{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ROIPI4F4FO3UPHAK7UFLRM7ZPW","short_pith_number":"pith:ROIPI4F4","schema_version":"1.0","canonical_sha256":"8b90f470bc2bb7479c0afd0ab8b3f97d8820d1c7b497c2f1f52cc3d803f0030f","source":{"kind":"arxiv","id":"2501.10534","version":1},"attestation_state":"computed","paper":{"title":"4bit-Quantization in Vector-Embedding for RAG","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Taehee Jeong","submitted_at":"2025-01-17T20:15:11Z","abstract_excerpt":"Retrieval-augmented generation (RAG) is a promising technique that has shown great potential in addressing some of the limitations of large language models (LLMs). LLMs have two major limitations: they can contain outdated information due to their training data, and they can generate factually inaccurate responses, a phenomenon known as hallucinations. RAG aims to mitigate these issues by leveraging a database of relevant documents, which are stored as embedding vectors in a high-dimensional space. However, one of the challenges of using high-dimensional embeddings is that they require a signi"},"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":"2501.10534","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-17T20:15:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c8f70aaceae3400aa85722e9fcf30c179221edce3ddc801de87659761a429225","abstract_canon_sha256":"32621fd63d33d864284da654142b3bdee4468a4434ee8b52e2ce60e12efd19b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:29.262805Z","signature_b64":"OwZHo0I8SKg0xcOzw0EIBdBv/WsNqKS3ftWQuShAmtXVsLO1mzub0I0Q8Pwqto+nz6O1Gfqdf/zsGMUkHt8mAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b90f470bc2bb7479c0afd0ab8b3f97d8820d1c7b497c2f1f52cc3d803f0030f","last_reissued_at":"2026-07-05T10:02:29.262303Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:29.262303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"4bit-Quantization in Vector-Embedding for RAG","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Taehee Jeong","submitted_at":"2025-01-17T20:15:11Z","abstract_excerpt":"Retrieval-augmented generation (RAG) is a promising technique that has shown great potential in addressing some of the limitations of large language models (LLMs). LLMs have two major limitations: they can contain outdated information due to their training data, and they can generate factually inaccurate responses, a phenomenon known as hallucinations. RAG aims to mitigate these issues by leveraging a database of relevant documents, which are stored as embedding vectors in a high-dimensional space. However, one of the challenges of using high-dimensional embeddings is that they require a signi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10534","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/2501.10534/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":"2501.10534","created_at":"2026-07-05T10:02:29.262377+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10534v1","created_at":"2026-07-05T10:02:29.262377+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10534","created_at":"2026-07-05T10:02:29.262377+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROIPI4F4FO3U","created_at":"2026-07-05T10:02:29.262377+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROIPI4F4FO3UPHAK","created_at":"2026-07-05T10:02:29.262377+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROIPI4F4","created_at":"2026-07-05T10:02:29.262377+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05543","citing_title":"omni-macos: On-Device Omni-Modal Search on Apple Silicon","ref_index":2011,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROIPI4F4FO3UPHAK7UFLRM7ZPW","json":"https://pith.science/pith/ROIPI4F4FO3UPHAK7UFLRM7ZPW.json","graph_json":"https://pith.science/api/pith-number/ROIPI4F4FO3UPHAK7UFLRM7ZPW/graph.json","events_json":"https://pith.science/api/pith-number/ROIPI4F4FO3UPHAK7UFLRM7ZPW/events.json","paper":"https://pith.science/paper/ROIPI4F4"},"agent_actions":{"view_html":"https://pith.science/pith/ROIPI4F4FO3UPHAK7UFLRM7ZPW","download_json":"https://pith.science/pith/ROIPI4F4FO3UPHAK7UFLRM7ZPW.json","view_paper":"https://pith.science/paper/ROIPI4F4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10534&json=true","fetch_graph":"https://pith.science/api/pith-number/ROIPI4F4FO3UPHAK7UFLRM7ZPW/graph.json","fetch_events":"https://pith.science/api/pith-number/ROIPI4F4FO3UPHAK7UFLRM7ZPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROIPI4F4FO3UPHAK7UFLRM7ZPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROIPI4F4FO3UPHAK7UFLRM7ZPW/action/storage_attestation","attest_author":"https://pith.science/pith/ROIPI4F4FO3UPHAK7UFLRM7ZPW/action/author_attestation","sign_citation":"https://pith.science/pith/ROIPI4F4FO3UPHAK7UFLRM7ZPW/action/citation_signature","submit_replication":"https://pith.science/pith/ROIPI4F4FO3UPHAK7UFLRM7ZPW/action/replication_record"}},"created_at":"2026-07-05T10:02:29.262377+00:00","updated_at":"2026-07-05T10:02:29.262377+00:00"}