{"as_of":"2026-08-11T20:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:38db2e1174a1201e89bfc6bad783ca44fc84377a4b15932d1f6825a99cb040d3","coverage":[{"denominator":84,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":84,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T17:14:06.763061Z","state":"measured"},{"denominator":84,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":84,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2501.12521/citation-record","integrity":"/paper/2501.12521/integrity","json":"/paper/2501.12521/citation-record.json","paper":"/paper/2501.12521"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:06.476401Z","title":"Available: https://figshare.com/s/930b08c981b41f28470c","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.476401Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:448dab90cca408739c01f63545c52bd720c5b4681a8e9322c5cf5c8a86171e1e","observation_id":"48e1025e-db17-4314-8a86-533511564813","resolution":{"observed_at":"2026-08-10T17:14:06.476401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.10300","last_updated":"2024-06-13T21:32:56Z","snapshot_observed_at":"2026-07-06T18:31:13.039726Z","submitted_at":"2024-06-13T21:32:56Z","title":"Large Language Models as Software Components: A Taxonomy for LLM-Integrated Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.10300","snapshot_observed_at":"2026-08-10T17:14:06.481037Z","title":"Large language models as software components: A taxonomy for llm-integrated applications,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.481037Z"},"links":{"cited_paper":"/paper/2406.10300","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:e4e66e3929a6d4099349d4647fdf6fb24573adabff982af05b8800c6923ba175","observation_id":"eb9ee4a8-5053-444e-9e30-64187cd938bb","resolution":{"observed_at":"2026-08-10T17:14:06.481037Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:06.485378Z","title":"Large language models: A comprehensive survey of its applications, challenges, limitations, and future prospects","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.485378Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:446367a9376b26a5f7f3470c8bfaf06cecd9aa990ca958618fc9a739bbc21fbe","observation_id":"d2873b26-1e8a-4847-a845-0ef30e4b83f6","resolution":{"observed_at":"2026-08-10T17:14:06.485378Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:06.489056Z","title":"Technique improves the reasoning capabilities of large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.489056Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:33a9235805df96756c6b8a5e66dbfe342741570bc58414bd3ff5a956457c8031","observation_id":"d2d66019-39a1-40db-90a0-f1dd85826eb9","resolution":{"observed_at":"2026-08-10T17:14:06.489056Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16932","last_updated":"2024-02-26T16:34:29Z","snapshot_observed_at":"2026-08-11T04:14:38.015633Z","submitted_at":"2024-02-26T16:34:29Z","title":"PromptSet: A Programmer's Prompting Dataset","version":1},"cited_work":{"arxiv_id":"2402.16932","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.16932","snapshot_observed_at":"2026-08-10T17:14:07.646158Z","title":"PromptSet: A Programmer's Prompting Dataset","venue":"cs.SE","work_id":"0b5755c8-69fe-415d-a838-d905da13d0df","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.492606Z"},"links":{"cited_paper":"/paper/2402.16932","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:afd4e6c9418a6041f04be5fa6ec1b5501f2577104795896c740a5efd591e3397","observation_id":"96c050ee-526f-45f5-b7b2-edb4599120c0","resolution":{"observed_at":"2026-08-10T17:14:07.649982Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:06.496195Z","title":"Auto-debias: Debiasing masked language models with automated biased prompts,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.496195Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:70f0e7bb0b593ee84cdcffa972c8c30c9070c9995a8cce69128cecb6fb8e5361","observation_id":"8e2d0d28-314f-406e-a0b8-b7df15236d7d","resolution":{"observed_at":"2026-08-10T17:14:06.496195Z","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":"2026-08-10T17:14:08.011107Z","title":"Precisedebias: An automatic prompt engineering approach for generative ai to mitigate image demographic biases,","venue":null,"work_id":"21c6f24c-389b-42ad-97e0-45b02f23370f","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.499704Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:758f00096bcf651a35b1770f359b9d9ba1914fb64414d519afc0247a155c1031","observation_id":"356c90da-41bf-4b8f-a5ae-945754935f6d","resolution":{"observed_at":"2026-08-10T17:14:08.014679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.03495","last_updated":"2023-10-19T04:37:25Z","snapshot_observed_at":"2026-08-06T03:31:54.947656Z","submitted_at":"2023-05-04T15:15:22Z","title":"Automatic Prompt Optimization with \"Gradient Descent\" and Beam Search","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.03495","snapshot_observed_at":"2026-08-10T17:14:06.503198Z","title":"Automatic prompt optimization with","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.503198Z"},"links":{"cited_paper":"/paper/2305.03495","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:80c3bbe443debc0b4e125fa9385f11c1f45ec7a7f2f1494dab44fe3098038eed","observation_id":"25a67637-65b7-4a28-8045-d49684bf27b2","resolution":{"observed_at":"2026-08-10T17:14:06.503198Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.04091","last_updated":"2023-05-26T07:06:48Z","snapshot_observed_at":"2026-07-06T15:24:07.662207Z","submitted_at":"2023-05-06T16:34:37Z","title":"Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.04091","snapshot_observed_at":"2026-08-10T17:14:06.507063Z","title":"Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.507063Z"},"links":{"cited_paper":"/paper/2305.04091","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:9abc6d401655157de8a316cbb77d278c41af953ad18c14f8f7e14bc6f361f3fb","observation_id":"951540bd-6c59-4121-917e-402c632ffea2","resolution":{"observed_at":"2026-08-10T17:14:06.507063Z","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":"2026-08-10T17:14:08.001665Z","title":"Language models get a gender makeover: Mitigating gender bias with few-shot data