{"as_of":"2026-08-21T10:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e82f04b16a18353296ee022f0dfcee0400c7358ea0b94008a8f15488770a5156","coverage":[{"denominator":61,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":61,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T20:04:29.497733Z","state":"measured"},{"denominator":61,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":61,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2509.08910/citation-record","integrity":"/paper/2509.08910/integrity","json":"/paper/2509.08910/citation-record.json","paper":"/paper/2509.08910"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T20:04:29.184383Z","title":"Language models are few-shot learners,","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.184383Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:3c335d779dd0529ea172093ac9fde146d98ce28ba8df78f3e1c8d5c0e2eabcf9","observation_id":"51b05c06-dacf-4552-8786-93e3f6698fbf","resolution":{"observed_at":"2026-08-04T20:04:29.184383Z","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":"2026-08-04T20:04:29.190658Z","title":"Privacy- preserving synthetic data generation for healthcare applications,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.190658Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:c5476e38be4035c5a2273a8d5c6f4945f04a2d0b27ee6e584c45ae055375156c","observation_id":"a54c30fe-3cc4-4341-b89a-6cd2fd771d9a","resolution":{"observed_at":"2026-08-04T20:04:29.190658Z","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":"2026-08-04T20:04:29.196090Z","title":"Synthea: An approach, method, and software mechanism for generating synthetic patients and the synthetic electronic health care record,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.196090Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:8ac5894553d2d80f2d9dfba7fc494c248fa0bee835fc236f8e1459358946776f","observation_id":"9685191d-7864-4341-99b6-d94564395fb5","resolution":{"observed_at":"2026-08-04T20:04:29.196090Z","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":"2026-08-04T20:04:29.202215Z","title":"On the dangers of stochastic parrots: Can language models be too big?","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.202215Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:724f4ffcf49037f01accf237207ced5c9b314e4f7279d293034c85b1515ffbc0","observation_id":"badb1f64-3409-4cb4-a19e-defab045c81b","resolution":{"observed_at":"2026-08-04T20:04:29.202215Z","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":"2026-08-04T20:04:29.207541Z","title":"Algorithmic injustice: A relational ethics approach,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.207541Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:6c5b92d0ca03b58099e51d4530bb449e43fc2fc55a72c18c2569af4d2a4250b5","observation_id":"855dc877-0463-4e20-96c1-e710ae0c6554","resolution":{"observed_at":"2026-08-04T20:04:29.207541Z","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":"2026-08-04T20:04:29.212269Z","title":"Ai4peoplean ethical framework for a good ai society: Opportunities, risks, principles, and recommendations,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.212269Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:982c03145345f8245896dfd45f6ecbd6f343830542a6e6bbbf2a3b631613de6d","observation_id":"b7953dfe-78f6-416f-ad03-67c6114dbbe3","resolution":{"observed_at":"2026-08-04T20:04:29.212269Z","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":"2026-08-04T20:04:29.217488Z","title":"Livingstone, G","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.217488Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:bcd104ac889059797939a8775bcab755dfdbafc066eee1ad74f16ba1e1231994","observation_id":"01e8756f-a79f-4ec2-be56-8d08bfd064ae","resolution":{"observed_at":"2026-08-04T20:04:29.217488Z","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":"2026-08-04T20:04:29.221937Z","title":"Eubanks,Automating Inequality: How High-Tech Tools Profile, Po- lice, and Punish the Poor","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.221937Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:54f8349c77f63c6efd26f29ba0bd3e0feb494353575e25a80bd1535b0baa478d","observation_id":"242acd1c-16c2-4620-a516-be2eef641e4a","resolution":{"observed_at":"2026-08-04T20:04:29.221937Z","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":"2026-08-04T20:04:29.226849Z","title":"The