{"as_of":"2026-08-15T23:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e231899cea873f2dc264f04fcacd7b1893fe4b468b234de4c2748029366acc48","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":5,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":5,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+00:00","state":"measured"},{"denominator":5,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T21:54:44.064381Z","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":"2026-05-20T19:03:39.513287Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2110.08527","last_updated":"2022-04-03T00:08:13Z","snapshot_observed_at":"2026-08-15T20:09:19.010539Z","submitted_at":"2021-10-16T09:40:30Z","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.08527","snapshot_observed_at":"2026-08-12T21:54:44.064381Z","title":"An empirical su rvey of the effectiveness of debiasing techniques for pre-t rained language models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.08181","last_updated":"2024-12-04T16:55:18Z","snapshot_observed_at":"2026-08-14T11:20:53.014041Z","submitted_at":"2024-11-12T20:57:12Z","title":"Challenges in Guardrailing Large Language Models for Science","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T21:54:44.064381Z"},"links":{"cited_paper":"/paper/2110.08527","citing_paper":"/paper/2411.08181"},"observation_digest":"sha256:0d111a38eeedca079c1eac187e3170aee364f0583a652d4bbd59d0ef70bcee16","observation_id":"0120ee3b-f2bc-41bb-b8d2-b35ff506f87e","resolution":{"observed_at":"2026-08-12T21:54:44.064381Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.08527","last_updated":"2022-04-03T00:08:13Z","snapshot_observed_at":"2026-08-15T20:09:19.010539Z","submitted_at":"2021-10-16T09:40:30Z","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.08527","snapshot_observed_at":"2026-08-12T19:46:44.570628Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.10351","last_updated":"2025-03-07T18:59:21Z","snapshot_observed_at":"2026-08-14T18:59:42.294876Z","submitted_at":"2024-11-15T16:55:57Z","title":"Bias Unveiled: Investigating Social Bias in LLM-Generated Code","version":4},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-12T19:46:44.570628Z"},"links":{"cited_paper":"/paper/2110.08527","citing_paper":"/paper/2411.10351"},"observation_digest":"sha256:c12d6bf14bc31adca95b75776d1a1b5486ff901876c16c5aaa9ac60c00195631","observation_id":"460f0386-c0a1-49de-9ce1-110c8fb804b9","resolution":{"observed_at":"2026-08-12T19:46:44.570628Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.08527","last_updated":"2022-04-03T00:08:13Z","snapshot_observed_at":"2026-08-15T20:09:19.010539Z","submitted_at":"2021-10-16T09:40:30Z","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.08527","snapshot_observed_at":"2026-08-05T12:32:13.548435Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.01535","last_updated":"2025-09-09T04:01:50Z","snapshot_observed_at":"2026-08-10T18:54:57.967074Z","submitted_at":"2025-09-01T15:13:15Z","title":"CAT: Causal Attention Tuning For Injecting Fine-grained Causal Knowledge into Large Language Models","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-05T12:32:13.548435Z"},"links":{"cited_paper":"/paper/2110.08527","citing_paper":"/paper/2509.01535"},"observation_digest":"sha256:30f4a149618a42419431e645d6de5b01f29a3b4d4453387ca51c783a77b3779e","observation_id":"6714122a-a1f8-4f8e-b121-a1186bb6a614","resolution":{"observed_at":"2026-08-05T12:32:13.548435Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.08527","last_updated":"2022-04-03T00:08:13Z","snapshot_observed_at":"2026-08-15T20:09:19.010539Z","submitted_at":"2021-10-16T09:40:30Z","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","version":3},"cited_work":{"arxiv_id":"2110.08527","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.08527","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2110.08527 , year=","venue":null,"work_id":"66bb2dff-cd30-4013-9ab8-2c6708b32102","year":2021},"citing_paper":{"arxiv_id":"2605.00382","last_updated":"2026-05-05T08:05:07Z","snapshot_observed_at":"2026-08-14T01:49:28.508000Z","submitted_at":"2026-05-01T04:06:02Z","title":"Social Bias in LLM-Generated Code: Benchmark and Mitigation","version":3},"reference_index":149,"source":"arxiv_source","source_observed_at":"2026-05-09T19:34:51.433422Z"},"links":{"cited_paper":"/paper/2110.08527","citing_paper":"/paper/2605.00382"},"observation_digest":"sha256:6c20fb2f5b5a8d7b2c62ae37c35877bdf945e6e696783a2b23acd1d84b37c441","observation_id":"183d18d1-28ae-426e-a6a2-9cdb9b84da9e","resolution":{"observed_at":"2026-05-11T15:36:08.804040Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.08527","last_updated":"2022-04-03T00:08:13Z","snapshot_observed_at":"2026-08-15T20:09:19.010539Z","submitted_at":"2021-10-16T09:40:30Z","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models","version":3},"cited_work":{"arxiv_id":"2110.08527","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.08527","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2110.08527 , year=","venue":null,"work_id":"66bb2dff-cd30-4013-9ab8-2c6708b32102","year":2021},"citing_paper":{"arxiv_id":"2605.16113","last_updated":"2026-05-15T15:58:10Z","snapshot_observed_at":"2026-08-14T01:11:46.445598Z","submitted_at":"2026-05-15T15:58:10Z","title":"DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-20T19:02:47.017761Z"},"links":{"cited_paper":"/paper/2110.08527","citing_paper":"/paper/2605.16113"},"observation_digest":"sha256:75c79bf72a5a924321380fd8dd10962453712561da96346d416006bdbec34447","observation_id":"65d66880-c10b-4c26-8ab5-6a9cc0ca15d5","resolution":{"observed_at":"2026-05-20T19:03:39.514963Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2110.08527/citation-record","integrity":"/paper/2110.08527/integrity","json":"/paper/2110.08527/citation-record.json","paper":"/paper/2110.08527"},"outbound":[],"paper":{"arxiv_id":"2110.08527","last_updated":"2022-04-03T00:08:13Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-15T20:09:19.010539Z","submitted_at":"2021-10-16T09:40:30Z","title":"An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:2110.08527."}