interventions,","venue":null,"work_id":"5b8cebd1-9634-40de-8617-fad946dbfca0","year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.510834Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:6aa576e204edae18eba4666047148589f1f03a19fa6a01b13711126cd0b5dc69","observation_id":"28508c63-8e5c-42d5-9429-4a17d8798571","resolution":{"observed_at":"2026-08-10T17:14:08.005051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.992074Z","title":"Formalizing and benchmarking prompt injection attacks and defenses,","venue":null,"work_id":"c6ab3d41-4ad2-487c-9014-ea17abb3042f","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.513656Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:3469e192d6182fda334a577ceaa5f2df19d941c340ef162e78e9bcc3e7058361","observation_id":"eaaec8e1-397b-47a3-8447-fb309e986bfb","resolution":{"observed_at":"2026-08-10T17:14:07.995373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.982582Z","title":"Promptcare: Prompt copyright protection by watermark injection and verification,","venue":null,"work_id":"bd06923c-0b72-46ec-b672-3b963c372c4c","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.516643Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:45921ed5d71bb3163ea0410d71cd0b6d7fe62c5cafefca3be7746a5f4ad81691","observation_id":"1330cd78-0aea-4bfd-9758-48632b2b07f8","resolution":{"observed_at":"2026-08-10T17:14:07.985965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.973196Z","title":"Don’t stop pretraining? make prompt-based fine-tuning powerful learner,","venue":null,"work_id":"94691740-69f3-4f06-8a4f-c94c7bb11ee4","year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.519476Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:db7d9b4c2da5f1fd0d0917263270a907ea1d357e2d9233402b6989f19a73ddb1","observation_id":"3c5ad0df-61ab-4a0d-a2a8-95e63aa63381","resolution":{"observed_at":"2026-08-10T17:14:07.976623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/s10115-024-02120-8","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:06.808262Z","title":"An analysis of large language models: their impact and potential applications,","venue":null,"work_id":"1522ef7f-722c-4a02-96be-24395727feaf","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.522677Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:e9e26d41da0b86abcba8d561ecb2a706a801d0d161deff2da68afbf4b6463a5f","observation_id":"4ae9cd2f-3e4b-422e-8d05-887c40a15578","resolution":{"observed_at":"2026-08-10T17:14:06.811443Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[{"edge_observation":{"observed_at":"2026-08-10T18:17:57.995914+00:00","source":"paper_reference_links","state":"open"},"event_date":"2024-07-16","event_type":"correction","notice_doi":"10.1007/s10115-024-02157-9","provenance":{"observed_at":"2026-07-11T03:08:43.809337+00:00","source":"crossref","source_record_id":"10.1007/s10115-024-02157-9->10.1007/s10115-024-02120-8:correction"}}],"reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.964432Z","title":"Large language models: Their success and impact,","venue":null,"work_id":"228a6d84-903d-42a9-8b2f-4e4b608aa049","year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.525896Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:1a4baa5f837ba9c5d36811e757e852f9047a7da849cba03242d650eb2722d934","observation_id":"b0846d0c-093c-4310-8658-7f33cafb77c8","resolution":{"observed_at":"2026-08-10T17:14:07.967663Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-10T17:14:06.529102Z","title":"Gpt-4 technical report,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.529102Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:63a7ebcf88168de8abdf6fcc41b4a30c347baf71ec26b5f3ce671d8e8a407d76","observation_id":"0e3458e5-a5c3-4017-939b-691da70df33c","resolution":{"observed_at":"2026-08-10T17:14:06.529102Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-10T16:40:37.411115Z","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":"2026-08-10T17:14:06.532535Z","title":"The llama 3 herd of models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.532535Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:72d3d3705f142d19923f7534ea82937be8bb4858327e59aaeec99ab0324af462","observation_id":"449afd2b-f76e-4dd8-b7ad-505b2227067f","resolution":{"observed_at":"2026-08-10T17:14:06.532535Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.13440","last_updated":"2021-11-26T11:49:07Z","snapshot_observed_at":"2026-08-11T08:50:11.264437Z","submitted_at":"2021-11-26T11:49:07Z","title":"True Few-Shot Learning with Prompts -- A Real-World Perspective","version":1},"cited_work":{"arxiv_id":"2111.13440","doi":null,"metadata_source":"pith","pith_arxiv_id":"2111.13440","snapshot_observed_at":"2026-08-10T17:14:07.594781Z","title":"True Few-Shot Learning with Prompts -- A Real-World Perspective","venue":"cs.CL","work_id":"8e302059-56eb-4a25-9391-091a928060ca","year":2021},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.536369Z"},"links":{"cited_paper":"/paper/2111.13440","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:83b7ae400a2412d33c5216295599c5fc1ca30cfe6985a634aac687c668e63748","observation_id":"41c3c111-6975-47ef-8b56-faa363046112","resolution":{"observed_at":"2026-08-10T17:14:07.598833Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.01390","last_updated":"2022-09-03T10:16:34Z","snapshot_observed_at":"2026-07-06T13:48:31.174395Z","submitted_at":"2022-09-03T10:16:34Z","title":"How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.01390","snapshot_observed_at":"2026-08-10T17:14:06.540154Z","title":"How to prompt? opportunities and challenges of zero- and few-shot learning for human-ai interaction in creative applications of generative models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.540154Z"},"links":{"cited_paper":"/paper/2209.01390","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:40781eaafc94c8a1bf90eb49c83a0b865acef798ef3e12ee5cb0644213c4fe1b","observation_id":"ac6d4ef9-1ce8-47f1-9a0c-ce8fd917b5c9","resolution":{"observed_at":"2026-08-10T17:14:06.540154Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.02680","last_updated":"2023-08-01T10:34:26Z","snapshot_observed_at":"2026-07-30T11:31:41.707170Z","submitted_at":"2023-08-01T10:34:26Z","title":"Fair Models in Credit: Intersectional Discrimination and the Amplification of Inequity","version":1},"cited_work":{"arxiv_id":"2308.02680","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.02680","snapshot_observed_at":"2026-08-10T17:14:07.571792Z","title":"Fair Models in Credit: Intersectional Discrimination and the Amplification of