{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2003:XIDHBOFZCI3ZK4JUYP57Y6VXM7","short_pith_number":"pith:XIDHBOFZ","schema_version":"1.0","canonical_sha256":"ba0670b8b91237957134c3fbfc7ab767e53e4c3d57719c7fc7477836c70048e8","source":{"kind":"arxiv","id":"cs/0306099","version":1},"attestation_state":"computed","paper":{"title":"An Improved k-Nearest Neighbor Algorithm for Text Categorization","license":"","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baoli Li, Qin Lu, Shiwen Yu","submitted_at":"2003-06-16T13:54:03Z","abstract_excerpt":"k is the most important parameter in a text categorization system based on k-Nearest Neighbor algorithm (kNN).In the classification process, k nearest documents to the test one in the training set are determined firstly. Then, the predication can be made according to the category distribution among these k nearest neighbors. Generally speaking, the class distribution in the training set is uneven. Some classes may have more samples than others. Therefore, the system performance is very sensitive to the choice of the parameter k. And it is very likely that a fixed k value will result in a bias "},"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":"cs/0306099","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.CL","submitted_at":"2003-06-16T13:54:03Z","cross_cats_sorted":[],"title_canon_sha256":"3a92c111d4649c8daee5d92f9eb283e802c1bf929109bb57b8fc39fc6dc6cd2b","abstract_canon_sha256":"82516dc31759dfb65fb06ae69e0616ecdbb48fe454355f4d2b2ecc434d47c965"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T14:24:34.440001Z","signature_b64":"JnJv9DQmZ7sf1M6noTY5jr/Tlxldp8CKBe80Vzt6A9NL6YQI5BTa122uIFjmc/b3kiSV5djCjhsHMXD31JXzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba0670b8b91237957134c3fbfc7ab767e53e4c3d57719c7fc7477836c70048e8","last_reissued_at":"2026-07-04T14:24:34.439637Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T14:24:34.439637Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Improved k-Nearest Neighbor Algorithm for Text Categorization","license":"","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baoli Li, Qin Lu, Shiwen Yu","submitted_at":"2003-06-16T13:54:03Z","abstract_excerpt":"k is the most important parameter in a text categorization system based on k-Nearest Neighbor algorithm (kNN).In the classification process, k nearest documents to the test one in the training set are determined firstly. Then, the predication can be made according to the category distribution among these k nearest neighbors. Generally speaking, the class distribution in the training set is uneven. Some classes may have more samples than others. Therefore, the system performance is very sensitive to the choice of the parameter k. And it is very likely that a fixed k value will result in a bias "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0306099","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/cs/0306099/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":"cs/0306099","created_at":"2026-07-04T14:24:34.439692+00:00"},{"alias_kind":"arxiv_version","alias_value":"cs/0306099v1","created_at":"2026-07-04T14:24:34.439692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0306099","created_at":"2026-07-04T14:24:34.439692+00:00"},{"alias_kind":"pith_short_12","alias_value":"XIDHBOFZCI3Z","created_at":"2026-07-04T14:24:34.439692+00:00"},{"alias_kind":"pith_short_16","alias_value":"XIDHBOFZCI3ZK4JU","created_at":"2026-07-04T14:24:34.439692+00:00"},{"alias_kind":"pith_short_8","alias_value":"XIDHBOFZ","created_at":"2026-07-04T14:24:34.439692+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/XIDHBOFZCI3ZK4JUYP57Y6VXM7","json":"https://pith.science/pith/XIDHBOFZCI3ZK4JUYP57Y6VXM7.json","graph_json":"https://pith.science/api/pith-number/XIDHBOFZCI3ZK4JUYP57Y6VXM7/graph.json","events_json":"https://pith.science/api/pith-number/XIDHBOFZCI3ZK4JUYP57Y6VXM7/events.json","paper":"https://pith.science/paper/XIDHBOFZ"},"agent_actions":{"view_html":"https://pith.science/pith/XIDHBOFZCI3ZK4JUYP57Y6VXM7","download_json":"https://pith.science/pith/XIDHBOFZCI3ZK4JUYP57Y6VXM7.json","view_paper":"https://pith.science/paper/XIDHBOFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cs/0306099&json=true","fetch_graph":"https://pith.science/api/pith-number/XIDHBOFZCI3ZK4JUYP57Y6VXM7/graph.json","fetch_events":"https://pith.science/api/pith-number/XIDHBOFZCI3ZK4JUYP57Y6VXM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XIDHBOFZCI3ZK4JUYP57Y6VXM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XIDHBOFZCI3ZK4JUYP57Y6VXM7/action/storage_attestation","attest_author":"https://pith.science/pith/XIDHBOFZCI3ZK4JUYP57Y6VXM7/action/author_attestation","sign_citation":"https://pith.science/pith/XIDHBOFZCI3ZK4JUYP57Y6VXM7/action/citation_signature","submit_replication":"https://pith.science/pith/XIDHBOFZCI3ZK4JUYP57Y6VXM7/action/replication_record"}},"created_at":"2026-07-04T14:24:34.439692+00:00","updated_at":"2026-07-04T14:24:34.439692+00:00"}