{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:H252C2CDX4T7FVGC22JXYFC6RL","short_pith_number":"pith:H252C2CD","canonical_record":{"source":{"id":"2305.17116","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T17:33:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad8f8496fd6d1eee70afd820b0be2480cdde36568812a5ac7fae5cb364e5697b","abstract_canon_sha256":"11679706265747cbcdb494bfaf68af88494b5c372528db12873fc3d273a78b0b"},"schema_version":"1.0"},"canonical_sha256":"3ebba16843bf27f2d4c2d6937c145e8af72cd1a3eea2eeba14daec02a7cb8434","source":{"kind":"arxiv","id":"2305.17116","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17116","created_at":"2026-07-05T08:59:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17116v2","created_at":"2026-07-05T08:59:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17116","created_at":"2026-07-05T08:59:02Z"},{"alias_kind":"pith_short_12","alias_value":"H252C2CDX4T7","created_at":"2026-07-05T08:59:02Z"},{"alias_kind":"pith_short_16","alias_value":"H252C2CDX4T7FVGC","created_at":"2026-07-05T08:59:02Z"},{"alias_kind":"pith_short_8","alias_value":"H252C2CD","created_at":"2026-07-05T08:59:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:H252C2CDX4T7FVGC22JXYFC6RL","target":"record","payload":{"canonical_record":{"source":{"id":"2305.17116","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T17:33:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ad8f8496fd6d1eee70afd820b0be2480cdde36568812a5ac7fae5cb364e5697b","abstract_canon_sha256":"11679706265747cbcdb494bfaf68af88494b5c372528db12873fc3d273a78b0b"},"schema_version":"1.0"},"canonical_sha256":"3ebba16843bf27f2d4c2d6937c145e8af72cd1a3eea2eeba14daec02a7cb8434","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:02.759241Z","signature_b64":"4cBovBF3TyOI68UQYI5P9Dg76nefxhfSYIiBjJ0nzczFRorR50MDP291xdAMaTpXqn/AO07z1hnDDKgkQUCYBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ebba16843bf27f2d4c2d6937c145e8af72cd1a3eea2eeba14daec02a7cb8434","last_reissued_at":"2026-07-05T08:59:02.758668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:02.758668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.17116","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:59:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J8F8QptTOmoSFkpBnveXFVUnZUp5ni3gO0CHoNz2fhq0PLUfUzxisuDRLnFPl/vXVYk6fwwDkw/NfU5klXqCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T23:21:07.069822Z"},"content_sha256":"f13fb45a16f8b9567103395862cfff8ffde1d4b498ad548de631ebf06d13a804","schema_version":"1.0","event_id":"sha256:f13fb45a16f8b9567103395862cfff8ffde1d4b498ad548de631ebf06d13a804"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:H252C2CDX4T7FVGC22JXYFC6RL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving accuracy of GPT-3/4 results on biomedical data using a retrieval-augmented language model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ana Caroline Costa S\\'a, Brandon W Higgs, Christina Y Yu, David Soong, Han Si, Hisham Hamadeh, Jan-Samuel Wagner, Kubra Karagoz, Meijian Guan, Sriram Sridhar","submitted_at":"2023-05-26T17:33:05Z","abstract_excerpt":"Large language models (LLMs) have made significant advancements in natural language processing (NLP). Broad corpora capture diverse patterns but can introduce irrelevance, while focused corpora enhance reliability by reducing misleading information. Training LLMs on focused corpora poses computational challenges. An alternative approach is to use a retrieval-augmentation (RetA) method tested in a specific domain.\n  To evaluate LLM performance, OpenAI's GPT-3, GPT-4, Bing's Prometheus, and a custom RetA model were compared using 19 questions on diffuse large B-cell lymphoma (DLBCL) disease. Eig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17116","kind":"arxiv","version":2},"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/2305.17116/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":"2026-07-05T08:59:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9EGAA2vpIb5vAWN0MtZhOUvGzWjfPzn5SyYwT16TuWVdiL5YsJ5ZevhzKbhYLPhD7o2fL/3dB3V6mDQnHWsqAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T23:21:07.070324Z"},"content_sha256":"18890f6aaa0117072757d5d983b0b061dd504d0ea619e0ae81c22a3b325ea961","schema_version":"1.0","event_id":"sha256:18890f6aaa0117072757d5d983b0b061dd504d0ea619e0ae81c22a3b325ea961"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H252C2CDX4T7FVGC22JXYFC6RL/bundle.json","state_url":"https