Inequity","venue":"cs.CY","work_id":"e94310af-bb26-4c48-ad96-1532e72f75d8","year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.543547Z"},"links":{"cited_paper":"/paper/2308.02680","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:cd5f45899dfdb55d7ecb8ae324df03b7aeefa512b612802bee3cd1b7e3c6dff4","observation_id":"e26aea38-8cc3-4af8-aaf4-520036bfc339","resolution":{"observed_at":"2026-08-10T17:14:07.575490Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.955777Z","title":"Evaluating racial bias in large language models: The necessity for “smoky","venue":null,"work_id":"5b829278-3bb3-4687-b7b0-153615264e15","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.547239Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:7f0563227e9582506bed837ffc66464794a43d6617e3ce32a17e95cfdce7b68c","observation_id":"8d68b099-7e9e-45d4-a9cb-77c0954df054","resolution":{"observed_at":"2026-08-10T17:14:07.959021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.00770","last_updated":"2024-07-12T20:29:57Z","snapshot_observed_at":"2026-08-09T13:21:58.456670Z","submitted_at":"2023-09-02T00:32:55Z","title":"Bias and Fairness in Large Language Models: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.00770","snapshot_observed_at":"2026-08-10T17:14:06.550646Z","title":"Bias and fairness in large language models: A survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.550646Z"},"links":{"cited_paper":"/paper/2309.00770","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:b88ea2de3ad84b9958ca95266ab0ad62c05801dcc9c145e38544ffdcf2f7e8bb","observation_id":"f096aea0-374c-44db-8bb0-e311cecdf81c","resolution":{"observed_at":"2026-08-10T17:14:06.550646Z","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":"2026-08-10T17:14:07.946483Z","title":"Marked personas: Using natural language prompts to measure stereotypes in language models,","venue":null,"work_id":"16959656-7b76-4258-a5ea-2498211360ba","year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.554344Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:c4ced2b24ee548caa9e18485e1e293a4a6f2fe25d748fa25de6099ad9c0a83b8","observation_id":"3d39f49c-caab-4218-894a-24717bbe4c9b","resolution":{"observed_at":"2026-08-10T17:14:07.949708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.937209Z","title":"Large language models propagate race-based medicine,","venue":null,"work_id":"e3be3b52-9afe-41a1-8355-c6a3989ba6ba","year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.557692Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:671ac10c9bef5a63dbd06ef598ee8c7539d8e097032fc0ca5511f28700839a3d","observation_id":"969e0b52-68c1-4d2e-b93b-ffe57019e1d4","resolution":{"observed_at":"2026-08-10T17:14:07.940509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.00742","last_updated":"2024-03-01T18:43:09Z","snapshot_observed_at":"2026-08-10T13:04:29.169945Z","submitted_at":"2024-03-01T18:43:09Z","title":"Dialect prejudice predicts AI decisions about people's character, employability, and criminality","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.00742","snapshot_observed_at":"2026-08-10T17:14:06.561235Z","title":"Dialect prejudice predicts ai decisions about people’s character, employability, and criminality,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.561235Z"},"links":{"cited_paper":"/paper/2403.00742","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:d735672e4ee7c8a1cc4bb3618051690be4d5dbd4a3fec6177adb707b4e60071c","observation_id":"4b36d7a2-763a-4710-b248-fe2a8d45a356","resolution":{"observed_at":"2026-08-10T17:14:06.561235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00898","last_updated":"2024-01-31T19:52:00Z","snapshot_observed_at":"2026-08-06T01:29:20.953609Z","submitted_at":"2024-01-31T19:52:00Z","title":"An Early Categorization of Prompt Injection Attacks on Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00898","snapshot_observed_at":"2026-08-10T17:14:06.564741Z","title":"An early categorization of prompt injection attacks on large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.564741Z"},"links":{"cited_paper":"/paper/2402.00898","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:de2f9c3e0aec0ecdcaa78da89c9e82d2b24d796328e45cf8d5394ba2e638ad78","observation_id":"aa00d522-7d49-45b3-86c5-9f9008358386","resolution":{"observed_at":"2026-08-10T17:14:06.564741Z","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":"2026-08-10T17:14:07.927592Z","title":"How strangers got my email address from chatgpt’s model,","venue":null,"work_id":"1a6ea6e6-4b03-4e4b-a77d-ba41d4daac3c","year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.567631Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:c7ced807c19cebac6f32230f9c5864797fdd933e415da2f4693353810ef84ea9","observation_id":"d9d1bffa-232b-45ec-8ddc-72c39427d15f","resolution":{"observed_at":"2026-08-10T17:14:07.931040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.06823","last_updated":"2025-06-13T02:24:21Z","snapshot_observed_at":"2026-08-11T10:00:27.407495Z","submitted_at":"2024-05-10T21:52:34Z","title":"PLeak: Prompt Leaking Attacks against Large Language Model Applications","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.06823","snapshot_observed_at":"2026-08-10T17:14:06.570591Z","title":"Pleak: Prompt leaking attacks against large language model applications,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.570591Z"},"links":{"cited_paper":"/paper/2405.06823","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:0a3827ec1237c0977e00e81f367b1265ded44e9829c609bee4b7d0525fb38656","observation_id":"14fb2311-bbbe-4be8-b1b4-b2c4a9f2de1d","resolution":{"observed_at":"2026-08-10T17:14:06.570591Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:06.573434Z","title":"Prompt injection attacks and defenses in llm-integrated applications,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.573434Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:3feed47b804590ee8873de2cc9e1e044ae0cbfb40b883e6ce153f4b31a95a659","observation_id":"87eabee7-ed58-4ba9-9e34-d1612866a837","resolution":{"observed_at":"2026-08-10T17:14:06.573434Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.05499","last_updated":"2025-12-29T02:25:27Z","snapshot_observed_at":"2026-07-06T15:40:27.639368Z","submitted_at":"2023-06-08T18:43:11Z","title":"Prompt Injection attack against LLM-integrated Applications","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.05499","snapshot_observed_at":"2026-08-10T17:14:06.576461Z","title":"Prompt injection attack against llm-integrated