{"as_of":"2026-08-19T16:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0cb2d6ec73a2bc9615439601373ce113e8b867e69ac88bee2a6333997550dbed","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T00:16:04.823633Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+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/2608.08284/citation-record","integrity":"/paper/2608.08284/integrity","json":"/paper/2608.08284/citation-record.json","paper":"/paper/2608.08284"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:04.253269Z","title":"O’Brien, Carrie J","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.253269Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:f08beafb7577d004631f284d66de4e15723ba5b9ddcf4ae57e33c4817fdae5f3","observation_id":"bdd3e10c-7cf5-48d5-b1fd-68abdb895d92","resolution":{"observed_at":"2026-08-12T00:16:04.253269Z","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":"2026-08-12T00:16:10.254191Z","title":"The rise and potential of large language model based agents: A survey.Science China Information Sciences, 68, 2025","venue":null,"work_id":"2d32d29c-2f79-47cd-9ddb-eeac40ce2151","year":2025},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.269051Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:ab3f989f91cf4cf397c959c8b15e8d21d659d44cf866387b84e45c17af221520","observation_id":"b7312d88-de5d-431c-82f8-af401e943e1f","resolution":{"observed_at":"2026-08-12T00:16:10.272694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.09332","last_updated":"2022-06-01T19:08:11Z","snapshot_observed_at":"2026-08-19T02:54:55.334346Z","submitted_at":"2021-12-17T05:43:43Z","title":"WebGPT: Browser-assisted question-answering with human feedback","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.09332","snapshot_observed_at":"2026-08-12T00:16:04.274817Z","title":"WebGPT: Browser-assisted question-answering with human feedback.arXiv preprint arXiv:2112.09332, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.274817Z"},"links":{"cited_paper":"/paper/2112.09332","citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:496406df969b10f86855ab17e750f72b39b058e6a82ea5d55d299feaaf90b380","observation_id":"0d175eaf-60a7-48a0-99cd-d235ef420302","resolution":{"observed_at":"2026-08-12T00:16:04.274817Z","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":"2026-08-12T00:16:04.280799Z","title":"Large language models for information retrieval: A survey.ACM Transactions on Information Systems, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.280799Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:9c8a3b53e84d524e582a75dc2b1f3ef40f6f597fe273325c3d6663a45ab0212a","observation_id":"edc1ff38-0707-414b-b0f3-12c124714785","resolution":{"observed_at":"2026-08-12T00:16:04.280799Z","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":"2026-08-12T00:16:04.286143Z","title":"Recommender systems in the era of large language models.IEEE Transactions on Knowledge and Data Engineering, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.286143Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:f4def32614ab623daec7f8a17f1f96143c7291d5b6b85f3f4ba99b6b7676f068","observation_id":"ec7e02d1-ac35-43a8-9859-dc26aa10ff58","resolution":{"observed_at":"2026-08-12T00:16:04.286143Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.01157","last_updated":"2024-03-23T17:05:42Z","snapshot_observed_at":"2026-08-16T15:03:42.440584Z","submitted_at":"2023-09-03T12:33:47Z","title":"Large Language Models for Generative Recommendation: A Survey and Visionary Discussions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.01157","snapshot_observed_at":"2026-08-12T00:16:04.292471Z","title":"Large language models for generative recommendation: A survey and visionary discussions.arXiv preprint arXiv:2309.01157, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.292471Z"},"links":{"cited_paper":"/paper/2309.01157","citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:d254e57b16c90daf1b7eddd59767c3657d58a716f53112e9f5f7e493297d197d","observation_id":"691727cb-9af3-46e9-a7c7-18b1a25c44ba","resolution":{"observed_at":"2026-08-12T00:16:04.292471Z","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":"2026-08-12T00:16:10.171196Z","title":"Zhang, K","venue":null,"work_id":"274008b7-436e-46ff-ad74-2adf84498328","year":2023},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.296431Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:976b460a1ccb30e0698d9f292a80a84be650e3610baed60c7f29933454387baf","observation_id":"4195c852-bd8f-4ea7-988e-fccbba081cf7","resolution":{"observed_at":"2026-08-12T00:16:10.188791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:10.095647Z","title":null,"venue":null,"work_id":"fe1e24ec-2de4-4ab0-b8a6-2f9728927ea6","year":2024},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.303723Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:5a6231d4a5d0a8d765ee8a924acb50593fe1514fc9d0997248302413b6edb824","observation_id":"bd474469-4884-4dd5-b7d4-116d27c34e1e","resolution":{"observed_at":"2026-08-12T00:16:10.111646Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.10149","last_updated":"2024-02-21T13:52:11Z","snapshot_observed_at":"2026-08-16T15:07:16.573910Z","submitted_at":"2023-08-20T03:30:22Z","title":"A