{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:KFDWPMWUZQNXPWWRX32I5W4FIG","short_pith_number":"pith:KFDWPMWU","schema_version":"1.0","canonical_sha256":"514767b2d4cc1b77dad1bef48edb85418aa77af9f4d4643cbab7b162a692fa98","source":{"kind":"arxiv","id":"1502.02277","version":1},"attestation_state":"computed","paper":{"title":"Improving Term Frequency Normalization for Multi-topical Documents, and Application to Language Modeling Approaches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"In-Su Kang, Jong-Hyeok Lee, Seung-Hoon Na","submitted_at":"2015-02-08T17:32:44Z","abstract_excerpt":"Term frequency normalization is a serious issue since lengths of documents are various. Generally, documents become long due to two different reasons - verbosity and multi-topicality. First, verbosity means that the same topic is repeatedly mentioned by terms related to the topic, so that term frequency is more increased than the well-summarized one. Second, multi-topicality indicates that a document has a broad discussion of multi-topics, rather than single topic. Although these document characteristics should be differently handled, all previous methods of term frequency normalization have i"},"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":"1502.02277","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2015-02-08T17:32:44Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d967e2f7d35065f73f3b4535a05564b808c34bb7c09395987814316924838845","abstract_canon_sha256":"b63b5395d14b74549422b8f8ee1f38d3f7ede07ed02baad18f183d2695c9e86f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:27:43.038541Z","signature_b64":"qAM9kDISqqcvVzEd/OIuoB6VPbU+4NlXHRWEH7hIdKXX+K0muh7bzF2Z7CtpCIPo+xkaQPdN+Smx9bj65TpoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"514767b2d4cc1b77dad1bef48edb85418aa77af9f4d4643cbab7b162a692fa98","last_reissued_at":"2026-05-18T02:27:43.037736Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:27:43.037736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Term Frequency Normalization for Multi-topical Documents, and Application to Language Modeling Approaches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"In-Su Kang, Jong-Hyeok Lee, Seung-Hoon Na","submitted_at":"2015-02-08T17:32:44Z","abstract_excerpt":"Term frequency normalization is a serious issue since lengths of documents are various. Generally, documents become long due to two different reasons - verbosity and multi-topicality. First, verbosity means that the same topic is repeatedly mentioned by terms related to the topic, so that term frequency is more increased than the well-summarized one. Second, multi-topicality indicates that a document has a broad discussion of multi-topics, rather than single topic. Although these document characteristics should be differently handled, all previous methods of term frequency normalization have i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.02277","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":"1502.02277","created_at":"2026-05-18T02:27:43.037859+00:00"},{"alias_kind":"arxiv_version","alias_value":"1502.02277v1","created_at":"2026-05-18T02:27:43.037859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.02277","created_at":"2026-05-18T02:27:43.037859+00:00"},{"alias_kind":"pith_short_12","alias_value":"KFDWPMWUZQNX","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_16","alias_value":"KFDWPMWUZQNXPWWR","created_at":"2026-05-18T12:29:27.538025+00:00"},{"alias_kind":"pith_short_8","alias_value":"KFDWPMWU","created_at":"2026-05-18T12:29:27.538025+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/KFDWPMWUZQNXPWWRX32I5W4FIG","json":"https://pith.science/pith/KFDWPMWUZQNXPWWRX32I5W4FIG.json","graph_json":"https://pith.science/api/pith-number/KFDWPMWUZQNXPWWRX32I5W4FIG/graph.json","events_json":"https://pith.science/api/pith-number/KFDWPMWUZQNXPWWRX32I5W4FIG/events.json","paper":"https://pith.science/paper/KFDWPMWU"},"agent_actions":{"view_html":"https://pith.science/pith/KFDWPMWUZQNXPWWRX32I5W4FIG","download_json":"https://pith.science/pith/KFDWPMWUZQNXPWWRX32I5W4FIG.json","view_paper":"https://pith.science/paper/KFDWPMWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1502.02277&json=true","fetch_graph":"https://pith.science/api/pith-number/KFDWPMWUZQNXPWWRX32I5W4FIG/graph.json","fetch_events":"https://pith.science/api/pith-number/KFDWPMWUZQNXPWWRX32I5W4FIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KFDWPMWUZQNXPWWRX32I5W4FIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KFDWPMWUZQNXPWWRX32I5W4FIG/action/storage_attestation","attest_author":"https://pith.science/pith/KFDWPMWUZQNXPWWRX32I5W4FIG/action/author_attestation","sign_citation":"https://pith.science/pith/KFDWPMWUZQNXPWWRX32I5W4FIG/action/citation_signature","submit_replication":"https://pith.science/pith/KFDWPMWUZQNXPWWRX32I5W4FIG/action/replication_record"}},"created_at":"2026-05-18T02:27:43.037859+00:00","updated_at":"2026-05-18T02:27:43.037859+00:00"}