{"as_of":"2026-08-19T08:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:16a369ae85dea4309a4de132700de8c00f493f5033e1efadc620448151fdb469","coverage":[{"denominator":49,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":49,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:24:45.661930Z","state":"measured"},{"denominator":50,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":50,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T19:05:28.806009Z","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":"2026-06-28T19:12:34.989967Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"cited_work":{"arxiv_id":"2505.07351","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.07351","snapshot_observed_at":"2026-06-28T19:12:34.989967Z","title":null,"venue":null,"work_id":"5a436a25-323a-4add-add6-b6eeb19406ed","year":2025},"citing_paper":{"arxiv_id":"2606.00503","last_updated":"2026-05-30T03:36:03Z","snapshot_observed_at":"2026-08-14T22:18:10.402980Z","submitted_at":"2026-05-30T03:36:03Z","title":"TabChange: Precise Attribute Changes in Tabular Data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-28T19:05:28.806009Z"},"links":{"cited_paper":"/paper/2505.07351","citing_paper":"/paper/2606.00503"},"observation_digest":"sha256:e15eb99d348c4d4bdd25edf701ae8b504a9a078d5f0028a3451135282ddf83f4","observation_id":"71a3d70f-308b-4d54-bed7-0d4e9317cae7","resolution":{"observed_at":"2026-06-28T19:12:34.991125Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2505.07351/citation-record","integrity":"/paper/2505.07351/integrity","json":"/paper/2505.07351/citation-record.json","paper":"/paper/2505.07351"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:24:45.434299Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.434299Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:bcc5d3f1b50829f7f79d78157f9cdfef5c29e6e49e873c9188a8190032716c75","observation_id":"152df9bf-488c-467e-bba9-842d8dd01c51","resolution":{"observed_at":"2026-08-15T22:24:45.434299Z","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":"2026-08-15T22:24:46.518035Z","title":"M achine B ias --- propublica.org, 2016","venue":null,"work_id":"d934fa6a-28f1-4511-bd9b-4d2c79dde955","year":2016},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.441107Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:f730f5cf712eca14f48ba41fa264d981e22e113be9e9d9aa4709c6a9873555e9","observation_id":"6334bb49-4fe2-42f4-bbaf-909953c37bdb","resolution":{"observed_at":"2026-08-15T22:24:46.523371Z","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":"2006.06848","last_updated":"2021-03-18T11:26:59Z","snapshot_observed_at":"2026-08-17T16:58:08.665315Z","submitted_at":"2020-06-11T21:53:15Z","title":"Getting a CLUE: A Method for Explaining Uncertainty Estimates","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.06848","snapshot_observed_at":"2026-08-15T22:24:45.445981Z","title":"Getting a clue: A method for explaining uncertainty estimates","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.445981Z"},"links":{"cited_paper":"/paper/2006.06848","citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:796da081e1452c7384f5996679224c5c6338475ec4ac6b4269dc17dadd743b66","observation_id":"7d56bcaf-8c26-4675-aa10-8610b40ae03d","resolution":{"observed_at":"2026-08-15T22:24:45.445981Z","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":"2026-08-15T22:24:45.451595Z","title":"Fairness and Machine Learning: Limitations and Opportunities","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.451595Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:6ecbbecbd8dc77be0705620ced07f78ecd6d84f74ff3200d3430e222806cea68","observation_id":"c56c1db8-c318-492b-9c49-bd017e9ea26f","resolution":{"observed_at":"2026-08-15T22:24:45.451595Z","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":"2026-08-15T22:24:45.458940Z","title":null,"venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.458940Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:37b484dccffa2a8a52cb2dd720c2550aba3b67b3e62c0a4eebcd6d80b621c244","observation_id":"f4fa2a71-060b-46ef-b328-cb9b3881c4f5","resolution":{"observed_at":"2026-08-15T22:24:45.458940Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.18875","last_updated":"2024-05-29T08:35:17Z","snapshot_observed_at":"2026-08-16T13:48:17.889966Z","submitted_at":"2024-05-29T08:35:17Z","title":"Counterfactual