{"as_of":"2026-08-10T05:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2b4a880549f906c249e0e2af77ff27033c2c66c421026e77040eca406a6b3f91","coverage":[{"denominator":57,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":57,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T23:12:13.517006Z","state":"measured"},{"denominator":57,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":57,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2506.19630/citation-record","integrity":"/paper/2506.19630/integrity","json":"/paper/2506.19630/citation-record.json","paper":"/paper/2506.19630"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:12:13.889804Z","title":"Explainable machine learning in deployment","venue":null,"work_id":"7fafc227-ab95-4eec-9a49-dc4491ed30e8","year":2020},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.374023Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:1099939532d648d1fd7e552ccd7359bdc7a4bc0de872e9f2e97ecf5ee4cb32d0","observation_id":"cbe46324-7e9a-49d5-97d7-59059b2a536d","resolution":{"observed_at":"2026-08-06T23:12:13.892386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.883625Z","title":"Reliability, sufficiency, and the decomposition of proper scores","venue":null,"work_id":"b985c05b-a261-4992-9f5c-2736ebcced50","year":2009},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.376616Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:a61f559cc3f35cf04fff6abf1904212d7ac8adecfac4ada79b8f2e1868702bf3","observation_id":"90ad382a-fcd9-42ab-9dfc-9ddd2e59b433","resolution":{"observed_at":"2026-08-06T23:12:13.885937Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.876949Z","title":"Overinterpretation reveals image classification model pathologies","venue":null,"work_id":"1896638a-8815-49b5-956b-d99d76d8363c","year":2021},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.378770Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:00dea03267e8bd8189ea1acd521cdf87e6c88f4865a22c7b05d59fb74c2108fa","observation_id":"00d2fa7b-0324-40ad-b8e8-63c53cdfb120","resolution":{"observed_at":"2026-08-06T23:12:13.879819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.870596Z","title":"Learning to explain: An information-theoretic perspective on model interpretation","venue":null,"work_id":"3bcf0144-bf2e-46fb-a0b9-c6aebb144f2d","year":2018},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.381353Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:6edf13b669f67481e25f757025e09240854863c986b327ae9e9caade3e2b3692","observation_id":"f6b32e7f-7432-49e6-b5c1-3da95395e527","resolution":{"observed_at":"2026-08-06T23:12:13.872738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.864062Z","title":"Understanding global feature contributions with additive importance measures","venue":null,"work_id":"09c82be8-0e39-471a-8360-926a651d6fe5","year":2020},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.383543Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:be399dd6bd4c79ab7c7b741223dae814ec84f930de7051591666781b3eec044c","observation_id":"043c1847-5e0e-4e9e-9c56-b92fbcce6388","resolution":{"observed_at":"2026-08-06T23:12:13.866452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.856102Z","title":"Explaining by removing: A unified framework for model explanation","venue":null,"work_id":"bf52a654-3189-428f-bb45-b9fced9e64a3","year":2021},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.385578Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:fea576423fe5cec833b986e531016d644983435b05b18ebac2fe72fea2c8ad6e","observation_id":"6a1c79b3-0b7a-43cd-babb-41f868708e56","resolution":{"observed_at":"2026-08-06T23:12:13.859292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.847557Z","title":"Does your model think like an engineer? explainable ai for bearing fault detection with deep learning","venue":null,"work_id":"1049371f-3f4d-4a05-8e49-569c6aa1b886","year":2023},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.388857Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:e6ffe0c2d0b5349a21fb82e6c410ebdae67e4aeab3465afb1a65856b7cbb9b33","observation_id":"6d010294-6a4c-4f9f-9ddc-20584750eec2","resolution":{"observed_at":"2026-08-06T23:12:13.851713Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.840572Z","title":"Explanatory model monitoring to understand the effects of feature shifts on performance","venue":null,"work_id":"ad7db84a-ee0c-45de-87dc-d6e81a6c2e9d","year":2024},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.391337Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:55ea69a1f7ddeb1dff79722dbb7cc07f39c7b5412f455a7ddb3e6d856ef764a3","observation_id":"d3cd1215-f01f-4bb7-b83e-bb2ef5c5a765","resolution":{"observed_at":"2026-08-06T23:12:13.843049Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.393236Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.393236Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:62d29964e1a8563e616af492367a1a64356423ab5f1a90b4e83404b6f7f1189a","observation_id":"1956851d-c4b6-4954-a60f-bc5e8671225c","resolution":{"observed_at":"2026-08-06T23:12:13.393236Z","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":"2026-08-06T23:12:13.828439Z","title":"Look