{"as_of":"2026-08-21T09:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e76c130fca1a6620f5b4a0d0042c64269fe6f0dc58763713736fc65f425c250f","coverage":[{"denominator":61,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":61,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T14:46:12.359134Z","state":"measured"},{"denominator":61,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":61,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2411.14946/citation-record","integrity":"/paper/2411.14946/integrity","json":"/paper/2411.14946/citation-record.json","paper":"/paper/2411.14946"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T14:46:13.094389Z","title":"Explaining explanations: An overview of interpretability of machine learning","venue":null,"work_id":"69bfbaa6-315d-4f51-9dbd-cccf024d055e","year":2018},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.184298Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:c8ca9f5aee72dd9a331f8c49c1fe6cadf87cb835d5540c6132a9334ca1d78148","observation_id":"b1d5fc6f-deb8-4d77-93ca-6b1d1d52374b","resolution":{"observed_at":"2026-08-12T14:46:13.097171Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T14:46:13.087201Z","title":"Overview of cnn research: 25 years history and the current trends","venue":null,"work_id":"364078cc-39c6-49fd-ba4d-b6a13ae357fe","year":2015},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.188336Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:16113572cf941661dc610200e41a591827aa68b01a48ea5ee34a3780c5d5d8b6","observation_id":"6f8d4322-6f92-4ce4-9b42-a4f83a924b8a","resolution":{"observed_at":"2026-08-12T14:46:13.090077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1905.11946","last_updated":"2020-09-11T05:08:01Z","snapshot_observed_at":"2026-08-10T19:44:30.311627Z","submitted_at":"2019-05-28T17:05:32Z","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.11946","snapshot_observed_at":"2026-08-12T14:46:12.191414Z","title":null,"venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.191414Z"},"links":{"cited_paper":"/paper/1905.11946","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:7c6e947ce59c9903897f43fab0901499307386bed66b1fca0e57a254671f882f","observation_id":"0c1f5520-a654-4375-9d47-b024cf46ed91","resolution":{"observed_at":"2026-08-12T14:46:12.191414Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.03296","last_updated":"2021-12-03T15:05:54Z","snapshot_observed_at":"2026-08-15T09:56:11.308983Z","submitted_at":"2017-04-11T14:15:20Z","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.03296","snapshot_observed_at":"2026-08-12T14:46:12.194568Z","title":"Interpretable explanations of black boxes by meaningful perturbation","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.194568Z"},"links":{"cited_paper":"/paper/1704.03296","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:fd4071c0a75ba015b6b25a1cd176d971ffad53eea029cb77d24bdd8c3549b0e0","observation_id":"048f5286-e2f5-4aba-a2ea-f30c3be46e3b","resolution":{"observed_at":"2026-08-12T14:46:12.194568Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09788","last_updated":"2021-06-17T20:00:55Z","snapshot_observed_at":"2026-08-16T18:16:15.931727Z","submitted_at":"2021-06-17T20:00:55Z","title":"Guided Integrated Gradients: An Adaptive Path Method for Removing Noise","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09788","snapshot_observed_at":"2026-08-12T14:46:12.201030Z","title":"Guided integrated gradients: An adaptive path method for removing noise","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.201030Z"},"links":{"cited_paper":"/paper/2106.09788","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:6b594d93d14924b87c770b4e14e3071a5943dd0b63d0949c71f16294f71f1704","observation_id":"ce16f47c-0a17-4cbf-b6be-138921155aa9","resolution":{"observed_at":"2026-08-12T14:46:12.201030Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.03383","last_updated":"2020-04-08T16:41:12Z","snapshot_observed_at":"2026-08-13T21:16:19.379766Z","submitted_at":"2020-04-03T17:04:16Z","title":"Attribution in Scale and Space","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.03383","snapshot_observed_at":"2026-08-12T14:46:12.204104Z","title":"Attribution in scale and