Metarules for Local and Global Recourse","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.18875","snapshot_observed_at":"2026-08-15T22:24:45.463540Z","title":"Amoukou, Saumitra Mishra, Daniele Magazzeni, and Manuela Veloso","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.463540Z"},"links":{"cited_paper":"/paper/2405.18875","citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:840a3bfdadc15602cfa9925cbe4f946cf5308801ebaf9f3bb3b477b1a1403f35","observation_id":"ae663e55-21a9-41d2-9d59-b894cfb96f9f","resolution":{"observed_at":"2026-08-15T22:24:45.463540Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.03109","last_updated":"2021-10-06T23:48:55Z","snapshot_observed_at":"2026-08-18T12:41:34.914187Z","submitted_at":"2021-10-06T23:48:55Z","title":"Consistent Counterfactuals for Deep Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.03109","snapshot_observed_at":"2026-08-15T22:24:45.468960Z","title":"Consistent counterfactuals for deep models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.468960Z"},"links":{"cited_paper":"/paper/2110.03109","citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:73c7cc08acd6fdabe2d2b99e68c84c8c696f2b2539207fe1f4289c9aea7123d9","observation_id":"4a089fe4-c5ef-498e-9363-78a4b2e0a90b","resolution":{"observed_at":"2026-08-15T22:24:45.468960Z","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":"2026-08-15T22:24:45.479071Z","title":"Breunig, Hans-Peter Kriegel, Raymond T","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.479071Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:512e39f57a0508db68c9bb5d48695ae4188d7fafbf6a027b565c2f7663fac387","observation_id":"8b517e43-2df1-475d-bb2b-e9784cde87d5","resolution":{"observed_at":"2026-08-15T22:24:45.479071Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.06615","last_updated":"2022-01-20T05:25:43Z","snapshot_observed_at":"2026-07-06T08:51:19.378706Z","submitted_at":"2020-01-18T06:52:47Z","title":"The Risk to Population Health Equity Posed by Automated Decision Systems: A Narrative Review","version":2},"cited_work":{"arxiv_id":"2001.06615","doi":null,"metadata_source":"pith","pith_arxiv_id":"2001.06615","snapshot_observed_at":"2026-08-15T22:24:45.962024Z","title":"The Risk to Population Health Equity Posed by Automated Decision Systems: A Narrative Review","venue":"cs.CY","work_id":"2d35ddc7-81e3-46ec-bf1f-c1638085e231","year":2020},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.483211Z"},"links":{"cited_paper":"/paper/2001.06615","citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:4e6992b997b356783ca81dd03648d783d6f0e60a7a2697c1784f9e582d54a296","observation_id":"7c17bc91-4900-420d-8059-b392a38cc4a3","resolution":{"observed_at":"2026-08-15T22:24:45.967830Z","resolver_source":"local_arxiv","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":"2026-08-15T22:24:46.491485Z","title":"On the adversarial robustness of causal algorithmic recourse","venue":null,"work_id":"20ea7cc4-89f0-4f4a-a68a-9fb9e2063df2","year":2022},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.487753Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:5f6f259faaaf27e8ca852bd84f31f9e35dc6792c4c9e0c613210d1cede2061ae","observation_id":"b7d07875-6049-4b48-8079-e4cdd91c8f0a","resolution":{"observed_at":"2026-08-15T22:24:46.496506Z","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":"2026-08-15T22:24:46.479466Z","title":"Cruds: Counterfactual recourse using disentangled subspaces","venue":null,"work_id":"43f3e83d-dedf-4e66-b032-9749661488ba","year":2020},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.491836Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:9deb1d775f769dd7888be0225fefb1da801c93b6e9e836d2aa70ed6088d0449d","observation_id":"cea2695d-ce4e-46b9-a011-165e0988ff83","resolution":{"observed_at":"2026-08-15T22:24:46.483745Z","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":"2026-08-15T22:24:46.463762Z","title":"Bail or jail? judicial versus algorithmic decision-making in the pretrial