at the variance! efficient black-box explanations with sobol-based sensitivity analysis","venue":null,"work_id":"5ed95911-8a93-442a-b50e-f9b0233ffa3f","year":2021},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.396176Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:903f3d6ea4dd451adb4130bba3311ae3fd9ec78046641d0ee457152fc28bad1c","observation_id":"7737f2ad-fb02-4481-a322-dfbeb25c725f","resolution":{"observed_at":"2026-08-06T23:12:13.831698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.399111Z","title":"Harmonizing the object recognition strategies of deep neural networks with humans","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.399111Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:4e6e52562b1ffe49b99d3e0fc1e7b0cf703dd8285cc62261ec67368f969ba8dd","observation_id":"b05ab142-0b29-4a2d-8a5b-25fe9bb13bfb","resolution":{"observed_at":"2026-08-06T23:12:13.399111Z","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":"2026-08-06T23:12:13.817518Z","title":"Pathologies of neural models make interpretations difficult","venue":null,"work_id":"56af2e87-4b02-4e89-8941-9defcbbe4aa0","year":2018},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.402386Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:132f6f6d9b479e2648df5455f4acf54e74612d102ba73e3bdacef377ea6308b0","observation_id":"002108dc-0e71-4531-9ffd-d6279c008233","resolution":{"observed_at":"2026-08-06T23:12:13.819889Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.811440Z","title":"Shapley explainability on the data manifold","venue":null,"work_id":"a568beaf-0606-4702-a59e-308903e2f29e","year":2021},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.404747Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:a5ee2f3c67543cf6f62f7566000c8a79b4e2a9f60e639d1532daf3572ae0c082","observation_id":"e8e96824-6990-4073-b826-16ce8f24f019","resolution":{"observed_at":"2026-08-06T23:12:13.813726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.407222Z","title":"Strictly proper scoring rules, prediction, and estimation","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.407222Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:22ab2c0d4768f767a9dade35ba5a82ee08b99297057756a283f244dc398aa903","observation_id":"641b2018-211b-464b-b01a-2e541e21a7d5","resolution":{"observed_at":"2026-08-06T23:12:13.407222Z","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":"2026-08-06T23:12:13.796967Z","title":"Better uncertainty calibration via proper scores for classification and beyond","venue":null,"work_id":"90b1e641-fca3-4e09-8f5c-dc1d0fb4d431","year":2022},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.410623Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:d8ce6e60a56f0afecb3d17931c2860071bba0f04c4485855b2322d097acd1e80","observation_id":"bb9f07ba-9fcc-4682-8a91-e6b5bf1e5f7e","resolution":{"observed_at":"2026-08-06T23:12:13.800697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.412460Z","title":"On calibration of modern neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.412460Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:71bb7e7460af003a039a05a5c6beee9ac2b9821027508dfe8ddf5ba6e0be18c2","observation_id":"54610d1f-daf8-4233-81eb-e4f82f885b4a","resolution":{"observed_at":"2026-08-06T23:12:13.412460Z","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":"2026-08-06T23:12:13.784403Z","title":"The out-of-distribution problem in explainability and search methods for feature importance explanations","venue":null,"work_id":"bf927891-e91c-4d5d-b92a-a09c0715f546","year":2021},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.414589Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:023714a6564db1f8a665a3576bcc0d67a69128db76b378ce8cfdd1d6109ef2aa","observation_id":"693075e2-8658-4182-9df2-ae07513f3a69","resolution":{"observed_at":"2026-08-06T23:12:13.786948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.778278Z","title":"o m, Leander Weber, Daniel Krakowczyk, Dilyara Bareeva, Franz Motzkus, Wojciech Samek, Sebastian Lapuschkin, and Marina M-C H \\","venue":null,"work_id":"a4910065-6f7f-4451-9dc0-3718a4c60bc8","year":2023},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.417416Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:f2b79ffa6a234dc534fe9b109f857a1dcf7610b6a2357cc6b52642024a73a5ae","observation_id":"f437c625-c89c-481b-a487-7e3e67220030","resolution":{"observed_at":"2026-08-06T23:12:13.780567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.420379Z","title":"Densely connected convolutional networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.420379Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:6a3ec50f3c088514b6425b0475b5e78e9e69f777a5e4f1e70ac0c72c83ec8176","observation_id":"211afeae-a203-4b86-8516-a1af6167330c","resolution":{"observed_at":"2026-08-06T23:12:13.420379Z","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":"2026-08-06T23:12:13.422506Z","title":"Openclip, July 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.422506Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:f95192d8a37f67f260d374dec4506a045c8374c53c6f888bb461886ddc7246e7","observation_id":"97e12b28-0bf2-4125-aa21-251d47ea1b3f","resolution":{"observed_at":"2026-08-06T23:12:13.422506Z","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":"2026-08-06T23:12:13.765742Z","title":"Perturbation-based methods for explaining deep neural networks: A survey","venue":null,"work_id":"a8d87161-9d8a-4844-8a97-e68420af3707","year":2021},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.424826Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:2c69aeea8756c1da264bfd0285af5309ea723f6a2c66260e710837855f0ed6bb","observation_id":"fe9eb2cd-6326-42ec-943a-88e37e845592","resolution":{"observed_at":"2026-08-06T23:12:13.769309Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.758565Z","title":"Missingness bias in model debugging","venue":null,"work_id":"4e4d4552-94ca-49ed-97f5-b85e347a544a","year":2022},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.427098Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:fd32d93e8f5d54aa501affe225160e3974b0d34b4a1c3ccd5a0f6d10eeb5063e","observation_id":"85d350ca-927a-4daf-b740-731fae71c98c","resolution":{"observed_at":"2026-08-06T23:12:13.761228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.750150Z","title":"Trustworthy artificial intelligence: a review","venue":null,"work_id":"f1dd612d-8e17-44a8-b563-77e1d619b598","year":2022},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.429393Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:1015614f05d12095000341203ba3a3c930d3312a24637e80062b73d6e35c666e","observation_id":"f7c589a1-e127-4629-82bf-bf1017212eb6","resolution":{"observed_at":"2026-08-06T23:12:13.753872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2009.07896","last_updated":"2020-09-16T18:57:57Z","snapshot_observed_at":"2026-07-06T09:56:16.122954Z","submitted_at":"2020-09-16T18:57:57Z","title":"Captum: A unified and generic model interpretability library for PyTorch","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.07896","snapshot_observed_at":"2026-08-06T23:12:13.432211Z","title":"Captum: A unified and generic model interpretability library for pytorch","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.432211Z"},"links":{"cited_paper":"/paper/2009.07896","citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:fe90cb18cf4db314d8e2ba3fa405f759220c52023e35c84b70e65c107f26b618","observation_id":"ff6668a4-5ad6-4df9-8b84-19ad188b4c25","resolution":{"observed_at":"2026-08-06T23:12:13.432211Z","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":"2026-08-06T23:12:13.742856Z","title":"Novel decompositions of proper scoring rules for classification: Score adjustment as precursor to calibration","venue":null,"work_id":"4cf4080d-7ea4-49f9-85a6-15821958289e","year":2015},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.434857Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:946b540be6521e8aea1a129f8ecccb3d96cadbd56672b6c11f0643df987e0774","observation_id":"28e8533d-56c3-4d96-a806-2b7896bd4b95","resolution":{"observed_at":"2026-08-06T23:12:13.745054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.735995Z","title":"On the robustness of removal-based feature attributions","venue":null,"work_id":"23e4dd91-b8e1-4fe7-a851-0b46dedcbbb1","year":2024},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.436901Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:1d3682eae1886af75e8b080cac28404fdf50cdd8fa57add0d2640da80d94b83c","observation_id":"6c4e3e7c-d1e6-4b83-92c6-312c73fce8df","resolution":{"observed_at":"2026-08-06T23:12:13.738773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.728839Z","title":"Learning what and where to attend","venue":null,"work_id":"09064636-9c4c-479b-9ae6-7b0399ed1917","year":2019},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.438997Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:5bb8ada0aa4af0c067cb0459f236ba69ecce8d7c0b36f82503f3c754efb70718","observation_id":"6ba5cc88-bd0c-4eb9-a558-9052f17f0b61","resolution":{"observed_at":"2026-08-06T23:12:13.731475Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.441178Z","title":"On the limited memory bfgs method for large scale optimization","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.441178Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:10eac46620b52cc853b570ebeac87ba40c3975998ff2971c9b4fbd2e602b6e90","observation_id":"6326eb2d-c206-47bb-941e-7d204df9c8f0","resolution":{"observed_at":"2026-08-06T23:12:13.441178Z","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":"2026-08-06T23:12:13.718627Z","title":"o