space","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.204104Z"},"links":{"cited_paper":"/paper/2004.03383","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:af3683e7edf3ea04f117b55566a53870ca4e1abf08019a13982d116eeaed8a7e","observation_id":"5355345b-2204-4c42-9ed6-7436c6fbb08f","resolution":{"observed_at":"2026-08-12T14:46:12.204104Z","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":"2026-08-12T14:46:13.079635Z","title":"A survey on neural network interpretability","venue":null,"work_id":"23cab514-0e0d-477e-8dee-b19af5484223","year":2021},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.207223Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:0f34e248a8e87265a676c9de49393c68b6ac656605ad007e8cee1e642d0f4abd","observation_id":"77810fa8-6b66-49a0-aca4-ff8b12fad4c7","resolution":{"observed_at":"2026-08-12T14:46:13.082426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T14:46:13.072604Z","title":"Challenging the black box: A comprehensive evaluation of attribution maps of cnn applications in agriculture and forestry, 2024","venue":null,"work_id":"848c6ca0-398d-4a8c-ab2a-4431c19aaa5c","year":2024},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.209918Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:d73fd17cd2c1c4de60d927041bde47358f7fe49f16a826a73ca134a0d2e7e96c","observation_id":"a019035a-6207-478a-a9cb-65af1b503f31","resolution":{"observed_at":"2026-08-12T14:46:13.075273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T14:46:13.065738Z","title":"Convolutional networks for images, speech, and time series","venue":null,"work_id":"53079561-5c4e-4fd9-bb48-a967ee412a17","year":null},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.213052Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:b80098e3422407612068c1de5d344f9ff273cecbcb7e120dad887f1723f598dd","observation_id":"ac9b9fec-2107-4215-9227-9fe2c52c1a63","resolution":{"observed_at":"2026-08-12T14:46:13.068307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6034","last_updated":"2014-04-19T11:54:52Z","snapshot_observed_at":"2026-08-17T14:45:30.096775Z","submitted_at":"2013-12-20T16:45:54Z","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6034","snapshot_observed_at":"2026-08-12T14:46:12.215784Z","title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.215784Z"},"links":{"cited_paper":"/paper/1312.6034","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:90492545d1225e2052d32c12ee53c8f160b73fd1217e12c4511fdf22f2a7d919","observation_id":"df942a52-2a0e-4117-bd21-a321de2f0e51","resolution":{"observed_at":"2026-08-12T14:46:12.215784Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1311.2901","last_updated":"2013-11-28T23:04:01Z","snapshot_observed_at":"2026-08-14T23:55:35.657994Z","submitted_at":"2013-11-12T20:02:22Z","title":"Visualizing and Understanding Convolutional Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1311.2901","snapshot_observed_at":"2026-08-12T14:46:12.219069Z","title":"Zeiler and Rob Fergus","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.219069Z"},"links":{"cited_paper":"/paper/1311.2901","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:90299b0990e7d771704ba1cd16af3bbc9eab23fefd4679390ae88b33d19b5053","observation_id":"2ed1f3a0-f567-4820-85cd-306e0e0c5c61","resolution":{"observed_at":"2026-08-12T14:46:12.219069Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6806","last_updated":"2015-04-13T07:58:17Z","snapshot_observed_at":"2026-08-18T17:02:01.677257Z","submitted_at":"2014-12-21T16:16:37Z","title":"Striving for Simplicity: The All Convolutional Net","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6806","snapshot_observed_at":"2026-08-12T14:46:12.222173Z","title":"Riedmiller","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.222173Z"},"links":{"cited_paper":"/paper/1412.6806","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:39f267c9d470656bc361ca1f94cdfd77d8f52d2946950b7972c90909d9105615","observation_id":"c0f8a2f0-b2d9-4850-b857-458207452dc6","resolution":{"observed_at":"2026-08-12T14:46:12.222173Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.03825","last_updated":"2017-06-12T19:53:30Z","snapshot_observed_at":"2026-08-14T20:54:30.978618Z","submitted_at":"2017-06-12T19:53:30Z","title":"SmoothGrad: removing noise by adding noise","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.03825","snapshot_observed_at":"2026-08-12T14:46:12.225419Z","title":"Vi \\' e gas, and Martin