://pith.science/pith/H252C2CDX4T7FVGC22JXYFC6RL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H252C2CDX4T7FVGC22JXYFC6RL/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":"2026-08-23T23:21:07Z","links":{"resolver":"https://pith.science/pith/H252C2CDX4T7FVGC22JXYFC6RL","bundle":"https://pith.science/pith/H252C2CDX4T7FVGC22JXYFC6RL/bundle.json","state":"https://pith.science/pith/H252C2CDX4T7FVGC22JXYFC6RL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H252C2CDX4T7FVGC22JXYFC6RL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:H252C2CDX4T7FVGC22JXYFC6RL","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":"11679706265747cbcdb494bfaf68af88494b5c372528db12873fc3d273a78b0b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T17:33:05Z","title_canon_sha256":"ad8f8496fd6d1eee70afd820b0be2480cdde36568812a5ac7fae5cb364e5697b"},"schema_version":"1.0","source":{"id":"2305.17116","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.17116","created_at":"2026-07-05T08:59:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.17116v2","created_at":"2026-07-05T08:59:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17116","created_at":"2026-07-05T08:59:02Z"},{"alias_kind":"pith_short_12","alias_value":"H252C2CDX4T7","created_at":"2026-07-05T08:59:02Z"},{"alias_kind":"pith_short_16","alias_value":"H252C2CDX4T7FVGC","created_at":"2026-07-05T08:59:02Z"},{"alias_kind":"pith_short_8","alias_value":"H252C2CD","created_at":"2026-07-05T08:59:02Z"}],"graph_snapshots":[{"event_id":"sha256:18890f6aaa0117072757d5d983b0b061dd504d0ea619e0ae81c22a3b325ea961","target":"graph","created_at":"2026-07-05T08:59:02Z","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/2305.17116/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have made significant advancements in natural language processing (NLP). Broad corpora capture diverse patterns but can introduce irrelevance, while focused corpora enhance reliability by reducing misleading information. Training LLMs on focused corpora poses computational challenges. An alternative approach is to use a retrieval-augmentation (RetA) method tested in a specific domain.\n  To evaluate LLM performance, OpenAI's GPT-3, GPT-4, Bing's Prometheus, and a custom RetA model were compared using 19 questions on diffuse large B-cell lymphoma (DLBCL) disease. Eig","authors_text":"Ana Caroline Costa S\\'a, Brandon W Higgs, Christina Y Yu, David Soong, Han Si, Hisham Hamadeh, Jan-Samuel Wagner, Kubra Karagoz, Meijian Guan, Sriram Sridhar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T17:33:05Z","title":"Improving accuracy of GPT-3/4 results on biomedical data using a retrieval-augmented language model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17116","kind":"arxiv","version":2},"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:f13fb45a16f8b9567103395862cfff8ffde1d4b498ad548de631ebf06d13a804","target":"record","created_at":"2026-07-05T08:59:02Z","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":"11679706265747cbcdb494bfaf68af88494b5c372528db12873fc3d273a78b0b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-26T17:33:05Z","title_canon_sha256":"ad8f8496fd6d1eee70afd820b0be2480cdde36568812a5ac7fae5cb364e5697b"},"schema_version":"1.0","source":{"id":"2305.17116","kind":"arxiv","version":2}},"canonical_sha256":"3ebba16843bf27f2d4c2d6937c145e8af72cd1a3eea2eeba14daec02a7cb8434","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ebba16843bf27f2d4c2d6937c145e8af72cd1a3eea2eeba14daec02a7cb8434","first_computed_at":"2026-07-05T08:59:02.758668Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:59:02.758668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4cBovBF3TyOI68UQYI5P9Dg76nefxhfSYIiBjJ0nzczFRorR50MDP291xdAMaTpXqn/AO07z1hnDDKgkQUCYBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:59:02.759241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.17116","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f13fb45a16f8b9567103395862cfff8ffde1d4b498ad548de631ebf06d13a804","sha256:18890f6aaa0117072757d5d983b0b061dd504d0ea619e0ae81c22a3b325ea961"],"state_sha256":"0bf4df51c56a7b040519902a8508c9d35053da384ee271b08beb4251fe133402"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3IxWApBxyV4x3w/z80VyhyoB/gHHV/a12js5mcd71jAWbBGugNh/n2Y3SUNHk3QErcOmjT4vPOIt1TJPaStADA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T23:21:07.074928Z","bundle_sha256":"61a2381309569bd94713e67442233b01e0a3cf564f85e773e7f263c75c48cffd"}}