{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:J6PLYUFKBHESMKQMHPOCU76Q2U","short_pith_number":"pith:J6PLYUFK","schema_version":"1.0","canonical_sha256":"4f9ebc50aa09c9262a0c3bdc2a7fd0d50e8bff1dc3abec33c5b16cd21aea6b17","source":{"kind":"arxiv","id":"1604.04007","version":1},"attestation_state":"computed","paper":{"title":"Balancing Between Over-Weighting and Under-Weighting in Supervised Term Weighting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Haibing Wu, Xiaodong Gu","submitted_at":"2016-04-14T01:29:52Z","abstract_excerpt":"Supervised term weighting could improve the performance of text categorization. A way proven to be effective is to give more weight to terms with more imbalanced distributions across categories. This paper shows that supervised term weighting should not just assign large weights to imbalanced terms, but should also control the trade-off between over-weighting and under-weighting. Over-weighting, a new concept proposed in this paper, is caused by the improper handling of singular terms and too large ratios between term weights. To prevent over-weighting, we present three regularization techniqu"},"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":"1604.04007","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2016-04-14T01:29:52Z","cross_cats_sorted":[],"title_canon_sha256":"dd6b011cf1ca8e65ba0023cb8051990a3f9d4fd981c113a6f0835acde3996682","abstract_canon_sha256":"df4365e127f62ae5ca745d469e0fa8d0af07681ea871a90f1ba02e844cfef761"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:06.957578Z","signature_b64":"8JrXoOPrS2WACO9KHC6Mn3357DMvwGaE/4BR6/qMgNyKcwImHYQ5jn1LW2+evfAkGBCG2Y1TVp/mNaz5H5T+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f9ebc50aa09c9262a0c3bdc2a7fd0d50e8bff1dc3abec33c5b16cd21aea6b17","last_reissued_at":"2026-05-18T01:17:06.956934Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:06.956934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Balancing Between Over-Weighting and Under-Weighting in Supervised Term Weighting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Haibing Wu, Xiaodong Gu","submitted_at":"2016-04-14T01:29:52Z","abstract_excerpt":"Supervised term weighting could improve the performance of text categorization. A way proven to be effective is to give more weight to terms with more imbalanced distributions across categories. This paper shows that supervised term weighting should not just assign large weights to imbalanced terms, but should also control the trade-off between over-weighting and under-weighting. Over-weighting, a new concept proposed in this paper, is caused by the improper handling of singular terms and too large ratios between term weights. To prevent over-weighting, we present three regularization techniqu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.04007","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":""},"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":"1604.04007","created_at":"2026-05-18T01:17:06.957054+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.04007v1","created_at":"2026-05-18T01:17:06.957054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.04007","created_at":"2026-05-18T01:17:06.957054+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6PLYUFKBHES","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6PLYUFKBHESMKQM","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6PLYUFK","created_at":"2026-05-18T12:30:22.444734+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/J6PLYUFKBHESMKQMHPOCU76Q2U","json":"https://pith.science/pith/J6PLYUFKBHESMKQMHPOCU76Q2U.json","graph_json":"https://pith.science/api/pith-number/J6PLYUFKBHESMKQMHPOCU76Q2U/graph.json","events_json":"https://pith.science/api/pith-number/J6PLYUFKBHESMKQMHPOCU76Q2U/events.json","paper":"https://pith.science/paper/J6PLYUFK"},"agent_actions":{"view_html":"https://pith.science/pith/J6PLYUFKBHESMKQMHPOCU76Q2U","download_json":"https://pith.science/pith/J6PLYUFKBHESMKQMHPOCU76Q2U.json","view_paper":"https://pith.science/paper/J6PLYUFK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.04007&json=true","fetch_graph":"https://pith.science/api/pith-number/J6PLYUFKBHESMKQMHPOCU76Q2U/graph.json","fetch_events":"https://pith.science/api/pith-number/J6PLYUFKBHESMKQMHPOCU76Q2U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6PLYUFKBHESMKQMHPOCU76Q2U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6PLYUFKBHESMKQMHPOCU76Q2U/action/storage_attestation","attest_author":"https://pith.science/pith/J6PLYUFKBHESMKQMHPOCU76Q2U/action/author_attestation","sign_citation":"https://pith.science/pith/J6PLYUFKBHESMKQMHPOCU76Q2U/action/citation_signature","submit_replication":"https://pith.science/pith/J6PLYUFKBHESMKQMHPOCU76Q2U/action/replication_record"}},"created_at":"2026-05-18T01:17:06.957054+00:00","updated_at":"2026-05-18T01:17:06.957054+00:00"}