{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AWXAAJWQZWRJAMZUDV4KDMKTXJ","short_pith_number":"pith:AWXAAJWQ","canonical_record":{"source":{"id":"2403.01432","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-03T08:07:55Z","cross_cats_sorted":[],"title_canon_sha256":"00cb1a662fb734a09c5c1640667bcdd83d56e05f7307884a7d7d670fddd679fb","abstract_canon_sha256":"f69fb09e1ff2faa889eceda4acb16a0cbaec1e1ec9694413fd0c8e311cef35f7"},"schema_version":"1.0"},"canonical_sha256":"05ae0026d0cda29033341d78a1b153ba74f321b94ee1476719b95a123a663ca1","source":{"kind":"arxiv","id":"2403.01432","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01432","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01432v5","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01432","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_12","alias_value":"AWXAAJWQZWRJ","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_16","alias_value":"AWXAAJWQZWRJAMZU","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_8","alias_value":"AWXAAJWQ","created_at":"2026-07-05T09:42:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AWXAAJWQZWRJAMZUDV4KDMKTXJ","target":"record","payload":{"canonical_record":{"source":{"id":"2403.01432","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-03T08:07:55Z","cross_cats_sorted":[],"title_canon_sha256":"00cb1a662fb734a09c5c1640667bcdd83d56e05f7307884a7d7d670fddd679fb","abstract_canon_sha256":"f69fb09e1ff2faa889eceda4acb16a0cbaec1e1ec9694413fd0c8e311cef35f7"},"schema_version":"1.0"},"canonical_sha256":"05ae0026d0cda29033341d78a1b153ba74f321b94ee1476719b95a123a663ca1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:23.320751Z","signature_b64":"MCw/hJnJIt2gufpYnMme1+UrBmY43TW/ca2Mao+a02ZOp8cESQKQNuzrv7PkuAVQ+UZociSoB0bV7nuzTFjOBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05ae0026d0cda29033341d78a1b153ba74f321b94ee1476719b95a123a663ca1","last_reissued_at":"2026-07-05T09:42:23.320256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:23.320256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.01432","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:42:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1z2W8ldGwj2Fg316lSQ0V+Iqm+0PEGBfEYa8F+ql+Kxl/9LmnkpAfoCepvU2kKSJ/v/ngETaXy51qMwKqmSUCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:39:32.711331Z"},"content_sha256":"439d1b1f85adcdf719153f0436dd4537b3aaff195dd5ca137d4ecd73b75d9ada","schema_version":"1.0","event_id":"sha256:439d1b1f85adcdf719153f0436dd4537b3aaff195dd5ca137d4ecd73b75d9ada"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AWXAAJWQZWRJAMZUDV4KDMKTXJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Evangelos Kanoulas, Faegheh Hasibi, Heydar Soudani","submitted_at":"2024-03-03T08:07:55Z","abstract_excerpt":"Language Models (LMs) memorize a vast amount of factual knowledge, exhibiting strong performance across diverse tasks and domains. However, it has been observed that the performance diminishes when dealing with less-popular or low-frequency concepts and entities, for example in domain specific applications. The two prominent approaches to enhance the performance of LMs on low-frequent topics are: Retrieval Augmented Generation (RAG) and fine-tuning (FT) over synthetic data. This paper explores and evaluates the impact of RAG and FT on customizing LMs in handling low-frequency entities on quest"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01432","kind":"arxiv","version":5},"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/2403.01432/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":"2026-07-05T09:42:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lZr9+4eWehRLHty3msyMaIP73rewLO0i4jMDzHfhYzmw+pQai/qskMSkAs9aAYCN0kFpc6AijcHQ2YYR2qKmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:39:32.711855Z"},"content_sha256":"f2628602e1f0afcedbe40389e3074015d943edd86c3dfd353d379863a303b5ad","schema_version":"1.0","event_id":"sha256:f2628602e1f0afcedbe40389e3074015d943edd86c3dfd353d379863a303b5ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AWXAAJWQZWRJAMZUDV4KDMKTXJ/bundle.json","state_url":"https://pith.science/pith/AWXAAJWQZWRJAMZUDV4KDMKTXJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