misgendering machines: Trans/hci implications of automatic gender recognition,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.226849Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:b61cdad676d7357f286ab643952b8840beec9df165bf8305d252954535ac557f","observation_id":"4a6c2bb9-1950-4c52-bccf-548a6acdd5ea","resolution":{"observed_at":"2026-08-04T20:04:29.226849Z","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":"2026-08-04T20:04:29.231363Z","title":"Technocolonialism: Digital innovation and data practices in the humanitarian response to refugee crises,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.231363Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:eb6e67c3593c50637adbc4ab31e79c2b996b85effbb0bf04babf50952a7a14e5","observation_id":"d89cff6b-5ae7-4873-b4d6-ab0ae472b5d6","resolution":{"observed_at":"2026-08-04T20:04:29.231363Z","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":"2026-08-04T20:04:29.236782Z","title":"Under- standing social media disclosures of sexual abuse through the lenses of support seeking and anonymity,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.236782Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:85ccfcfc3bfcd17c30b0aa361087f6d39fe3472c7f2576a2a026f2cc07966bee","observation_id":"7dd72c37-7c2c-4269-bc35-5e1f8c422247","resolution":{"observed_at":"2026-08-04T20:04:29.236782Z","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":"2026-08-04T20:04:29.241348Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.241348Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:d91aba86dac770bf3f7893d4ff98581e024381c025c2de5ca7a8ecd97d1fb041","observation_id":"e530ed93-6d07-42c8-adaa-c26d5ac7bc2d","resolution":{"observed_at":"2026-08-04T20:04:29.241348Z","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":"2026-08-04T20:04:29.245953Z","title":"Kukutai and J","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.245953Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:0f87ea9be54ffd8064704920e4eee62533f581719f0645fb59bebe5b9b1eb22c","observation_id":"f20be303-24d2-401c-93f0-aa9fb875066a","resolution":{"observed_at":"2026-08-04T20:04:29.245953Z","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":"2026-08-04T20:04:29.250125Z","title":"Language (technology) is power: A critical survey of","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.250125Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:2ff960661602cfb56c993f3c9c4895ebc85d01d6771db4df9421f3c3c539b3d8","observation_id":"dde1c9bf-806b-483d-8426-b5da58b6e447","resolution":{"observed_at":"2026-08-04T20:04:29.250125Z","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":"2026-08-04T20:04:29.256657Z","title":"Realtoxicityprompts: Evaluating neural toxic degeneration in language models,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.256657Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:ab9bd25712e304fb65927f7f9add732e5e94a9cfc78bfd3027eedc116c503fd5","observation_id":"b546674b-8f15-4f28-af94-7e0be6d97025","resolution":{"observed_at":"2026-08-04T20:04:29.256657Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.04359","last_updated":"2021-12-08T16:09:48Z","snapshot_observed_at":"2026-08-09T15:17:43.394064Z","submitted_at":"2021-12-08T16:09:48Z","title":"Ethical and social risks of harm from Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.04359","snapshot_observed_at":"2026-08-04T20:04:29.262910Z","title":"Ethical and social risks of harm from language models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.262910Z"},"links":{"cited_paper":"/paper/2112.04359","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:68ac4619cdb03f6ec81aab9452dc8f8cb79b7801d6b8f1cb8127ba76b1509f68","observation_id":"1c5c4f04-30de-4a33-80dd-ff244314a268","resolution":{"observed_at":"2026-08-04T20:04:29.262910Z","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":"2026-08-04T20:04:29.268949Z","title":"Automated hate speech detection and the problem of offensive language,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.268949Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:acde39e4eaf005767eecd601c79fb3d44bf99004754e7886c21c5d2f7db7d575","observation_id":"52917745-8184-444f-adf8-d4c7b45d9910","resolution":{"observed_at":"2026-08-04T20:04:29.268949Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.08073","last_updated":"2022-12-15T06:19:23Z","snapshot_observed_at":"2026-08-16T03:49:00.703994Z","submitted_at":"2022-12-15T06:19:23Z","title":"Constitutional