{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CLZN363SIONW2UBVG6JTWRVVJY","short_pith_number":"pith:CLZN363S","schema_version":"1.0","canonical_sha256":"12f2ddfb72439b6d503537933b46b54e1b672b8e5ec95ea7d9bc8ba08388b17b","source":{"kind":"arxiv","id":"2506.01435","version":1},"attestation_state":"computed","paper":{"title":"Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hayato Tsukagoshi, Ryohei Sasano","submitted_at":"2025-06-02T08:50:38Z","abstract_excerpt":"Prompt-based text embedding models, which generate task-specific embeddings upon receiving tailored prompts, have recently demonstrated remarkable performance. However, their resulting embeddings often have thousands of dimensions, leading to high storage costs and increased computational costs of embedding-based operations. In this paper, we investigate how post-hoc dimensionality reduction applied to the embeddings affects the performance of various tasks that leverage these embeddings, specifically classification, clustering, retrieval, and semantic textual similarity (STS) tasks. Our exper"},"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":"2506.01435","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T08:50:38Z","cross_cats_sorted":[],"title_canon_sha256":"4680ed560ce6799e99402ffa12fe4d66eaf5e0c8eb11d0c57b67bc964ed968ef","abstract_canon_sha256":"893d1902e7ab51f298857180b30d6741f2399716172c725de5f2ea665656baab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:13.347686Z","signature_b64":"dtOLr5ImC/QX3Wr82PEknv/6SvGd4fhhdunFzel2V6me3Y41hXf3qiHGnrKc6P2Yf6ZqLgP7HNoS1Fo7Q2lGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12f2ddfb72439b6d503537933b46b54e1b672b8e5ec95ea7d9bc8ba08388b17b","last_reissued_at":"2026-07-05T11:14:13.347206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:13.347206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hayato Tsukagoshi, Ryohei Sasano","submitted_at":"2025-06-02T08:50:38Z","abstract_excerpt":"Prompt-based text embedding models, which generate task-specific embeddings upon receiving tailored prompts, have recently demonstrated remarkable performance. However, their resulting embeddings often have thousands of dimensions, leading to high storage costs and increased computational costs of embedding-based operations. In this paper, we investigate how post-hoc dimensionality reduction applied to the embeddings affects the performance of various tasks that leverage these embeddings, specifically classification, clustering, retrieval, and semantic textual similarity (STS) tasks. Our exper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01435","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.01435/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":"2506.01435","created_at":"2026-07-05T11:14:13.347262+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01435v1","created_at":"2026-07-05T11:14:13.347262+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01435","created_at":"2026-07-05T11:14:13.347262+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLZN363SIONW","created_at":"2026-07-05T11:14:13.347262+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLZN363SIONW2UBV","created_at":"2026-07-05T11:14:13.347262+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLZN363S","created_at":"2026-07-05T11:14:13.347262+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03346","citing_title":"Provable Accuracy Collapse in Embedding-Based Representations under Dimensionality Mismatch","ref_index":231,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CLZN363SIONW2UBVG6JTWRVVJY","json":"https://pith.science/pith/CLZN363SIONW2UBVG6JTWRVVJY.json","graph_json":"https://pith.science/api/pith-number/CLZN363SIONW2UBVG6JTWRVVJY/graph.json","events_json":"https://pith.science/api/pith-number/CLZN363SIONW2UBVG6JTWRVVJY/events.json","paper":"https://pith.science/paper/CLZN363S"},"agent_actions":{"view_html":"https://pith.science/pith/CLZN363SIONW2UBVG6JTWRVVJY","download_json":"https://pith.science/pith/CLZN363SIONW2UBVG6JTWRVVJY.json","view_paper":"https://pith.science/paper/CLZN363S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01435&json=true","fetch_graph":"https://pith.science/api/pith-number/CLZN363SIONW2UBVG6JTWRVVJY/graph.json","fetch_events":"https://pith.science/api/pith-number/CLZN363SIONW2UBVG6JTWRVVJY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLZN363SIONW2UBVG6JTWRVVJY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLZN363SIONW2UBVG6JTWRVVJY/action/storage_attestation","attest_author":"https://pith.science/pith/CLZN363SIONW2UBVG6JTWRVVJY/action/author_attestation","sign_citation":"https://pith.science/pith/CLZN363SIONW2UBVG6JTWRVVJY/action/citation_signature","submit_replication":"https://pith.science/pith/CLZN363SIONW2UBVG6JTWRVVJY/action/replication_record"}},"created_at":"2026-07-05T11:14:13.347262+00:00","updated_at":"2026-07-05T11:14:13.347262+00:00"}