Wattenberg","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.225419Z"},"links":{"cited_paper":"/paper/1706.03825","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:4ed658459accd9a0a18584f3b6cfc0274c2d5836a0470e6ae93ebeacb11b812e","observation_id":"b3b74c5f-3272-4dfd-8227-7723a2424708","resolution":{"observed_at":"2026-08-12T14:46:12.225419Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.01365","last_updated":"2017-06-13T01:52:38Z","snapshot_observed_at":"2026-08-14T21:44:23.381879Z","submitted_at":"2017-03-04T00:18:49Z","title":"Axiomatic Attribution for Deep Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.01365","snapshot_observed_at":"2026-08-12T14:46:12.228309Z","title":"Axiomatic attribution for deep networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.228309Z"},"links":{"cited_paper":"/paper/1703.01365","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:f90de721a44bf72239cb2ef948c76301cd57e58d0b0f014ff9f6af0780c8e66a","observation_id":"2eb80369-5397-44ce-9afd-f5c31d56a78d","resolution":{"observed_at":"2026-08-12T14:46:12.228309Z","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":"2026-08-12T14:46:12.231267Z","title":"Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.231267Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:759155332ac3722efcddc5968f4e22f2f15eb0a2f4c994644b0c5b7866f1bca2","observation_id":"fb02ec87-d6d3-4f39-aae3-e3b9ea6b824a","resolution":{"observed_at":"2026-08-12T14:46:12.231267Z","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":"2026-08-12T14:46:12.234580Z","title":"Grad- CAM ++: Generalized gradient-based visual explanations for deep convolutional networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.234580Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:617c2d520e711ab4c7877bd79495bd54beaa60fada91b67c3de2259815f409f4","observation_id":"adb517d0-8856-4f9e-b822-bbcfad411b2b","resolution":{"observed_at":"2026-08-12T14:46:12.234580Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.01224","last_updated":"2019-08-03T20:09:40Z","snapshot_observed_at":"2026-08-18T00:43:15.611907Z","submitted_at":"2019-08-03T20:09:40Z","title":"Smooth Grad-CAM++: An Enhanced Inference Level Visualization Technique for Deep Convolutional Neural Network Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.01224","snapshot_observed_at":"2026-08-12T14:46:12.237819Z","title":"Smooth grad-cam++: An enhanced inference level visualization technique for deep convolutional neural network models","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.237819Z"},"links":{"cited_paper":"/paper/1908.01224","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:e7d52c922a449ac375c944b5cfa7c97cc43066fc82700b6221400f237fc76f84","observation_id":"7fb42600-e942-463f-8f47-dfa2a9960f41","resolution":{"observed_at":"2026-08-12T14:46:12.237819Z","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":"2026-08-12T14:46:12.240848Z","title":"Layercam: Exploring hierarchical class activation maps for localization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.240848Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:155f7453c654ef77f5d8fafeb3472486b79d43175c1466c810c3d5dca5af6aba","observation_id":"bda1f54c-f433-44a0-975c-c3845df04adb","resolution":{"observed_at":"2026-08-12T14:46:12.240848Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2008.02312","last_updated":"2020-08-19T06:04:28Z","snapshot_observed_at":"2026-08-20T03:24:05.236901Z","submitted_at":"2020-08-05T18:42:33Z","title":"Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.02312","snapshot_observed_at":"2026-08-12T14:46:12.243374Z","title":"Axiom-based grad-cam: Towards accurate visualization and explanation of cnns","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.243374Z"},"links":{"cited_paper":"/paper/2008.02312","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:d3c0306dd177d4621817308c3dc85d28fd4f2dab732ab68048f8aeb733c28e19","observation_id":"c4e3d39d-20c9-4967-987c-b4a547ee614c","resolution":{"observed_at":"2026-08-12T14:46:12.243374Z","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":"2026-08-12T14:46:13.058927Z","title":"Score-cam: Score-weighted visual explanations for convolutional neural networks, 2020 a","venue":null,"work_id":"71eb2d0b-0b83-4522-a552-accec0a0eaf3","year":2020},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.246510Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:fc2b1077c9a749f6a8f0122b60ac8abfeb64c0d23ebf6882f66ebcc66c5be007","observation_id":"7d9e37d4-5137-44c2-b4ef-8e70c99f8d9a","resolution":{"observed_at":"2026-08-12T14:46:13.061328Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.06104","last_updated":"2018-03-07T10:49:28Z","snapshot_observed_at":"2026-08-17T18:58:08.791936Z","submitted_at":"2017-11-16T14:19:29Z","title":"Towards