{"as_of":"2026-08-07T23:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:510e430c391f4d0c12ab70381af72de00efb0a62c1b7fb7e1fa4396d331fb214","coverage":[{"denominator":12,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T04:18:35.273492Z","state":"measured"},{"denominator":16,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":16,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:34:55.741915Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T02:49:25.205923Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.10922","snapshot_observed_at":"2026-08-06T19:34:55.741915Z","title":"30 When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors T","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.05246","last_updated":"2025-07-07T17:54:52Z","snapshot_observed_at":"2026-08-06T19:26:32.984962Z","submitted_at":"2025-07-07T17:54:52Z","title":"When Chain of Thought is Necessary, Language Models Struggle to Evade Monitors","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T19:34:55.741915Z"},"links":{"cited_paper":"/paper/2506.10922","citing_paper":"/paper/2507.05246"},"observation_digest":"sha256:6e2e4234f66a8a8b4ca426776a8f32ca2cbf0863ebd22f5617f5f8c4babc600d","observation_id":"b5cb2b18-bf5b-4cb2-a368-6079c85538e4","resolution":{"observed_at":"2026-08-06T19:34:55.741915Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.10922","snapshot_observed_at":"2026-08-03T01:20:07.487646Z","title":"Robustly improving llm fairness in realistic settings via interpretability, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2602.10117","last_updated":"2026-05-29T17:54:32Z","snapshot_observed_at":"2026-08-03T01:20:05.847701Z","submitted_at":"2026-02-10T18:59:56Z","title":"Biases in the Blind Spot: Detecting What LLMs Fail to Mention","version":5},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T01:20:07.487646Z"},"links":{"cited_paper":"/paper/2506.10922","citing_paper":"/paper/2602.10117"},"observation_digest":"sha256:aa2c82194528c29782279f83301ad90b19420bb7026468869cdcf5bd62d6d2a0","observation_id":"3d41ad85-7460-4f61-bd0f-d3b7029a0480","resolution":{"observed_at":"2026-08-03T01:20:07.487646Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"cited_work":{"arxiv_id":"2506.10922","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.10922","snapshot_observed_at":"2026-07-04T02:49:25.205923Z","title":"Robustly improving llm fairness in realistic settings via interpretability","venue":null,"work_id":"7ae7372c-e9f6-4b01-ac09-9907baf2995e","year":2025},"citing_paper":{"arxiv_id":"2604.08525","last_updated":"2026-04-09T17:57:50Z","snapshot_observed_at":"2026-07-06T22:57:35.435713Z","submitted_at":"2026-04-09T17:57:50Z","title":"Ads in AI Chatbots? An Analysis of How Large Language Models Navigate Conflicts of Interest","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-05-10T17:11:13.189660Z"},"links":{"cited_paper":"/paper/2506.10922","citing_paper":"/paper/2604.08525"},"observation_digest":"sha256:f909051cb60ad25dd83640f2ee1ab8d4460dc9eb2ca6b3ef3b6c96a194dfd883","observation_id":"d184ba1b-a8be-4a5f-863d-2dd155580bfc","resolution":{"observed_at":"2026-05-11T07:26:02.249650Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"cited_work":{"arxiv_id":"2506.10922","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.10922","snapshot_observed_at":"2026-07-04T02:49:25.205923Z","title":"Robustly improving llm fairness in realistic settings via interpretability","venue":null,"work_id":"7ae7372c-e9f6-4b01-ac09-9907baf2995e","year":2025},"citing_paper":{"arxiv_id":"2606.18649","last_updated":"2026-06-17T03:33:25Z","snapshot_observed_at":"2026-08-06T08:39:21.941113Z","submitted_at":"2026-06-17T03:33:25Z","title":"Gender Bias in LLM Hiring Decisions: Evidence from a Japanese Context and Evaluation of Mitigation Strategies","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-26T18:57:43.012369Z"},"links":{"cited_paper":"/paper/2506.10922","citing_paper":"/paper/2606.18649"},"observation_digest":"sha256:c9eccf0dcfdc54753e6a795b7d94f6726e37ff8e4df71a914e8fbdaefeab514a","observation_id":"c9b1b196-d0a5-4b8c-b08c-abbc02fc9cf2","resolution":{"observed_at":"2026-07-04T02:49:25.207323Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.10922/citation-record","integrity":"/paper/2506.10922/integrity","json":"/paper/2506.10922/citation-record.json","paper":"/paper/2506.10922"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:38.379053Z","title":null,"venue":null,"work_id":"c7efe65f-93f4-476f-9f15-c2f3f1fa03a7","year":2004},"citing_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:33.789845Z"},"links":{"citing_paper":"/paper/2506.10922"},"observation_digest":"sha256:3b978855d4cddbc13b18e136a8346dd4499485fb33e9927cfc98d72703ad7458","observation_id":"b513dae3-75aa-45d7-850b-0c0bec077196","resolution":{"observed_at":"2026-08-07T04:18:38.571581Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:18:38.087735Z","title":null,"venue":null,"work_id":"e51a433f-153e-4256-9b49-8e7ed900cd7b","year":null},"citing_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:33.924391Z"},"links":{"citing_paper":"/paper/2506.10922"},"observation_digest":"sha256:0047eb88711a5cf3d547873b5ef161b87e03c1836149771739da384104afbedb","observation_id":"678282f1-1739-4db3-bdc3-e7dbc7ce51ab","resolution":{"observed_at":"2026-08-07T04:18:38.239137Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:18:37.771683Z","title":null,"venue":null,"work_id":"efbea1dc-e918-4581-a2b7-eb27096b1ef0","year":null},"citing_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:34.098662Z