fstr \\","venue":null,"work_id":"e5a1f667-be33-4a9e-ad66-55e8de95784f","year":2024},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.443184Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:ec1cfcac2ac1cfe40e9dd1894ade25317ec5b037dcb1b4a9a53c2c20820dc91d","observation_id":"1d69042f-81ba-4b58-a524-16b62ae51598","resolution":{"observed_at":"2026-08-06T23:12:13.721542Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.445024Z","title":"A unified approach to interpreting model predictions","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.445024Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:7c03093f46101080b0e5d46ad5a54bd918d5cf5feccde71594dac925cb60ebe4","observation_id":"450710ac-cce2-4553-bcd9-b79801f31f30","resolution":{"observed_at":"2026-08-06T23:12:13.445024Z","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":"2026-08-06T23:12:13.708828Z","title":"From local explanations to global understanding with explainable ai for trees","venue":null,"work_id":"89d929b5-8edd-4360-85a9-fb46a760e729","year":2020},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.447869Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:3910a161de7c9f8cfd8175b04617ed9a45ef0a03d21446be6134c73d4348f167","observation_id":"bd06c595-b314-4ee4-bdad-5ad5ccad1130","resolution":{"observed_at":"2026-08-06T23:12:13.711349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.701425Z","title":"Local calibration: metrics and recalibration","venue":null,"work_id":"662d261c-764d-4c97-804f-089649758f98","year":2022},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.451078Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:6b6ace3547c41c5c6d019f614a5af902a58b8578d9c1c11a919c558c363779e3","observation_id":"6a5826bb-11ad-4650-80d8-42269afa0ffc","resolution":{"observed_at":"2026-08-06T23:12:13.703668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.452955Z","title":"Revisiting the calibration of modern neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.452955Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:0ad3151d9ac94e94510f21a5e2b83b11bf49fdd5c78762ba673ea94b8b83ac3e","observation_id":"1a5b77e1-7b78-48db-99ad-b46bb225d27b","resolution":{"observed_at":"2026-08-06T23:12:13.452955Z","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":"2026-08-06T23:12:13.455324Z","title":"Obtaining well calibrated probabilities using bayesian binning","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.455324Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:7d6e92c59c98790f89f658f25ae15e9fe1de2b7b3267cad8196d8e774cc396df","observation_id":"ec5689f2-b285-429b-8da5-d7d06da9320c","resolution":{"observed_at":"2026-08-06T23:12:13.455324Z","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":"2026-08-06T23:12:13.686942Z","title":"Predicting good probabilities with supervised learning","venue":null,"work_id":"c4ced2af-b76d-40ad-a04c-14f1e24c8de7","year":2005},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.457456Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:be5689c7500c3ca09f0f171355049835d2caea483d29286105f40a410a4732e3","observation_id":"e6675572-172c-4e27-8ca4-a8a7c8c60910","resolution":{"observed_at":"2026-08-06T23:12:13.689801Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.679933Z","title":"Making sense of dependence: Efficient black-box explanations using dependence measure","venue":null,"work_id":"8a315744-3abe-48f0-9b8b-c3af13dad805","year":2022},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.461652Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:b129e2b5c70e8ffc3eb4b567cf8b19623cfe53f6bfc692e0f9a7472bc25e14f6","observation_id":"bb6e1816-e729-4b98-b47d-8e0d92d92057","resolution":{"observed_at":"2026-08-06T23:12:13.682492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.464226Z","title":"Can you trust your model's uncertainty? evaluating predictive uncertainty under dataset shift","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.464226Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:c93d43c021e8d98e0eb81cd4958738fb0e5ecbe16d3fa3cbd88d81b076416aa4","observation_id":"4bc062b9-685d-45e7-9d7d-d8b941738f72","resolution":{"observed_at":"2026-08-06T23:12:13.464226Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.07421","last_updated":"2018-09-25T18:16:18Z","snapshot_observed_at":"2026-07-06T06:45:42.492990Z","submitted_at":"2018-06-19T18:41:30Z","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.07421","snapshot_observed_at":"2026-08-06T23:12:13.466747Z","title":"Rise: Randomized input sampling for explanation of black-box