{"as_of":"2026-08-21T12:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a596354c9c059beb2b3c3dcf887d93a578e61f6e5d0cca56be0294d97d2da6bb","coverage":[{"denominator":10,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":10,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:44:09.814119Z","state":"measured"},{"denominator":10,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":10,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.17037/citation-record","integrity":"/paper/2505.17037/integrity","json":"/paper/2505.17037/citation-record.json","paper":"/paper/2505.17037"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2202.01279","last_updated":"2022-03-29T16:37:47Z","snapshot_observed_at":"2026-08-16T17:24:01.303787Z","submitted_at":"2022-02-02T20:48:54Z","title":"PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.01279","snapshot_observed_at":"2026-08-15T22:44:09.776779Z","title":"Specificity in En- glish for Academic Purposes (EAP): A Corpus Analysis of Lexical Bundles in Academic Writ- ing","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.17037","last_updated":"2025-05-10T08:40:04Z","snapshot_observed_at":"2026-08-20T22:03:09.281557Z","submitted_at":"2025-05-10T08:40:04Z","title":"Prompt Engineering: How Prompt Vocabulary affects Domain Knowledge","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T22:44:09.776779Z"},"links":{"cited_paper":"/paper/2202.01279","citing_paper":"/paper/2505.17037"},"observation_digest":"sha256:88014dbe771ec09b5dad3d0a15081a385d54abe38f9b4685d46fb0987ddd9146","observation_id":"d206144f-9587-49f1-8776-ab207a773b56","resolution":{"observed_at":"2026-08-15T22:44:09.776779Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-08-13T17:41:53.092611Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-15T22:44:09.793745Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.17037","last_updated":"2025-05-10T08:40:04Z","snapshot_observed_at":"2026-08-20T22:03:09.281557Z","submitted_at":"2025-05-10T08:40:04Z","title":"Prompt Engineering: How Prompt Vocabulary affects Domain Knowledge","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T22:44:09.793745Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2505.17037"},"observation_digest":"sha256:b91be74879a4faa8e83148ace76a451069403d1b7bf2d119ea7b269010e1764f","observation_id":"6d4f65a8-d89f-43ea-b42a-e7d465834ce5","resolution":{"observed_at":"2026-08-15T22:44:09.793745Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.02155","last_updated":"2022-03-04T07:04:42Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-03-04T07:04:42Z","title":"Training language models to follow instructions with human feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.02155","snapshot_observed_at":"2026-08-15T22:44:09.802661Z","title":"Direct Prefer- ence Optimization: Your Language Model is Secretly a Reward Model","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.17037","last_updated":"2025-05-10T08:40:04Z","snapshot_observed_at":"2026-08-20T22:03:09.281557Z","submitted_at":"2025-05-10T08:40:04Z","title":"Prompt Engineering: How Prompt Vocabulary affects Domain Knowledge","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T22:44:09.802661Z"},"links":{"cited_paper":"/paper/2203.02155","citing_paper":"/paper/2505.17037"},"observation_digest":"sha256:85e06b5b72a9a0a0b971cf91406c5c71cc28536e5a4f60225f6bd1a61c549693","observation_id":"7d584076-00de-4089-a497-41d4b529e87f","resolution":{"observed_at":"2026-08-15T22:44:09.802661Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.11064","last_updated":"2023-09-20T05:04:16Z","snapshot_observed_at":"2026-08-21T10:23:20.098550Z","submitted_at":"2023-09-20T05:04:16Z","title":"Exploring the Relationship between LLM Hallucinations and Prompt Linguistic Nuances: Readability, Formality, and Concreteness","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.11064","snapshot_observed_at":"2026-08-15T22:44:09.806638Z","title":"An Information- theoretic Approach to Prompt Engineering Without Ground Truth Labels","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.17037","last_updated":"2025-05-10T08:40:04Z","snapshot_observed_at":"2026-08-20T22:03:09.281557Z","submitted_at":"2025-05-10T08:40:04Z","title":"Prompt Engineering: How Prompt Vocabulary affects Domain Knowledge","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T22:44:09.806638Z"},"links":{"cited_paper":"/paper/2309.11064","citing_paper":"/paper/2505.17037"},"observation_digest":"sha256:0ae4c09b0ca1400de00b4203e4067677fbbbab883abdb73a21cfcb7e1d585dac","observation_id":"32c0d388-045f-4810-95d8-d03290554d44","resolution":{"observed_at":"2026-08-15T22:44:09.806638Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.07705","last_updated":"2022-10-24T07:00:15Z","snapshot_observed_at":"2026-08-19T23:18:55.569234Z","submitted_at":"2022-04-16T03:12:30Z","title":"Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.07705","snapshot_observed_at":"2026-08-15T22:44:09.810650Z","title":"Prompt Learning with Structured Semantic Knowl- edge Makes Pre-Trained Language Mod- els Better","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.17037","last_updated":"2025-05-10T08:40:04Z","snapshot_observed_at":"2026-08-20T22:03:09.281557Z","submitted_at":"2025-05-10T08:40:04Z","title":"Prompt Engineering: How Prompt Vocabulary affects Domain