{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2010:RG5IBQ75U5D6YTU7KFDZIEPSB5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"de49cf1059dacbafc5534c7707c6a3335e4eda5f40672ba105e1bd1591197984","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","primary_cat":"cs.LG","submitted_at":"2010-12-13T01:22:36Z","title_canon_sha256":"0d836e7cb2d49c1f9d8b1d0d7bb2cf0c792a66ce14f0a471f6a95a6578ffdfbd"},"schema_version":"1.0","source":{"id":"1012.2609","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1012.2609","created_at":"2026-05-18T03:54:15Z"},{"alias_kind":"arxiv_version","alias_value":"1012.2609v4","created_at":"2026-05-18T03:54:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1012.2609","created_at":"2026-05-18T03:54:15Z"},{"alias_kind":"pith_short_12","alias_value":"RG5IBQ75U5D6","created_at":"2026-05-18T12:26:13Z"},{"alias_kind":"pith_short_16","alias_value":"RG5IBQ75U5D6YTU7","created_at":"2026-05-18T12:26:13Z"},{"alias_kind":"pith_short_8","alias_value":"RG5IBQ75","created_at":"2026-05-18T12:26:13Z"}],"graph_snapshots":[{"event_id":"sha256:66dfeb6c80a0e7e187920f7ce8afa48a9ffde8f0af1c22b68baac85cbb42697f","target":"graph","created_at":"2026-05-18T03:54:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Term weighting schemes often dominate the performance of many classifiers, such as kNN, centroid-based classifier and SVMs. The widely used term weighting scheme in text categorization, i.e., tf.idf, is originated from information retrieval (IR) field. The intuition behind idf for text categorization seems less reasonable than IR. In this paper, we introduce inverse category frequency (icf) into term weighting scheme and propose two novel approaches, i.e., tf.icf and icf-based supervised term weighting schemes. The tf.icf adopts icf to substitute idf factor and favors terms occurring in fewer ","authors_text":"Deqing Wang, Hui Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","primary_cat":"cs.LG","submitted_at":"2010-12-13T01:22:36Z","title":"Inverse-Category-Frequency based supervised term weighting scheme for text categorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1012.2609","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:707bb0171e6ac2d4312f0c04ebeca769c33ff404bc8058f7680505f433b12a7d","target":"record","created_at":"2026-05-18T03:54:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"de49cf1059dacbafc5534c7707c6a3335e4eda5f40672ba105e1bd1591197984","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/3.0/","primary_cat":"cs.LG","submitted_at":"2010-12-13T01:22:36Z","title_canon_sha256":"0d836e7cb2d49c1f9d8b1d0d7bb2cf0c792a66ce14f0a471f6a95a6578ffdfbd"},"schema_version":"1.0","source":{"id":"1012.2609","kind":"arxiv","version":4}},"canonical_sha256":"89ba80c3fda747ec4e9f51479411f20f4e11c3fd876ec5e1f9e2e0f6aa8add5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"89ba80c3fda747ec4e9f51479411f20f4e11c3fd876ec5e1f9e2e0f6aa8add5e","first_computed_at":"2026-05-18T03:54:15.368720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:54:15.368720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OHJ47upExyqJ5RvWmYsvFPF+JID5neaSF56/Qqh/9sqn2JRubNkEKwu7TWHxegNDiGvQUeQK3fVxm/1haBCyCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:54:15.369416Z","signed_message":"canonical_sha256_bytes"},"source_id":"1012.2609","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:707bb0171e6ac2d4312f0c04ebeca769c33ff404bc8058f7680505f433b12a7d","sha256:66dfeb6c80a0e7e187920f7ce8afa48a9ffde8f0af1c22b68baac85cbb42697f"],"state_sha256":"8f2c45233e492cc50cb959e6c7692066eaef95511023aaca85a64064f6ae006e"}