{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PSEWPCJYZXFPNUWQHXJ3AJVSM6","short_pith_number":"pith:PSEWPCJY","schema_version":"1.0","canonical_sha256":"7c89678938cdcaf6d2d03dd3b026b267839953791e18563ea3211970e59f4885","source":{"kind":"arxiv","id":"1902.03402","version":1},"attestation_state":"computed","paper":{"title":"A new simple and effective measure for bag-of-word inter-document similarity measurement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Gholamreza Haffari, Kai Ming Ting, Sunil Aryal, Takashi Washio","submitted_at":"2019-02-09T10:32:45Z","abstract_excerpt":"To measure the similarity of two documents in the bag-of-words (BoW) vector representation, different term weighting schemes are used to improve the performance of cosine similarity---the most widely used inter-document similarity measure in text mining. In this paper, we identify the shortcomings of the underlying assumptions of term weighting in the inter-document similarity measurement task; and provide a more fit-to-the-purpose alternative. Based on this new assumption, we introduce a new simple but effective similarity measure which does not require explicit term weighting. The proposed m"},"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":"1902.03402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2019-02-09T10:32:45Z","cross_cats_sorted":[],"title_canon_sha256":"65ba0186787f77ae5d249a804819eb00704255939804ff921e78ed0ea3da9133","abstract_canon_sha256":"e0677a66a7e11aa7eeb3593c3cb6442a7196c4ebef68815b34f26f6a3a5e411e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:20.965877Z","signature_b64":"8lGkyDpQ1Rk+wWHfu3jsnn0z8Rq1tXRApYqDAWtUr2pdpLP9nopTfFc79n9FfmI8hNKXDToA8wGgJbQOdovGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c89678938cdcaf6d2d03dd3b026b267839953791e18563ea3211970e59f4885","last_reissued_at":"2026-05-17T23:54:20.965263Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:20.965263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A new simple and effective measure for bag-of-word inter-document similarity measurement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Gholamreza Haffari, Kai Ming Ting, Sunil Aryal, Takashi Washio","submitted_at":"2019-02-09T10:32:45Z","abstract_excerpt":"To measure the similarity of two documents in the bag-of-words (BoW) vector representation, different term weighting schemes are used to improve the performance of cosine similarity---the most widely used inter-document similarity measure in text mining. In this paper, we identify the shortcomings of the underlying assumptions of term weighting in the inter-document similarity measurement task; and provide a more fit-to-the-purpose alternative. Based on this new assumption, we introduce a new simple but effective similarity measure which does not require explicit term weighting. The proposed m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.03402","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":"1902.03402","created_at":"2026-05-17T23:54:20.965375+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.03402v1","created_at":"2026-05-17T23:54:20.965375+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.03402","created_at":"2026-05-17T23:54:20.965375+00:00"},{"alias_kind":"pith_short_12","alias_value":"PSEWPCJYZXFP","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"PSEWPCJYZXFPNUWQ","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"PSEWPCJY","created_at":"2026-05-18T12:33:24.271573+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/PSEWPCJYZXFPNUWQHXJ3AJVSM6","json":"https://pith.science/pith/PSEWPCJYZXFPNUWQHXJ3AJVSM6.json","graph_json":"https://pith.science/api/pith-number/PSEWPCJYZXFPNUWQHXJ3AJVSM6/graph.json","events_json":"https://pith.science/api/pith-number/PSEWPCJYZXFPNUWQHXJ3AJVSM6/events.json","paper":"https://pith.science/paper/PSEWPCJY"},"agent_actions":{"view_html":"https://pith.science/pith/PSEWPCJYZXFPNUWQHXJ3AJVSM6","download_json":"https://pith.science/pith/PSEWPCJYZXFPNUWQHXJ3AJVSM6.json","view_paper":"https://pith.science/paper/PSEWPCJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.03402&json=true","fetch_graph":"https://pith.science/api/pith-number/PSEWPCJYZXFPNUWQHXJ3AJVSM6/graph.json","fetch_events":"https://pith.science/api/pith-number/PSEWPCJYZXFPNUWQHXJ3AJVSM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PSEWPCJYZXFPNUWQHXJ3AJVSM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PSEWPCJYZXFPNUWQHXJ3AJVSM6/action/storage_attestation","attest_author":"https://pith.science/pith/PSEWPCJYZXFPNUWQHXJ3AJVSM6/action/author_attestation","sign_citation":"https://pith.science/pith/PSEWPCJYZXFPNUWQHXJ3AJVSM6/action/citation_signature","submit_replication":"https://pith.science/pith/PSEWPCJYZXFPNUWQHXJ3AJVSM6/action/replication_record"}},"created_at":"2026-05-17T23:54:20.965375+00:00","updated_at":"2026-05-17T23:54:20.965375+00:00"}