{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EXHK6EN6CMCWEHD7ECJDRCQPKE","short_pith_number":"pith:EXHK6EN6","schema_version":"1.0","canonical_sha256":"25ceaf11be1305621c7f2092388a0f51051bb779603dc74f12442aabd6462314","source":{"kind":"arxiv","id":"2606.10361","version":1},"attestation_state":"computed","paper":{"title":"Near-Exponential Convergence Rates for kNN Classification based on Boltzmann Margin","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chao Lan, Luyuan Yang, Shayan Shafaei","submitted_at":"2026-06-09T03:21:48Z","abstract_excerpt":"Convergence-rate analysis for classifiers is often conducted under either Tsybakov margin or Massart margin. The former is a relatively weak condition that typically yields polynomial rates, while the latter is substantially stronger but can guarantee exponential rates. In this paper, we introduce a new condition, called Boltzmann margin, that bridges the gap between these two regimes. It is weaker than Massart margin, generally stronger than Tsybakov margin, and can imply many of their properties under suitable conditions. We apply Boltzmann margin to the analysis of kNN classifiers and estab"},"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":"2606.10361","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-06-09T03:21:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eb84055e67ebd85a286c3b854bdeaf17cd4b22352331fc0a61589494bdd5d8b2","abstract_canon_sha256":"7c592672b9fbfc39ae51163bf9e13e47b2649004c865cfbfa8f73bfcdc666e89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:13.697046Z","signature_b64":"/NCAisfyKHUDkFJxNuOhFRZyx7VfWJFfEp+iERZwc7DasavZmAFx2EsIvfQGpyN7rUu3tFGuiBqHN4pql5IPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25ceaf11be1305621c7f2092388a0f51051bb779603dc74f12442aabd6462314","last_reissued_at":"2026-06-10T01:10:13.696145Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:13.696145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-Exponential Convergence Rates for kNN Classification based on Boltzmann Margin","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chao Lan, Luyuan Yang, Shayan Shafaei","submitted_at":"2026-06-09T03:21:48Z","abstract_excerpt":"Convergence-rate analysis for classifiers is often conducted under either Tsybakov margin or Massart margin. The former is a relatively weak condition that typically yields polynomial rates, while the latter is substantially stronger but can guarantee exponential rates. In this paper, we introduce a new condition, called Boltzmann margin, that bridges the gap between these two regimes. It is weaker than Massart margin, generally stronger than Tsybakov margin, and can imply many of their properties under suitable conditions. We apply Boltzmann margin to the analysis of kNN classifiers and estab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10361","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/2606.10361/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":"2606.10361","created_at":"2026-06-10T01:10:13.696279+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10361v1","created_at":"2026-06-10T01:10:13.696279+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10361","created_at":"2026-06-10T01:10:13.696279+00:00"},{"alias_kind":"pith_short_12","alias_value":"EXHK6EN6CMCW","created_at":"2026-06-10T01:10:13.696279+00:00"},{"alias_kind":"pith_short_16","alias_value":"EXHK6EN6CMCWEHD7","created_at":"2026-06-10T01:10:13.696279+00:00"},{"alias_kind":"pith_short_8","alias_value":"EXHK6EN6","created_at":"2026-06-10T01:10:13.696279+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EXHK6EN6CMCWEHD7ECJDRCQPKE","json":"https://pith.science/pith/EXHK6EN6CMCWEHD7ECJDRCQPKE.json","graph_json":"https://pith.science/api/pith-number/EXHK6EN6CMCWEHD7ECJDRCQPKE/graph.json","events_json":"https://pith.science/api/pith-number/EXHK6EN6CMCWEHD7ECJDRCQPKE/events.json","paper":"https://pith.science/paper/EXHK6EN6"},"agent_actions":{"view_html":"https://pith.science/pith/EXHK6EN6CMCWEHD7ECJDRCQPKE","download_json":"https://pith.science/pith/EXHK6EN6CMCWEHD7ECJDRCQPKE.json","view_paper":"https://pith.science/paper/EXHK6EN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10361&json=true","fetch_graph":"https://pith.science/api/pith-number/EXHK6EN6CMCWEHD7ECJDRCQPKE/graph.json","fetch_events":"https://pith.science/api/pith-number/EXHK6EN6CMCWEHD7ECJDRCQPKE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EXHK6EN6CMCWEHD7ECJDRCQPKE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EXHK6EN6CMCWEHD7ECJDRCQPKE/action/storage_attestation","attest_author":"https://pith.science/pith/EXHK6EN6CMCWEHD7ECJDRCQPKE/action/author_attestation","sign_citation":"https://pith.science/pith/EXHK6EN6CMCWEHD7ECJDRCQPKE/action/citation_signature","submit_replication":"https://pith.science/pith/EXHK6EN6CMCWEHD7ECJDRCQPKE/action/replication_record"}},"created_at":"2026-06-10T01:10:13.696279+00:00","updated_at":"2026-06-10T01:10:13.696279+00:00"}