{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UGGZ3FB5X6RMFU25YBT5NUUEWL","short_pith_number":"pith:UGGZ3FB5","schema_version":"1.0","canonical_sha256":"a18d9d943dbfa2c2d35dc067d6d284b2ec2a93bd581d5a1623ccdf4d6d8ddc1d","source":{"kind":"arxiv","id":"2602.16449","version":2},"attestation_state":"computed","paper":{"title":"GICDM: Mitigating Hubness for Reliable Distance-Based Generative Model Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bertrand Thirion, Hugues Talbot, Nicolas Salvy","submitted_at":"2026-02-18T13:33:54Z","abstract_excerpt":"Generative model evaluation commonly relies on high-dimensional embedding spaces to compute distances between samples. We show that dataset representations in these spaces are affected by the hubness phenomenon, which distorts nearest-neighbor relationships and biases distance-based metrics. Building on the classical Iterative Contextual Dissimilarity Measure (ICDM), we introduce Generative ICDM (GICDM), a method to correct neighborhood estimation for both real and generated data. We introduce a multi-scale extension to improve empirical behavior. Extensive experiments on synthetic and real be"},"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":"2602.16449","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-18T13:33:54Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"4b7e6d8f9049cbe1d36afade80a3ac43b576248bc6c723498962963ebf1b18d1","abstract_canon_sha256":"c48be22864af889ff7eee40b9b217cc69e911e425e4c6f89a74b889461c402df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:05:12.230064Z","signature_b64":"iK7kueu2LUB4ViU/LhTPlhffUtDiJrCa+B8ZVi83vNTOJOUO0lT+t+k9vFKIXA0cCIs8tQZOWSBaSwPFD1BQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a18d9d943dbfa2c2d35dc067d6d284b2ec2a93bd581d5a1623ccdf4d6d8ddc1d","last_reissued_at":"2026-05-27T02:05:12.229251Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:05:12.229251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GICDM: Mitigating Hubness for Reliable Distance-Based Generative Model Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bertrand Thirion, Hugues Talbot, Nicolas Salvy","submitted_at":"2026-02-18T13:33:54Z","abstract_excerpt":"Generative model evaluation commonly relies on high-dimensional embedding spaces to compute distances between samples. We show that dataset representations in these spaces are affected by the hubness phenomenon, which distorts nearest-neighbor relationships and biases distance-based metrics. Building on the classical Iterative Contextual Dissimilarity Measure (ICDM), we introduce Generative ICDM (GICDM), a method to correct neighborhood estimation for both real and generated data. We introduce a multi-scale extension to improve empirical behavior. Extensive experiments on synthetic and real be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.16449","kind":"arxiv","version":2},"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/2602.16449/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":"2602.16449","created_at":"2026-05-27T02:05:12.229372+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.16449v2","created_at":"2026-05-27T02:05:12.229372+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.16449","created_at":"2026-05-27T02:05:12.229372+00:00"},{"alias_kind":"pith_short_12","alias_value":"UGGZ3FB5X6RM","created_at":"2026-05-27T02:05:12.229372+00:00"},{"alias_kind":"pith_short_16","alias_value":"UGGZ3FB5X6RMFU25","created_at":"2026-05-27T02:05:12.229372+00:00"},{"alias_kind":"pith_short_8","alias_value":"UGGZ3FB5","created_at":"2026-05-27T02:05:12.229372+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/UGGZ3FB5X6RMFU25YBT5NUUEWL","json":"https://pith.science/pith/UGGZ3FB5X6RMFU25YBT5NUUEWL.json","graph_json":"https://pith.science/api/pith-number/UGGZ3FB5X6RMFU25YBT5NUUEWL/graph.json","events_json":"https://pith.science/api/pith-number/UGGZ3FB5X6RMFU25YBT5NUUEWL/events.json","paper":"https://pith.science/paper/UGGZ3FB5"},"agent_actions":{"view_html":"https://pith.science/pith/UGGZ3FB5X6RMFU25YBT5NUUEWL","download_json":"https://pith.science/pith/UGGZ3FB5X6RMFU25YBT5NUUEWL.json","view_paper":"https://pith.science/paper/UGGZ3FB5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.16449&json=true","fetch_graph":"https://pith.science/api/pith-number/UGGZ3FB5X6RMFU25YBT5NUUEWL/graph.json","fetch_events":"https://pith.science/api/pith-number/UGGZ3FB5X6RMFU25YBT5NUUEWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UGGZ3FB5X6RMFU25YBT5NUUEWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UGGZ3FB5X6RMFU25YBT5NUUEWL/action/storage_attestation","attest_author":"https://pith.science/pith/UGGZ3FB5X6RMFU25YBT5NUUEWL/action/author_attestation","sign_citation":"https://pith.science/pith/UGGZ3FB5X6RMFU25YBT5NUUEWL/action/citation_signature","submit_replication":"https://pith.science/pith/UGGZ3FB5X6RMFU25YBT5NUUEWL/action/replication_record"}},"created_at":"2026-05-27T02:05:12.229372+00:00","updated_at":"2026-05-27T02:05:12.229372+00:00"}