models","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.466747Z"},"links":{"cited_paper":"/paper/1806.07421","citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:02c7605c506f58d5a35e3a9ac8985a453ae548395769567a9681a0d0a0392dcd","observation_id":"6ab0fae1-db12-4f76-82ff-0b8412067ffe","resolution":{"observed_at":"2026-08-06T23:12:13.466747Z","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":"2026-08-06T23:12:13.668648Z","title":"Consistent and asymptotically unbiased estimation of proper calibration errors","venue":null,"work_id":"3f688a21-8754-48ba-a215-9343a96854d9","year":2024},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.469257Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:00f2463794288df161f9914ae3324960e8c1f994fce0bb3ac95119effab75d27","observation_id":"6a787449-fa4a-4727-b3a1-978db7cc39b3","resolution":{"observed_at":"2026-08-06T23:12:13.672073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.661575Z","title":"why should i trust you?","venue":null,"work_id":"03172ac3-9825-4c7c-bf09-27f887b91bd4","year":2016},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.471522Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:a4e6bdd8e7d120d0988eb8170b7ddec276305925421299d01f5b282acf6a38a6","observation_id":"b4644362-7888-49a4-be30-9a919fadfe4d","resolution":{"observed_at":"2026-08-06T23:12:13.663864Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.652555Z","title":"Perturbation-based explanations of prediction models","venue":null,"work_id":"e9382c5f-217d-47d9-930e-5bd01e83fee9","year":2018},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.474049Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:68cd9548214d6354598dcd1f4a732c2bcad91169cbc48528790f9e76576cf70d","observation_id":"823f9b78-890b-4f03-afe9-d05e098db6fc","resolution":{"observed_at":"2026-08-06T23:12:13.655929Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.644633Z","title":"Calibrate to interpret","venue":null,"work_id":"be03a373-66ab-4421-8552-40cd2bcea8b5","year":2022},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.475958Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:4750323475e464c5e51ff56636235c205b35fbc5b41b8f79dc12b887bc833ef4","observation_id":"a89d50ae-5ce0-4b88-b606-3fa543c84516","resolution":{"observed_at":"2026-08-06T23:12:13.647079Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.00396","last_updated":"2020-05-25T14:21:37Z","snapshot_observed_at":"2026-08-07T10:55:35.251706Z","submitted_at":"2020-01-02T11:24:35Z","title":"Restricting the Flow: Information Bottlenecks for Attribution","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.00396","snapshot_observed_at":"2026-08-06T23:12:13.478646Z","title":"Restricting the flow: Information bottlenecks for attribution","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.478646Z"},"links":{"cited_paper":"/paper/2001.00396","citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:77123a0d5c304a94b91fec93ede99a4d22996a93be50fe75fab9f117d86448fe","observation_id":"50041b42-73dd-4f95-b818-71d9ad975210","resolution":{"observed_at":"2026-08-06T23:12:13.478646Z","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":"2026-08-06T23:12:13.637882Z","title":"Classifier calibration: a survey on how to assess and improve predicted class probabilities","venue":null,"work_id":"17880624-a757-414f-bbc7-04d8bc683efa","year":2023},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.481657Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:b46a0005372385726b6b5afebcfa075919a8f26caa6fd9c9a34293f886f3bc71","observation_id":"ccdcdbd7-3137-4f18-8348-8127badbb65f","resolution":{"observed_at":"2026-08-06T23:12:13.640524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.631408Z","title":"Visualizing the impact of feature attribution baselines","venue":null,"work_id":"298d38a1-0536-4432-9fb3-1798609addeb","year":2020},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.484274Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:910af9586f42ce647bc85be99343556ebf9eea7c70e24a2082679b12484840a4","observation_id":"5bf66e56-af44-4712-a933-acda60f71a4e","resolution":{"observed_at":"2026-08-06T23:12:13.633923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.625003Z","title":"The many shapley values for model explanation","venue":null,"work_id":"fa33ba39-d076-43de-a547-96d0870d2969","year":2020},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.486888Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:662d54ded9261f4ee98b693d32e637092703093c31d0a075f20ab9911b05b18f","observation_id":"c8e8d55e-ccf3-4b78-9918-5b0a5507a14f","resolution":{"observed_at":"2026-08-06T23:12:13.627557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.618118Z","title":"Post-hoc uncertainty calibration for domain drift