{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AITFLWIEMS5DOB4Q5AH7N7ATZA","short_pith_number":"pith:AITFLWIE","schema_version":"1.0","canonical_sha256":"022655d90464ba370790e80ff6fc13c80317f46d34d0663f173dc4784ae3c1bc","source":{"kind":"arxiv","id":"2506.21568","version":1},"attestation_state":"computed","paper":{"title":"Assessing RAG and HyDE on 1B vs. 4B-Parameter Gemma LLMs for Personal Assistants Integretion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrejs Sorstkins","submitted_at":"2025-06-12T15:05:39Z","abstract_excerpt":"Resource efficiency is a critical barrier to deploying large language models (LLMs) in edge and privacy-sensitive applications. This study evaluates the efficacy of two augmentation strategies--Retrieval-Augmented Generation (RAG) and Hypothetical Document Embeddings (HyDE)--on compact Gemma LLMs of 1 billion and 4 billion parameters, within the context of a privacy-first personal assistant. We implement short-term memory via MongoDB and long-term semantic storage via Qdrant, orchestrated through FastAPI and LangChain, and expose the system through a React.js frontend. Across both model scales"},"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":"2506.21568","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-12T15:05:39Z","cross_cats_sorted":[],"title_canon_sha256":"ad0c657334e53aa2c970e1e38a28d3fd779c4c548dac230d8f0f81f59c105be3","abstract_canon_sha256":"f196cfae4d91cb790220019dc92d3df476d88f8659ad28bcd0b91ecac4c23af9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:56.496412Z","signature_b64":"gEQkmZVw6U5TqgkIbom7oOdlESJywQqoIQxqX4FoX0W7YVEatDVJVAqKgunRyMBnrb/6IhX+L5SyhqN4bfV+AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"022655d90464ba370790e80ff6fc13c80317f46d34d0663f173dc4784ae3c1bc","last_reissued_at":"2026-07-05T11:27:56.495899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:56.495899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing RAG and HyDE on 1B vs. 4B-Parameter Gemma LLMs for Personal Assistants Integretion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrejs Sorstkins","submitted_at":"2025-06-12T15:05:39Z","abstract_excerpt":"Resource efficiency is a critical barrier to deploying large language models (LLMs) in edge and privacy-sensitive applications. This study evaluates the efficacy of two augmentation strategies--Retrieval-Augmented Generation (RAG) and Hypothetical Document Embeddings (HyDE)--on compact Gemma LLMs of 1 billion and 4 billion parameters, within the context of a privacy-first personal assistant. We implement short-term memory via MongoDB and long-term semantic storage via Qdrant, orchestrated through FastAPI and LangChain, and expose the system through a React.js frontend. Across both model scales"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21568","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/2506.21568/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":"2506.21568","created_at":"2026-07-05T11:27:56.495956+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21568v1","created_at":"2026-07-05T11:27:56.495956+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21568","created_at":"2026-07-05T11:27:56.495956+00:00"},{"alias_kind":"pith_short_12","alias_value":"AITFLWIEMS5D","created_at":"2026-07-05T11:27:56.495956+00:00"},{"alias_kind":"pith_short_16","alias_value":"AITFLWIEMS5DOB4Q","created_at":"2026-07-05T11:27:56.495956+00:00"},{"alias_kind":"pith_short_8","alias_value":"AITFLWIE","created_at":"2026-07-05T11:27:56.495956+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/AITFLWIEMS5DOB4Q5AH7N7ATZA","json":"https://pith.science/pith/AITFLWIEMS5DOB4Q5AH7N7ATZA.json","graph_json":"https://pith.science/api/pith-number/AITFLWIEMS5DOB4Q5AH7N7ATZA/graph.json","events_json":"https://pith.science/api/pith-number/AITFLWIEMS5DOB4Q5AH7N7ATZA/events.json","paper":"https://pith.science/paper/AITFLWIE"},"agent_actions":{"view_html":"https://pith.science/pith/AITFLWIEMS5DOB4Q5AH7N7ATZA","download_json":"https://pith.science/pith/AITFLWIEMS5DOB4Q5AH7N7ATZA.json","view_paper":"https://pith.science/paper/AITFLWIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21568&json=true","fetch_graph":"https://pith.science/api/pith-number/AITFLWIEMS5DOB4Q5AH7N7ATZA/graph.json","fetch_events":"https://pith.science/api/pith-number/AITFLWIEMS5DOB4Q5AH7N7ATZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AITFLWIEMS5DOB4Q5AH7N7ATZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AITFLWIEMS5DOB4Q5AH7N7ATZA/action/storage_attestation","attest_author":"https://pith.science/pith/AITFLWIEMS5DOB4Q5AH7N7ATZA/action/author_attestation","sign_citation":"https://pith.science/pith/AITFLWIEMS5DOB4Q5AH7N7ATZA/action/citation_signature","submit_replication":"https://pith.science/pith/AITFLWIEMS5DOB4Q5AH7N7ATZA/action/replication_record"}},"created_at":"2026-07-05T11:27:56.495956+00:00","updated_at":"2026-07-05T11:27:56.495956+00:00"}