.17215","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-15T18:56:27Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"ecc8c3e2b505cfda3d5390913f73cd74a02a968932e579fa9f7397c6cef2112d","abstract_canon_sha256":"4edd6cc936eeb8caeea8e01d164ebe0e18e4f17a704a0d37d65599b1cfff8655"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:06.182703Z","signature_b64":"sDkOJ1OX5V9BoYuCjyHRHJ6zNuzui3A8MONU2lvQy8waiVo4aaEJRGN8x+w7umu0Z3IXz5n/XR/8Fbbm9iUsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89437c73b81c12b0641a22a7cc8e6a70f1eb0a4b0f83c112c6e6f3d4dd4c1800","last_reissued_at":"2026-06-19T16:10:06.182243Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:06.182243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sum-of-Squares Degree Barriers for the Reweighted-Hinge Method in Robust Halfspace Learning: A Christoffel-Function Characterization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Xiaoyu Li","submitted_at":"2026-06-15T18:56:27Z","abstract_excerpt":"A certificate that removes outliers sees the data only through its low-degree moments, and an adversary exploits exactly this, hiding corruption where the clean data already looks typical, in the blind spot no bounded-degree test resolves. That blind spot turns out to have an exact size: the Christoffel function of the clean marginal, the very quantity modern data analysis thresholds to detect outliers, here read from the adversary's side as the corruption a bounded-degree certificate cannot remove. We turn this inversion into the organizing principle of the reweighted-hinge approach to robust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17215","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/2606.17215/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":"2606.17215","created_at":"2026-06-19T16:10:06.182298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17215v1","created_at":"2026-06-19T16:10:06.182298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17215","created_at":"2026-06-19T16:10:06.182298+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFBXY45YDQJL","created_at":"2026-06-19T16:10:06.182298+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFBXY45YDQJLAZA2","created_at":"2026-06-19T16:10:06.182298+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFBXY45Y","created_at":"2026-06-19T16:10:06.182298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05226","citing_title":"The Exact Worst-Case Tail Probability under Bounded Kurtosis","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RFBXY45YDQJLAZA2EKT4ZDTKOD","json":"https://pith.science/pith/RFBXY45YDQJLAZA2EKT4ZDTKOD.json","graph_json":"https://pith.science/api/pith-number/RFBXY45YDQJLAZA2EKT4ZDTKOD/graph.json","events_json":"https://pith.science/api/pith-number/RFBXY45YDQJLAZA2EKT4ZDTKOD/events.json","paper":"https://pith.science/paper/RFBXY45Y"},"agent_actions":{"view_html":"https://pith.science/pith/RFBXY45YDQJLAZA2EKT4ZDTKOD","download_json":"https://pith.science/pith/RFBXY45YDQJLAZA2EKT4ZDTKOD.json","view_paper":"https://pith.science/paper/RFBXY45Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17215&json=true","fetch_graph":"https://pith.science/api/pith-number/RFBXY45YDQJLAZA2EKT4ZDTKOD/graph.json","fetch_events":"https://pith.science/api/pith-number/RFBXY45YDQJLAZA2EKT4ZDTKOD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFBXY45YDQJLAZA2EKT4ZDTKOD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFBXY45YDQJLAZA2EKT4ZDTKOD/action/storage_attestation","attest_author":"https://pith.science/pith/RFBXY45YDQJLAZA2EKT4ZDTKOD/action/author_attestation","sign_citation":"https://pith.science/pith/RFBXY45YDQJLAZA2EKT4ZDTKOD/action/citation_signature","submit_replication":"https://pith.science/pith/RFBXY45YDQJLAZA2EKT4ZDTKOD/action/replication_record"}},"created_at":"2026-06-19T16:10:06.182298+00:00","updated_at":"2026-06-19T16:10:06.182298+00:00"}