applications,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.576461Z"},"links":{"cited_paper":"/paper/2306.05499","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:ce139a20896a5045ce67aeebfa24a99763bb6103f07c92b16d25f089a3f4c15c","observation_id":"5492defb-1ec3-440d-8aa9-5e22911e8122","resolution":{"observed_at":"2026-08-10T17:14:06.576461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.11538","last_updated":"2024-05-25T05:32:39Z","snapshot_observed_at":"2026-08-04T02:40:34.940411Z","submitted_at":"2023-11-20T04:56:46Z","title":"Assessing Prompt Injection Risks in 200+ Custom GPTs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.11538","snapshot_observed_at":"2026-08-10T17:14:06.580235Z","title":"Assessing prompt injection risks in 200+ custom gpts,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.580235Z"},"links":{"cited_paper":"/paper/2311.11538","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:5915609efdc43735f4f8e9107425bfd0880bb90646d7fcc94aef03402bd1f8f0","observation_id":"d85b2162-33b8-4ec5-9eb1-cda53c06a1d9","resolution":{"observed_at":"2026-08-10T17:14:06.580235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.12173","last_updated":"2023-05-05T14:26:17Z","snapshot_observed_at":"2026-07-06T14:55:08.682906Z","submitted_at":"2023-02-23T17:14:38Z","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.12173","snapshot_observed_at":"2026-08-10T17:14:06.584167Z","title":"Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.584167Z"},"links":{"cited_paper":"/paper/2302.12173","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:eb420f3fabbff00da6d25407a75c2fbffad31e2a22e204a9bc6e8faa60c2ca59","observation_id":"3097485e-52e1-4c76-8b08-5c09e8490ee8","resolution":{"observed_at":"2026-08-10T17:14:06.584167Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.13692","last_updated":"2023-07-28T03:31:08Z","snapshot_observed_at":"2026-08-09T12:39:36.870016Z","submitted_at":"2023-07-25T17:55:19Z","title":"ARB: Advanced Reasoning Benchmark for Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.13692","snapshot_observed_at":"2026-08-10T17:14:06.587621Z","title":"Arb: Advanced reasoning benchmark for large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.587621Z"},"links":{"cited_paper":"/paper/2307.13692","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:ac924737d90421a9ab12574a4cc91131c13c677cde5f822f10dd18d0845fad08","observation_id":"a62da953-c012-46cd-b23b-03e4c61b2995","resolution":{"observed_at":"2026-08-10T17:14:06.587621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.10839","last_updated":"2024-12-19T15:25:41Z","snapshot_observed_at":"2026-08-02T04:19:09.502994Z","submitted_at":"2024-08-20T13:34:17Z","title":"Benchmarking Large Language Models for Math Reasoning Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.10839","snapshot_observed_at":"2026-08-10T17:14:06.591219Z","title":"Benchmarking large language models for math reasoning tasks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.591219Z"},"links":{"cited_paper":"/paper/2408.10839","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:7467770d4ed8def5fe33b6c38f17564c7205b23f606dcead0ba4fada6708e0e8","observation_id":"f5d12f69-25cc-4900-a383-8c02d634fc85","resolution":{"observed_at":"2026-08-10T17:14:06.591219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.11382","last_updated":"2023-02-21T12:42:44Z","snapshot_observed_at":"2026-07-06T14:54:37.559648Z","submitted_at":"2023-02-21T12:42:44Z","title":"A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.11382","snapshot_observed_at":"2026-08-10T17:14:06.594625Z","title":"A prompt pattern catalog to enhance prompt engineering with chatgpt,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.594625Z"},"links":{"cited_paper":"/paper/2302.11382","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:804661125bcf40f242a332e77275306575609d61912ff5b5484ee1bd7cc4195a","observation_id":"bdb44f23-706e-4fe9-b267-92b31a5b490d","resolution":{"observed_at":"2026-08-10T17:14:06.594625Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14423","last_updated":"2024-05-05T00:54:26Z","snapshot_observed_at":"2026-08-08T12:36:30.073772Z","submitted_at":"2024-01-24T06:20:18Z","title":"Prompt Design and Engineering: Introduction and Advanced Methods","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.14423","snapshot_observed_at":"2026-08-10T17:14:06.598300Z","title":"Prompt design and engineering: Introduction and advanced methods,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.598300Z"},"links":{"cited_paper":"/paper/2401.14423","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:d1a0ba432a2d1a9dfbcd4414977f0630f6364c6916ab270aea586218c2b571b0","observation_id":"013edcce-94e5-445b-9c0b-216c9575a3cc","resolution":{"observed_at":"2026-08-10T17:14:06.598300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07927","last_updated":"2025-03-16T06:23:34Z","snapshot_observed_at":"2026-08-05T17:55:26.008016Z","submitted_at":"2024-02-05T19:49:13Z","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07927","snapshot_observed_at":"2026-08-10T17:14:06.602381Z","title":"A systematic survey of prompt engineering in large language models: Techniques and applications,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.602381Z"},"links":{"cited_paper":"/paper/2402.07927","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:9106f45606b0a485e0ab1bfabe90e43757ed8341a599a560e298badcc1d39b7d","observation_id":"c5321732-44f6-4e2e-a9a5-a6c048ba23fa","resolution":{"observed_at":"2026-08-10T17:14:06.602381Z","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":"2026-08-10T17:14:07.917614Z","title":"Synthetic data (almost) from scratch: Generalized instruction tuning for language models,","venue":null,"work_id":"f06d058f-7d56-4317-a99f-2425fe79cf3c","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.605768Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:8e598eaabe60a24aa88ccb397f93592e197ebd351b17f8fd7ab2e4148277a97d","observation_id":"48ca361f-c129-4984-869c-5ce361205010","resolution":{"observed_at":"2026-08-10T17:14:07.921257Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.907643Z","title":"spaCy: Industrial-strength Natural Language Processing in