{"as_of":"2026-08-23T21:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:58a581ec5cbe987c521e81ea2d644d2c5d39b9598822f0f31537bc56164ca641","coverage":[{"denominator":36,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":36,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T15:02:33.362408Z","state":"measured"},{"denominator":37,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":37,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T13:06:12.594872Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-05T13:06:13.929163Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"cited_work":{"arxiv_id":"2412.11414","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.11414","snapshot_observed_at":"2026-08-05T13:06:13.929163Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","venue":"cs.CL","work_id":"331278c4-605c-4551-bd88-4bcebc092974","year":2024},"citing_paper":{"arxiv_id":"2509.00963","last_updated":"2025-08-31T19:12:01Z","snapshot_observed_at":"2026-08-21T08:31:50.036584Z","submitted_at":"2025-08-31T19:12:01Z","title":"Who Gets Left Behind? Auditing Disability Inclusivity in Large Language Models","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-05T13:06:12.594872Z"},"links":{"cited_paper":"/paper/2412.11414","citing_paper":"/paper/2509.00963"},"observation_digest":"sha256:4b0ea6b6e70e837c674914a2249569fea8b4a8393118bf4b29b993028f4e5a68","observation_id":"8b35a536-c347-48da-bd27-4be22b8560d2","resolution":{"observed_at":"2026-08-05T13:06:14.018913Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.11414/citation-record","integrity":"/paper/2412.11414/integrity","json":"/paper/2412.11414/citation-record.json","paper":"/paper/2412.11414"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T15:02:33.175600Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.175600Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:2d1c678e220c38d5614018eb23837581cfc1116c3d576bd0f3170e420349af3a","observation_id":"d1010e54-5894-4ef4-9fd3-0b84c4f8e440","resolution":{"observed_at":"2026-08-11T15:02:33.175600Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.14165","last_updated":"2020-07-22T19:47:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-05-28T17:29:03Z","title":"Language Models are Few-Shot Learners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.14165","snapshot_observed_at":"2026-08-11T15:02:33.181079Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.181079Z"},"links":{"cited_paper":"/paper/2005.14165","citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:d623bc5850a0694d1b18e8883407babea055044eb5ab1b569ae426386dbe4e96","observation_id":"152e8668-a9f0-4c8d-bc7e-3c0bece228b9","resolution":{"observed_at":"2026-08-11T15:02:33.181079Z","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":"2026-08-11T15:02:33.186940Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.186940Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:721d03ae2e3521444667960ffb7fd6ba95f090c366831c5ec7cb2c78cc2745fa","observation_id":"98468e61-7697-4dd3-a345-4863660fb994","resolution":{"observed_at":"2026-08-11T15:02:33.186940Z","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":"2026-08-11T15:02:33.192239Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.192239Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:cc0650b31ea7c5d470fa556b6134391d6cbc6bc1a71f83cc23b621aec2daac68","observation_id":"5c00b466-eced-4802-822d-9135758df796","resolution":{"observed_at":"2026-08-11T15:02:33.192239Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.07459","last_updated":"2023-02-18T21:30:27Z","snapshot_observed_at":"2026-08-16T15:55:15.315299Z","submitted_at":"2023-02-15T04:25:40Z","title":"The Capacity for Moral Self-Correction in Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.07459","snapshot_observed_at":"2026-08-11T15:02:33.198617Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.198617Z"},"links":{"cited_paper":"/paper/2302.07459","citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:276759ce9375de66d821a6ff8d1f9f6cc15e55c25424c4f4b0971012c11a7734","observation_id":"e3e7b37d-073b-4f93-b286-7d73d84a736d","resolution":{"observed_at":"2026-08-11T15:02:33.198617Z","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":"2026-08-11T15:02:33.204689Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.204689Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:a73a79a7a87f76e63ad81e64bcc1173084a303ee4e70702fba6672130e11fdad","observation_id":"e542c312-99d0-45aa-b277-766aac16169c","resolution":{"observed_at":"2026-08-11T15:02:33.204689Z","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":"2026-08-11T15:02:33.211173Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.211173Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:7a08999c264f8690c99608f4102489d7925c9fc190ceb9cc6073f3f765a9c3c1","observation_id":"ed84199f-db55-4feb-a643-419a7bda3ebb","resolution":{"observed_at":"2026-08-11T15:02:33.211173Z","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":"2026-08-11T15:02:33.216328Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.216328Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:b29922963052ba511c356a516d4723098d6db52b1f64540eeaa8e763f9c7a68c","observation_id":"f85825f2-0d94-4717-b9a1-296df7ea6f68","resolution":{"observed_at":"2026-08-11T15:02:33.216328Z","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":"2026-08-11T15:02:33.221557Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.221557Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:e34de48fc064ded8c9f2ce42c13e5e0f00ad509769dc9073525e14a05bb78306","observation_id":"3ac6cdef-eaa7-4ce8-8059-00732bc297e4","resolution":{"observed_at":"2026-08-11T15:02:33.221557Z","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":"2026-08-11T15:02:33.226740Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.226740Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:11989b3150252b6849cc8980ea0e8c87b26e462046e29b2758d9cb6e63a636c6","observation_id":"c689a983-788f-45fe-b6d0-328a2184ff19","resolution":{"observed_at":"2026-08-11T15:02:33.226740Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06825","last_updated":"2023-10-10T17:54:58Z","snapshot_observed_at":"2026-08-17T20:30:34.016254Z","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06825","snapshot_observed_at":"2026-08-11T15:02:33.232714Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.232714Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:01bd60ee838dc3ffff15031b5c8de00fb49a6c1245a539af1ce8269181e31904","observation_id":"f72e36b0-a886-405b-88b2-a9371e234bb3","resolution":{"observed_at":"2026-08-11T15:02:33.232714Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.04088","last_updated":"2024-01-08T18:47:34Z","snapshot_observed_at":"2026-08-23T11:47:44.729242Z","submitted_at":"2024-01-08T18:47:34Z","title":"Mixtral of Experts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.04088","snapshot_observed_at":"2026-08-11T15:02:33.238891Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.238891Z"},"links":{"cited_paper":"/paper/2401.04088","citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:aacda301293d6caa3a4d86d0ebb2aab0d05672386392baa45407b77586f1878b","observation_id":"87c2c973-e3c1-420c-b52f-ff0e97d5606c","resolution":{"observed_at":"2026-08-11T15:02:33.238891Z","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":"2026-08-11T15:02:33.244698Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.244698Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:243d8a3306cb3f4c2793480110c62783610b08e3654b3c61208297ac0bc383be","observation_id":"ad2489d4-16ca-43f4-887a-d3b141feba41","resolution":{"observed_at":"2026-08-11T15:02:33.244698Z","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":"10.18653/v1/2021.eacl-main.16","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T15:02:33.477608Z","title":null,"venue":null,"work_id":"d22849eb-6d39-4dbd-b492-43bd5bcc1644","year":2021},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.249780Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:d62b31da908fa7aaeeb8cfa1da2f68867c49b88d4888df2c84a077d248ecac4e","observation_id":"1c8088e5-d2e3-49fa-a0d2-97718d67032e","resolution":{"observed_at":"2026-08-11T15:02:33.484946Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-11T15:02:33.254319Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.254319Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:dacfd427de7bdadda023c6ce8f008a4a1adcac32b6d3cf68ae3b9b757a55ccc3","observation_id":"1292f11c-bce4-4e71-a382-2b50c4d18c8f","resolution":{"observed_at":"2026-08-11T15:02:33.254319Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.09110","last_updated":"2023-10-01T21:44:23Z","snapshot_observed_at":"2026-08-10T23:10:13.900680Z","submitted_at":"2022-11-16T18:51:34Z","title":"Holistic Evaluation of Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.09110","snapshot_observed_at":"2026-08-11T15:02:33.258973Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.258973Z"},"links":{"cited_paper":"/paper/2211.09110","citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:687dd4e235f3a98cbb884932930a9b084a7dbb1cd9453dc70880bdfd19ecf9bb","observation_id":"3f8c4ce8-bd46-455b-b93b-5700c83e709a","resolution":{"observed_at":"2026-08-11T15:02:33.258973Z","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":"2026-08-11T15:02:33.263749Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.263749Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:c2eeb1b89651dff1499ae513dcd70e1322447814e17a5f4be7ab4faf91aff22d","observation_id":"5bbfed0a-2e42-43c4-949b-6d320d153a4e","resolution":{"observed_at":"2026-08-11T15:02:33.263749Z","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":"2026-08-11T15:02:33.267974Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.267974Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:2f5586ab4553e1cfe192de78bc40f91490b01be129bcf51b0a341c400ef62c1f","observation_id":"0d1336ca-d6ce-4df1-a208-d7d136244c07","resolution":{"observed_at":"2026-08-11T15:02:33.267974Z","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":"2026-08-11T15:02:33.272184Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.272184Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:b5851d33961782ed7a6996158c6d07610d0ad1bc6bdc7f86ebe53eed61662624","observation_id":"07433049-7122-4293-9cf3-4441fad753c0","resolution":{"observed_at":"2026-08-11T15:02:33.272184Z","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":"2026-08-11T15:02:33.915052Z","title":null,"venue":null,"work_id":"4ea2b943-6c78-4b2a-93af-4685859d1e77","year":2024},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.277024Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:63e9da8fa254f873e161e8368687568c8b004a8aa64ff78a889bd5cb8a6592fa","observation_id":"a35c0eba-e39c-4369-9eb5-ca791270e8f4","resolution":{"observed_at":"2026-08-11T15:02:33.920957Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T15:02:33.281373Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.281373Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:31831141513db0a0d8f426a1ee654a695cf4e44e687533076ee51bcb7ae80555","observation_id":"6eb9e8f8-cce0-48d6-ab9c-dbe1c52239c3","resolution":{"observed_at":"2026-08-11T15:02:33.281373Z","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":"2026-08-11T15:02:33.286255Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.286255Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:558553ef3d9cbc7bd074605e33c86f8970a3b2f79bcc969a781dc99e26afdfcd","observation_id":"830b24ee-01d4-434b-be6b-776de4574b51","resolution":{"observed_at":"2026-08-11T15:02:33.286255Z","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":"2026-08-11T15:02:33.291495Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.291495Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:0e8b98f58432ec9e94e132f0e658c70bd074230d732144c30ca469e5cb61401b","observation_id":"c30c625b-5b44-4626-9d6b-b6d16baede4a","resolution":{"observed_at":"2026-08-11T15:02:33.291495Z","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":"2026-08-11T15:02:33.296596Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.296596Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:cf83d0a550f7e395e57ba4648cd8df65acecfc18e03283fe9074b9cd58ab7449","observation_id":"08e29d0c-34ed-4284-b1a8-34eae0be578b","resolution":{"observed_at":"2026-08-11T15:02:33.296596Z","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":"2026-08-11T15:02:33.301960Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.301960Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:16a85d097f6b2f41992806c38decc41419b509162708b2b3714463f17cbe2ded","observation_id":"21d6a9bf-57f4-48e9-bf0c-99904962f0a9","resolution":{"observed_at":"2026-08-11T15:02:33.301960Z","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":"2026-08-11T15:02:33.857689Z","title":null,"venue":null,"work_id":"5d07242d-6db6-4246-95eb-da95e0753968","year":2021},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.306841Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:28ff31c7b39f313519b26a110dff1b36fe9965f9db6866c510a302af6a197eae","observation_id":"732d64b5-7925-4da7-8431-bb45d24d5d3c","resolution":{"observed_at":"2026-08-11T15:02:33.863844Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.09150","last_updated":"2023-02-15T02:24:43Z","snapshot_observed_at":"2026-08-16T16:23:31.471283Z","submitted_at":"2022-10-17T14:52:39Z","title":"Prompting GPT-3 To Be