{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IPHUXZUDIDL6NQSJSSTCPURHHH","short_pith_number":"pith:IPHUXZUD","schema_version":"1.0","canonical_sha256":"43cf4be68340d7e6c24994a627d22739fa7d2d683f840ba8e297691829599f93","source":{"kind":"arxiv","id":"2112.11478","version":1},"attestation_state":"computed","paper":{"title":"LSH methods for data deduplication in a Wikipedia artificial dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel Galvez, David Kanter, Juan Ciro, Tim Schlippe","submitted_at":"2021-12-10T20:01:26Z","abstract_excerpt":"This paper illustrates locality sensitive hasing (LSH) models for the identification and removal of nearly redundant data in a text dataset. To evaluate the different models, we create an artificial dataset for data deduplication using English Wikipedia articles. Area-Under-Curve (AUC) over 0.9 were observed for most models, with the best model reaching 0.96. Deduplication enables more effective model training by preventing the model from learning a distribution that differs from the real one as a result of the repeated data."},"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":"2112.11478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-12-10T20:01:26Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"928917af050c7f86fd1a1f645661a71f9dcca8cfa39ab3839c6f73c1d2055d79","abstract_canon_sha256":"0198f371b88c15f300ea301e91587553d11aa2016713fafedae96e830fb18d30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:07.377215Z","signature_b64":"fCXaKTnY4gGN0FknhELvmmE5hUWrtXplLgtdLa48BHI8yYGTftnK/MPGz55FyZ7rZISOqJGHBO+hDZRumGm2AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43cf4be68340d7e6c24994a627d22739fa7d2d683f840ba8e297691829599f93","last_reissued_at":"2026-07-05T03:43:07.376691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:07.376691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LSH methods for data deduplication in a Wikipedia artificial dataset","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel Galvez, David Kanter, Juan Ciro, Tim Schlippe","submitted_at":"2021-12-10T20:01:26Z","abstract_excerpt":"This paper illustrates locality sensitive hasing (LSH) models for the identification and removal of nearly redundant data in a text dataset. To evaluate the different models, we create an artificial dataset for data deduplication using English Wikipedia articles. Area-Under-Curve (AUC) over 0.9 were observed for most models, with the best model reaching 0.96. Deduplication enables more effective model training by preventing the model from learning a distribution that differs from the real one as a result of the repeated data."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.11478","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2112.11478/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":"2112.11478","created_at":"2026-07-05T03:43:07.376757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.11478v1","created_at":"2026-07-05T03:43:07.376757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.11478","created_at":"2026-07-05T03:43:07.376757+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPHUXZUDIDL6","created_at":"2026-07-05T03:43:07.376757+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPHUXZUDIDL6NQSJ","created_at":"2026-07-05T03:43:07.376757+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPHUXZUD","created_at":"2026-07-05T03:43:07.376757+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/IPHUXZUDIDL6NQSJSSTCPURHHH","json":"https://pith.science/pith/IPHUXZUDIDL6NQSJSSTCPURHHH.json","graph_json":"https://pith.science/api/pith-number/IPHUXZUDIDL6NQSJSSTCPURHHH/graph.json","events_json":"https://pith.science/api/pith-number/IPHUXZUDIDL6NQSJSSTCPURHHH/events.json","paper":"https://pith.science/paper/IPHUXZUD"},"agent_actions":{"view_html":"https://pith.science/pith/IPHUXZUDIDL6NQSJSSTCPURHHH","download_json":"https://pith.science/pith/IPHUXZUDIDL6NQSJSSTCPURHHH.json","view_paper":"https://pith.science/paper/IPHUXZUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.11478&json=true","fetch_graph":"https://pith.science/api/pith-number/IPHUXZUDIDL6NQSJSSTCPURHHH/graph.json","fetch_events":"https://pith.science/api/pith-number/IPHUXZUDIDL6NQSJSSTCPURHHH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPHUXZUDIDL6NQSJSSTCPURHHH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPHUXZUDIDL6NQSJSSTCPURHHH/action/storage_attestation","attest_author":"https://pith.science/pith/IPHUXZUDIDL6NQSJSSTCPURHHH/action/author_attestation","sign_citation":"https://pith.science/pith/IPHUXZUDIDL6NQSJSSTCPURHHH/action/citation_signature","submit_replication":"https://pith.science/pith/IPHUXZUDIDL6NQSJSSTCPURHHH/action/replication_record"}},"created_at":"2026-07-05T03:43:07.376757+00:00","updated_at":"2026-07-05T03:43:07.376757+00:00"}