{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DHYMZWWP7HZEGXY4VGKV3HI4DV","short_pith_number":"pith:DHYMZWWP","schema_version":"1.0","canonical_sha256":"19f0ccdacff9f2435f1ca9955d9d1c1d7dba22401fa9757d52715d8c9929b7be","source":{"kind":"arxiv","id":"1810.03102","version":3},"attestation_state":"computed","paper":{"title":"A Fast Text Similarity Measure for Large Document Collections using Multi-reference Cosine and Genetic Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hamid Mohammadi, Seyed Hossein Khasteh","submitted_at":"2018-10-07T08:17:07Z","abstract_excerpt":"One of the important factors that make a search engine fast and accurate is a concise and duplicate free index. In order to remove duplicate and near-duplicate documents from the index, a search engine needs a swift and reliable duplicate and near-duplicate text document detection system. Traditional approaches to this problem, such as brute force comparisons or simple hash-based algorithms are not suitable as they are not scalable and are not capable of detecting near-duplicate documents effectively. In this paper, a new signature-based approach to text similarity detection is introduced whic"},"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":"1810.03102","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-07T08:17:07Z","cross_cats_sorted":[],"title_canon_sha256":"5a10b46cb3a71944f82225a20c60bed5a1daeced912e819ccb5e664334b167be","abstract_canon_sha256":"c08304f2b6b4c92ddb8113d2733db63d0b45217420666e4c45c2a2dfec7ebd4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:05.753955Z","signature_b64":"q5XH0F5JYFvgShogW9BrziXQyOwFgQza+BWgAqXR/rIlBq7aGLW1EiGGMUqO8O/45cpVFel/8PWmJ5o4UP/xAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19f0ccdacff9f2435f1ca9955d9d1c1d7dba22401fa9757d52715d8c9929b7be","last_reissued_at":"2026-07-05T00:07:05.753463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:05.753463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Fast Text Similarity Measure for Large Document Collections using Multi-reference Cosine and Genetic Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hamid Mohammadi, Seyed Hossein Khasteh","submitted_at":"2018-10-07T08:17:07Z","abstract_excerpt":"One of the important factors that make a search engine fast and accurate is a concise and duplicate free index. In order to remove duplicate and near-duplicate documents from the index, a search engine needs a swift and reliable duplicate and near-duplicate text document detection system. Traditional approaches to this problem, such as brute force comparisons or simple hash-based algorithms are not suitable as they are not scalable and are not capable of detecting near-duplicate documents effectively. In this paper, a new signature-based approach to text similarity detection is introduced whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03102","kind":"arxiv","version":3},"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/1810.03102/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":"1810.03102","created_at":"2026-07-05T00:07:05.753523+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.03102v3","created_at":"2026-07-05T00:07:05.753523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03102","created_at":"2026-07-05T00:07:05.753523+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHYMZWWP7HZE","created_at":"2026-07-05T00:07:05.753523+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHYMZWWP7HZEGXY4","created_at":"2026-07-05T00:07:05.753523+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHYMZWWP","created_at":"2026-07-05T00:07:05.753523+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/DHYMZWWP7HZEGXY4VGKV3HI4DV","json":"https://pith.science/pith/DHYMZWWP7HZEGXY4VGKV3HI4DV.json","graph_json":"https://pith.science/api/pith-number/DHYMZWWP7HZEGXY4VGKV3HI4DV/graph.json","events_json":"https://pith.science/api/pith-number/DHYMZWWP7HZEGXY4VGKV3HI4DV/events.json","paper":"https://pith.science/paper/DHYMZWWP"},"agent_actions":{"view_html":"https://pith.science/pith/DHYMZWWP7HZEGXY4VGKV3HI4DV","download_json":"https://pith.science/pith/DHYMZWWP7HZEGXY4VGKV3HI4DV.json","view_paper":"https://pith.science/paper/DHYMZWWP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.03102&json=true","fetch_graph":"https://pith.science/api/pith-number/DHYMZWWP7HZEGXY4VGKV3HI4DV/graph.json","fetch_events":"https://pith.science/api/pith-number/DHYMZWWP7HZEGXY4VGKV3HI4DV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHYMZWWP7HZEGXY4VGKV3HI4DV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHYMZWWP7HZEGXY4VGKV3HI4DV/action/storage_attestation","attest_author":"https://pith.science/pith/DHYMZWWP7HZEGXY4VGKV3HI4DV/action/author_attestation","sign_citation":"https://pith.science/pith/DHYMZWWP7HZEGXY4VGKV3HI4DV/action/citation_signature","submit_replication":"https://pith.science/pith/DHYMZWWP7HZEGXY4VGKV3HI4DV/action/replication_record"}},"created_at":"2026-07-05T00:07:05.753523+00:00","updated_at":"2026-07-05T00:07:05.753523+00:00"}