{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:OOGLEW65Q7HTMRTVI6O3WU4Y52","short_pith_number":"pith:OOGLEW65","schema_version":"1.0","canonical_sha256":"738cb25bdd87cf364675479dbb5398eeb5fb4e67fd9a1c8ebc7970361975b0a6","source":{"kind":"arxiv","id":"1908.10410","version":3},"attestation_state":"computed","paper":{"title":"Visualization of Very Large High-Dimensional Data Sets as Minimum Spanning Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.DS","cs.IR"],"primary_cat":"cs.HC","authors_text":"Daniel Probst, Jean-Louis Reymond","submitted_at":"2019-08-16T15:14:19Z","abstract_excerpt":"The chemical sciences are producing an unprecedented amount of large, high-dimensional data sets containing chemical structures and associated properties. However, there are currently no algorithms to visualize such data while preserving both global and local features with a sufficient level of detail to allow for human inspection and interpretation. Here, we propose a solution to this problem with a new data visualization method, TMAP, capable of representing data sets of up to millions of data points and arbitrary high dimensionality as a two-dimensional tree (http://tmap.gdb.tools). Visuali"},"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":"1908.10410","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2019-08-16T15:14:19Z","cross_cats_sorted":["cs.CV","cs.DS","cs.IR"],"title_canon_sha256":"f580a31fede88af4576fb1962e62631c2334cf963cba78ce6cc124b16f70172c","abstract_canon_sha256":"a096dd16c7c07e4ccb4c75b240fc6e6f4ef242e82f2bb6fc1a4d392e286c4d06"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:29:39.755650Z","signature_b64":"Wk89obfmWplDke7kzCEUzgF+xC5Sd+2BxID+Sf5kK/Z7Rl9ip6LOQbh8nHkP3B20tsrE9vzBFv8pHc6cEny/Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"738cb25bdd87cf364675479dbb5398eeb5fb4e67fd9a1c8ebc7970361975b0a6","last_reissued_at":"2026-07-05T00:29:39.755263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:29:39.755263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visualization of Very Large High-Dimensional Data Sets as Minimum Spanning Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.DS","cs.IR"],"primary_cat":"cs.HC","authors_text":"Daniel Probst, Jean-Louis Reymond","submitted_at":"2019-08-16T15:14:19Z","abstract_excerpt":"The chemical sciences are producing an unprecedented amount of large, high-dimensional data sets containing chemical structures and associated properties. However, there are currently no algorithms to visualize such data while preserving both global and local features with a sufficient level of detail to allow for human inspection and interpretation. Here, we propose a solution to this problem with a new data visualization method, TMAP, capable of representing data sets of up to millions of data points and arbitrary high dimensionality as a two-dimensional tree (http://tmap.gdb.tools). Visuali"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.10410","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/1908.10410/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":"1908.10410","created_at":"2026-07-05T00:29:39.755324+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.10410v3","created_at":"2026-07-05T00:29:39.755324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.10410","created_at":"2026-07-05T00:29:39.755324+00:00"},{"alias_kind":"pith_short_12","alias_value":"OOGLEW65Q7HT","created_at":"2026-07-05T00:29:39.755324+00:00"},{"alias_kind":"pith_short_16","alias_value":"OOGLEW65Q7HTMRTV","created_at":"2026-07-05T00:29:39.755324+00:00"},{"alias_kind":"pith_short_8","alias_value":"OOGLEW65","created_at":"2026-07-05T00:29:39.755324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.05114","citing_title":"PaccMann$^{RL}$: Designing anticancer drugs from transcriptomic data via reinforcement learning","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OOGLEW65Q7HTMRTVI6O3WU4Y52","json":"https://pith.science/pith/OOGLEW65Q7HTMRTVI6O3WU4Y52.json","graph_json":"https://pith.science/api/pith-number/OOGLEW65Q7HTMRTVI6O3WU4Y52/graph.json","events_json":"https://pith.science/api/pith-number/OOGLEW65Q7HTMRTVI6O3WU4Y52/events.json","paper":"https://pith.science/paper/OOGLEW65"},"agent_actions":{"view_html":"https://pith.science/pith/OOGLEW65Q7HTMRTVI6O3WU4Y52","download_json":"https://pith.science/pith/OOGLEW65Q7HTMRTVI6O3WU4Y52.json","view_paper":"https://pith.science/paper/OOGLEW65","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.10410&json=true","fetch_graph":"https://pith.science/api/pith-number/OOGLEW65Q7HTMRTVI6O3WU4Y52/graph.json","fetch_events":"https://pith.science/api/pith-number/OOGLEW65Q7HTMRTVI6O3WU4Y52/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OOGLEW65Q7HTMRTVI6O3WU4Y52/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OOGLEW65Q7HTMRTVI6O3WU4Y52/action/storage_attestation","attest_author":"https://pith.science/pith/OOGLEW65Q7HTMRTVI6O3WU4Y52/action/author_attestation","sign_citation":"https://pith.science/pith/OOGLEW65Q7HTMRTVI6O3WU4Y52/action/citation_signature","submit_replication":"https://pith.science/pith/OOGLEW65Q7HTMRTVI6O3WU4Y52/action/replication_record"}},"created_at":"2026-07-05T00:29:39.755324+00:00","updated_at":"2026-07-05T00:29:39.755324+00:00"}