{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EWBGX2JGQRFASMMTBLKFO2GHKA","short_pith_number":"pith:EWBGX2JG","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"},"canonical_sha256":"25826be926844a0931930ad45768c7501a6753862f93d98f213f3c5fce39090c","source":{"kind":"arxiv","id":"2312.05934","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.05934","created_at":"2026-07-05T07:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2312.05934v3","created_at":"2026-07-05T07:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05934","created_at":"2026-07-05T07:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"EWBGX2JGQRFA","created_at":"2026-07-05T07:39:12Z"},{"alias_kind":"pith_short_16","alias_value":"EWBGX2JGQRFASMMT","created_at":"2026-07-05T07:39:12Z"},{"alias_kind":"pith_short_8","alias_value":"EWBGX2JG","created_at":"2026-07-05T07:39:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EWBGX2JGQRFASMMTBLKFO2GHKA","target":"record","payload":{"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"},"canonical_sha256":"25826be926844a0931930ad45768c7501a6753862f93d98f213f3c5fce39090c","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"},"source_kind":"arxiv","source_id":"2312.05934","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ec3dARZ/m5SKWt2TT7HgEJHhdnj9+HBYVhq69BHLjbuLOz9d21PoIzlnisNjsqJ5/UySkCfwFUnpGceEisTvAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:30:13.098410Z"},"content_sha256":"56ace05d6dda883277f7decd561e463a9e762cd8f970e6d0e65fcfcab81ac966","schema_version":"1.0","event_id":"sha256:56ace05d6dda883277f7decd561e463a9e762cd8f970e6d0e65fcfcab81ac966"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EWBGX2JGQRFASMMTBLKFO2GHKA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:39:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vCYNWTV9pmDdwPMW3xelFpGBMuhreO/SusTMDvJ4etqRLrsc2TaI56TQPhqUQYjf4+M2E9IW6uA0Ok8sN97IAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:30:13.098784Z"},"content_sha256":"3985a65bc20e64555888ef1e342339d34b1000712a1fb0eaf6677cea67e6ca35","schema_version":"1.0","event_id":"sha256:3985a65bc20e64555888ef1e342339d34b1000712a1fb0eaf6677cea67e6ca35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EWBGX2JGQRFASMMTBLKFO2GHKA/bundle.json","state_url":"https://pith.science/pith/EWBGX2JGQRFASMMTBLKFO2GHKA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EWBGX2JGQRFASMMTBLKFO2GHKA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T08:30:13Z","links":{"resolver":"https://pith.science/pith/EWBGX2JGQRFASMMTBLKFO2GHKA","bundle":"https://pith.science/pith/EWBGX2JGQRFASMMTBLKFO2GHKA/bundle.json","state":"https://pith.science/pith/EWBGX2JGQRFASMMTBLKFO2GHKA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EWBGX2JGQRFASMMTBLKFO2GHKA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EWBGX2JGQRFASMMTBLKFO2GHKA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6b05a4c6d58cf22514da2c4cb31f7c082fd87c992bd4cb137b5ac8003d19e44d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-10T16:52:00Z","title_canon_sha256":"318d61895441ac5ec4cce5bcdaf86049e8dee5382bf398ddada5fd6c07e5c006"},"schema_version":"1.0","source":{"id":"2312.05934","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.05934","created_at":"2026-07-05T07:39:12Z"},{"alias_kind":"arxiv_version","alias_value":"2312.05934v3","created_at":"2026-07-05T07:39:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.05934","created_at":"2026-07-05T07:39:12Z"},{"alias_kind":"pith_short_12","alias_value":"EWBGX2JGQRFA","created_at":"2026-07-05T07:39:12Z"},{"alias_kind":"pith_short_16","alias_value":"EWBGX2JGQRFASMMT","created_at":"2026-07-05T07:39:12Z"},{"alias_kind":"pith_short_8","alias_value":"EWBGX2JG","created_at":"2026-07-05T07:39:12Z"}],"graph_snapshots":[{"event_id":"sha256:3985a65bc20e64555888ef1e342339d34b1000712a1fb0eaf6677cea67e6ca35","target":"graph","created_at":"2026-07-05T07:39:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.05934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Menachem Brief, Moshik Mishaeli, Oded Ovadia, Oren Elisha","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-10T16:52:00Z","title":"Fine-Tuning or Retrieval? Comparing Knowledge Injection in LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.05934","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:56ace05d6dda883277f7decd561e463a9e762cd8f970e6d0e65fcfcab81ac966","target":"record","created_at":"2026-07-05T07:39:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6b05a4c6d58cf22514da2c4cb31f7c082fd87c992bd4cb137b5ac8003d19e44d","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-10T16:52:00Z","title_canon_sha256":"318d61895441ac5ec4cce5bcdaf86049e8dee5382bf398ddada5fd6c07e5c006"},"schema_version":"1.0","source":{"id":"2312.05934","kind":"arxiv","version":3}},"canonical_sha256":"25826be926844a0931930ad45768c7501a6753862f93d98f213f3c5fce39090c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25826be926844a0931930ad45768c7501a6753862f93d98f213f3c5fce39090c","first_computed_at":"2026-07-05T07:39:12.070797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:39:12.070797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pqmKPBxWTKQbaODzW0KL+eIkAOVpYCbi5NDh7/eumLacOFij3+zZTrls0G+yo+B7TWNfbTk/rpQKMsGggimLCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:39:12.071269Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.05934","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56ace05d6dda883277f7decd561e463a9e762cd8f970e6d0e65fcfcab81ac966","sha256:3985a65bc20e64555888ef1e342339d34b1000712a1fb0eaf6677cea67e6ca35"],"state_sha256":"f5cbc537840ccd5d48a2cc67328236999e1598bd71577a4943faea4aba598556"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TTHJMubU+r0P7ePfcv3Ili5vMQWuQRyE7GFW0K2QCN8ngdmX/Iv1NMTADDfmPsTtFvR3ovIgWdmV0v86nDeLCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:30:13.100722Z","bundle_sha256":"3a453f88cd31b8ce0c402cf044b18b1eb61f20ef63f5f4ebf74c7f02baeab5b4"}}