{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DKDGFLZQALV6RQ72DX4YI5CSTB","short_pith_number":"pith:DKDGFLZQ","schema_version":"1.0","canonical_sha256":"1a8662af3002ebe8c3fa1df9847452985fc45ba10905beea3bc1f314cb99f7fc","source":{"kind":"arxiv","id":"2108.06197","version":4},"attestation_state":"computed","paper":{"title":"A comparison of latent semantic analysis and correspondence analysis of document-term matrices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"David J. Hessen, Peter G. M. van der Heijden, Qianqian Qi, Tejaswini Deoskar","submitted_at":"2021-07-25T09:10:10Z","abstract_excerpt":"Latent semantic analysis (LSA) and correspondence analysis (CA) are two techniques that use a singular value decomposition (SVD) for dimensionality reduction. LSA has been extensively used to obtain low-dimensional representations that capture relationships among documents and terms. In this article, we present a theoretical analysis and comparison of the two techniques in the context of document-term matrices. We show that CA has some attractive properties as compared to LSA, for instance that effects of margins, i.e. sums of row elements and column elements, arising from differing document-l"},"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":"2108.06197","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2021-07-25T09:10:10Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"c9cf950327b8865fe9481a5638f6061b1fd18c22d3226a5259c17ab10faaac31","abstract_canon_sha256":"69cc2d1b418f0e512a7be5412e0e3296f478ea66759ae45c2b6e4384bc0ec4c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:27.521061Z","signature_b64":"tEZB6VHB0ahVV2fuZ3tMdN7EyW034qMyMR1EgmsU0I3iaaJiWvVRMNIcRB+9QobnPm6yZ7Os9/l3aN0MHbLUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a8662af3002ebe8c3fa1df9847452985fc45ba10905beea3bc1f314cb99f7fc","last_reissued_at":"2026-07-05T09:37:27.520555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:27.520555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A comparison of latent semantic analysis and correspondence analysis of document-term matrices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.IR","authors_text":"David J. Hessen, Peter G. M. van der Heijden, Qianqian Qi, Tejaswini Deoskar","submitted_at":"2021-07-25T09:10:10Z","abstract_excerpt":"Latent semantic analysis (LSA) and correspondence analysis (CA) are two techniques that use a singular value decomposition (SVD) for dimensionality reduction. LSA has been extensively used to obtain low-dimensional representations that capture relationships among documents and terms. In this article, we present a theoretical analysis and comparison of the two techniques in the context of document-term matrices. We show that CA has some attractive properties as compared to LSA, for instance that effects of margins, i.e. sums of row elements and column elements, arising from differing document-l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.06197","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/2108.06197/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":"2108.06197","created_at":"2026-07-05T09:37:27.520618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.06197v4","created_at":"2026-07-05T09:37:27.520618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.06197","created_at":"2026-07-05T09:37:27.520618+00:00"},{"alias_kind":"pith_short_12","alias_value":"DKDGFLZQALV6","created_at":"2026-07-05T09:37:27.520618+00:00"},{"alias_kind":"pith_short_16","alias_value":"DKDGFLZQALV6RQ72","created_at":"2026-07-05T09:37:27.520618+00:00"},{"alias_kind":"pith_short_8","alias_value":"DKDGFLZQ","created_at":"2026-07-05T09:37:27.520618+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/DKDGFLZQALV6RQ72DX4YI5CSTB","json":"https://pith.science/pith/DKDGFLZQALV6RQ72DX4YI5CSTB.json","graph_json":"https://pith.science/api/pith-number/DKDGFLZQALV6RQ72DX4YI5CSTB/graph.json","events_json":"https://pith.science/api/pith-number/DKDGFLZQALV6RQ72DX4YI5CSTB/events.json","paper":"https://pith.science/paper/DKDGFLZQ"},"agent_actions":{"view_html":"https://pith.science/pith/DKDGFLZQALV6RQ72DX4YI5CSTB","download_json":"https://pith.science/pith/DKDGFLZQALV6RQ72DX4YI5CSTB.json","view_paper":"https://pith.science/paper/DKDGFLZQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.06197&json=true","fetch_graph":"https://pith.science/api/pith-number/DKDGFLZQALV6RQ72DX4YI5CSTB/graph.json","fetch_events":"https://pith.science/api/pith-number/DKDGFLZQALV6RQ72DX4YI5CSTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DKDGFLZQALV6RQ72DX4YI5CSTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DKDGFLZQALV6RQ72DX4YI5CSTB/action/storage_attestation","attest_author":"https://pith.science/pith/DKDGFLZQALV6RQ72DX4YI5CSTB/action/author_attestation","sign_citation":"https://pith.science/pith/DKDGFLZQALV6RQ72DX4YI5CSTB/action/citation_signature","submit_replication":"https://pith.science/pith/DKDGFLZQALV6RQ72DX4YI5CSTB/action/replication_record"}},"created_at":"2026-07-05T09:37:27.520618+00:00","updated_at":"2026-07-05T09:37:27.520618+00:00"}