Reliable","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.09150","snapshot_observed_at":"2026-08-11T15:02:33.311353Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.311353Z"},"links":{"cited_paper":"/paper/2210.09150","citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:8655851b0f2a69b5fae77ef0b0a79ed02efaffe2d7f5c811607fd2ca5cda3aee","observation_id":"bb4c3f9e-65b7-40eb-b648-fb73354bc17f","resolution":{"observed_at":"2026-08-11T15:02:33.311353Z","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":"2026-08-11T15:02:33.317164Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.317164Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:33addddeae36ebf9fcf65e6a936e3769c02b6ff416ad5390c2253d68bbcca9dd","observation_id":"fe4cc006-b55e-4277-b792-771efe5ba9c9","resolution":{"observed_at":"2026-08-11T15:02:33.317164Z","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":"2026-08-11T15:02:33.322179Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.322179Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:cf5108a595b68ef12ebcc45d95d1c5b67b39cbeb88cb9c107687239c94d032e6","observation_id":"36faa5ab-bbc4-438b-a62c-6490ad959afb","resolution":{"observed_at":"2026-08-11T15:02:33.322179Z","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":"2026-08-11T15:02:33.327593Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.327593Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:f58e3aa75d10ff6d2db23fcac1182a8b47bdeb3f9a4d4bf1e21eb4b6fdc48a54","observation_id":"7d572eea-80f3-41c9-bbbc-9d55ac6a8b19","resolution":{"observed_at":"2026-08-11T15:02:33.327593Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-11T15:02:33.332513Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.332513Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:ca6dd09bd6e023c44f5533cced5ef01a105bb06ac14e763cc12c2e0eb7c63e4c","observation_id":"29f4f237-85f0-42cc-931d-97bf4fc66e35","resolution":{"observed_at":"2026-08-11T15:02:33.332513Z","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":"2026-08-11T15:02:33.338047Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.338047Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:9117805254070b5edd3b50ddd69ce5dae40644c1fc86df3eed7a8ccebad779c3","observation_id":"69f04ac5-6677-45c4-a1f1-82027d1c9ea2","resolution":{"observed_at":"2026-08-11T15:02:33.338047Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.06032","last_updated":"2021-03-02T21:04:26Z","snapshot_observed_at":"2026-08-18T15:14:13.097650Z","submitted_at":"2020-10-12T21:15:29Z","title":"Measuring and Reducing Gendered Correlations in Pre-trained Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.06032","snapshot_observed_at":"2026-08-11T15:02:33.343291Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.343291Z"},"links":{"cited_paper":"/paper/2010.06032","citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:5c263eac347108c20cfe985868e765746a06a93300b080c5c468181f279c403b","observation_id":"0f3db3ad-0c7e-4f15-80a8-266b02d3ce20","resolution":{"observed_at":"2026-08-11T15:02:33.343291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.01652","last_updated":"2022-02-08T20:26:45Z","snapshot_observed_at":"2026-08-14T06:11:14.515796Z","submitted_at":"2021-09-03T17:55:52Z","title":"Finetuned Language Models Are Zero-Shot Learners","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.01652","snapshot_observed_at":"2026-08-11T15:02:33.350351Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.350351Z"},"links":{"cited_paper":"/paper/2109.01652","citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:3e5cad63698f97671201cfa663533a9d7e4a547e391f3dfdaeff022e07cf3816","observation_id":"2f61da4d-c09b-4abd-b66e-9b522014c89c","resolution":{"observed_at":"2026-08-11T15:02:33.350351Z","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":"2026-08-11T15:02:33.356276Z","title":"URL: \" 'urlintro :=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.356276Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:285cb349ccdae1ab67279d1baec4ec7ccef73590c2c50915bde418b4703bf197","observation_id":"0f77a88a-83ff-44dc-8816-1ca77c2cfc9e","resolution":{"observed_at":"2026-08-11T15:02:33.356276Z","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":"2026-08-11T15:02:33.362408Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-11T15:02:33.362408Z"},"links":{"citing_paper":"/paper/2412.11414"},"observation_digest":"sha256:8afe108ad8ea5169f8a429e4138f89218cf448bcc1d2d79f9ade551f3f571049","observation_id":"a933ebd1-b328-45ea-9ea5-d9a710995668","resolution":{"observed_at":"2026-08-11T15:02:33.362408Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.11414","last_updated":"2024-12-16T03:29:08Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-15T19:51:21.848714Z","submitted_at":"2024-12-16T03:29:08Z","title":"Biased or Flawed? Mitigating Stereotypes in Generative Language Models by Addressing Task-Specific Flaws"},"reference_resolution":{"displayed":36,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":35,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":36},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 1 inbound Pith citation observation for arXiv:2412.11414."}