{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MXCWJF3NNDMN442IAOTAUEAWVT","short_pith_number":"pith:MXCWJF3N","schema_version":"1.0","canonical_sha256":"65c564976d68d8de734803a60a1016acdf338ebe854ffc7466d8d7d420a38d9b","source":{"kind":"arxiv","id":"1907.02821","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking unsupervised near-duplicate image detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG","cs.MM","stat.ML"],"primary_cat":"cs.CV","authors_text":"Fabrizio Lamberti, Lia Morra","submitted_at":"2019-07-03T09:08:47Z","abstract_excerpt":"Unsupervised near-duplicate detection has many practical applications ranging from social media analysis and web-scale retrieval, to digital image forensics. It entails running a threshold-limited query on a set of descriptors extracted from the images, with the goal of identifying all possible near-duplicates, while limiting the false positives due to visually similar images. Since the rate of false alarms grows with the dataset size, a very high specificity is thus required, up to $1 - 10^{-9}$ for realistic use cases; this important requirement, however, is often overlooked in literature. 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":"1907.02821","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2019-07-03T09:08:47Z","cross_cats_sorted":["cs.CR","cs.LG","cs.MM","stat.ML"],"title_canon_sha256":"ff550abf164c56ae0be3abcd9fdb220011df02d092af788c06bddf43da023cad","abstract_canon_sha256":"1ca030a96d5b831bf847c89663029e15f4106706fb94ffc9363e2f1e210dacc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:07.068145Z","signature_b64":"hhLU2TtbCe+fdmf4/5iPNkA0rZd1fuUZmUViVbsAdflv911Yu3rt1GxMGJXfTdP5bMuYLFQtzPkUy65DT9xsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65c564976d68d8de734803a60a1016acdf338ebe854ffc7466d8d7d420a38d9b","last_reissued_at":"2026-07-05T00:15:07.067633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:07.067633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking unsupervised near-duplicate image detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.LG","cs.MM","stat.ML"],"primary_cat":"cs.CV","authors_text":"Fabrizio Lamberti, Lia Morra","submitted_at":"2019-07-03T09:08:47Z","abstract_excerpt":"Unsupervised near-duplicate detection has many practical applications ranging from social media analysis and web-scale retrieval, to digital image forensics. It entails running a threshold-limited query on a set of descriptors extracted from the images, with the goal of identifying all possible near-duplicates, while limiting the false positives due to visually similar images. Since the rate of false alarms grows with the dataset size, a very high specificity is thus required, up to $1 - 10^{-9}$ for realistic use cases; this important requirement, however, is often overlooked in literature. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02821","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/1907.02821/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":"1907.02821","created_at":"2026-07-05T00:15:07.067696+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.02821v1","created_at":"2026-07-05T00:15:07.067696+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02821","created_at":"2026-07-05T00:15:07.067696+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXCWJF3NNDMN","created_at":"2026-07-05T00:15:07.067696+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXCWJF3NNDMN442I","created_at":"2026-07-05T00:15:07.067696+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXCWJF3N","created_at":"2026-07-05T00:15:07.067696+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/MXCWJF3NNDMN442IAOTAUEAWVT","json":"https://pith.science/pith/MXCWJF3NNDMN442IAOTAUEAWVT.json","graph_json":"https://pith.science/api/pith-number/MXCWJF3NNDMN442IAOTAUEAWVT/graph.json","events_json":"https://pith.science/api/pith-number/MXCWJF3NNDMN442IAOTAUEAWVT/events.json","paper":"https://pith.science/paper/MXCWJF3N"},"agent_actions":{"view_html":"https://pith.science/pith/MXCWJF3NNDMN442IAOTAUEAWVT","download_json":"https://pith.science/pith/MXCWJF3NNDMN442IAOTAUEAWVT.json","view_paper":"https://pith.science/paper/MXCWJF3N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.02821&json=true","fetch_graph":"https://pith.science/api/pith-number/MXCWJF3NNDMN442IAOTAUEAWVT/graph.json","fetch_events":"https://pith.science/api/pith-number/MXCWJF3NNDMN442IAOTAUEAWVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXCWJF3NNDMN442IAOTAUEAWVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXCWJF3NNDMN442IAOTAUEAWVT/action/storage_attestation","attest_author":"https://pith.science/pith/MXCWJF3NNDMN442IAOTAUEAWVT/action/author_attestation","sign_citation":"https://pith.science/pith/MXCWJF3NNDMN442IAOTAUEAWVT/action/citation_signature","submit_replication":"https://pith.science/pith/MXCWJF3NNDMN442IAOTAUEAWVT/action/replication_record"}},"created_at":"2026-07-05T00:15:07.067696+00:00","updated_at":"2026-07-05T00:15:07.067696+00:00"}