{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SH6SOAGMD2DY6NOXCVJOHYO2C7","short_pith_number":"pith:SH6SOAGM","schema_version":"1.0","canonical_sha256":"91fd2700cc1e878f35d71552e3e1da17da088d33b138d3554cd3a67ab0d17144","source":{"kind":"arxiv","id":"2608.06337","version":1},"attestation_state":"computed","paper":{"title":"Optimal Rates for Learning with Monotone Adversaries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Anay Mehrotra","submitted_at":"2026-08-06T17:45:32Z","abstract_excerpt":"A monotone adversary observes an i.i.d. labeled sample and appends a finite number of further examples of its choice, every one of them labeled correctly by the target hypothesis. The learner sees a uniform shuffle of the combined sample and is scored on the original distribution. Every example is correctly labeled, but the insertions depend on the clean sample, so the combined sample is not exchangeable. Larsen, Pabbaraju, and Shetty, who introduced this model, showed that empirical risk minimization attains expected error $O((d/n)\\log(n/d))$ for classes of VC dimension $d$, and that every kn"},"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":"2608.06337","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-08-06T17:45:32Z","cross_cats_sorted":["cs.DS","cs.LG","math.ST","stat.TH"],"title_canon_sha256":"1e71c8b74ec021f8c7a46df1269e1f135f38041c0c525ad854fd97666101eb6a","abstract_canon_sha256":"c6476116292be2dc47f891cf3af8303a02a5aa9e4c91c30ac1f9a5b542dfef02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T01:41:23.583786Z","signature_b64":"xtOMj21TDC6GP0/x6p+vGMX5+fZGcXRKj+dXnx89XtLLlLGeMNc85R8S8DIPbXrM8BOm17HTozD3PE/pEtZkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91fd2700cc1e878f35d71552e3e1da17da088d33b138d3554cd3a67ab0d17144","last_reissued_at":"2026-08-07T01:41:23.581937Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T01:41:23.581937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Rates for Learning with Monotone Adversaries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Anay Mehrotra","submitted_at":"2026-08-06T17:45:32Z","abstract_excerpt":"A monotone adversary observes an i.i.d. labeled sample and appends a finite number of further examples of its choice, every one of them labeled correctly by the target hypothesis. The learner sees a uniform shuffle of the combined sample and is scored on the original distribution. Every example is correctly labeled, but the insertions depend on the clean sample, so the combined sample is not exchangeable. Larsen, Pabbaraju, and Shetty, who introduced this model, showed that empirical risk minimization attains expected error $O((d/n)\\log(n/d))$ for classes of VC dimension $d$, and that every kn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06337","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/2608.06337/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":"2608.06337","created_at":"2026-08-07T01:41:23.584657+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06337v1","created_at":"2026-08-07T01:41:23.584657+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06337","created_at":"2026-08-07T01:41:23.584657+00:00"},{"alias_kind":"pith_short_12","alias_value":"SH6SOAGMD2DY","created_at":"2026-08-07T01:41:23.584657+00:00"},{"alias_kind":"pith_short_16","alias_value":"SH6SOAGMD2DY6NOX","created_at":"2026-08-07T01:41:23.584657+00:00"},{"alias_kind":"pith_short_8","alias_value":"SH6SOAGM","created_at":"2026-08-07T01:41:23.584657+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.13514","citing_title":"Bagging Robustly Learns VC Classes with Linear Sample Complexity","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SH6SOAGMD2DY6NOXCVJOHYO2C7","json":"https://pith.science/pith/SH6SOAGMD2DY6NOXCVJOHYO2C7.json","graph_json":"https://pith.science/api/pith-number/SH6SOAGMD2DY6NOXCVJOHYO2C7/graph.json","events_json":"https://pith.science/api/pith-number/SH6SOAGMD2DY6NOXCVJOHYO2C7/events.json","paper":"https://pith.science/paper/SH6SOAGM"},"agent_actions":{"view_html":"https://pith.science/pith/SH6SOAGMD2DY6NOXCVJOHYO2C7","download_json":"https://pith.science/pith/SH6SOAGMD2DY6NOXCVJOHYO2C7.json","view_paper":"https://pith.science/paper/SH6SOAGM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06337&json=true","fetch_graph":"https://pith.science/api/pith-number/SH6SOAGMD2DY6NOXCVJOHYO2C7/graph.json","fetch_events":"https://pith.science/api/pith-number/SH6SOAGMD2DY6NOXCVJOHYO2C7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SH6SOAGMD2DY6NOXCVJOHYO2C7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SH6SOAGMD2DY6NOXCVJOHYO2C7/action/storage_attestation","attest_author":"https://pith.science/pith/SH6SOAGMD2DY6NOXCVJOHYO2C7/action/author_attestation","sign_citation":"https://pith.science/pith/SH6SOAGMD2DY6NOXCVJOHYO2C7/action/citation_signature","submit_replication":"https://pith.science/pith/SH6SOAGMD2DY6NOXCVJOHYO2C7/action/replication_record"}},"created_at":"2026-08-07T01:41:23.584657+00:00","updated_at":"2026-08-07T01:41:23.584657+00:00"}