system","venue":null,"work_id":"47227514-a7f7-40eb-a602-5693dd0bde25","year":2019},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.495848Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:05077357f3627a0a2eb41474515cd24ef560a252e3e964f311cff56bcf70733a","observation_id":"2d74e562-57a6-41ef-aaff-efef6fdd519a","resolution":{"observed_at":"2026-08-15T22:24:46.468310Z","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":"2026-08-15T22:24:46.449848Z","title":"Fico xml challenge","venue":null,"work_id":"23d7c2fe-559c-4954-98e3-c3e7fc30f118","year":2018},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.499890Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:807058243a7eb3089ca7dceca2f5b0c7d1605fe4217ae99ba9d03a836b59b62c","observation_id":"2f9f5bf2-69bb-4e6d-9f52-6dd13c565cde","resolution":{"observed_at":"2026-08-15T22:24:46.454335Z","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":"2026-08-15T22:24:46.433457Z","title":"The risks of recourse in binary classification","venue":null,"work_id":"c6b7762e-96a8-48ba-87d8-d5acf8d8f01d","year":2024},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.503575Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:6270d70b3cd36d990ef4545c4a9ad27d619d1d4468eb14c432285bab2f3af1cc","observation_id":"52ab1f40-beb3-4eb6-bf6a-154679e31138","resolution":{"observed_at":"2026-08-15T22:24:46.437870Z","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":"2405.11195","last_updated":"2024-05-18T06:14:00Z","snapshot_observed_at":"2026-08-17T17:46:24.353140Z","submitted_at":"2024-05-18T06:14:00Z","title":"Trustworthy Actionable Perturbations","version":1},"cited_work":{"arxiv_id":"2405.11195","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.11195","snapshot_observed_at":"2026-08-15T22:24:45.944306Z","title":"Trustworthy Actionable Perturbations","venue":"cs.LG","work_id":"aada787d-fbc0-4618-8fc2-1f25cad1435b","year":2024},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.507381Z"},"links":{"cited_paper":"/paper/2405.11195","citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:d8a778dec435e5019845370f5fb3475d645e68577548a895cee47c263019aea3","observation_id":"5d5163c7-43d4-4a41-b512-889ae7b6655d","resolution":{"observed_at":"2026-08-15T22:24:45.948735Z","resolver_source":"local_arxiv","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":"2026-08-15T22:24:46.419719Z","title":"On the impact of algorithmic recourse on social segregation","venue":null,"work_id":"51d97bd2-c428-41dd-941b-159ee72e61ef","year":2024},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.511893Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:8210dadb419bdf644c9f26569aea7a757dfbec2eebb1f67030fa60875033008e","observation_id":"55419f02-79e9-4e30-8aa1-e1270da035e7","resolution":{"observed_at":"2026-08-15T22:24:46.424185Z","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":"2026-08-15T22:24:46.405336Z","title":"Robust counterfactual explanations for neural networks with probabilistic guarantees","venue":null,"work_id":"432f229d-2554-4626-83af-2b901ecb3aa3","year":2023},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.515823Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:0dc53af2ae34c05aa7efe06ad58f5c991d02687e13b2ee3f82f511ad64c77233","observation_id":"7a9e3464-7f04-44d4-ae6a-8662914f4132","resolution":{"observed_at":"2026-08-15T22:24:46.410169Z","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":"2026-08-15T22:24:46.392034Z","title":"Strategic classification","venue":null,"work_id":"9bac022b-0203-4487-9d3e-179bb980a42b","year":2016},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.519911Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:6fb89fa94ce18e7e632c24537a8c91ca85482e11933187f6ab925f7f5292e302","observation_id":"f3dd1b21-0b89-4a31-8093-8c5df2a47c93","resolution":{"observed_at":"2026-08-15T22:24:46.396164Z","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":"1907.09615","last_updated":"2019-07-22T22:35:51Z","snapshot_observed_at":"2026-08-15T13:38:56.059585Z","submitted_at":"2019-07-22T22:35:51Z","title":"Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.09615","snapshot_observed_at":"2026-08-15T22:24:45.523899Z","title":"Towards realistic individual recourse and actionable explanations in black-box decision making