{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5RYRRAWLMTW65JLSLSXHVCA3NE","short_pith_number":"pith:5RYRRAWL","schema_version":"1.0","canonical_sha256":"ec711882cb64edeea5725cae7a881b6934c200e422f6dcbe4296be6b310f3027","source":{"kind":"arxiv","id":"2308.15513","version":2},"attestation_state":"computed","paper":{"title":"Navigating Perplexity: A linear relationship with the data set size in t-SNE embeddings","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","q-bio.QM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Elmar Eisemann, Klaus Hildebrandt, Martin Skrodzki, Nicolas F. Chaves-de-Plaza, Thomas H\\\"ollt","submitted_at":"2023-08-29T16:24:11Z","abstract_excerpt":"Widely used pipelines for analyzing high-dimensional data utilize two-dimensional visualizations. These are created, for instance, via t-distributed stochastic neighbor embedding (t-SNE). A crucial element of the t-SNE embedding procedure is the perplexity hyperparameter. That is because the embedding structure varies when perplexity is changed. A suitable perplexity choice depends on the data set and the intended usage for the embedding. Therefore, perplexity is often chosen based on heuristics, intuition, and prior experience. This paper uncovers a linear relationship between perplexity and "},"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":"2308.15513","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-29T16:24:11Z","cross_cats_sorted":["cs.AI","q-bio.QM","stat.ML"],"title_canon_sha256":"978cfb10d07ffbc32e90f4e55ab1968ef8b111c2a3c065c34d5bc24a3c5f1986","abstract_canon_sha256":"157bc13faecb828ec6d1a3449ad51f72dd8853324b80d80de59a87de015cac72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:32.707267Z","signature_b64":"ED875SfXLh8zMwqBZXgaWjy9h+qr4LJ6qfw0LWbZDiVNf/3IBDru1XfzwooHwVExYPF2lso0XFIiKXcSOnptCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec711882cb64edeea5725cae7a881b6934c200e422f6dcbe4296be6b310f3027","last_reissued_at":"2026-07-05T09:44:32.706756Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:32.706756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Navigating Perplexity: A linear relationship with the data set size in t-SNE embeddings","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","q-bio.QM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Elmar Eisemann, Klaus Hildebrandt, Martin Skrodzki, Nicolas F. Chaves-de-Plaza, Thomas H\\\"ollt","submitted_at":"2023-08-29T16:24:11Z","abstract_excerpt":"Widely used pipelines for analyzing high-dimensional data utilize two-dimensional visualizations. These are created, for instance, via t-distributed stochastic neighbor embedding (t-SNE). A crucial element of the t-SNE embedding procedure is the perplexity hyperparameter. That is because the embedding structure varies when perplexity is changed. A suitable perplexity choice depends on the data set and the intended usage for the embedding. Therefore, perplexity is often chosen based on heuristics, intuition, and prior experience. This paper uncovers a linear relationship between perplexity and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15513","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/2308.15513/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":"2308.15513","created_at":"2026-07-05T09:44:32.706815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.15513v2","created_at":"2026-07-05T09:44:32.706815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15513","created_at":"2026-07-05T09:44:32.706815+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RYRRAWLMTW6","created_at":"2026-07-05T09:44:32.706815+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RYRRAWLMTW65JLS","created_at":"2026-07-05T09:44:32.706815+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RYRRAWL","created_at":"2026-07-05T09:44:32.706815+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/5RYRRAWLMTW65JLSLSXHVCA3NE","json":"https://pith.science/pith/5RYRRAWLMTW65JLSLSXHVCA3NE.json","graph_json":"https://pith.science/api/pith-number/5RYRRAWLMTW65JLSLSXHVCA3NE/graph.json","events_json":"https://pith.science/api/pith-number/5RYRRAWLMTW65JLSLSXHVCA3NE/events.json","paper":"https://pith.science/paper/5RYRRAWL"},"agent_actions":{"view_html":"https://pith.science/pith/5RYRRAWLMTW65JLSLSXHVCA3NE","download_json":"https://pith.science/pith/5RYRRAWLMTW65JLSLSXHVCA3NE.json","view_paper":"https://pith.science/paper/5RYRRAWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.15513&json=true","fetch_graph":"https://pith.science/api/pith-number/5RYRRAWLMTW65JLSLSXHVCA3NE/graph.json","fetch_events":"https://pith.science/api/pith-number/5RYRRAWLMTW65JLSLSXHVCA3NE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RYRRAWLMTW65JLSLSXHVCA3NE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RYRRAWLMTW65JLSLSXHVCA3NE/action/storage_attestation","attest_author":"https://pith.science/pith/5RYRRAWLMTW65JLSLSXHVCA3NE/action/author_attestation","sign_citation":"https://pith.science/pith/5RYRRAWLMTW65JLSLSXHVCA3NE/action/citation_signature","submit_replication":"https://pith.science/pith/5RYRRAWLMTW65JLSLSXHVCA3NE/action/replication_record"}},"created_at":"2026-07-05T09:44:32.706815+00:00","updated_at":"2026-07-05T09:44:32.706815+00:00"}