scenarios","venue":null,"work_id":"5c45db6b-dc8c-4125-a6e1-8b66779e2081","year":2021},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.489060Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:1dcf92f1e15f419712a7937a4c70c0b75a4a2a0f4e7e17562d85aeda37ed06df","observation_id":"6b329ca3-68f7-404e-bb8c-d29b791d4002","resolution":{"observed_at":"2026-08-06T23:12:13.620701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.01222","last_updated":"2025-09-14T12:53:07Z","snapshot_observed_at":"2026-07-06T16:01:41.830509Z","submitted_at":"2023-08-02T15:28:10Z","title":"Calibration in Deep Learning: A Survey of the State-of-the-Art","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.01222","snapshot_observed_at":"2026-08-06T23:12:13.491717Z","title":"Calibration in deep learning: A survey of the state-of-the-art","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.491717Z"},"links":{"cited_paper":"/paper/2308.01222","citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:35af98d3a21f3243fc9b4c248772f88aca366750c5f08ae6a65ee4e2e0ae1c92","observation_id":"4569844e-db5e-4f1a-9c63-563c969e54f3","resolution":{"observed_at":"2026-08-06T23:12:13.491717Z","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":"2026-08-06T23:12:13.494014Z","title":"Pytorch image models","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.494014Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:f780008dd96203b33aa35de1994e467045b5b9f567e80b48b7d68a35493b0b7e","observation_id":"d1629c51-569f-4800-ab02-046fa522b654","resolution":{"observed_at":"2026-08-06T23:12:13.494014Z","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":"2026-08-06T23:12:13.606676Z","title":"Robust calibration with multi-domain temperature scaling","venue":null,"work_id":"0cfa4431-7956-4644-93bb-fac41a2695d5","year":2022},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.496198Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:3e23a5cef72e19506a7cf2c8efddb130aae03984eb89e1cf91082a69520a13c5","observation_id":"f8128b4b-3d18-45fc-953d-a54c1deaca40","resolution":{"observed_at":"2026-08-06T23:12:13.609362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.598406Z","title":"Visualizing and understanding convolutional networks","venue":null,"work_id":"d4f290b7-70c8-45f6-8810-e734200f3862","year":2014},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.499701Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:704bbc9e25abd7186010b1c915698f38afd4caf493afbd5090ba5cf0b194ec56","observation_id":"751ff5a8-6646-4da1-9dd4-a72cf6a463db","resolution":{"observed_at":"2026-08-06T23:12:13.601453Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.503638Z","title":"Sigmoid loss for language image pre-training","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.503638Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:e60cc67f6be1d123cd3404cf293d5ff517af44f732c36f80185acdd4b00e3aeb","observation_id":"91007510-d278-45fb-bcfb-8a41556d06c6","resolution":{"observed_at":"2026-08-06T23:12:13.503638Z","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":"2026-08-06T23:12:13.587136Z","title":"Mix-n-match: Ensemble and compositional methods for uncertainty calibration in deep learning","venue":null,"work_id":"b6084cfb-5cb1-4fc4-bf5d-ddb07d5ca611","year":2020},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.506207Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:c3fbaef38cc4ac611e565ee0b2fcf9b6620a9ed39f11b2c3d0d880742321c88d","observation_id":"376d3321-6c2a-4ca9-9e1c-bb3becfb0b3d","resolution":{"observed_at":"2026-08-06T23:12:13.590110Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.579479Z","title":"Individual calibration with randomized forecasting","venue":null,"work_id":"6eba356b-c691-4e18-b3e3-8491bb7235bc","year":2020},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.508959Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:46762b594dba60e0651ef503fedf2a90c080ff83d64dc8958cbc56a39d691e42","observation_id":"21d90738-8972-4aef-b9d3-f9e617c862e5","resolution":{"observed_at":"2026-08-06T23:12:13.583118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T23:12:13.511998Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.511998Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:a93a70c832bb77f3f74ca9762d835d631cdac5fb6309a775cfa2907ba0efab00","observation_id":"8acbcdc7-968b-439b-9078-73671b21b829","resolution":{"observed_at":"2026-08-06T23:12:13.511998Z","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":"2026-08-06T23:12:13.514880Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.19630","last_updated":"2025-06-24T13:54:12Z","snapshot_observed_at":"2026-08-08T12:28:17.980227Z","submitted_at":"2025-06-24T13:54:12Z","title":"Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-06T23:12:13.514880Z"},"links":{"citing_paper":"/paper/2506.19630"},"observation_digest":"sha256:019ea52e2e97e9b0323cfc69b39a8dd31e9d59b5caece14332b3fea727bddb60","observation_id":"17003933-3322-442d-a735-9907dbf17b96","resolution":{"observed_at":"2026-08-06T23:12:13.514880Z","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":"2026-08-06T23:12:13.564351Z","title":"P;!־ ֪PTRޖP ՖQJ TIK ĒD Id_52d uz