systems","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.523899Z"},"links":{"cited_paper":"/paper/1907.09615","citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:c57f84e292f763a03ea60bbc6302e2d20b245b2617eb6292705dd145dbf034c2","observation_id":"e6816b5f-6da5-4395-8d75-caa7b5844e61","resolution":{"observed_at":"2026-08-15T22:24:45.523899Z","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":"2026-08-15T22:24:46.378437Z","title":"Leveraging ai and ml to automate financial predictions and recommendations","venue":null,"work_id":"87b4a1e4-3847-40ab-af2f-dbeeefa0b259","year":2024},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.528530Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:d34c99e8734b803f2f9accdb8920018995b2bef2f0429e9f85d2c846503ce6e5","observation_id":"30fdceeb-32f6-493b-877b-fc2cdb734f07","resolution":{"observed_at":"2026-08-15T22:24:46.382556Z","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":"record/1128984","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:24:45.909297Z","title":"the right to explanation, explained","venue":null,"work_id":"761474ea-c037-4670-b4a0-a0bca01f30bc","year":2019},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.532406Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:c8daec30074fb66652347a57f5a3c689978d8c70a1fe0ee17a892934b1a9870a","observation_id":"f2ce44fd-86f8-4645-9528-3e261ca5b450","resolution":{"observed_at":"2026-08-15T22:24:45.917232Z","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":{"arxiv_id":"2406.01098","last_updated":"2024-06-03T08:33:42Z","snapshot_observed_at":"2026-08-16T13:46:50.799042Z","submitted_at":"2024-06-03T08:33:42Z","title":"Learning Decision Trees and Forests with Algorithmic Recourse","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.01098","snapshot_observed_at":"2026-08-15T22:24:45.535982Z","title":"Learning decision trees and forests with algorithmic recourse","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.535982Z"},"links":{"cited_paper":"/paper/2406.01098","citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:668607965392672515f7e42dbbea9d943482e52182a0aa18d69fc1f9d6cdd3ee","observation_id":"03fbe394-78f4-449a-b0ef-57eaa6640d05","resolution":{"observed_at":"2026-08-15T22:24:45.535982Z","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":"2026-08-15T22:24:46.364995Z","title":"Model-agnostic counterfactual explanations for consequential decisions","venue":null,"work_id":"894af8fd-d6d5-4094-94af-4e2ad71e3dad","year":2020},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.539820Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:4746b5fafabd48fb1f4c687a449c17f50f8ea9e34d2f6cec93217118fba327f3","observation_id":"6534a488-27dc-4d0f-8c43-23c1070cec0f","resolution":{"observed_at":"2026-08-15T22:24:46.369909Z","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":"2026-08-15T22:24:46.351456Z","title":"u gelgen, Bernhard Sch \\","venue":null,"work_id":"4b76ceff-f808-4993-b48b-5b1d4916b03f","year":2020},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.544124Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:04df0235c51d2c209b999a231d4da349190d7c30793cfd93a6dd858634a5a43a","observation_id":"29b2c897-cef5-42cb-b05d-a8c8164154cf","resolution":{"observed_at":"2026-08-15T22:24:46.355631Z","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":"2026-08-15T22:24:46.332679Z","title":"A survey of algorithmic recourse: Contrastive explanations and consequential recommendations","venue":null,"work_id":"e5035d9a-c489-44fc-96f2-1478acc34195","year":2022},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.548784Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:25f863d027ab6691b66f8f92c474d1e2379dff1928bd27254129016e55cc2a2f","observation_id":"e34a9c8d-1f56-4d61-b6d1-bb1a3830f715","resolution":{"observed_at":"2026-08-15T22:24:46.339859Z","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":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-08-14T23:50:45.029465Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-08-15T22:24:45.552525Z","title":"Kingma and Max Welling","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.552525Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:d0c3adc2a38d34fe8f95f4cdb56f877e292fb341e41014ca129453a29d948a62","observation_id":"b11e6b9d-71e8-42cc-89df-0132777ef92b","resolution":{"observed_at":"2026-08-15T22:24:45.552525Z","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":"2026-08-15T22:24:45.556459Z","title":"Probabilistic