"},"links":{"citing_paper":"/paper/2506.10922"},"observation_digest":"sha256:5eccf66600a4a84c2b9a323eb47202d372c89daa297191742cb161d7e1435b63","observation_id":"88db4111-061a-4f40-8fe0-79f7effeadda","resolution":{"observed_at":"2026-08-07T04:18:37.936451Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:18:37.539848Z","title":null,"venue":null,"work_id":"68fef93d-bc71-4a36-90cc-c8e6117e1819","year":null},"citing_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:34.249163Z"},"links":{"citing_paper":"/paper/2506.10922"},"observation_digest":"sha256:739a44de214c7afd0c7df73e4505a50fbc09d27e14ddb3b55adf1bcefabe298b","observation_id":"42dc0808-fe27-486c-8da7-936ef5b93001","resolution":{"observed_at":"2026-08-07T04:18:37.664027Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:18:37.246006Z","title":null,"venue":null,"work_id":"6cd9cd9d-e7b9-4107-8a5c-14f078190f99","year":null},"citing_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:34.431618Z"},"links":{"citing_paper":"/paper/2506.10922"},"observation_digest":"sha256:d05dbd206293c05d0f22cd1dd57655af8c02c003c37d91c307e3ae7147ef75d6","observation_id":"92430ae4-cb81-4f45-a3f6-ff663b2ce928","resolution":{"observed_at":"2026-08-07T04:18:37.399810Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:18:36.951548Z","title":null,"venue":null,"work_id":"6c3317f6-fad8-4a85-af76-6507d3eaec30","year":null},"citing_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:34.562242Z"},"links":{"citing_paper":"/paper/2506.10922"},"observation_digest":"sha256:54c62c04297e75c9237c08a6e088dd1ffb7929a9173771c880a640427831fd63","observation_id":"4b9e6f59-290b-47e1-ba7d-a6b593daca2b","resolution":{"observed_at":"2026-08-07T04:18:37.080267Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:18:36.685641Z","title":null,"venue":null,"work_id":"f5f0e6f8-c9ed-4bd1-8a9d-29578f380e87","year":null},"citing_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:34.756518Z"},"links":{"citing_paper":"/paper/2506.10922"},"observation_digest":"sha256:ebd4b91bdc198f96c29fd464aa8054b925b865616b438f2e71d290dd6c39badb","observation_id":"8cba65c7-996a-427e-9e9d-328cf1e5d5d3","resolution":{"observed_at":"2026-08-07T04:18:36.812543Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:18:36.308692Z","title":null,"venue":null,"work_id":"c5e159e7-51dd-43a9-9c17-f33a8cb62eb2","year":null},"citing_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:34.918481Z"},"links":{"citing_paper":"/paper/2506.10922"},"observation_digest":"sha256:09895c633a7d27c996e9a24032fcbcddd1a4ff28e9a81410aa2b7fc66b620122","observation_id":"0ec5b0ae-f43d-453f-9ed0-63dec65fda68","resolution":{"observed_at":"2026-08-07T04:18:36.491245Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:18:36.007999Z","title":null,"venue":null,"work_id":"67bddffb-0d45-4828-aba7-28b7c37e92a9","year":null},"citing_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:35.047403Z"},"links":{"citing_paper":"/paper/2506.10922"},"observation_digest":"sha256:3ad992fddf183ecbc5631a66bd8827e516bc89ff57691b0c939d74c2807c34f9","observation_id":"7fd4468d-0ad2-438d-9b21-c7447b16accc","resolution":{"observed_at":"2026-08-07T04:18:36.187909Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:18:35.716993Z","title":null,"venue":null,"work_id":"997c0c94-4f44-4758-8089-a74cb769c9f0","year":null},"citing_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:35.147515Z"},"links":{"citing_paper":"/paper/2506.10922"},"observation_digest":"sha256:d27f334be90e7c26dda468a36ac38e114eeba4b55c1923c7393dd86e95db4be0","observation_id":"34c0ec5f-8171-49ef-b6d8-ad7ba90d1823","resolution":{"observed_at":"2026-08-07T04:18:35.866522Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:18:35.445731Z","title":"highly competitive","venue":null,"work_id":"68c2f703-89c5-4ee2-b8c6-8e33e5cb8e5a","year":2004},"citing_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:35.273492Z"},"links":{"citing_paper":"/paper/2506.10922"},"observation_digest":"sha256:13f1a64c3fc17c29bd58fc5bb99da31f9003946cfb494ec66dae0ee78e4b66aa","observation_id":"e5898876-3473-4e73-b335-f209089629f2","resolution":{"observed_at":"2026-08-07T04:18:35.594889Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07882","last_updated":"2024-10-14T17:46:28Z","snapshot_observed_at":"2026-07-06T18:29:21.709395Z","submitted_at":"2024-06-12T05:20:16Z","title":"Designing a Dashboard for Transparency and Control of Conversational AI","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07882","snapshot_observed_at":"2026-08-07T04:18:33.646142Z","title":"yes” and “no","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability","version":1},"reference_index":9203,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:33.646142Z"},"links":{"cited_paper":"/paper/2406.07882","citing_paper":"/paper/2506.10922"},"observation_digest":"sha256:2729852ee5b660fb91d7fb70ade608403983553e69ee29d6627d1545551a1182","observation_id":"b9afb0f9-c4cc-4efd-afd8-86a0355162a3","resolution":{"observed_at":"2026-08-07T04:18:33.646142Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.10922","last_updated":"2025-06-12T17:34:38Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T04:11:28.799257Z","submitted_at":"2025-06-12T17:34:38Z","title":"Robustly Improving LLM Fairness in Realistic Settings via Interpretability"},"reference_resolution":{"displayed":12,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":0,"verified_fuzzy":1},"total_outbound_references":12},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 4 inbound Pith citation observations for arXiv:2506.10922."}