AI: Harmlessness from AI Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.08073","snapshot_observed_at":"2026-08-04T20:04:29.273817Z","title":"Constitutional ai: Harmlessness from ai feedback,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.273817Z"},"links":{"cited_paper":"/paper/2212.08073","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:024c5d9271dbf4ce31afafb05e0d69762151b6e236c4b758ee00b239f0b6f0fe","observation_id":"ab4e8985-104c-4f4c-ae79-43759b328545","resolution":{"observed_at":"2026-08-04T20:04:29.273817Z","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":"2026-08-04T20:04:29.279135Z","title":"Ethically aligned design: A vision for prioritizing human well-being with autonomous and intelligent systems,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.279135Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:341b9346b39876e88465543d79d1e6dffcc5431711b590cabfa7d3aa4fb1c744","observation_id":"b8bc796a-5bfd-4c8a-ad22-9e2d0045680e","resolution":{"observed_at":"2026-08-04T20:04:29.279135Z","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":"2026-08-04T20:04:29.283255Z","title":"Russell and P","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.283255Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:63900055cb5833bb8f0123d2b470b4fa31c33bf4c47f83682a5c14bed724fa6f","observation_id":"2f8ae808-d8e3-4a2b-8348-c9a6c935103b","resolution":{"observed_at":"2026-08-04T20:04:29.283255Z","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":"2026-08-04T20:04:29.287989Z","title":"Training language models to follow instructions with human feedback,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.287989Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:7efad270bb52974ab42868dc89bd0182662f98c07b4b62e6b87e880d794da0e8","observation_id":"6ff0a8ba-feb7-46f4-816e-394b1fb332a7","resolution":{"observed_at":"2026-08-04T20:04:29.287989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03714","last_updated":"2023-10-05T17:37:25Z","snapshot_observed_at":"2026-08-04T05:21:05.846165Z","submitted_at":"2023-10-05T17:37:25Z","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03714","snapshot_observed_at":"2026-08-04T20:04:29.293716Z","title":"Dspy: Compiling declarative language model calls into self-improving pipelines,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.293716Z"},"links":{"cited_paper":"/paper/2310.03714","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:589377dd75cf43e058fba106e37589f9eadc1ac823f71cb93a55be643c0b4ffe","observation_id":"1e46a0b3-6614-4f0c-95df-78acbf3ab0da","resolution":{"observed_at":"2026-08-04T20:04:29.293716Z","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":"2026-08-04T20:04:29.301606Z","title":"Chain-of-thought prompting elicits reasoning in large language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.301606Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:a3be64b3dd9fa512f2c0f1031ef702e9ae0976c7178f3a57337770a7520fcfdc","observation_id":"998289f1-9afa-408d-a612-374fcf8d94d9","resolution":{"observed_at":"2026-08-04T20:04:29.301606Z","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":"2026-08-04T20:04:29.307002Z","title":"Tree of thoughts: Deliberate problem solving with large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.307002Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:6418cfc948b6f4b393a47e495c8d831807457836721b9468174b5e274ae5990a","observation_id":"7e0c98c7-d38f-4ed4-935c-8331b01171f9","resolution":{"observed_at":"2026-08-04T20:04:29.307002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06117","last_updated":"2024-03-12T04:38:27Z","snapshot_observed_at":"2026-08-16T14:53:41.073902Z","submitted_at":"2023-10-09T19:48:55Z","title":"Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06117","snapshot_observed_at":"2026-08-04T20:04:29.311700Z","title":"Take a step back: Evoking reasoning via abstraction in