Survey on Fairness in Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.10149","snapshot_observed_at":"2026-08-12T00:16:04.334752Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.334752Z"},"links":{"cited_paper":"/paper/2308.10149","citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:094f47529cd6145926b5b01c2969af38e02d4e886a3a1edea8339279e4b6e749","observation_id":"66d9afd7-4e2c-4f23-a2d6-70622629767e","resolution":{"observed_at":"2026-08-12T00:16:04.334752Z","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":"2026-08-12T00:16:10.014744Z","title":null,"venue":null,"work_id":"25ce3206-ecb7-4896-ae43-6c2f35b44242","year":2024},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.349200Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:2bced721726db556a4ac3a350415b9eb80a8576d646e11f4778ffbb53f839440","observation_id":"b973d6ff-3b01-436a-8b0d-605a57efc983","resolution":{"observed_at":"2026-08-12T00:16:10.035054Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-12T00:16:04.352199Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.352199Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:38bd0dbc4cfaeb302c517630457db20be348266f21a35919f5fd57777f58b508","observation_id":"2bf3a105-88e7-46c9-9263-dc373e87269e","resolution":{"observed_at":"2026-08-12T00:16:04.352199Z","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":"2026-08-12T00:16:04.355722Z","title":"Griffiths","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.355722Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:31321df6ee08a3c8dd3763dba75ae58ab1531fa99feff34de1d94d74cefcb0bd","observation_id":"561e0fff-6c59-4ba1-8f2c-42aaecdfbe47","resolution":{"observed_at":"2026-08-12T00:16:04.355722Z","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":"2026-08-12T00:16:09.904749Z","title":"Aligned but blind: Align- ment increases implicit bias by reducing awareness of race","venue":null,"work_id":"fe4789d5-50e7-4345-89bc-8291b98e6b84","year":2025},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.359883Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:acdbce2bb7b24448b57bb5d39597191f438a2b2f46ea0d7f79e036da055a090d","observation_id":"241bf840-93b1-410a-a0e7-ee4a31e2b113","resolution":{"observed_at":"2026-08-12T00:16:09.944745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:09.797911Z","title":"Cassese, G","venue":null,"work_id":"c2c9f011-d264-4915-a796-64f3f72aaadc","year":2025},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.362950Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:9c0a4aa45f8aa6ea56b151d4fca5db9cadf003333ee4cceb2c5af52f73ad258b","observation_id":"07388f77-af69-426e-a49b-a34a98ecb6e5","resolution":{"observed_at":"2026-08-12T00:16:09.824415Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-12T00:16:04.369579Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.369579Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:a1af6c4d782b5f645ff52ae2cf2d2830ddcdb1eaa9815434563e9754659eaaa6","observation_id":"a40f9b52-3742-4ead-a249-4f33251e7e7a","resolution":{"observed_at":"2026-08-12T00:16:04.369579Z","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":"2026-08-12T00:16:09.644744Z","title":"Hernandez, B.Z","venue":null,"work_id":"391d12cc-b5ef-462e-a958-c032cdd6c50a","year":2024},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.373153Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:04d794bf01c426f37c0df34fa743b3312d336b8e52fe2c2e2d11874ba34c33b7","observation_id":"ffa2779a-67e8-42e2-b0a7-9b9e3e92fa99","resolution":{"observed_at":"2026-08-12T00:16:09.685673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:06.946472Z","title":"Gender bias in coreference resolution: Evaluation and debiasing