{"as_of":"2026-08-11T10:38:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7070cb0cf5305e2573a5f4e6d079f5899cbcfd9d50c58d6fecc5c23ef3b848f5","coverage":[{"denominator":22,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":22,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T20:35:25.728621Z","state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2501.07885/citation-record","integrity":"/paper/2501.07885/integrity","json":"/paper/2501.07885/citation-record.json","paper":"/paper/2501.07885"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T20:35:25.628076Z","title":"A survey on bias and fairness in machine learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.628076Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:0712d1e3ac08a3823a866a855ca2059c9d2788fec8c1a2b34710009f3c878adb","observation_id":"a6329994-6267-415d-ac1d-3edc3755b00b","resolution":{"observed_at":"2026-08-10T20:35:25.628076Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07683","last_updated":"2023-12-07T22:00:59Z","snapshot_observed_at":"2026-08-10T18:12:48.975981Z","submitted_at":"2023-04-16T03:23:55Z","title":"Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07683","snapshot_observed_at":"2026-08-10T20:35:25.633650Z","title":"Fairness and bias in artificial intelligence: A brief survey of sources, impacts, and mitigation strategies,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.633650Z"},"links":{"cited_paper":"/paper/2304.07683","citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:cfb7a8527a5adbe6d0bd6c46ba13c129213cd339935d69366307baa3597debe7","observation_id":"7dede9d2-0f1c-4d84-a363-2a62d6a9a774","resolution":{"observed_at":"2026-08-10T20:35:25.633650Z","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":"2026-08-10T20:35:26.382012Z","title":"Mahoney, K","venue":null,"work_id":"44dbcf7f-e2de-40b5-bdf2-58f01e95478c","year":2020},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.638882Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:0284c1e20d20f3d033db0958e2912be6ee9d9b8785c3fc2535756627549b4254","observation_id":"d07ab902-8fcd-4c2d-a2db-bf75424ae65e","resolution":{"observed_at":"2026-08-10T20:35:26.387526Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:35:26.366500Z","title":"Hardt, E","venue":null,"work_id":"6d4106a0-09af-4432-b5e7-34fd488f1b88","year":2016},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.643526Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:48eec50ef02694b8749ed89758d184a882e86fb1456f48d4ac071517c5f2875b","observation_id":"73f000ce-9e8c-4215-8d84-6687bde93acb","resolution":{"observed_at":"2026-08-10T20:35:26.371514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1109/cc","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T20:35:26.165889Z","title":"Detecting and mitigating algorithmic bias in binary classification using causal modeling,","venue":null,"work_id":"ec7f8156-1506-40d5-9431-f0fa5db38b08","year":2024},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.648203Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:71e38abb2009e275c09ea27adff1eede43f89262a35a3c10af3cd343bac934ee","observation_id":"60262ad0-4aaa-4cbf-a7e9-44180b5d606e","resolution":{"observed_at":"2026-08-10T20:35:26.170416Z","resolver_source":"doi_truncated","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:35:26.350153Z","title":"Putzel and S","venue":null,"work_id":"81d90777-3c9c-4638-abf4-f1699c9442cd","year":null},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.652433Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:17ab6c1a13f3b203945c7447652c375e5f5630326b39495c10a90365efdb467d","observation_id":"5e7fda7f-3e67-4e62-9eb7-5e4262b6de8c","resolution":{"observed_at":"2026-08-10T20:35:26.355004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"document/1060551","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T20:35:26.073030Z","title":"Mitigating Nonlinear Algorithmic Bias in Binary Classification,","venue":null,"work_id":"97615249-6c5c-45a0-bc36-28969d3c44c3","year":2024},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.662478Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:a261c97f6eaff62500a915bb6e9901dc182d9d158e177b634814f738f430c88f","observation_id":"78b82969-ecf8-45a6-94d5-88bc4ff71f8c","resolution":{"observed_at":"2026-08-10T20:35:26.081224Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:35:26.335346Z","title":"Data