large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.311700Z"},"links":{"cited_paper":"/paper/2310.06117","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:068580b7ebef478dcaa78110bc1daa1a06060263464a533ae48638f240b9dbde","observation_id":"783d4722-f542-4da3-8f32-9cdc05625efe","resolution":{"observed_at":"2026-08-04T20:04:29.311700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.03629","last_updated":"2023-03-10T01:00:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-10-06T01:00:32Z","title":"ReAct: Synergizing Reasoning and Acting in Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.03629","snapshot_observed_at":"2026-08-04T20:04:29.317190Z","title":"React: Synergizing reasoning and acting in language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.317190Z"},"links":{"cited_paper":"/paper/2210.03629","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:f53d8e187da101398aad68466da68cebbd6418619e730d66706fc4a93923ecb4","observation_id":"3f9db9fd-b9b4-46b7-b25d-e707c5a59bf7","resolution":{"observed_at":"2026-08-04T20:04:29.317190Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.05802","last_updated":"2022-06-14T01:16:24Z","snapshot_observed_at":"2026-08-19T21:55:00.332987Z","submitted_at":"2022-06-12T17:40:53Z","title":"Self-critiquing models for assisting human evaluators","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.05802","snapshot_observed_at":"2026-08-04T20:04:29.322589Z","title":"Self-critiquing models for assisting human evaluators,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.322589Z"},"links":{"cited_paper":"/paper/2206.05802","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:3bea69814fb309da9f9b5504803251771ee6a450ff50bdbb041dff24482f5982","observation_id":"60d7822b-1b20-4a43-b07d-22018ed151d6","resolution":{"observed_at":"2026-08-04T20:04:29.322589Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.17651","last_updated":"2023-05-25T19:13:47Z","snapshot_observed_at":"2026-08-17T09:48:37.358540Z","submitted_at":"2023-03-30T18:30:01Z","title":"Self-Refine: Iterative Refinement with Self-Feedback","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.17651","snapshot_observed_at":"2026-08-04T20:04:29.327259Z","title":"Self-refine: Iterative refinement with self-feedback,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.327259Z"},"links":{"cited_paper":"/paper/2303.17651","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:a3540761feb68b717432172096766edb4a587c89695c419f4548ad97ac4df88e","observation_id":"5b846f34-1cfc-4503-9748-02ebaccb41ac","resolution":{"observed_at":"2026-08-04T20:04:29.327259Z","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":"2026-08-04T20:04:29.340747Z","title":"A prompt pattern catalog to enhance prompt engineering with chatgpt,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.340747Z"},"links":{"cited_paper":"/paper/2302.11382","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:f8fe215b8ad14e79166963c85d0c171f296f329a93562287b07afc7cddd848e7","observation_id":"501f1d9a-93f8-455a-8bff-5cac58f1c3b9","resolution":{"observed_at":"2026-08-04T20:04:29.340747Z","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":"2026-08-04T20:04:29.346703Z","title":"Prompt programming for large language models: Beyond the few-shot paradigm,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.346703Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:c0886c9005720bbfc437e04fdd9b2d18482a415c9b76a8cb4ec014128a2d93d6","observation_id":"9af085ab-320e-4d79-9102-0e7c1d4dc082","resolution":{"observed_at":"2026-08-04T20:04:29.346703Z","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":"2026-08-04T20:04:29.351865Z","title":"Calibrating noise to sensitivity in private data analysis,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.351865Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:0c811ecc823645102a574e2242c2a24bdb5f7f25944f38f197952818f9301205","observation_id":"85b3fb20-e237-4f96-862b-49360b356886","resolution":{"observed_at":"2026-08-04T20:04:29.351865Z","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":"2026-08-04T20:04:29.356428Z","title":"Extracting training data from large language models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.356428Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:a22333c46767fffb18272ebd9a03f734be6e1bb46d11e1fd88643276f9cf354c","observation_id":"95dc3264-bf43-40d7-8fd8-0ea8b1cee6f2","resolution":{"observed_at":"2026-08-04T20:04:29.356428Z","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":"2026-08-04T20:04:29.360626Z","title":"An