{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IO4YQL6DA556J6ARIRPQYAZ45A","short_pith_number":"pith:IO4YQL6D","schema_version":"1.0","canonical_sha256":"43b9882fc3077be4f811445f0c033ce811094f2ccaf7a9d04a7ebfc3ccc1fa63","source":{"kind":"arxiv","id":"2105.07536","version":4},"attestation_state":"computed","paper":{"title":"Theoretical Foundations of t-SNE for Visualizing High-Dimensional Clustered Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Rong Ma, T. Tony Cai","submitted_at":"2021-05-16T22:43:20Z","abstract_excerpt":"This paper investigates the theoretical foundations of the t-distributed stochastic neighbor embedding (t-SNE) algorithm, a popular nonlinear dimension reduction and data visualization method. A novel theoretical framework for the analysis of t-SNE based on the gradient descent approach is presented. For the early exaggeration stage of t-SNE, we show its asymptotic equivalence to power iterations based on the underlying graph Laplacian, characterize its limiting behavior, and uncover its deep connection to Laplacian spectral clustering, and fundamental principles including early stopping as im"},"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":"2105.07536","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2021-05-16T22:43:20Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"790db1f485d7474772f99aa5795f8fa08c099a7f985a4da623900b9eafdee9fe","abstract_canon_sha256":"5f44ce580a95a0c0887e16666e1cec24f2045fe59a405f221c34a941b66c3771"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:08.122276Z","signature_b64":"LzsI0tj9TVxcisPCQ392WgEy/0qLc4EEeZ5/0Mh3PiDc2zvU2cU/suGKnpHGHdCjQfwPmnuAG0eZNABPLMMQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43b9882fc3077be4f811445f0c033ce811094f2ccaf7a9d04a7ebfc3ccc1fa63","last_reissued_at":"2026-07-05T05:12:08.121790Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:08.121790Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theoretical Foundations of t-SNE for Visualizing High-Dimensional Clustered Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Rong Ma, T. Tony Cai","submitted_at":"2021-05-16T22:43:20Z","abstract_excerpt":"This paper investigates the theoretical foundations of the t-distributed stochastic neighbor embedding (t-SNE) algorithm, a popular nonlinear dimension reduction and data visualization method. A novel theoretical framework for the analysis of t-SNE based on the gradient descent approach is presented. For the early exaggeration stage of t-SNE, we show its asymptotic equivalence to power iterations based on the underlying graph Laplacian, characterize its limiting behavior, and uncover its deep connection to Laplacian spectral clustering, and fundamental principles including early stopping as im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.07536","kind":"arxiv","version":4},"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/2105.07536/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":"2105.07536","created_at":"2026-07-05T05:12:08.121848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.07536v4","created_at":"2026-07-05T05:12:08.121848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.07536","created_at":"2026-07-05T05:12:08.121848+00:00"},{"alias_kind":"pith_short_12","alias_value":"IO4YQL6DA556","created_at":"2026-07-05T05:12:08.121848+00:00"},{"alias_kind":"pith_short_16","alias_value":"IO4YQL6DA556J6AR","created_at":"2026-07-05T05:12:08.121848+00:00"},{"alias_kind":"pith_short_8","alias_value":"IO4YQL6D","created_at":"2026-07-05T05:12:08.121848+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27227","citing_title":"Realistic Time-Domain Synthesis of Gravitational-Wave Detector Glitches using Class-Conditional Derivative Generative Adversarial Networks","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27227","citing_title":"Realistic Time-Domain Synthesis of Gravitational-Wave Detector Glitches using Class-Conditional Derivative Generative Adversarial Networks","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13947","citing_title":"Heuristic Style Transfer for Real-Time, Efficient Weather Attribute Detection","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IO4YQL6DA556J6ARIRPQYAZ45A","json":"https://pith.science/pith/IO4YQL6DA556J6ARIRPQYAZ45A.json","graph_json":"https://pith.science/api/pith-number/IO4YQL6DA556J6ARIRPQYAZ45A/graph.json","events_json":"https://pith.science/api/pith-number/IO4YQL6DA556J6ARIRPQYAZ45A/events.json","paper":"https://pith.science/paper/IO4YQL6D"},"agent_actions":{"view_html":"https://pith.science/pith/IO4YQL6DA556J6ARIRPQYAZ45A","download_json":"https://pith.science/pith/IO4YQL6DA556J6ARIRPQYAZ45A.json","view_paper":"https://pith.science/paper/IO4YQL6D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.07536&json=true","fetch_graph":"https://pith.science/api/pith-number/IO4YQL6DA556J6ARIRPQYAZ45A/graph.json","fetch_events":"https://pith.science/api/pith-number/IO4YQL6DA556J6ARIRPQYAZ45A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IO4YQL6DA556J6ARIRPQYAZ45A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IO4YQL6DA556J6ARIRPQYAZ45A/action/storage_attestation","attest_author":"https://pith.science/pith/IO4YQL6DA556J6ARIRPQYAZ45A/action/author_attestation","sign_citation":"https://pith.science/pith/IO4YQL6DA556J6ARIRPQYAZ45A/action/citation_signature","submit_replication":"https://pith.science/pith/IO4YQL6DA556J6ARIRPQYAZ45A/action/replication_record"}},"created_at":"2026-07-05T05:12:08.121848+00:00","updated_at":"2026-07-05T05:12:08.121848+00:00"}