augmentation for discrimination prevention and bias disambiguation,","venue":null,"work_id":"4c3ad8e2-05a7-4613-af7c-d024fceda578","year":2020},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.666803Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:79b299146b6ba1ffb1da1b32aa4a637bb74352f9557d7c15c9eac91d0c1e1299","observation_id":"f2447299-664e-4486-a10c-d83d86f9663d","resolution":{"observed_at":"2026-08-10T20:35:26.339981Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.01109","last_updated":"2021-03-15T22:55:51Z","snapshot_observed_at":"2026-07-06T10:56:03.985637Z","submitted_at":"2021-03-15T22:55:51Z","title":"AI Fairness via Domain Adaptation","version":1},"cited_work":{"arxiv_id":"2104.01109","doi":null,"metadata_source":"pith","pith_arxiv_id":"2104.01109","snapshot_observed_at":"2026-08-10T20:35:25.983548Z","title":"AI Fairness via Domain Adaptation","venue":"cs.CV","work_id":"c6003691-470b-468d-a20c-9f13c8d5f232","year":2021},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.671187Z"},"links":{"cited_paper":"/paper/2104.01109","citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:a2c690ca4dc5b8585fdb1ad127fd91ae48a4c51efa741b5b592da1c3c621aa59","observation_id":"e4b5c564-ed27-4e31-aade-dad9f6ab51b9","resolution":{"observed_at":"2026-08-10T20:35:25.990185Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:35:26.319895Z","title":"Classification with fairness constraints: A meta-algorithm with provable guarantees,","venue":null,"work_id":"db8ceaae-b36a-495e-b510-24317fbeaffb","year":2019},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.676045Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:08946a7ecf9d6d1b0b4f06318e62a4d99cb5095e3135ef16e44c19e2d82db549","observation_id":"c6cd6a36-2b92-4782-aa86-887a8dcb1303","resolution":{"observed_at":"2026-08-10T20:35:26.324694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1707.00075","last_updated":"2017-07-07T01:31:36Z","snapshot_observed_at":"2026-07-06T05:49:19.425378Z","submitted_at":"2017-07-01T01:09:33Z","title":"Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.00075","snapshot_observed_at":"2026-08-10T20:35:25.680631Z","title":"Beutel, J","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.680631Z"},"links":{"cited_paper":"/paper/1707.00075","citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:82e29696e06fe74c2b8e311d87bfd30f87f82861a0debf8d99b61bfa54bec57b","observation_id":"e2191966-4b57-4049-9850-993c6ac4551a","resolution":{"observed_at":"2026-08-10T20:35:25.680631Z","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":"2026-08-10T20:35:26.304794Z","title":null,"venue":null,"work_id":"26ff229c-4e89-4842-b77b-f52230a2fd7e","year":2022},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.685845Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:96b55c7eb4da6766d21daffffc3503f113a948f70af6788f03f971a4faaffea6","observation_id":"8f9263cd-56f7-4bee-b783-0bd78fa88849","resolution":{"observed_at":"2026-08-10T20:35:26.309839Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:35:26.289326Z","title":"Direct and indirect effects,","venue":null,"work_id":"09823583-6c4f-4d66-a254-e8af3a4e1e33","year":2001},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.690519Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:c1263e65199e96f88084caa41da643c4dc59e4acb8cba651fee0509ed104b76a","observation_id":"123ab1f2-b42c-4897-966c-dba4c85cbc58","resolution":{"observed_at":"2026-08-10T20:35:26.294262Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:35:25.695211Z","title":"Pearl, Causality","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.695211Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:007258821832c6df5948de101891bc5401ad1a666d0379b3ff5727be97b7d486","observation_id":"38edef7c-1451-47b4-a9cd-a91fb0c4ef13","resolution":{"observed_at":"2026-08-10T20:35:25.695211Z","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":"2026-08-10T20:35:26.263726Z","title":"Counterfactual fairness,","venue":null,"work_id":"c24aaf5c-343a-4f2c-a702-b0498ea9253a","year":2017},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.699651Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:cff4eac28790298dc5aa22185c3c6cb58df88a5fc4cdc32074c7c3c03fcbcdae","observation_id":"e3843b8c-4a80-4f30-88d8-149e1672f708","resolution":{"observed_at":"2026-08-10T20:35:26.268268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:35:25.704067Z","title":"Fairness