{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DHYMZWWP7HZEGXY4VGKV3HI4DV","short_pith_number":"pith:DHYMZWWP","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"},"canonical_sha256":"19f0ccdacff9f2435f1ca9955d9d1c1d7dba22401fa9757d52715d8c9929b7be","source":{"kind":"arxiv","id":"1810.03102","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03102","created_at":"2026-07-05T00:07:05Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03102v3","created_at":"2026-07-05T00:07:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03102","created_at":"2026-07-05T00:07:05Z"},{"alias_kind":"pith_short_12","alias_value":"DHYMZWWP7HZE","created_at":"2026-07-05T00:07:05Z"},{"alias_kind":"pith_short_16","alias_value":"DHYMZWWP7HZEGXY4","created_at":"2026-07-05T00:07:05Z"},{"alias_kind":"pith_short_8","alias_value":"DHYMZWWP","created_at":"2026-07-05T00:07:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DHYMZWWP7HZEGXY4VGKV3HI4DV","target":"record","payload":{"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"},"canonical_sha256":"19f0ccdacff9f2435f1ca9955d9d1c1d7dba22401fa9757d52715d8c9929b7be","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"},"source_kind":"arxiv","source_id":"1810.03102","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:07:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZvyZA7jfsLt4UrIsSoTIpQUWDY3PMmzKvI5+lxH4T+9orKxeeLIrAljctifDER2rDC2Hz62VJ8I4YXAvYFNQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:05:59.273641Z"},"content_sha256":"d5b98c64327139b43a7f56c2d5348486fc0871dfb5c5ac28bbbc57ae96b37b6f","schema_version":"1.0","event_id":"sha256:d5b98c64327139b43a7f56c2d5348486fc0871dfb5c5ac28bbbc57ae96b37b6f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DHYMZWWP7HZEGXY4VGKV3HI4DV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:07:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FAQw4guMZ0WASHEi0XPkOSbXIccaXeD1fA9SKRQ0pClSYE//1NvooPD5vM0ROXoc2z7MQQ0e+Bv7+xD2r5naAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T12:05:59.274020Z"},"content_sha256":"c7ddc6ff5c7dddf63f5ab277e008b6e34f4ab9ce97603ec95b0567ca286a65a4","schema_version":"1.0","event_id":"sha256:c7ddc6ff5c7dddf63f5ab277e008b6e34f4ab9ce97603ec95b0567ca286a65a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DHYMZWWP7HZEGXY4VGKV3HI4DV/bundle.json","state_url":"https://pith.science/pith/DHYMZWWP7HZEGXY4VGKV3HI4DV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DHYMZWWP7HZEGXY4VGKV3HI4DV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T12:05:59Z","links":{"resolver":"https://pith.science/pith/DHYMZWWP7HZEGXY4VGKV3HI4DV","bundle":"https://pith.science/pith/DHYMZWWP7HZEGXY4VGKV3HI4DV/bundle.json","state":"https://pith.science/pith/DHYMZWWP7HZEGXY4VGKV3HI4DV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DHYMZWWP7HZEGXY4VGKV3HI4DV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DHYMZWWP7HZEGXY4VGKV3HI4DV","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":"c08304f2b6b4c92ddb8113d2733db63d0b45217420666e4c45c2a2dfec7ebd4b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-07T08:17:07Z","title_canon_sha256":"5a10b46cb3a71944f82225a20c60bed5a1daeced912e819ccb5e664334b167be"},"schema_version":"1.0","source":{"id":"1810.03102","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.03102","created_at":"2026-07-05T00:07:05Z"},{"alias_kind":"arxiv_version","alias_value":"1810.03102v3","created_at":"2026-07-05T00:07:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.03102","created_at":"2026-07-05T00:07:05Z"},{"alias_kind":"pith_short_12","alias_value":"DHYMZWWP7HZE","created_at":"2026-07-05T00:07:05Z"},{"alias_kind":"pith_short_16","alias_value":"DHYMZWWP7HZEGXY4","created_at":"2026-07-05T00:07:05Z"},{"alias_kind":"pith_short_8","alias_value":"DHYMZWWP","created_at":"2026-07-05T00:07:05Z"}],"graph_snapshots":[{"event_id":"sha256:c7ddc6ff5c7dddf63f5ab277e008b6e34f4ab9ce97603ec95b0567ca286a65a4","target":"graph","created_at":"2026-07-05T00:07:05Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1810.03102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hamid Mohammadi, Seyed Hossein Khasteh","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-07T08:17:07Z","title":"A Fast Text Similarity Measure for Large Document Collections using Multi-reference Cosine and Genetic Algorithm"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.03102","kind":"arxiv","version":3},"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:d5b98c64327139b43a7f56c2d5348486fc0871dfb5c5ac28bbbc57ae96b37b6f","target":"record","created_at":"2026-07-05T00:07:05Z","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":"c08304f2b6b4c92ddb8113d2733db63d0b45217420666e4c45c2a2dfec7ebd4b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2018-10-07T08:17:07Z","title_canon_sha256":"5a10b46cb3a71944f82225a20c60bed5a1daeced912e819ccb5e664334b167be"},"schema_version":"1.0","source":{"id":"1810.03102","kind":"arxiv","version":3}},"canonical_sha256":"19f0ccdacff9f2435f1ca9955d9d1c1d7dba22401fa9757d52715d8c9929b7be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19f0ccdacff9f2435f1ca9955d9d1c1d7dba22401fa9757d52715d8c9929b7be","first_computed_at":"2026-07-05T00:07:05.753463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:07:05.753463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q5XH0F5JYFvgShogW9BrziXQyOwFgQza+BWgAqXR/rIlBq7aGLW1EiGGMUqO8O/45cpVFel/8PWmJ5o4UP/xAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:07:05.753955Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.03102","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5b98c64327139b43a7f56c2d5348486fc0871dfb5c5ac28bbbc57ae96b37b6f","sha256:c7ddc6ff5c7dddf63f5ab277e008b6e34f4ab9ce97603ec95b0567ca286a65a4"],"state_sha256":"955b638abcf4c29a6bbeb14ead2c6c64601b715ca2f70121486d59892148bb5c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0FEBxFGka6o4v7tpmVPhvjSQUIUN6F3aoYKt6BeeWGDeYE8e4BH48knisBew4LzPMgxgV1aYYxk7jt4M9e00Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T12:05:59.276437Z","bundle_sha256":"8afa6cd4b3aca8d14fa79c5b4b41e688a177d88629126cd6b5508ea69e3b25da"}}