{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:T3JSZE4WAGTGHEPLEAW3YBMORW","short_pith_number":"pith:T3JSZE4W","schema_version":"1.0","canonical_sha256":"9ed32c939601a66391eb202dbc058e8d9a367b0e0ff21f8d4faad70d19a4e581","source":{"kind":"arxiv","id":"2210.09879","version":3},"attestation_state":"computed","paper":{"title":"Unsupervised visualization of image datasets using contrastive learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.HC"],"primary_cat":"cs.LG","authors_text":"Dmitry Kobak, Jan Niklas B\\\"ohm, Philipp Berens","submitted_at":"2022-10-18T14:13:20Z","abstract_excerpt":"Visualization methods based on the nearest neighbor graph, such as t-SNE or UMAP, are widely used for visualizing high-dimensional data. Yet, these approaches only produce meaningful results if the nearest neighbors themselves are meaningful. For images represented in pixel space this is not the case, as distances in pixel space are often not capturing our sense of similarity and therefore neighbors are not semantically close. This problem can be circumvented by self-supervised approaches based on contrastive learning, such as SimCLR, relying on data augmentation to generate implicit neighbors"},"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":"2210.09879","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-18T14:13:20Z","cross_cats_sorted":["cs.CV","cs.HC"],"title_canon_sha256":"c804087f2a92c0627ee419394b4b280a8c6943f1e8204e986821c1334a33adc0","abstract_canon_sha256":"67eb5ba9e98bab9f8435d9192c1ea848fe519e3d42e9dbdf71ca73d6263b4742"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:21.765765Z","signature_b64":"UX3n9GAV0hUUyworiLQn9gpZlf/QOl3951DDJ3M8ZYaH+HdFhoTR97Df8Wi9wTRO0juw9ZlWZ18ieEjkgvvQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ed32c939601a66391eb202dbc058e8d9a367b0e0ff21f8d4faad70d19a4e581","last_reissued_at":"2026-07-05T08:27:21.765201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:21.765201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised visualization of image datasets using contrastive learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.HC"],"primary_cat":"cs.LG","authors_text":"Dmitry Kobak, Jan Niklas B\\\"ohm, Philipp Berens","submitted_at":"2022-10-18T14:13:20Z","abstract_excerpt":"Visualization methods based on the nearest neighbor graph, such as t-SNE or UMAP, are widely used for visualizing high-dimensional data. Yet, these approaches only produce meaningful results if the nearest neighbors themselves are meaningful. For images represented in pixel space this is not the case, as distances in pixel space are often not capturing our sense of similarity and therefore neighbors are not semantically close. This problem can be circumvented by self-supervised approaches based on contrastive learning, such as SimCLR, relying on data augmentation to generate implicit neighbors"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09879","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/2210.09879/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":"2210.09879","created_at":"2026-07-05T08:27:21.765263+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09879v3","created_at":"2026-07-05T08:27:21.765263+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09879","created_at":"2026-07-05T08:27:21.765263+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3JSZE4WAGTG","created_at":"2026-07-05T08:27:21.765263+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3JSZE4WAGTGHEPL","created_at":"2026-07-05T08:27:21.765263+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3JSZE4W","created_at":"2026-07-05T08:27:21.765263+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.20173","citing_title":"MAPLE: Self-Supervised Learning-Enhanced Nonlinear Dimensionality Reduction for Visual Analysis","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02535","citing_title":"A Spectral Framework for Multi-Scale Nonlinear Dimensionality Reduction","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T3JSZE4WAGTGHEPLEAW3YBMORW","json":"https://pith.science/pith/T3JSZE4WAGTGHEPLEAW3YBMORW.json","graph_json":"https://pith.science/api/pith-number/T3JSZE4WAGTGHEPLEAW3YBMORW/graph.json","events_json":"https://pith.science/api/pith-number/T3JSZE4WAGTGHEPLEAW3YBMORW/events.json","paper":"https://pith.science/paper/T3JSZE4W"},"agent_actions":{"view_html":"https://pith.science/pith/T3JSZE4WAGTGHEPLEAW3YBMORW","download_json":"https://pith.science/pith/T3JSZE4WAGTGHEPLEAW3YBMORW.json","view_paper":"https://pith.science/paper/T3JSZE4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09879&json=true","fetch_graph":"https://pith.science/api/pith-number/T3JSZE4WAGTGHEPLEAW3YBMORW/graph.json","fetch_events":"https://pith.science/api/pith-number/T3JSZE4WAGTGHEPLEAW3YBMORW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3JSZE4WAGTGHEPLEAW3YBMORW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3JSZE4WAGTGHEPLEAW3YBMORW/action/storage_attestation","attest_author":"https://pith.science/pith/T3JSZE4WAGTGHEPLEAW3YBMORW/action/author_attestation","sign_citation":"https://pith.science/pith/T3JSZE4WAGTGHEPLEAW3YBMORW/action/citation_signature","submit_replication":"https://pith.science/pith/T3JSZE4WAGTGHEPLEAW3YBMORW/action/replication_record"}},"created_at":"2026-07-05T08:27:21.765263+00:00","updated_at":"2026-07-05T08:27:21.765263+00:00"}