Python,","venue":null,"work_id":"2a40a419-98f3-4221-b461-74bc5a41e2fb","year":2020},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.609559Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:67586cd6f08b6d8593a0104555c40f8b1580876ab795404d913cf4e5a268e5ab","observation_id":"084e20c4-8582-450f-aa50-f334090d25d0","resolution":{"observed_at":"2026-08-10T17:14:07.911096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.898548Z","title":"Gender bias in big data analysis,","venue":null,"work_id":"ddb66e30-516e-46b3-b727-16d805dfade0","year":2022},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.613039Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:18d34b75c35693edadd5148c3c31041a9bbd08fe9109eecb5a447d88546baf55","observation_id":"01c973ed-bfcf-421f-b7cf-0d976e1174cc","resolution":{"observed_at":"2026-08-10T17:14:07.901805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.888772Z","title":"Available: https://ssir.org/articles/entry/when_good_algorithms_go_sexist_why_and_how_to_advance_ai_ gender_equity","venue":null,"work_id":"cda67ea7-0070-4cd3-881d-0a4fabbb04b5","year":null},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.616207Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:7bc44bb883a0a9391df8f784dedc4a336883f650d0160d0d75b2aac7aeebb6eb","observation_id":"eee44b48-fa1b-49b1-a359-d2a7549fee14","resolution":{"observed_at":"2026-08-10T17:14:07.892394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.414548Z","title":"From gender biases to gender-inclusive design: An empirical investigation,","venue":null,"work_id":"27940d20-4f55-4fb9-8b49-2171f5471d89","year":2019},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.619498Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:970450e28bcce9a8534411376b7ec40c54cce846ea2e04371bc553112a5f895c","observation_id":"a02d37e3-9489-419a-869c-da1b7c3eabb5","resolution":{"observed_at":"2026-08-10T17:14:07.417985Z","resolver_source":"arxiv_id_nonexistent","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:06.622586Z","title":"Mind the gap: gender, micro-inequities and barriers in software development,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.622586Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:02917274ea36221230f5b2a5a4ca01ce86b0aee89cd386f3e42741e5e1402ca7","observation_id":"095aee23-152d-40bd-8640-eb6f098c69e0","resolution":{"observed_at":"2026-08-10T17:14:06.622586Z","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":"2026-08-10T17:14:07.879437Z","title":"Gender differences and bias in open source: pull request acceptance of women versus men,","venue":null,"work_id":"a2b778d6-f194-45f8-bdd3-d10a6ad5d430","year":2017},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.625295Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:fb5934614303e6c4e8e041ab187b78f25ba5f26e8a37304413d00d9932e24687","observation_id":"d1469dfc-15ec-420d-89cf-b54ccb1c2e07","resolution":{"observed_at":"2026-08-10T17:14:07.882872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.869723Z","title":"All the ways hiring algorithms can introduce bias,","venue":null,"work_id":"93bbc73a-5987-496c-868f-40cbe7318722","year":2019},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.628610Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:dff10775f15502fd9b66acb16e3df524c3374f68b1a715e2d0d68fcbe1332645","observation_id":"27194e7e-bb42-4873-a9a3-6aee57518735","resolution":{"observed_at":"2026-08-10T17:14:07.873368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.860482Z","title":"The risk of racial bias in hate speech detection,","venue":null,"work_id":"a210229b-fb35-4cea-9163-22766d066962","year":2019},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.631736Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:0c202b2cb52e9da75d026d6af29e50189b02b0b7e6c4f9c1405040e3c21969e7","observation_id":"a671278d-1b64-4f0d-940f-42e7b227ed7e","resolution":{"observed_at":"2026-08-10T17:14:07.863498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.851265Z","title":"Dissecting racial bias in an algorithm used to manage the health of populations,","venue":null,"work_id":"97ccddc3-66c2-40d5-9490-da3d77c486e1","year":2019},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.635109Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:dc8208c86daf1749e4f0cc49bbe0e4bfe3fd0c06c375093ce0cb4c382367c99d","observation_id":"cf91aa93-cbe4-494e-861d-ccd00b6f7877","resolution":{"observed_at":"2026-08-10T17:14:07.854662Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1108/edi-02-2022-0049/full/html","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:06.789340Z","title":"Lgbtq+ in workplace: a systematic review and reconsideration,","venue":null,"work_id":"d643fe53-d2e4-4705-9c34-8f736a432c01","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.638164Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:ed43428efc10619db1e981710b87bfde9d4051018fa3aa9f14b99f379fed4ada","observation_id":"fddea232-cff2-490e-9b71-b95df0d4f634","resolution":{"observed_at":"2026-08-10T17:14:06.794361Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.00212","last_updated":"2021-07-01T04:44:10Z","snapshot_observed_at":"2026-08-11T19:59:35.015298Z","submitted_at":"2021-07-01T04:44:10Z","title":"Identifying the Prevalence of Gender Biases among the Computing Organizations","version":1},"cited_work":{"arxiv_id":"2107.00212","doi":null,"metadata_source":"pith","pith_arxiv_id":"2107.00212","snapshot_observed_at":"2026-08-10T17:14:07.382935Z","title":"Identifying the Prevalence of Gender Biases among the Computing Organizations","venue":"cs.SE","work_id":"e0aea786-b306-412e-9398-57fa437d9be7","year":2021},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.641736Z"},"links":{"cited_paper":"/paper/2107.00212","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:c7be6ab4efcc4c5c4f62f1e8d9973b70a4b6f98890c1b474e2e476c5348a497b","observation_id":"03b0ff6e-fb6f-43be-b424-e8d3e1e64739","resolution":{"observed_at":"2026-08-10T17:14:07.386492Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.15087","last_updated":"2024-10-17T19:30:08Z","snapshot_observed_at":"2026-08-10T14:51:00.232286Z","submitted_at":"2023-06-26T22:07:33Z","title":"WinoQueer: A Community-in-the-Loop Benchmark for Anti-LGBTQ+ Bias in Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.15087","snapshot_observed_at":"2026-08-10T17:14:06.645368Z","title":"Winoqueer: A community-in-the-loop benchmark for anti-lgbtq+ bias in