AWXAAJWQZWRJAMZUDV4KDMKTXJ/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":"2026-08-08T19:39:32Z","links":{"resolver":"https://pith.science/pith/AWXAAJWQZWRJAMZUDV4KDMKTXJ","bundle":"https://pith.science/pith/AWXAAJWQZWRJAMZUDV4KDMKTXJ/bundle.json","state":"https://pith.science/pith/AWXAAJWQZWRJAMZUDV4KDMKTXJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AWXAAJWQZWRJAMZUDV4KDMKTXJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AWXAAJWQZWRJAMZUDV4KDMKTXJ","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":"f69fb09e1ff2faa889eceda4acb16a0cbaec1e1ec9694413fd0c8e311cef35f7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-03T08:07:55Z","title_canon_sha256":"00cb1a662fb734a09c5c1640667bcdd83d56e05f7307884a7d7d670fddd679fb"},"schema_version":"1.0","source":{"id":"2403.01432","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.01432","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"arxiv_version","alias_value":"2403.01432v5","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01432","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_12","alias_value":"AWXAAJWQZWRJ","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_16","alias_value":"AWXAAJWQZWRJAMZU","created_at":"2026-07-05T09:42:23Z"},{"alias_kind":"pith_short_8","alias_value":"AWXAAJWQ","created_at":"2026-07-05T09:42:23Z"}],"graph_snapshots":[{"event_id":"sha256:f2628602e1f0afcedbe40389e3074015d943edd86c3dfd353d379863a303b5ad","target":"graph","created_at":"2026-07-05T09:42:23Z","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/2403.01432/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language Models (LMs) memorize a vast amount of factual knowledge, exhibiting strong performance across diverse tasks and domains. However, it has been observed that the performance diminishes when dealing with less-popular or low-frequency concepts and entities, for example in domain specific applications. The two prominent approaches to enhance the performance of LMs on low-frequent topics are: Retrieval Augmented Generation (RAG) and fine-tuning (FT) over synthetic data. This paper explores and evaluates the impact of RAG and FT on customizing LMs in handling low-frequency entities on quest","authors_text":"Evangelos Kanoulas, Faegheh Hasibi, Heydar Soudani","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-03T08:07:55Z","title":"Fine Tuning vs. Retrieval Augmented Generation for Less Popular Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01432","kind":"arxiv","version":5},"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":"sha256:439d1b1f85adcdf719153f0436dd4537b3aaff195dd5ca137d4ecd73b75d9ada","target":"record","created_at":"2026-07-05T09:42:23Z","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":"f69fb09e1ff2faa889eceda4acb16a0cbaec1e1ec9694413fd0c8e311cef35f7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-03T08:07:55Z","title_canon_sha256":"00cb1a662fb734a09c5c1640667bcdd83d56e05f7307884a7d7d670fddd679fb"},"schema_version":"1.0","source":{"id":"2403.01432","kind":"arxiv","version":5}},"canonical_sha256":"05ae0026d0cda29033341d78a1b153ba74f321b94ee1476719b95a123a663ca1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"05ae0026d0cda29033341d78a1b153ba74f321b94ee1476719b95a123a663ca1","first_computed_at":"2026-07-05T09:42:23.320256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:23.320256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MCw/hJnJIt2gufpYnMme1+UrBmY43TW/ca2Mao+a02ZOp8cESQKQNuzrv7PkuAVQ+UZociSoB0bV7nuzTFjOBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:23.320751Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.01432","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:439d1b1f85adcdf719153f0436dd4537b3aaff195dd5ca137d4ecd73b75d9ada","sha256:f2628602e1f0afcedbe40389e3074015d943edd86c3dfd353d379863a303b5ad"],"state_sha256":"73d15bc8cecf521a5dd33927e146d13d0716ede06da22c557e805adc79a98e88"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+VFwebs4DWy4TY+teZhtHksqMPsnNTa/EFq4P3KP7QdNEfZpR23ymx0dc95es8fMybRO9C9myrQTa7w/xuUrAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:39:32.716595Z","bundle_sha256":"acd69d0edfb2dbecfddcc638ae7a2a07f1efda89de55059f103d926ff787b0b1"}}