{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IZ6LBAPJ4SJ55KK4G2CDOI2FPU","short_pith_number":"pith:IZ6LBAPJ","schema_version":"1.0","canonical_sha256":"467cb081e9e493dea95c36843723457d02e3c56a547e929375c9c16f8c08453c","source":{"kind":"arxiv","id":"2406.02465","version":1},"attestation_state":"computed","paper":{"title":"An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Graham W. Taylor, Joakim Bruslund Haurum, Sageev Oore, Scott C. Lowe, Thomas B. Moeslund","submitted_at":"2024-06-04T16:34:17Z","abstract_excerpt":"Can pretrained models generalize to new datasets without any retraining? We deploy pretrained image models on datasets they were not trained for, and investigate whether their embeddings form meaningful clusters. Our suite of benchmarking experiments use encoders pretrained solely on ImageNet-1k with either supervised or self-supervised training techniques, deployed on image datasets that were not seen during training, and clustered with conventional clustering algorithms. This evaluation provides new insights into the embeddings of self-supervised models, which prioritize different features t"},"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":"2406.02465","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-04T16:34:17Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"33200b647a5a613bef42185138ec30087cf388ae8b6042dc7e3324141ebcef6e","abstract_canon_sha256":"7ba7e67c55373ccf73075f37e6efa666d51af5ce7d1516024196a7173bb1a264"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:20.165580Z","signature_b64":"9iCA3abr8bQgDQ7rF5qLd+lORd6k+dZ0DOdCfOrAe+jRUj4d8ur6y8ZazPRGrxXCRIdCF7zBb4S/HH1RhLYwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"467cb081e9e493dea95c36843723457d02e3c56a547e929375c9c16f8c08453c","last_reissued_at":"2026-07-05T08:27:20.165160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:20.165160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Study into Clustering of Unseen Datasets with Self-Supervised Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Graham W. Taylor, Joakim Bruslund Haurum, Sageev Oore, Scott C. Lowe, Thomas B. Moeslund","submitted_at":"2024-06-04T16:34:17Z","abstract_excerpt":"Can pretrained models generalize to new datasets without any retraining? We deploy pretrained image models on datasets they were not trained for, and investigate whether their embeddings form meaningful clusters. Our suite of benchmarking experiments use encoders pretrained solely on ImageNet-1k with either supervised or self-supervised training techniques, deployed on image datasets that were not seen during training, and clustered with conventional clustering algorithms. This evaluation provides new insights into the embeddings of self-supervised models, which prioritize different features t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02465","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/2406.02465/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":"2406.02465","created_at":"2026-07-05T08:27:20.165214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02465v1","created_at":"2026-07-05T08:27:20.165214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02465","created_at":"2026-07-05T08:27:20.165214+00:00"},{"alias_kind":"pith_short_12","alias_value":"IZ6LBAPJ4SJ5","created_at":"2026-07-05T08:27:20.165214+00:00"},{"alias_kind":"pith_short_16","alias_value":"IZ6LBAPJ4SJ55KK4","created_at":"2026-07-05T08:27:20.165214+00:00"},{"alias_kind":"pith_short_8","alias_value":"IZ6LBAPJ","created_at":"2026-07-05T08:27:20.165214+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/IZ6LBAPJ4SJ55KK4G2CDOI2FPU","json":"https://pith.science/pith/IZ6LBAPJ4SJ55KK4G2CDOI2FPU.json","graph_json":"https://pith.science/api/pith-number/IZ6LBAPJ4SJ55KK4G2CDOI2FPU/graph.json","events_json":"https://pith.science/api/pith-number/IZ6LBAPJ4SJ55KK4G2CDOI2FPU/events.json","paper":"https://pith.science/paper/IZ6LBAPJ"},"agent_actions":{"view_html":"https://pith.science/pith/IZ6LBAPJ4SJ55KK4G2CDOI2FPU","download_json":"https://pith.science/pith/IZ6LBAPJ4SJ55KK4G2CDOI2FPU.json","view_paper":"https://pith.science/paper/IZ6LBAPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02465&json=true","fetch_graph":"https://pith.science/api/pith-number/IZ6LBAPJ4SJ55KK4G2CDOI2FPU/graph.json","fetch_events":"https://pith.science/api/pith-number/IZ6LBAPJ4SJ55KK4G2CDOI2FPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IZ6LBAPJ4SJ55KK4G2CDOI2FPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IZ6LBAPJ4SJ55KK4G2CDOI2FPU/action/storage_attestation","attest_author":"https://pith.science/pith/IZ6LBAPJ4SJ55KK4G2CDOI2FPU/action/author_attestation","sign_citation":"https://pith.science/pith/IZ6LBAPJ4SJ55KK4G2CDOI2FPU/action/citation_signature","submit_replication":"https://pith.science/pith/IZ6LBAPJ4SJ55KK4G2CDOI2FPU/action/replication_record"}},"created_at":"2026-07-05T08:27:20.165214+00:00","updated_at":"2026-07-05T08:27:20.165214+00:00"}