large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.645368Z"},"links":{"cited_paper":"/paper/2306.15087","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:64f64b11e421f2cb802b62527d9d9de1726ea513ee83b76ed920a656d8b533f7","observation_id":"d215c163-92b5-46c8-81fe-8f651d3dab26","resolution":{"observed_at":"2026-08-10T17:14:06.645368Z","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":"2026-08-10T17:14:07.842259Z","title":"Language models are unsupervised multitask learners","venue":null,"work_id":"7c9c8837-93b2-43c6-8bb7-76a89516e871","year":null},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.649174Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:cdcd8755761aefa9bce7c9f089e5c634e142154141a96ea7acc7d391f4f9fbe1","observation_id":"28c5ec2b-6982-4c84-8cd0-2c607a301492","resolution":{"observed_at":"2026-08-10T17:14:07.845355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.832489Z","title":"Language models are few-shot learners,","venue":null,"work_id":"dbf813e0-16cf-46a4-b317-4b8dafb2b996","year":2020},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.652711Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:b22051981735988df73b5ed44925a9a6aaa6fc350e2e2ea097f026ebe1c630a5","observation_id":"ae014fbd-db33-41ea-b0a9-ad98ae873e47","resolution":{"observed_at":"2026-08-10T17:14:07.835851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.03409","last_updated":"2024-04-15T07:50:32Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-07T00:07:15Z","title":"Large Language Models as Optimizers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.03409","snapshot_observed_at":"2026-08-10T17:14:06.655877Z","title":"Large language models as optimizers,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.655877Z"},"links":{"cited_paper":"/paper/2309.03409","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:13b196e85b4d6cd9440895c5ffc56cd7d1023a2f6039d6b8ff5c31babbc3b440","observation_id":"fb3e956e-d655-48f6-991d-6352a80d7461","resolution":{"observed_at":"2026-08-10T17:14:06.655877Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16797","last_updated":"2023-09-28T19:01:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-28T19:01:07Z","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.16797","snapshot_observed_at":"2026-08-10T17:14:06.659718Z","title":"Promptbreeder: Self-referential self-improvement via prompt evolution,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.659718Z"},"links":{"cited_paper":"/paper/2309.16797","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:ff47663ec6309efd9963e8f58b5adc9ed82ce40b11961e845ee64a6c188760e1","observation_id":"7bd00904-5d0d-4675-962b-b513b7d6a7b8","resolution":{"observed_at":"2026-08-10T17:14:06.659718Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.18369","last_updated":"2024-10-03T09:45:47Z","snapshot_observed_at":"2026-08-11T14:38:45.537689Z","submitted_at":"2024-05-28T17:08:31Z","title":"PromptWizard: Task-Aware Prompt Optimization Framework","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.18369","snapshot_observed_at":"2026-08-10T17:14:06.663336Z","title":"Promptwizard: Task-aware agent-driven prompt optimization framework,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.663336Z"},"links":{"cited_paper":"/paper/2405.18369","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:daa231a6395bbf8f71592812a889fe4f0b44c58e42c6c0978bd7652db1c5206a","observation_id":"1da25d1d-2e0b-46ac-8e7d-96318d2692ef","resolution":{"observed_at":"2026-08-10T17:14:06.663336Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:06.667128Z","title":"Choice over control: How users write with large language models using diegetic and non-diegetic prompting,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.667128Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:c002829a50d0849eec8c502d2bcc9709209c9657e874b8a5ab979f8a060a59f6","observation_id":"416e0372-09fc-4503-adc4-6dbb43b327de","resolution":{"observed_at":"2026-08-10T17:14:06.667128Z","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":"2026-08-10T17:14:07.822754Z","title":"Signed-prompt: A new approach to prevent prompt injection attacks against llm-integrated applications,","venue":null,"work_id":"977f3d84-c011-4875-bd56-a001075b4ead","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.670469Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:992afcf0ddc2abf1dbaa1983eaa9a3ebb85a95d7d0990d0153de33be99b906af","observation_id":"761f2992-b105-444a-8adc-0b4ab0a0ea8e","resolution":{"observed_at":"2026-08-10T17:14:07.826256Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.14197","last_updated":"2025-01-27T08:51:16Z","snapshot_observed_at":"2026-08-11T04:13:43.714152Z","submitted_at":"2023-12-21T01:08:39Z","title":"Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.14197","snapshot_observed_at":"2026-08-10T17:14:06.673638Z","title":"Benchmarking and defending against indirect prompt injection attacks on large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.673638Z"},"links":{"cited_paper":"/paper/2312.14197","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:fb821746303b50cdc2e8534ef0ccbe6586dff87af3deb0e49e0d5de369f132e0","observation_id":"6f00fc47-e5b9-4b82-9945-2331dffb882b","resolution":{"observed_at":"2026-08-10T17:14:06.673638Z","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":"2026-08-10T17:14:07.812800Z","title":"Prompt shields in azure ai content safety - azure ai services,","venue":null,"work_id":"6da00c8f-41e6-4753-afa0-742c043b3468","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.676930Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:503b5beedfb98e31c231a15fbf82dd6f00d7d99db36e217afa9845f5af274098","observation_id":"a3903aa3-4306-48e8-be3f-18e4b1f19d92","resolution":{"observed_at":"2026-08-10T17:14:07.816369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:06.680236Z","title":"Why johnny can’t prompt: How non-ai experts try (and fail) to design llm prompts,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.680236Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:6684a96d6c5e2f41d68941aac0de76a606b5ac0ce2413e5f8d85d4294542508c","observation_id":"6a6a38fb-558e-4474-babe-1dd8c56435ca","resolution":{"observed_at":"2026-08-10T17:14:06.680236Z","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":"2026-08-10T17:14:07.802567Z","title":"Prompt engineering,","venue":null,"work_id":"f719aaf2-7171-4871-8df0-070365873c40","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.683241Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:fb20b4be864495cbf9f36eb7d45eeeef7b244732afd214304008619c9f0bf768","observation_id":"fc628f94-bb25-4a93-a901-a9155d704709","resolution":{"observed_at":"2026-08-10T17:14:07.806755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.792767Z","title":"Prompt