empirical survey of the effectiveness of debiasing techniques for pre-trained language models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.360626Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:d450f87f87408d61031ea69536a8bd32584e950376e327be9ae33d76bfc95e39","observation_id":"1b9f5122-6fda-4e51-9711-2fa47248fe6b","resolution":{"observed_at":"2026-08-04T20:04:29.360626Z","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":"2026-08-04T20:04:29.365014Z","title":"Racial microaggressions in everyday life: Implications for clinical practice,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.365014Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:749d78b95512a2c7ddf2f8ab15d55dcce22613e4224088c252b1e564dd15461b","observation_id":"2315fb1e-8226-4267-a954-2feebbd3a997","resolution":{"observed_at":"2026-08-04T20:04:29.365014Z","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":"2026-08-04T20:04:29.369970Z","title":"Machine ethics: Creating an ethical intelligent agent,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.369970Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:25a4ea09fc797f20414af0a11e150819748eb89b6d042222891dafd99229bfdc","observation_id":"9f4d94e5-1e06-4269-bffa-274b1927004f","resolution":{"observed_at":"2026-08-04T20:04:29.369970Z","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":"2026-08-04T20:04:29.377246Z","title":"Wallach and C","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.377246Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:08a5be1681dec7432970db186510c6f7242cb6d1e9371c6386ad8f5214b89f26","observation_id":"f28054cc-b33b-4899-9b8d-e6fb921efe20","resolution":{"observed_at":"2026-08-04T20:04:29.377246Z","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":"2026-08-04T20:04:29.382165Z","title":"Microsoft presidio,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.382165Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:625cf43e4155c7684d0f74bbb9d2571e1c021f7b8444a54583162dc2fc5fc8c8","observation_id":"67944279-ae8c-47b7-bdd4-4a310f6221cc","resolution":{"observed_at":"2026-08-04T20:04:29.382165Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.10716","last_updated":"2024-03-14T22:15:20Z","snapshot_observed_at":"2026-08-20T06:10:15.371408Z","submitted_at":"2023-10-16T18:00:01Z","title":"$W$ state is not the unique ground state of any local Hamiltonian","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.10716","snapshot_observed_at":"2026-08-04T20:04:29.386632Z","title":"Lost in PII: Towards fair and private text data with large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.386632Z"},"links":{"cited_paper":"/paper/2310.10716","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:42c8271b2ff1bc62663ddde9ffbccf961670ba3676beeab4059846a7f4758b12","observation_id":"c95aa2a6-219d-414c-a6dd-9816ee7d358f","resolution":{"observed_at":"2026-08-04T20:04:29.386632Z","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":"2026-08-04T20:04:29.391550Z","title":"A survey on content moderation and its challenges in social media,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.391550Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:3d66bc521c953a8a79275c214077a7448496b2f9b0752ac840fc85b21572d4d0","observation_id":"ecb638af-6f2a-4645-b199-67e14e93e5fe","resolution":{"observed_at":"2026-08-04T20:04:29.391550Z","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":"2026-08-04T20:04:29.396368Z","title":"k-anonymity: A model for protecting privacy,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.396368Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:4db22d5fbe513000dffe81142df8c120d975fc4b9d2e86aff1fc47caf4087d31","observation_id":"a87dd40e-6cac-4cfc-a932-52e9933b5091","resolution":{"observed_at":"2026-08-04T20:04:29.396368Z","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":"2026-08-04T20:04:29.400799Z","title":"Perspective API,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.400799Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:bd6d4d2378ad2bcba94a4affe423951fc909c617ee4ad4c8bdc2cbccd6043fa3","observation_id":"b75534ac-38b1-41e1-95e5-590746af5290","resolution":{"observed_at":"2026-08-04T20:04:29.400799Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.04205","last_updated":"2024-04-18T23:49:56Z","snapshot_observed_at":"2026-08-18T21:47:36.698819Z","submitted_at":"2023-11-07T18:43:34Z","title":"Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.04205","snapshot_observed_at":"2026-08-04T20:04:29.405226Z","title":"Rephrase