Knowledge","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T22:44:09.810650Z"},"links":{"cited_paper":"/paper/2204.07705","citing_paper":"/paper/2505.17037"},"observation_digest":"sha256:6bba58020470d00ec22284a8ddff15da50bc8c8ed19ac46e0d10c7c3163c0a50","observation_id":"b397d09c-7e98-4b2c-a52b-45cfc6cc07ad","resolution":{"observed_at":"2026-08-15T22:44:09.810650Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:44:09.940784Z","title":"org / 2023","venue":null,"work_id":"d1715e66-61db-40f6-a86a-2f709f3f8826","year":2023},"citing_paper":{"arxiv_id":"2505.17037","last_updated":"2025-05-10T08:40:04Z","snapshot_observed_at":"2026-08-20T22:03:09.281557Z","submitted_at":"2025-05-10T08:40:04Z","title":"Prompt Engineering: How Prompt Vocabulary affects Domain Knowledge","version":1},"reference_index":494,"source":"pdf_text","source_observed_at":"2026-08-15T22:44:09.789961Z"},"links":{"citing_paper":"/paper/2505.17037"},"observation_digest":"sha256:c479c9f92e81eb35e705f38b7cce927942de966e2f50c257b8c01154e62eac75","observation_id":"3472f322-883e-43bf-833d-84355bab43cb","resolution":{"observed_at":"2026-08-15T22:44:09.944437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-15T22:44:09.786227Z","title":"Measuring Mas- sive Multitask Language Understanding","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17037","last_updated":"2025-05-10T08:40:04Z","snapshot_observed_at":"2026-08-20T22:03:09.281557Z","submitted_at":"2025-05-10T08:40:04Z","title":"Prompt Engineering: How Prompt Vocabulary affects Domain Knowledge","version":1},"reference_index":1128,"source":"pdf_text","source_observed_at":"2026-08-15T22:44:09.786227Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2505.17037"},"observation_digest":"sha256:1ce20e00a000061597103834eeff8eb2a2c93272b9ab1afdf0b478bf0e35e836","observation_id":"53bc41d5-1982-40a6-a306-90b6842b9bd1","resolution":{"observed_at":"2026-08-15T22:44:09.786227Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.14735","last_updated":"2025-05-11T09:23:41Z","snapshot_observed_at":"2026-08-18T20:37:49.047473Z","submitted_at":"2023-10-23T09:15:18Z","title":"Unleashing the potential of prompt engineering for large language models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.14735","snapshot_observed_at":"2026-08-15T22:44:09.782119Z","title":"A tutorial on kernel den- sity estimation and recent advances","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17037","last_updated":"2025-05-10T08:40:04Z","snapshot_observed_at":"2026-08-20T22:03:09.281557Z","submitted_at":"2025-05-10T08:40:04Z","title":"Prompt Engineering: How Prompt Vocabulary affects Domain Knowledge","version":1},"reference_index":2005,"source":"pdf_text","source_observed_at":"2026-08-15T22:44:09.782119Z"},"links":{"cited_paper":"/paper/2310.14735","citing_paper":"/paper/2505.17037"},"observation_digest":"sha256:01bd84cf4eb3ead8f1ec0076f9d2fce04a7d62a64e547bba687ba4c6d8c44f2c","observation_id":"521c8ab9-9271-41eb-a695-56b881badfd6","resolution":{"observed_at":"2026-08-15T22:44:09.782119Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.02038","last_updated":"2024-01-06T03:32:08Z","snapshot_observed_at":"2026-08-16T14:29:57.858582Z","submitted_at":"2024-01-04T02:43:57Z","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.02038","snapshot_observed_at":"2026-08-15T22:44:09.798238Z","title":"Pre-Train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.17037","last_updated":"2025-05-10T08:40:04Z","snapshot_observed_at":"2026-08-20T22:03:09.281557Z","submitted_at":"2025-05-10T08:40:04Z","title":"Prompt Engineering: How Prompt Vocabulary affects Domain Knowledge","version":1},"reference_index":2205,"source":"pdf_text","source_observed_at":"2026-08-15T22:44:09.798238Z"},"links":{"cited_paper":"/paper/2401.02038","citing_paper":"/paper/2505.17037"},"observation_digest":"sha256:7708e9f58ad8558019614691664baea82b3efd00475320d26d8fa728ec44e192","observation_id":"f48a5ec3-7ec3-4a16-b17c-2d560c7c0f71","resolution":{"observed_at":"2026-08-15T22:44:09.798238Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:44:09.928742Z","title":null,"venue":null,"work_id":"1812bd13-4cdc-49f7-9649-8cfe2b28994e","year":null},"citing_paper":{"arxiv_id":"2505.17037","last_updated":"2025-05-10T08:40:04Z","snapshot_observed_at":"2026-08-20T22:03:09.281557Z","submitted_at":"2025-05-10T08:40:04Z","title":"Prompt Engineering: How Prompt Vocabulary affects Domain Knowledge","version":1},"reference_index":3281,"source":"pdf_text","source_observed_at":"2026-08-15T22:44:09.814119Z"},"links":{"citing_paper":"/paper/2505.17037"},"observation_digest":"sha256:31b5fb9ed64c5afc3a52495b0898dc2e0556c93634ba30e8381ac6e57acb82c2","observation_id":"c04edd6e-698c-4ecf-81ec-c663594029ba","resolution":{"observed_at":"2026-08-15T22:44:09.933379Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.17037","last_updated":"2025-05-10T08:40:04Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-20T22:03:09.281557Z","submitted_at":"2025-05-10T08:40:04Z","title":"Prompt Engineering: How Prompt Vocabulary affects Domain Knowledge"},"reference_resolution":{"displayed":10,"state_counts":{"malformed_identifier":3,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":0,"verified_fuzzy":1},"total_outbound_references":10},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 10 of 10 outbound references and 0 inbound Pith citation observations for arXiv:2505.17037."}