engineering overview,","venue":null,"work_id":"bb829a0f-3f52-4cd2-8c96-197a623ebe9b","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.686140Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:211903094fbb8565c9d31245b7e119a8e44b45f68c7bc2e92a174850c9067f50","observation_id":"11d239eb-9ba5-4c33-98f8-b2ae485c9616","resolution":{"observed_at":"2026-08-10T17:14:07.796428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:06.689002Z","title":"Bleu: a method for automatic evaluation of machine translation,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.689002Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:4e9238f98487b47b5c1c3943051dd78522726e643ce34acb2addb3cf239bad95","observation_id":"661dd609-10db-445d-8996-2726a3a131eb","resolution":{"observed_at":"2026-08-10T17:14:06.689002Z","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":"2026-08-10T17:14:07.783163Z","title":"Sentence-bert: Sentence embeddings using siamese bert-networks,","venue":null,"work_id":"6335393d-539b-4c43-b8db-d641ced73c7a","year":2019},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.691814Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:f5e18fcd5bd70b6ddd5a697ddffbb02fbdbc0c682812bb2fab2a4d9ab4f3471f","observation_id":"13126b14-6006-49fb-ab24-fc41fef55698","resolution":{"observed_at":"2026-08-10T17:14:07.786794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.772688Z","title":"GLEU: Automatic evaluation of sentence-level fluency,","venue":null,"work_id":"32e271e6-b76b-4402-a9ee-61076418bee9","year":2007},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.699550Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:c0095abf86d4cb8c40af6c992bf173220b6433100d18b7d1c4a03552cbfbb025","observation_id":"5835b4df-3f25-47ca-9871-33e6e88e9004","resolution":{"observed_at":"2026-08-10T17:14:07.776101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.762754Z","title":"Judging llm-as-a-judge with mt-bench and chatbot arena,","venue":null,"work_id":"b98c5e38-caa3-4b86-a3c4-fda85b155129","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.702984Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:f094ec3675ceb9546c474d3d9443a9e55cb4aae16b3bc963209402850b240b9d","observation_id":"bbd28e9d-18e3-4aae-af33-89194dc51466","resolution":{"observed_at":"2026-08-10T17:14:07.766297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.752792Z","title":"“call me sexist, but","venue":null,"work_id":"a10ab1ea-d0a7-4b4a-b5c7-dc971213d4d6","year":2021},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.706374Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:f528e846e849561210c77535bfc3d02c671b67b094dc30826d8594ee3f490b23","observation_id":"9518a025-e7bf-4a9a-a38a-87a988cf84da","resolution":{"observed_at":"2026-08-10T17:14:07.756086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.742857Z","title":"Xhate-999: Analyzing and detecting abusive language across domains and languages,","venue":null,"work_id":"5b6e71ef-c3fd-4fc2-9b9b-cb6fbebfaf24","year":2020},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.710029Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:1407a4913d45958c39a946af0a38641990205df3afb0f2e057e56288211e6029","observation_id":"84bfe590-7e9d-474e-aefd-ddb5644650b0","resolution":{"observed_at":"2026-08-10T17:14:07.746421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2009.13081","last_updated":"2020-09-28T05:07:51Z","snapshot_observed_at":"2026-08-06T03:17:52.286711Z","submitted_at":"2020-09-28T05:07:51Z","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.13081","snapshot_observed_at":"2026-08-10T17:14:06.713339Z","title":"What disease does this patient have? a large-scale open domain question answering dataset from medical exams,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.713339Z"},"links":{"cited_paper":"/paper/2009.13081","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:6328d95d6a04ac34b8736fbbf2127acc8ded046f1228518391346980a4ea4986","observation_id":"3fefbbf6-6932-4672-88b2-63f5606d29c9","resolution":{"observed_at":"2026-08-10T17:14:06.713339Z","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":"2026-08-10T17:14:07.733554Z","title":"Pubmedqa: A dataset for biomedical research question answering,","venue":null,"work_id":"3a7b7507-0c9e-4229-a8e8-cba3be0f7f46","year":2019},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.717114Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:33cc9ef2e7213e7cd8c169c76272a102b4c20a5c7cbfc32a909d070f459adf9b","observation_id":"3ed4887e-342d-4b00-b10e-c89521fa2976","resolution":{"observed_at":"2026-08-10T17:14:07.736630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-07T01:45:38.840969Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-10T17:14:06.720574Z","title":"Training verifiers to solve math word problems,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.720574Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:e7b8cac8921a6985244abb770f0b4847500416fd13cb788a9e43f3cb2c85de58","observation_id":"283701ba-0876-4cdb-944e-603dfa8a0359","resolution":{"observed_at":"2026-08-10T17:14:06.720574Z","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":"2026-08-10T17:14:07.724887Z","title":"Ethos: Rectifying language models in orthogonal parameter space,","venue":null,"work_id":"fdf92f5e-c055-4740-8af2-de675485527c","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.724752Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:5fe39c521cf3da0e0a88f92e0a68c65317c8794d7eb226ec6b354986bc7d98fc","observation_id":"215903d3-9cf2-43d8-9d55-428584cad178","resolution":{"observed_at":"2026-08-10T17:14:07.727964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.715453Z","title":"Get to the point: Summarization with pointer-generator networks,","venue":null,"work_id":"18967fa0-b42e-47fd-b419-f33b57b93224","year":2017},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.728356Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:ec6e4abe24b67f5fcbd1d92e8ebbf7ce4f4de3257deda5da02eb3166f82ae22c","observation_id":"d9fc60e2-ee5b-4cd9-9020-79a80cf88507","resolution":{"observed_at":"2026-08-10T17:14:07.719050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.705773Z","title":"English-spanish translation