{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EWBGX2JGQRFASMMTBLKFO2GHKA","short_pith_number":"pith:EWBGX2JG","schema_version":"1.0","canonical_sha256":"25826be926844a0931930ad45768c7501a6753862f93d98f213f3c5fce39090c","source":{"kind":"arxiv","id":"2312.05934","version":3},"attestation_state":"computed","paper":{"title":"Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Menachem Brief, Moshik Mishaeli, Oded Ovadia, Oren Elisha","submitted_at":"2023-12-10T16:52:00Z","abstract_excerpt":"Large language models (LLMs) encapsulate a vast amount of factual information within their pre-trained weights, as evidenced by their ability to answer diverse questions across different domains. However, this knowledge is inherently limited, relying heavily on the characteristics of the training data. Consequently, using external datasets to incorporate new information or refine the capabilities of LLMs on previously seen information poses a significant challenge. In this study, we compare two common approaches: unsupervised fine-tuning and retrieval-augmented generation (RAG). We evaluate bo"},"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":"2312.05934","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-10T16:52:00Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"318d61895441ac5ec4cce5bcdaf86049e8dee5382bf398ddada5fd6c07e5c006","abstract_canon_sha256":"6b05a4c6d58cf22514da2c4cb31f7c082fd87c992bd4cb137b5ac8003d19e44d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:12.071269Z","signature_b64":"pqmKPBxWTKQbaODzW0KL+eIkAOVpYCbi5NDh7/eumLacOFij3+zZTrls0G+yo+B7TWNfbTk/rpQKMsGggimLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25826be926844a0931930ad45768c7501a6753862f93d98f213f3c5fce39090c","last_reissued_at":"2026-07-05T07:39:12.070797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:12.070797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Menachem Brief, Moshik Mishaeli, Oded Ovadia, Oren Elisha","submitted_at":"2023-12-10T16:52:00Z","abstract_excerpt":"Large language models (LLMs) encapsulate a vast amount of factual information within their pre-trained weights, as evidenced by their ability to answer diverse questions across different domains. However, this knowledge is inherently limited, relying heavily on the characteristics of the training data. Consequently, using external datasets to incorporate new information or refine the capabilities of LLMs on previously seen information poses a significant challenge. In this study, we compare two common approaches: unsupervised fine-tuning and retrieval-augmented generation (RAG). We evaluate bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05934","kind":"arxiv","version":3},"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/2312.05934/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":"2312.05934","created_at":"2026-07-05T07:39:12.070848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.05934v3","created_at":"2026-07-05T07:39:12.070848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05934","created_at":"2026-07-05T07:39:12.070848+00:00"},{"alias_kind":"pith_short_12","alias_value":"EWBGX2JGQRFA","created_at":"2026-07-05T07:39:12.070848+00:00"},{"alias_kind":"pith_short_16","alias_value":"EWBGX2JGQRFASMMT","created_at":"2026-07-05T07:39:12.070848+00:00"},{"alias_kind":"pith_short_8","alias_value":"EWBGX2JG","created_at":"2026-07-05T07:39:12.070848+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2511.02626","citing_title":"Understanding New-Knowledge-Induced Factual Hallucinations in LLMs: Analysis and Interpretation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06179","citing_title":"ARIA: Adaptive Retrieval Intelligence Assistant -- A Multimodal RAG Framework for Domain-Specific Engineering Education","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":205,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11922","citing_title":"StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":245,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09533","citing_title":"Assessment of RAG and Fine-Tuning for Industrial Question-Answering-Applications","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EWBGX2JGQRFASMMTBLKFO2GHKA","json":"https://pith.science/pith/EWBGX2JGQRFASMMTBLKFO2GHKA.json","graph_json":"https://pith.science/api/pith-number/EWBGX2JGQRFASMMTBLKFO2GHKA/graph.json","events_json":"https://pith.science/api/pith-number/EWBGX2JGQRFASMMTBLKFO2GHKA/events.json","paper":"https://pith.science/paper/EWBGX2JG"},"agent_actions":{"view_html":"https://pith.science/pith/EWBGX2JGQRFASMMTBLKFO2GHKA","download_json":"https://pith.science/pith/EWBGX2JGQRFASMMTBLKFO2GHKA.json","view_paper":"https://pith.science/paper/EWBGX2JG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.05934&json=true","fetch_graph":"https://pith.science/api/pith-number/EWBGX2JGQRFASMMTBLKFO2GHKA/graph.json","fetch_events":"https://pith.science/api/pith-number/EWBGX2JGQRFASMMTBLKFO2GHKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EWBGX2JGQRFASMMTBLKFO2GHKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EWBGX2JGQRFASMMTBLKFO2GHKA/action/storage_attestation","attest_author":"https://pith.science/pith/EWBGX2JGQRFASMMTBLKFO2GHKA/action/author_attestation","sign_citation":"https://pith.science/pith/EWBGX2JGQRFASMMTBLKFO2GHKA/action/citation_signature","submit_replication":"https://pith.science/pith/EWBGX2JGQRFASMMTBLKFO2GHKA/action/replication_record"}},"created_at":"2026-07-05T07:39:12.070848+00:00","updated_at":"2026-07-05T07:39:12.070848+00:00"}