graphical models: principles and techniques","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.556459Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:f69d26e3e7796b53553b68e282f75807fce3b3e6b3b5045e336fc8fc95d949b2","observation_id":"95b5cd37-267b-4f9b-b144-6b0a8c6f047f","resolution":{"observed_at":"2026-08-15T22:24:45.556459Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1712.08443","last_updated":"2017-12-22T13:51:21Z","snapshot_observed_at":"2026-08-14T20:00:49.823564Z","submitted_at":"2017-12-22T13:51:21Z","title":"Inverse Classification for Comparison-based Interpretability in Machine Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.08443","snapshot_observed_at":"2026-08-15T22:24:45.561344Z","title":"Inverse classification for comparison-based interpretability in machine learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.561344Z"},"links":{"cited_paper":"/paper/1712.08443","citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:e97e3278802778ac0b42108156e009a2f278e76c218ce4a0a164e13050f00830","observation_id":"8caeed83-fa6f-415f-8857-5a720917664a","resolution":{"observed_at":"2026-08-15T22:24:45.561344Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.08252","last_updated":"2024-10-25T02:50:44Z","snapshot_observed_at":"2026-08-16T13:26:12.987371Z","submitted_at":"2024-08-15T16:47:59Z","title":"Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.08252","snapshot_observed_at":"2026-08-15T22:24:45.566021Z","title":"Derivative-free guidance in continuous and discrete diffusion models with soft value-based decoding","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.566021Z"},"links":{"cited_paper":"/paper/2408.08252","citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:84bb550b3190474d8a11cf7ca550dde79539e44d764e63c52c46d366cd300dbe","observation_id":"b11789cb-b2a7-4dcf-afb3-3d42a39f4d61","resolution":{"observed_at":"2026-08-15T22:24:45.566021Z","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":"2026-08-15T22:24:46.310137Z","title":"Explaining machine learning classifiers through diverse counterfactual explanations","venue":null,"work_id":"e1f38fb8-8beb-41ed-93a9-3441be4a2332","year":2020},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.570708Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:5e9a475d4f85cfa1ac1f4543582e2c642f39599d481ab76e4dcaba4a9bbccafb","observation_id":"d7a6e394-9285-4c9b-89af-6f6d51b211d0","resolution":{"observed_at":"2026-08-15T22:24:46.314593Z","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":"2026-08-15T22:24:45.574894Z","title":"Pytorch: An imperative style, high-performance deep learning library","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.574894Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:70ffacf34ba73cf76a72104b98d97e06b2e13e6311a4c7f8be5b5a1f675bbef0","observation_id":"bc9da79b-8a29-4e5d-95ca-0078308299df","resolution":{"observed_at":"2026-08-15T22:24:45.574894Z","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":"2026-08-15T22:24:46.288085Z","title":"Learning model-agnostic counterfactual explanations for tabular data","venue":null,"work_id":"8e04acbe-ae8e-4710-af2c-c9a547ea9b78","year":2020},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.579394Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:1ab36c8f245e527ac1a248963c130228a694e75413cb0d7770bc54f3eaf15a25","observation_id":"c508c243-bba0-440e-8f06-26b71aedc426","resolution":{"observed_at":"2026-08-15T22:24:46.292668Z","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":"2026-08-15T22:24:46.273423Z","title":"On counterfactual explanations under predictive multiplicity","venue":null,"work_id":"c54c86e9-2655-41b7-8af5-65989a1b80b0","year":2020},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.584434Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:2085901d96d9c41d92c76b7bde7fa608643985a649e6146323067a0001089d40","observation_id":"42f70c75-5b33-4f6a-b407-be04019e1e4e","resolution":{"observed_at":"2026-08-15T22:24:46.278199Z","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":"2026-08-15T22:24:46.256576Z","title":"Carla: A python library to benchmark algorithmic recourse and counterfactual explanation algorithms, 