{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YZZGPREBEEHQDEE72ZRBJF3XML","short_pith_number":"pith:YZZGPREB","schema_version":"1.0","canonical_sha256":"c67267c481210f01909fd66214977762e01335050669d892949d3c12aa96d17c","source":{"kind":"arxiv","id":"2606.01074","version":1},"attestation_state":"computed","paper":{"title":"When Is 0.1% Enough? Analyzing the Combined Effects of Dimensionality Reduction and Quantization on Text Embedding Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hayato Tsukagoshi, Riku Kisako, Ryohei Sasano","submitted_at":"2026-05-31T07:37:34Z","abstract_excerpt":"Recent high-performing text embedding models often output high-dimensional real-valued vectors, resulting in substantial storage and computational costs. To address this issue, compression methods based on dimensionality reduction or quantization have been proposed; however, the effects of combining dimensionality reduction and quantization have not been sufficiently investigated. In this paper, we systematically examine the effectiveness of compressing text embeddings by combining dimensionality reduction and quantization, using four MTEB task families and four pretrained embedding models. Th"},"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":"2606.01074","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-31T07:37:34Z","cross_cats_sorted":[],"title_canon_sha256":"8e5718a8aff5db8cfe85b497163c4fe95e1c9e4ec93b8dc9ee3e18ea6a2f928a","abstract_canon_sha256":"d14da758782080870022336a1c01967b9d090b579bb5c7bbbf585df8266a5162"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:04:20.555449Z","signature_b64":"upyxvn5tjcGoVXvDOhkXXLT0fL8u+xys21l3cmNjGmPB+mmI/ah3R84ryNmn1TnYxawCHItzdV4VCQ7A13tmDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c67267c481210f01909fd66214977762e01335050669d892949d3c12aa96d17c","last_reissued_at":"2026-06-02T01:04:20.555023Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:04:20.555023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Is 0.1% Enough? Analyzing the Combined Effects of Dimensionality Reduction and Quantization on Text Embedding Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hayato Tsukagoshi, Riku Kisako, Ryohei Sasano","submitted_at":"2026-05-31T07:37:34Z","abstract_excerpt":"Recent high-performing text embedding models often output high-dimensional real-valued vectors, resulting in substantial storage and computational costs. To address this issue, compression methods based on dimensionality reduction or quantization have been proposed; however, the effects of combining dimensionality reduction and quantization have not been sufficiently investigated. In this paper, we systematically examine the effectiveness of compressing text embeddings by combining dimensionality reduction and quantization, using four MTEB task families and four pretrained embedding models. Th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01074","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/2606.01074/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":"2606.01074","created_at":"2026-06-02T01:04:20.555086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01074v1","created_at":"2026-06-02T01:04:20.555086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01074","created_at":"2026-06-02T01:04:20.555086+00:00"},{"alias_kind":"pith_short_12","alias_value":"YZZGPREBEEHQ","created_at":"2026-06-02T01:04:20.555086+00:00"},{"alias_kind":"pith_short_16","alias_value":"YZZGPREBEEHQDEE7","created_at":"2026-06-02T01:04:20.555086+00:00"},{"alias_kind":"pith_short_8","alias_value":"YZZGPREB","created_at":"2026-06-02T01:04:20.555086+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/YZZGPREBEEHQDEE72ZRBJF3XML","json":"https://pith.science/pith/YZZGPREBEEHQDEE72ZRBJF3XML.json","graph_json":"https://pith.science/api/pith-number/YZZGPREBEEHQDEE72ZRBJF3XML/graph.json","events_json":"https://pith.science/api/pith-number/YZZGPREBEEHQDEE72ZRBJF3XML/events.json","paper":"https://pith.science/paper/YZZGPREB"},"agent_actions":{"view_html":"https://pith.science/pith/YZZGPREBEEHQDEE72ZRBJF3XML","download_json":"https://pith.science/pith/YZZGPREBEEHQDEE72ZRBJF3XML.json","view_paper":"https://pith.science/paper/YZZGPREB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01074&json=true","fetch_graph":"https://pith.science/api/pith-number/YZZGPREBEEHQDEE72ZRBJF3XML/graph.json","fetch_events":"https://pith.science/api/pith-number/YZZGPREBEEHQDEE72ZRBJF3XML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YZZGPREBEEHQDEE72ZRBJF3XML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YZZGPREBEEHQDEE72ZRBJF3XML/action/storage_attestation","attest_author":"https://pith.science/pith/YZZGPREBEEHQDEE72ZRBJF3XML/action/author_attestation","sign_citation":"https://pith.science/pith/YZZGPREBEEHQDEE72ZRBJF3XML/action/citation_signature","submit_replication":"https://pith.science/pith/YZZGPREBEEHQDEE72ZRBJF3XML/action/replication_record"}},"created_at":"2026-06-02T01:04:20.555086+00:00","updated_at":"2026-06-02T01:04:20.555086+00:00"}