methods","venue":null,"work_id":"153f0c2c-df00-4445-923c-2f0c28519c8b","year":2018},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.383612Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:bedf49ac48a4bc3392b20ad9696f972314bbd6883af507c604966becd9ca4df9","observation_id":"38c11cfe-b47e-4b53-9039-0806298126bb","resolution":{"observed_at":"2026-08-12T00:16:07.056337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:06.807009Z","title":null,"venue":null,"work_id":"cb64b879-95ff-48f0-9d90-dfa70fa86914","year":2020},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.388631Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:ccff62402b0d11eb63c0186268c15544bfbf2600e2dc7fa9d7171e9e795d5a77","observation_id":"009c7ccf-d145-45cd-9402-22d7798523a9","resolution":{"observed_at":"2026-08-12T00:16:06.810235Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:06.782400Z","title":null,"venue":null,"work_id":"60025e60-b474-401f-9fc8-ffccc1756c36","year":2022},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.395968Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:e039b72a85a588f9b47e80bbaffd07ad358dc3fea051311ece5b306a80a26128","observation_id":"955d9460-cb4c-4acb-8c85-5068631f6779","resolution":{"observed_at":"2026-08-12T00:16:06.793344Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:06.768107Z","title":null,"venue":null,"work_id":"0d536eff-e54e-4a1f-9400-5e8cac273275","year":2020},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.404765Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:f11a27b4e0e5fceb482da945eb77e090eac161a2939c333f094204df7f89d495","observation_id":"6c89ffb6-1862-4790-91be-1aadac09277d","resolution":{"observed_at":"2026-08-12T00:16:06.770814Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:06.757558Z","title":"Greenwood, S","venue":null,"work_id":"ddc7526e-b4f0-4410-9f65-55d08986231a","year":2024},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.409599Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:cac95767b1f93869f609755bf61d733f25a31769d2ad911efffa55b74d304e5c","observation_id":"eb9da857-2c6f-436c-863b-6a95c4d4000a","resolution":{"observed_at":"2026-08-12T00:16:06.762048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:06.724748Z","title":null,"venue":null,"work_id":"05ce7c78-4aac-4b6a-8f68-9bbf4d816fcc","year":2024},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.417548Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:104ff6ce052b339f5bd8cb1fe2c8fdccfa85a500d74445ef194ff3c4112e3a50","observation_id":"2e477383-089a-4805-bbb8-b3f5cc2dc746","resolution":{"observed_at":"2026-08-12T00:16:06.730790Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:06.652791Z","title":"Rampisela, M","venue":null,"work_id":"37907509-6732-4c4f-8b1c-e07121088151","year":2025},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.420957Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:949e4ee7ab5169c0fc7647f51c62a182c7af4988380ee016219d48cac860f109","observation_id":"16c5d5a4-6176-425c-8c08-298dbecb8eae","resolution":{"observed_at":"2026-08-12T00:16:06.673904Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2602.02516","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:05.811551Z","title":"Rampisela, M","venue":null,"work_id":"0d1e5439-f789-452e-989d-27fc1ec3f432","year":2026},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.424047Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:9dd2b5d1761bdaa4f98cda837665fb39376fd5f6477eaa1f5cf117a21be4f2d2","observation_id":"9b479a70-92d9-4ad1-a376-8e68c0570db0","resolution":{"observed_at":"2026-08-12T00:16:05.830536Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:06.566734Z","title":null,"venue":null,"work_id":"6aad392f-5773-427d-8c0e-46073afd1eea","year":2025},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.452868Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:169211d9843116c16eadd0e319c5b518efef8618d2d0bce51fd8a0adcad25480","observation_id":"7527ee92-fff6-4be8-bfed-1f80e8eeabf4","resolution":{"observed_at":"2026-08-12T00:16:06.615199Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-12T00:16:04.458574Z","title":"Is ChatGPT fair for recommendation? Evaluating fairness in large language model recommendation.arXiv preprint arXiv:2305.07609, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.458574Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:f2de390e1e9a2c919a07688d4e8eaeba23f6914e31aa2ddea82ad4ac06c30143","observation_id":"77562cab-c48b-49b1-b1b4-65dcbc2b1876","resolution":{"observed_at":"2026-08-12T00:16:04.458574Z","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":"2026-08-12T00:16:04.461980Z","title":"Ethical and social risks of harm from language models.arXiv preprint arXiv:2112.04359, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.461980Z"},"links":{"cited_paper":"/paper/2112.04359","citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:b50ae28e8d3c23935db4d5aa6ec598754f5e1c14807edabc17815b5ee7117db8","observation_id":"55b5da81-9087-482d-a2af-1c2f5e0765e9","resolution":{"observed_at":"2026-08-12T00:16:04.461980Z","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":"2026-08-12T00:16:06.501945Z","title":"Gallegos, Ryan