and respond: Let large language models ask better questions for themselves,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.405226Z"},"links":{"cited_paper":"/paper/2311.04205","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:4905bd60a2cfd6befaf61f07a4606be2692af1b4cdc88a6ed7f945921e4f08ee","observation_id":"8259be97-7aa6-4e26-b87f-483c48fe1f0c","resolution":{"observed_at":"2026-08-04T20:04:29.405226Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.11760","last_updated":"2023-11-12T12:35:41Z","snapshot_observed_at":"2026-08-19T19:37:47.334752Z","submitted_at":"2023-07-14T00:57:12Z","title":"Large Language Models Understand and Can be Enhanced by Emotional Stimuli","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.11760","snapshot_observed_at":"2026-08-04T20:04:29.410105Z","title":"Large language models understand and can be enhanced by emotional stimuli,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.410105Z"},"links":{"cited_paper":"/paper/2307.11760","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:4677e0e57feab82e8695aa59fad6c5c50c865edd4b7ca5ef21144b0837d7f238","observation_id":"329f2ac3-a9f7-49b9-ba73-f5b1f659669b","resolution":{"observed_at":"2026-08-04T20:04:29.410105Z","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":"2026-08-04T20:04:29.414818Z","title":"Schuler and A","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.414818Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:c535243058038193d61d93df095039e2b82643832bd318d37335faa4dafab846","observation_id":"1e835d3a-b31c-4dc0-8f4b-10af00bedfe7","resolution":{"observed_at":"2026-08-04T20:04:29.414818Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.10560","last_updated":"2023-05-25T23:50:07Z","snapshot_observed_at":"2026-08-19T16:38:51.329886Z","submitted_at":"2022-12-20T18:59:19Z","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.10560","snapshot_observed_at":"2026-08-04T20:04:29.420262Z","title":"Self-instruct: Aligning language models with self-generated instructions,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.420262Z"},"links":{"cited_paper":"/paper/2212.10560","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:509f1458426fb03998808a9d16a1dd3ec3e52d6cf87360765d236f432f1220f3","observation_id":"7526675e-e85e-4b9e-a12f-c7a100663e37","resolution":{"observed_at":"2026-08-04T20:04:29.420262Z","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":"2026-08-04T20:04:29.424591Z","title":"[Online]","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.424591Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:fbcbd2408c9f849595d899cbf95dccd6f426465c009e3204e7fc41edbc3d4a18","observation_id":"acaf6066-a989-4f36-a0c1-9be7e6465d6a","resolution":{"observed_at":"2026-08-04T20:04:29.424591Z","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":"2026-08-04T20:04:29.428931Z","title":"UNHCR refugee data finder,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.428931Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:09e9f20fdd921d719843d8d09a62f4b69f125db24f277c60491a97ce03385d08","observation_id":"f772696a-15cf-43b0-9900-4f8309dda46d","resolution":{"observed_at":"2026-08-04T20:04:29.428931Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.05577","last_updated":"2019-04-29T16:28:23Z","snapshot_observed_at":"2026-08-15T22:26:04.309671Z","submitted_at":"2018-11-14T00:34:01Z","title":"Aequitas: A Bias and Fairness Audit Toolkit","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.05577","snapshot_observed_at":"2026-08-04T20:04:29.432970Z","title":"Aequitas: A bias and fairness audit toolkit,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.432970Z"},"links":{"cited_paper":"/paper/1811.05577","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:98dacaa027a4c73c69ed4a1c32627b77af41bbffbaed05eef0f36fa8991145e1","observation_id":"ebb5df7e-0994-4eae-9426-4809a1b65e8a","resolution":{"observed_at":"2026-08-04T20:04:29.432970Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.06983","last_updated":"2023-10-22T00:11:13Z","snapshot_observed_at":"2026-08-19T23:01:10.173441Z","submitted_at":"2023-05-11T17:13:40Z","title":"Active