{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:Y774AFPJYB6NQ4MP5B4MUSM3X4","short_pith_number":"pith:Y774AFPJ","schema_version":"1.0","canonical_sha256":"c7ffc015e9c07cd8718fe878ca499bbf26cbd5e2f8dea626c353ca0bbd32cb26","source":{"kind":"arxiv","id":"1708.03569","version":1},"attestation_state":"computed","paper":{"title":"Semantic Word Clouds with Background Corpus Normalization and t-distributed Stochastic Neighbor Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Andreas Spitz, Erich Schubert, Johanna Gei{\\ss}, Michael Gertz, Michael Weiler","submitted_at":"2017-08-11T15:19:53Z","abstract_excerpt":"Many word clouds provide no semantics to the word placement, but use a random layout optimized solely for aesthetic purposes. We propose a novel approach to model word significance and word affinity within a document, and in comparison to a large background corpus. We demonstrate its usefulness for generating more meaningful word clouds as a visual summary of a given document. We then select keywords based on their significance and construct the word cloud based on the derived affinity. Based on a modified t-distributed stochastic neighbor embedding (t-SNE), we generate a semantic word placeme"},"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":"1708.03569","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-08-11T15:19:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"761dd3fbee5b9cd0d4f420c02960fb945127333ceb7bfc6d12b2baf5c34df58e","abstract_canon_sha256":"7c765a16f39e8ffe0500c0f342b19687f90b0b8d83d5ee2d16a918176e1e77af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:12.321865Z","signature_b64":"jRHhXB5lBcJ9mwKsaEUBMootpwgsXE8a1lDH7NHlk51BkX6Et3BzkOpNv6ORWzs/qC2f5xjClpm4l9XN0wuEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7ffc015e9c07cd8718fe878ca499bbf26cbd5e2f8dea626c353ca0bbd32cb26","last_reissued_at":"2026-05-18T00:38:12.321237Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:12.321237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Word Clouds with Background Corpus Normalization and t-distributed Stochastic Neighbor Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Andreas Spitz, Erich Schubert, Johanna Gei{\\ss}, Michael Gertz, Michael Weiler","submitted_at":"2017-08-11T15:19:53Z","abstract_excerpt":"Many word clouds provide no semantics to the word placement, but use a random layout optimized solely for aesthetic purposes. We propose a novel approach to model word significance and word affinity within a document, and in comparison to a large background corpus. We demonstrate its usefulness for generating more meaningful word clouds as a visual summary of a given document. We then select keywords based on their significance and construct the word cloud based on the derived affinity. Based on a modified t-distributed stochastic neighbor embedding (t-SNE), we generate a semantic word placeme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.03569","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":""},"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":"1708.03569","created_at":"2026-05-18T00:38:12.321331+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.03569v1","created_at":"2026-05-18T00:38:12.321331+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.03569","created_at":"2026-05-18T00:38:12.321331+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y774AFPJYB6N","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y774AFPJYB6NQ4MP","created_at":"2026-05-18T12:31:56.362134+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y774AFPJ","created_at":"2026-05-18T12:31:56.362134+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/Y774AFPJYB6NQ4MP5B4MUSM3X4","json":"https://pith.science/pith/Y774AFPJYB6NQ4MP5B4MUSM3X4.json","graph_json":"https://pith.science/api/pith-number/Y774AFPJYB6NQ4MP5B4MUSM3X4/graph.json","events_json":"https://pith.science/api/pith-number/Y774AFPJYB6NQ4MP5B4MUSM3X4/events.json","paper":"https://pith.science/paper/Y774AFPJ"},"agent_actions":{"view_html":"https://pith.science/pith/Y774AFPJYB6NQ4MP5B4MUSM3X4","download_json":"https://pith.science/pith/Y774AFPJYB6NQ4MP5B4MUSM3X4.json","view_paper":"https://pith.science/paper/Y774AFPJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.03569&json=true","fetch_graph":"https://pith.science/api/pith-number/Y774AFPJYB6NQ4MP5B4MUSM3X4/graph.json","fetch_events":"https://pith.science/api/pith-number/Y774AFPJYB6NQ4MP5B4MUSM3X4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y774AFPJYB6NQ4MP5B4MUSM3X4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y774AFPJYB6NQ4MP5B4MUSM3X4/action/storage_attestation","attest_author":"https://pith.science/pith/Y774AFPJYB6NQ4MP5B4MUSM3X4/action/author_attestation","sign_citation":"https://pith.science/pith/Y774AFPJYB6NQ4MP5B4MUSM3X4/action/citation_signature","submit_replication":"https://pith.science/pith/Y774AFPJYB6NQ4MP5B4MUSM3X4/action/replication_record"}},"created_at":"2026-05-18T00:38:12.321331+00:00","updated_at":"2026-05-18T00:38:12.321331+00:00"}