2021","venue":null,"work_id":"dd303278-71e8-4a70-b886-03cbd766273c","year":2021},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.589363Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:81fbb27e60d518b22da808e7b2688124e1fab617842f66a03240ea1263f05a37","observation_id":"de889f94-7bcb-4c61-8dd1-25e44722c35d","resolution":{"observed_at":"2026-08-15T22:24:46.261299Z","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":"2026-08-15T22:24:46.242703Z","title":"Probabilistically robust recourse: Navigating the trade-offs between costs and robustness in algorithmic recourse","venue":null,"work_id":"a18be14d-7d3d-422e-8fe5-2fbabf201c40","year":2023},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.593989Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:da0882b53e8779af309e9fe93cb60cf251a8adc4daa8b6918414fb7903097b55","observation_id":"1b7e3161-2f3d-4d6d-9255-59f418193b1c","resolution":{"observed_at":"2026-08-15T22:24:46.247774Z","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":"2026-08-15T22:24:45.601984Z","title":"Pedregosa, G","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.601984Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:a40328f8112f1d4959300ff155edc38b2bda028babfbd8ad3ffb3c7d6295576e","observation_id":"474a476a-ee5e-4411-bf37-fc3cccaafbbb","resolution":{"observed_at":"2026-08-15T22:24:45.601984Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.11788","last_updated":"2021-06-26T01:58:37Z","snapshot_observed_at":"2026-08-16T18:56:49.198486Z","submitted_at":"2020-12-22T02:06:08Z","title":"Algorithmic Recourse in the Wild: Understanding the Impact of Data and Model Shifts","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.11788","snapshot_observed_at":"2026-08-15T22:24:45.606397Z","title":"Algorithmic recourse in the wild: Understanding the impact of data and model shifts","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.606397Z"},"links":{"cited_paper":"/paper/2012.11788","citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:38209a9bb23ce9674f2c177efa6da9c708e99a5c48a2f5969890fd499134db3d","observation_id":"5c9ca4b1-f485-406b-a94f-b2bd60ae31f9","resolution":{"observed_at":"2026-08-15T22:24:45.606397Z","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":"2026-08-15T22:24:45.611065Z","title":"Efficiently stealing your machine learning models","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.611065Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:c848da186882175af394d8a347ec53eb23b7b5725c8251bfc8235769b10bbd83","observation_id":"0e6a90d9-4664-4707-9da3-12b9ebfe0527","resolution":{"observed_at":"2026-08-15T22:24:45.611065Z","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":"2026-08-15T22:24:45.616253Z","title":"why should i trust you?","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.616253Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:fd358947a69a1435a07047da42e68ef9c72b277cb790f02c0c44485e84055163","observation_id":"c5bbbf56-748f-4880-9663-1c7b380ed4d0","resolution":{"observed_at":"2026-08-15T22:24:45.616253Z","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":"2026-08-15T22:24:46.212687Z","title":"Foster, Nicholas Mattei, and John P","venue":null,"work_id":"9f5949fe-ef43-47b8-9411-4f5e4055351e","year":2020},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.620573Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:22d3a86f1bb5c9c915a0e7de383da2c6ce9f554b78fae38f532d15461d389bb9","observation_id":"def475ad-0651-47ae-ba76-2c31b67833e1","resolution":{"observed_at":"2026-08-15T22:24:46.217029Z","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":"2026-08-15T22:24:46.199327Z","title":"Generating interpretable counterfactual explanations by implicit minimisation of epistemic and aleatoric uncertainties","venue":null,"work_id":"735a1565-d30d-4b46-aae6-9d4cbddacb8d","year":2021},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.625026Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:4dd6c786ded228ee1f723376758195099d49f07e271254a17278ee5ccdc9f844","observation_id":"8b5e2618-65c1-421a-a07b-311d42ba5274","resolution":{"observed_at":"2026-08-15T22:24:46.204287Z","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":"2026-08-15T22:24:46.185325Z","title":"Towards robust and reliable algorithmic