dataset,","venue":null,"work_id":"e87e227e-5780-401c-a95d-79d3fb687b36","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.731389Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:e6054449730043ff2c74772e1bb987566f1d0662eb4b6e074a788291627c56a5","observation_id":"175825d5-b92e-46d0-bec1-b5422b44f11b","resolution":{"observed_at":"2026-08-10T17:14:07.709051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.695892Z","title":"Mining & mastering the art of english corrections,","venue":null,"work_id":"b6dfc7ed-b814-43bf-818e-ffa0e99bd6de","year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.734616Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:96a17ee9157357ebdabe8c0d049bf6141744a40610d746ba05df75e3732f2057","observation_id":"853bab0d-626e-40f5-92f8-71fcea4e2edf","resolution":{"observed_at":"2026-08-10T17:14:07.699442Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.685608Z","title":"Decoding symbolism in language models,","venue":null,"work_id":"8e79ce96-7b33-44dc-ba00-d255defb8270","year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.737895Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:c501ed772fe713625bab242495c1028baec6d2db98e443bc06437aeb2a9c2a70","observation_id":"a23f7e5e-3319-43ba-9182-9f4a13968102","resolution":{"observed_at":"2026-08-10T17:14:07.689321Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:07.675316Z","title":"Universal and transferable adversarial attacks on aligned language models,","venue":null,"work_id":"90ec7e1d-89dc-49ad-a9ae-10cd71650b7a","year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.741049Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:b9ba61918812e6bfbbcf21dde5dcfd214cc977eeb29977a0f1126f171f6dcd6d","observation_id":"9b5c9314-d405-4702-b66d-1451814f0216","resolution":{"observed_at":"2026-08-10T17:14:07.679020Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.08419","last_updated":"2024-07-18T18:24:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-12T15:38:28Z","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.08419","snapshot_observed_at":"2026-08-10T17:14:06.744173Z","title":"Jailbreaking black box large language models in twenty queries,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.744173Z"},"links":{"cited_paper":"/paper/2310.08419","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:613b812730c4e8ad86b44cb80bb2e8b8df25735c7916685bdb9017d55d98449a","observation_id":"af08d188-5d3d-4470-9023-86ad78d46054","resolution":{"observed_at":"2026-08-10T17:14:06.744173Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.09527","last_updated":"2022-11-17T13:43:20Z","snapshot_observed_at":"2026-07-06T14:19:47.424778Z","submitted_at":"2022-11-17T13:43:20Z","title":"Ignore Previous Prompt: Attack Techniques For Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.09527","snapshot_observed_at":"2026-08-10T17:14:06.747481Z","title":"Ignore previous prompt: Attack techniques for language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.747481Z"},"links":{"cited_paper":"/paper/2211.09527","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:65c649c882022589fa6b0f8d62e8961ff156b992d45c1aadb387ba16da21cf5b","observation_id":"773f2da0-0e8e-41ac-b507-e7050b94abe2","resolution":{"observed_at":"2026-08-10T17:14:06.747481Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:06.751070Z","title":"Copiloting the copilots: Fusing large language models with completion engines for automated program repair,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.751070Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:80922fd8feab403819432afbb4db657e22a15c2ca09d5080184ed5be782d130a","observation_id":"f9800494-366f-4462-816c-f31594f2bb64","resolution":{"observed_at":"2026-08-10T17:14:06.751070Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:06.757291Z","title":"Automatic semantic augmentation of language model prompts (for code summarization),","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.757291Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:051e748256644b12f025c7ce6775fee278c93277fcd2e866933ec449d2dd739d","observation_id":"153c217e-d928-4ddd-b605-52aec7570809","resolution":{"observed_at":"2026-08-10T17:14:06.757291Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T17:14:06.760264Z","title":"Prompting is all you need: Automated android bug replay with large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.760264Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:60b27ac2daea45ce21ec44bf13bd37959cdce337731555d651075054983aa190","observation_id":"77eee360-f28d-47e1-9c40-eadced687773","resolution":{"observed_at":"2026-08-10T17:14:06.760264Z","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":"2026-08-10T17:14:07.665736Z","title":"Gpt-4o system card,","venue":null,"work_id":"5087f2ca-1f69-4fb0-8b55-569f9fe88300","year":2024},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.763061Z"},"links":{"citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:5ae70618c7cd478b6841a6348e5f83c9fbe5045dc1a57115224cb8335ce6425f","observation_id":"a4bbedf5-479b-407b-bdb2-ee6aa1a9703b","resolution":{"observed_at":"2026-08-10T17:14:07.669100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.10084","last_updated":"2019-08-27T08:50:17Z","snapshot_observed_at":"2026-07-06T08:17:05.681370Z","submitted_at":"2019-08-27T08:50:17Z","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.10084","snapshot_observed_at":"2026-08-10T17:14:06.695117Z","title":"Available: https://arxiv.org/abs/1908.10084","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-10T17:14:06.695117Z"},"links":{"cited_paper":"/paper/1908.10084","citing_paper":"/paper/2501.12521"},"observation_digest":"sha256:043c1d77a1544c3c5483b33ae90796bc09cf405f66474f08c52c241c1f1638cb","observation_id":"bc6ba37f-0315-40fc-bccd-f2e2f6a9d6bd","resolution":{"observed_at":"2026-08-10T17:14:06.695117Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.12521","last_updated":"2025-01-21T22:24:03Z","latest_version":1,"primary_category":"cs.SE","snapshot_observed_at":"2026-08-10T17:04:13.843791Z","submitted_at":"2025-01-21T22:24:03Z","title":"An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer Prompts"},"reference_resolution":{"displayed":84,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":40,"verified_exact":7,"verified_fuzzy":37},"total_outbound_references":84},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 84 of 84 outbound references and 0 inbound Pith citation observations for arXiv:2501.12521."}