A","venue":null,"work_id":"812762e5-fe8b-48a9-b720-5dfdd9d21523","year":2024},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.484748Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:dbd555fd02a0d4bee548f144b71829c2bb45c9b6cfe7e6b233bd3f18fa7d0571","observation_id":"baa8b4d8-80c5-49c1-84cf-565da0384096","resolution":{"observed_at":"2026-08-12T00:16:06.505626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:06.492926Z","title":"BOLD: Dataset and metrics for measuring biases in open-ended language generation","venue":null,"work_id":"c635957e-03d3-4991-84d7-503fae3345e0","year":2021},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.509799Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:622852f4ea7a326c982b83d6b04633c2c4c1e37e2b6f441cdbbd000d24aaeb52","observation_id":"90f9c2a5-fdce-475b-a11f-876ed95cc411","resolution":{"observed_at":"2026-08-12T00:16:06.496609Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:06.461243Z","title":null,"venue":null,"work_id":"764b4f8d-195b-45e4-ad54-8f819363b21d","year":2024},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.523188Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:f63260671bebb48363e84c8b52ceab74900c5ccae2a4bbbc474c5c1c44e1b341","observation_id":"adcbc09b-c94e-47e0-84b2-19d0ffeb607b","resolution":{"observed_at":"2026-08-12T00:16:06.484744Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:06.415661Z","title":null,"venue":null,"work_id":"b402c5be-56e5-4dde-82c5-7f9e087e8e7e","year":2025},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.554752Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:a38a19daea224b6da3a55f53c0b123f2bb7d0d833c2fe4b09e244e7f75bc1cfb","observation_id":"c81c6ff9-b6de-4ed9-be55-9a2779df83f1","resolution":{"observed_at":"2026-08-12T00:16:06.445235Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:06.391368Z","title":null,"venue":null,"work_id":"44285ca0-94f0-4b76-8106-a340da9e9520","year":2025},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.604749Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:2d0b5371892c2900625431c288604410832442c2f3056287b603d14673cb98a5","observation_id":"7adb1549-06c1-4468-840d-0203bf14f614","resolution":{"observed_at":"2026-08-12T00:16:06.399934Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:16:06.346384Z","title":"Iskander, K","venue":null,"work_id":"9324315d-2703-4b3d-9d97-35369dc280ed","year":2023},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.643599Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:d4b70e0186385edb54387f024b050eafe912316f05d31ebfa39303b8ed86943a","observation_id":"6a49772b-206c-499c-a907-891d3181c3db","resolution":{"observed_at":"2026-08-12T00:16:06.349326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01405","last_updated":"2025-03-03T06:14:14Z","snapshot_observed_at":"2026-07-06T16:26:38.284922Z","submitted_at":"2023-10-02T17:59:07Z","title":"Representation Engineering: A Top-Down Approach to AI Transparency","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01405","snapshot_observed_at":"2026-08-12T00:16:04.674074Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.674074Z"},"links":{"cited_paper":"/paper/2310.01405","citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:cd562ca145ea9a750c4dc306c8981dd4343486357fe0839d50d2f000b4ce0729","observation_id":"4d34b231-15eb-4128-93a2-4d555a7a078b","resolution":{"observed_at":"2026-08-12T00:16:04.674074Z","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":"2026-08-12T00:16:06.319176Z","title":"Golgoon, K","venue":null,"work_id":"483dd585-1d2b-49ef-a1c6-f72cb9b4eb3a","year":2024},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.685130Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:46b958e6a9920a8d7a041ea2f0676e1b71395a22f5100b053565c9c6e6f826e7","observation_id":"77d36062-9d72-4fe0-b184-f49c24e40424","resolution":{"observed_at":"2026-08-12T00:16:06.325323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.00729","last_updated":"2024-09-13T20:26:40Z","snapshot_observed_at":"2026-08-16T13:22:18.649123Z","submitted_at":"2024-09-01T14:36:36Z","title":"ContextCite: Attributing Model Generation to Context","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.00729","snapshot_observed_at":"2026-08-12T00:16:04.730849Z","title":"Cohen-Wang, H","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.730849Z"},"links":{"cited_paper":"/paper/2409.00729","citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:587e7f7e2a9f9ad659fd93e9a8bb15a9513f55d5c4ad1393ab20f1359c781a1a","observation_id":"dff72fb3-b543-49e0-9093-b40e8c72d1f9","resolution":{"observed_at":"2026-08-12T00:16:04.730849Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.03793","last_updated":"2026-04-17T19:17:37Z","snapshot_observed_at":"2026-07-06T22:08:21.728198Z","submitted_at":"2025-08-05T17:56:51Z","title":"AttnTrace: Contextual Attribution of Prompt Injection and Knowledge Corruption","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.03793","snapshot_observed_at":"2026-08-12T00:16:04.736426Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.736426Z"},"links":{"cited_paper":"/paper/2508.03793","citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:a2953770d7e776c3b3406097ff7023e272ec6c744817b7d90b034c0a122cafeb","observation_id":"70d60840-dd07-4f77-8aeb-28cac61aa006","resolution":{"observed_at":"2026-08-12T00:16:04.736426Z","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":"2026-08-12T00:16:06.279959Z","title":"Webber, A","venue":null,"work_id":"183b03ae-0294-476f-a17e-a771996f9bcc","year":2010},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.742566Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:f47506fff033c14716ce440f0276d838e2062befd1e40540f7eddbd87af38f88","observation_id":"765e4c74-8812-4e6f-97b6-d5712daa7b06","resolution":{"observed_at":"2026-08-12T00:16:06.292352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-12T00:16:04.754821Z","title":"A threshold selection method from gray-level histograms.IEEE Transactions on Systems, Man, and Cybernetics, 9(1):62–66, 1979","venue":null,"work_id":null,"year":1979},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.754821Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:f5596ee5217a06756d6302d957dee8f30e8b1c03925a29bbac6bdcb15bf9924a","observation_id":"1a161460-9fe6-4a2b-804b-60fa499385af","resolution":{"observed_at":"2026-08-12T00:16:04.754821Z","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":"2026-08-12T00:16:04.773729Z","title":"Item recommendation on monotonic behavior chains","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.773729Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:bc82db23b1b76db0e44929a43fa12d7a1a9a2b788abf3a6ff9ba301b7e3bc67e","observation_id":"5eb32153-2432-4fd2-92df-052bc04befef","resolution":{"observed_at":"2026-08-12T00:16:04.773729Z","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":"2026-08-12T00:16:04.784420Z","title":"Maxwell Harper and Joseph A","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.784420Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:ed8802be01647bae8cf9f237695415c7700bed2bb68ec3b22fa9d51daacf7010","observation_id":"8060759f-0bd7-48f0-a967-7ae6ffe34fa1","resolution":{"observed_at":"2026-08-12T00:16:04.784420Z","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":"2026-08-12T00:16:06.261249Z","title":"Game recommendations on steam","venue":null,"work_id":"3c55c48a-140e-40db-ac9c-39b3fdfac10f","year":2021},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.800881Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:d4e6f4c90f3b4eb311705b5ee50d4abc3cf61753fe03c4370a33c7fcfa1019a8","observation_id":"adec04b1-58f6-4044-ba68-772973050e33","resolution":{"observed_at":"2026-08-12T00:16:06.266482Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-12T00:16:04.806728Z","title":"System prompt optimization with meta- learning.arXiv preprint arXiv:2505.09666, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.806728Z"},"links":{"citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:6eaef982b312d6180be82d568121d0bf838db37c29319406c94af1b6fa899df1","observation_id":"e92e78f2-40f4-43c1-82c3-23d2699b433a","resolution":{"observed_at":"2026-08-12T00:16:04.806728Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.10248","last_updated":"2024-10-10T13:20:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-08-20T12:21:05Z","title":"Steering Language Models With Activation Engineering","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.10248","snapshot_observed_at":"2026-08-12T00:16:04.823633Z","title":"The user is a woman","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T00:16:04.823633Z"},"links":{"cited_paper":"/paper/2308.10248","citing_paper":"/paper/2608.08284"},"observation_digest":"sha256:1343c8f9b289e6f1231a2401370aa7d0aa89f2e3b4a23d266535f6b99a6d7fce","observation_id":"5d926c09-71cc-4928-99b9-003410d695e8","resolution":{"observed_at":"2026-08-12T00:16:04.823633Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.08284","last_updated":"2026-08-08T18:32:34Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-19T13:46:25.667040Z","submitted_at":"2026-08-08T18:32:34Z","title":"Fair on the Surface? Benchmarking Hidden-Output Fairness Gaps in LLM Recommenders"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":29,"verified_exact":1,"verified_fuzzy":14},"total_outbound_references":44},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2608.08284."}