recourse","venue":null,"work_id":"b2aa9608-eb9b-4a61-8b6d-f6e92a23b896","year":2021},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.629818Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:a2f25e0d8d7dec30c62fd0222afc96672a1b6b4583d8718f825e2900b34de0a6","observation_id":"d2cf75da-f3f7-451f-82e8-960ab58338e1","resolution":{"observed_at":"2026-08-15T22:24:46.189897Z","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":"2026-08-15T22:24:46.172003Z","title":"Actionable recourse in linear classification","venue":null,"work_id":"72d711d4-2da9-4725-96a6-e6fb5a31f423","year":2019},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.634417Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:8240aafa76132af1e1ccf98471c2b08db00dff38e2293f4587716ebaaf7ef0ac","observation_id":"9b8a9961-b0f1-42a2-824c-e25d21c2e034","resolution":{"observed_at":"2026-08-15T22:24:46.176668Z","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":"2026-08-15T22:24:45.638447Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.638447Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:7ed6b8b384675e374c6783d23d2df6299d28114857e8622ab7e20b5c5a3c963b","observation_id":"0cfc43fe-26f8-47a2-90f8-3d2660e068f1","resolution":{"observed_at":"2026-08-15T22:24:45.638447Z","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":"2026-08-15T22:24:46.148967Z","title":"Counterfactual explanations without opening the black box: Automated decisions and the gdpr","venue":null,"work_id":"e726479d-4ce3-42b3-8179-5deab4eaeb7f","year":2017},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.645116Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:2d56a3c81d973ccd888da81d46ee027aa697a5c28bb875aa4e36f87d4e4d7060","observation_id":"907e2d8c-9e2c-4826-948f-516ed2c4f765","resolution":{"observed_at":"2026-08-15T22:24:46.153652Z","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":"2026-08-15T22:24:46.134475Z","title":"Mixed-type tabular data synthesis with score-based diffusion in latent space","venue":null,"work_id":"2d0a3477-0baa-497e-aaa7-7e0e9243581a","year":2024},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.649814Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:e55508b19f7187ada3f403428648dcdf1efe5483916d97a4c8cf2b29cebb2481","observation_id":"bdc9b7d4-bb97-4f01-85df-be1a8d3bdeb7","resolution":{"observed_at":"2026-08-15T22:24:46.139502Z","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":"2026-08-15T22:24:45.653463Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.653463Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:2a071e1e364cee0116b5c233c3131206ccf147f2e36702eb99c494e7229f7ded","observation_id":"682032d4-29cb-47da-9b6f-1c8b2251a343","resolution":{"observed_at":"2026-08-15T22:24:45.653463Z","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":"2026-08-15T22:24:45.657764Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.657764Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:e4e67ec40d611136f325d0fde514d994f0c06986d6885db077541b44bc5573f6","observation_id":"815ddd2d-cda9-4bd9-900b-d2ca71c8df1f","resolution":{"observed_at":"2026-08-15T22:24:45.657764Z","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":"2026-08-15T22:24:46.102349Z","title":"Training instances are shown in light red (for ) and blue color (for )","venue":null,"work_id":"f0a9fb15-c296-4f2e-b476-80a73fd55fa4","year":null},"citing_paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-15T22:24:45.661930Z"},"links":{"citing_paper":"/paper/2505.07351"},"observation_digest":"sha256:0a905fd19f17c51f0fa48002480e71ea895bcecb30da634b8a955b80322aa03f","observation_id":"0ae8c58d-d6e2-4639-8eb1-1c8a0d792bd6","resolution":{"observed_at":"2026-08-15T22:24:46.107117Z","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"}}],"paper":{"arxiv_id":"2505.07351","last_updated":"2025-05-12T08:44:28Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T16:58:53.643620Z","submitted_at":"2025-05-12T08:44:28Z","title":"From Search To Sampling: Generative Models For Robust Algorithmic Recourse"},"reference_resolution":{"displayed":49,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":3,"verified_fuzzy":25},"total_outbound_references":49},"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 49 of 49 outbound references and 1 inbound Pith citation observation for arXiv:2505.07351."}