Retrieval Augmented Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.06983","snapshot_observed_at":"2026-08-04T20:04:29.437442Z","title":"Active retrieval augmented generation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.437442Z"},"links":{"cited_paper":"/paper/2305.06983","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:84c825545dd0d0bdc22c87c3d0a3095267def354f58ed4d59002c39964f77812","observation_id":"5ebb927b-ff45-4caf-9299-c4daeac18be9","resolution":{"observed_at":"2026-08-04T20:04:29.437442Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.05685","last_updated":"2023-12-24T02:01:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-06-09T05:55:52Z","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.05685","snapshot_observed_at":"2026-08-04T20:04:29.442012Z","title":"Judging LLM-as-a- judge with MT-bench and chatbot arena,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.442012Z"},"links":{"cited_paper":"/paper/2306.05685","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:d085da7aadc23fcdfbfa955d9e85618fbd4f619dce3e2f4349df1ede44ccc80b","observation_id":"963681bd-0677-4864-9bc4-8c316c747d66","resolution":{"observed_at":"2026-08-04T20:04:29.442012Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.03846","last_updated":"2023-03-08T07:37:43Z","snapshot_observed_at":"2026-08-18T13:27:58.239266Z","submitted_at":"2023-03-07T12:24:17Z","title":"Larger language models do in-context learning differently","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.03846","snapshot_observed_at":"2026-08-04T20:04:29.447841Z","title":"Larger language models do in-context learning differently,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.447841Z"},"links":{"cited_paper":"/paper/2303.03846","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:bc31eb85f60f5f1f76ada7878a2fa72c88a22edbf8d633b001281a2927fadcf0","observation_id":"e43ecbfb-f179-439d-802f-be5b4065a4af","resolution":{"observed_at":"2026-08-04T20:04:29.447841Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.06804","last_updated":"2021-01-17T23:38:40Z","snapshot_observed_at":"2026-08-16T18:51:47.106761Z","submitted_at":"2021-01-17T23:38:40Z","title":"What Makes Good In-Context Examples for GPT-$3$?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.06804","snapshot_observed_at":"2026-08-04T20:04:29.453557Z","title":"What makes good in-context examples for gpt-3?","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.453557Z"},"links":{"cited_paper":"/paper/2101.06804","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:d0a574d4bb8c08aafd0eed41144edfbc495f03abfd727c4dca40c0c49fc84f26","observation_id":"ce84cee4-4bbd-4e1d-b3ce-45d4de16c1af","resolution":{"observed_at":"2026-08-04T20:04:29.453557Z","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":"2026-08-04T20:04:29.459842Z","title":"Seer: A knapsack approach to exemplar selection for in-context learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.459842Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:70f3ae28657bc995b057b88effe6fd75b1aed387690c998fc1df94c082baddba","observation_id":"430ff536-1bce-411d-8c66-33d2efcf0485","resolution":{"observed_at":"2026-08-04T20:04:29.459842Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.03350","last_updated":"2023-10-17T18:57:17Z","snapshot_observed_at":"2026-08-15T17:25:43.175408Z","submitted_at":"2022-10-07T06:50:23Z","title":"Measuring and Narrowing the Compositionality Gap in Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.03350","snapshot_observed_at":"2026-08-04T20:04:29.464769Z","title":"Measuring and narrowing the compositionality gap in language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.464769Z"},"links":{"cited_paper":"/paper/2210.03350","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:217d8154ebcbd28be5bb27cd7a3dc353eda2cba1b0f830d754ca96f29d04570f","observation_id":"004dc40c-41cf-49a9-b57a-882d48e8477c","resolution":{"observed_at":"2026-08-04T20:04:29.464769Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.11171","last_updated":"2023-03-07T17:57:37Z","snapshot_observed_at":"2026-08-16T01:49:22.176843Z","submitted_at":"2022-03-21T17:48:52Z","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.11171","snapshot_observed_at":"2026-08-04T20:04:29.469812Z","title":"Self-consistency improves chain of thought