through causal awareness: Learning causal latent-variable models for biased data,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.704067Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:ad083435d46bc4d734633d10cc68130ec8922d76a62ba87edb2ce138957ca70f","observation_id":"06887638-8181-4044-8350-c65ada131670","resolution":{"observed_at":"2026-08-10T20:35:25.704067Z","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":"2026-08-10T20:35:26.247807Z","title":"Fairness in algorithmic decision making: An excursion through the lens of causality,","venue":null,"work_id":"40139be2-b5b6-4d70-9fce-1faa93fbe62a","year":2019},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.709209Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:2bd647734fef81bfd47ff3bf1beaee8940d5cd413ac1413c828030002deed47a","observation_id":"243ea819-b3f9-4f6b-a917-8152a66bf8e4","resolution":{"observed_at":"2026-08-10T20:35:26.253349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:35:26.231512Z","title":"Available: https://huggingface.co/datasets/HuggingF aceM4/FairFace","venue":null,"work_id":"a2b9fb61-7518-47c4-990b-678b651a20bb","year":null},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.714128Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:aa785c99d645fd01824a7f68ae067c8226a0adbd3c804fbc263305797af15ce6","observation_id":"972e411a-bf62-49aa-960e-c1e62470b925","resolution":{"observed_at":"2026-08-10T20:35:26.236618Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:35:26.214302Z","title":"Available: https://github.com/serengil/deepface","venue":null,"work_id":"c03038be-aaa1-4cb4-b72b-e291e489cafa","year":null},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.719067Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:ac1ba6709be137b86a6be16b1ac085f903a0f7ea46bb4e3f694a6c5c12f9f52d","observation_id":"3b5f6398-743b-46d1-84b6-0142f6704602","resolution":{"observed_at":"2026-08-10T20:35:26.219724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T20:35:25.723983Z","title":"Transforming classifier scores into accurate multiclass probability estimates,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.723983Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:22d23c24be7e1c3c30769b5d9ba6281db99ae3b07b65f92f36d8a27336065f1c","observation_id":"9b2e4d47-0115-44b6-ad45-9fe0a1627169","resolution":{"observed_at":"2026-08-10T20:35:25.723983Z","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":"2026-08-10T20:35:26.197190Z","title":"Zhang and L","venue":null,"work_id":"9179fa60-45fc-4e2c-a1da-14d156456654","year":null},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.728621Z"},"links":{"citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:568d921500660073cf57d038f36a4917c479e93a51762963a62422a45ce48abc","observation_id":"ceaab53c-83a1-42c1-821c-04ceeb448be4","resolution":{"observed_at":"2026-08-10T20:35:26.202116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.04461","last_updated":"2022-01-12T13:21:20Z","snapshot_observed_at":"2026-08-08T00:31:09.583852Z","submitted_at":"2022-01-12T13:21:20Z","title":"Blackbox Post-Processing for Multiclass Fairness","version":1},"cited_work":{"arxiv_id":"2201.04461","doi":null,"metadata_source":"pith","pith_arxiv_id":"2201.04461","snapshot_observed_at":"2026-08-10T20:35:26.098398Z","title":"Blackbox Post-Processing for Multiclass Fairness","venue":"cs.LG","work_id":"45d783d6-6b29-40c9-bc25-c0edb48683f1","year":2022},"citing_paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-10T20:35:25.657169Z"},"links":{"cited_paper":"/paper/2201.04461","citing_paper":"/paper/2501.07885"},"observation_digest":"sha256:b0638c3df8093bc6272ec165cd21ae96c0c5f377c6e02b8625db33c1714b876d","observation_id":"a24906b2-092d-48a3-8b4c-1dbfca8a9be9","resolution":{"observed_at":"2026-08-10T20:35:26.103145Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.07885","last_updated":"2025-01-14T06:51:27Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T20:27:35.052393Z","submitted_at":"2025-01-14T06:51:27Z","title":"Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling"},"reference_resolution":{"displayed":22,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":7,"verified_exact":2,"verified_fuzzy":11},"total_outbound_references":22},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2501.07885."}