reasoning in language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.469812Z"},"links":{"cited_paper":"/paper/2203.11171","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:126574518da6be102036b536b2b8e7593b14db76a2a788ecfe4dd9740d5b0d31","observation_id":"8bb2851b-5e29-465a-85ac-f21a5c917497","resolution":{"observed_at":"2026-08-04T20:04:29.469812Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01714","last_updated":"2024-03-09T05:54:39Z","snapshot_observed_at":"2026-08-16T14:55:39.362326Z","submitted_at":"2023-10-03T00:57:26Z","title":"Large Language Models as Analogical Reasoners","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01714","snapshot_observed_at":"2026-08-04T20:04:29.474609Z","title":"Large language models as analogical reasoners,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.474609Z"},"links":{"cited_paper":"/paper/2310.01714","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:8a665e05ba01e8bd2ba10db1e131736d5bc78d6aad5e2a3e969edf8a44ca8911","observation_id":"1c7c7268-8507-4382-bb22-6e070eda3d25","resolution":{"observed_at":"2026-08-04T20:04:29.474609Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.18223","last_updated":"2026-03-18T05:34:39Z","snapshot_observed_at":"2026-08-14T10:40:26.323157Z","submitted_at":"2023-03-31T17:28:46Z","title":"A Survey of Large Language Models","version":19},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.18223","snapshot_observed_at":"2026-08-04T20:04:29.479147Z","title":"A survey of large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.479147Z"},"links":{"cited_paper":"/paper/2303.18223","citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:624393c1159ec7361bd0a489a1f263c839c94e15974d2ad0d62a77890ec9dc79","observation_id":"a0f62acb-81b0-4cbb-bb8d-90eabee4d37d","resolution":{"observed_at":"2026-08-04T20:04:29.479147Z","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":"2026-08-04T20:04:29.483619Z","title":"On measuring social biases in sentence encoders,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.483619Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:798b873a94cb742a9ce61735da84caf0d94d6c0652df058bd8e4e646eb685212","observation_id":"ae3f27c0-2c16-4194-a6d7-9d9d3c64bf07","resolution":{"observed_at":"2026-08-04T20:04:29.483619Z","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":"2026-08-04T20:04:29.488107Z","title":"Semantics derived au- tomatically from language corpora contain human-like biases,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.488107Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:93b6da2420f451bf1ef8e500609a063084ac5cd9af77d0e30f0adb59f5f13e95","observation_id":"f58a9775-2855-4e8a-8fe6-3a6116b2ded1","resolution":{"observed_at":"2026-08-04T20:04:29.488107Z","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":"2026-08-04T20:04:29.492787Z","title":"Bertscore: Evaluating text generation with bert,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.492787Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:60da0017709615f7edb1c0cf4fd7b1f4b761c4284d2a4f59bfabd764260128a8","observation_id":"6f2a04ec-0ce2-4fee-b2fb-aa8238f2e2a8","resolution":{"observed_at":"2026-08-04T20:04:29.492787Z","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":"2026-08-04T20:04:29.497733Z","title":"Co-creation and the new landscapes of design,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-04T20:04:29.497733Z"},"links":{"citing_paper":"/paper/2509.08910"},"observation_digest":"sha256:cc222c32956428ffb4ce731930e8910b9250a578cdf44a08a95d6106f93692cd","observation_id":"4c748baf-4c32-4048-a1f8-97ddbb2867c4","resolution":{"observed_at":"2026-08-04T20:04:29.497733Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.08910","last_updated":"2025-09-10T18:14:52Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T12:46:19.307071Z","submitted_at":"2025-09-10T18:14:52Z","title":"PromptGuard: An Orchestrated Prompting Framework for Principled Synthetic Text Generation for Vulnerable Populations using LLMs with Enhanced Safety, Fairness, and Controllability"},"reference_resolution":{"displayed":61,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":61,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":61},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 0 inbound Pith citation observations for arXiv:2509.08910."}