better understanding of gradient-based attribution methods for Deep Neural Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.06104","snapshot_observed_at":"2026-08-12T14:46:12.248901Z","title":"Cengiz \\\" O ztireli, and Markus H","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.248901Z"},"links":{"cited_paper":"/paper/1711.06104","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:7284d9104646858d93e7bfdb16faa76871fadb97686985fc91bd83b33c4611d8","observation_id":"7ce18e93-d7d2-4d9c-ba79-8cbe85c9074f","resolution":{"observed_at":"2026-08-12T14:46:12.248901Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.14255","last_updated":"2020-11-12T13:02:55Z","snapshot_observed_at":"2026-08-14T19:50:18.599006Z","submitted_at":"2020-06-25T08:51:54Z","title":"SS-CAM: Smoothed Score-CAM for Sharper Visual Feature Localization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.14255","snapshot_observed_at":"2026-08-12T14:46:12.251664Z","title":"Ss-cam: Smoothed score-cam for sharper visual feature localization, 2020 b","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.251664Z"},"links":{"cited_paper":"/paper/2006.14255","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:c4b7f90fc96479b79e070385fadce8b4829040efb2bb52cc1b5f6c13432c31aa","observation_id":"27cb2151-2d95-4a9e-a262-cb49ac54ede2","resolution":{"observed_at":"2026-08-12T14:46:12.251664Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.03023","last_updated":"2020-10-06T21:03:03Z","snapshot_observed_at":"2026-08-16T19:15:23.503184Z","submitted_at":"2020-10-06T21:03:03Z","title":"IS-CAM: Integrated Score-CAM for axiomatic-based explanations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.03023","snapshot_observed_at":"2026-08-12T14:46:12.254110Z","title":"Nayak K, and Soumya Snigdha Kundu","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.254110Z"},"links":{"cited_paper":"/paper/2010.03023","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:2cf990324c0ec1fda020049bdb7213813788629d2f8fca82582b6f583a7d1886","observation_id":"fa08391e-a5a6-4bd1-a690-9ed33300975a","resolution":{"observed_at":"2026-08-12T14:46:12.254110Z","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":"2026-08-12T14:46:12.256785Z","title":"Ramaswamy","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.256785Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:4cdf60915cdd7d53d94fd9aa71d843620a660bb0bbba0c89af5265552ef53dd0","observation_id":"8b3347f9-a7ce-48a8-9738-82c3e2dd366a","resolution":{"observed_at":"2026-08-12T14:46:12.256785Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.08792","last_updated":"2022-06-17T14:08:39Z","snapshot_observed_at":"2026-08-16T16:52:14.450608Z","submitted_at":"2022-06-17T14:08:39Z","title":"FD-CAM: Improving Faithfulness and Discriminability of Visual Explanation for CNNs","version":1},"cited_work":{"arxiv_id":"2206.08792","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.08792","snapshot_observed_at":"2026-08-12T14:46:12.693714Z","title":"FD-CAM: Improving Faithfulness and Discriminability of Visual Explanation for CNNs","venue":"cs.CV","work_id":"fcabc069-57b5-4093-93c4-fb344f3daaaa","year":2022},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.259272Z"},"links":{"cited_paper":"/paper/2206.08792","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:586b5bdb55bec9e6f4f34fca16ea92b9640d6aa8a2bee3889dd0f61a53c76694","observation_id":"9eb78607-4ab4-49d7-a38f-fce49af502fe","resolution":{"observed_at":"2026-08-12T14:46:12.696616Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.13859","last_updated":"2021-06-19T09:40:17Z","snapshot_observed_at":"2026-08-16T18:36:21.981992Z","submitted_at":"2021-03-25T14:16:02Z","title":"Group-CAM: Group Score-Weighted Visual Explanations for Deep Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.13859","snapshot_observed_at":"2026-08-12T14:46:12.261907Z","title":"Group-cam: Group score-weighted visual explanations for deep convolutional networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.261907Z"},"links":{"cited_paper":"/paper/2103.13859","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:ec16dd4873449915f381aa13159c03e0d4e1c10543a2d205edbe09b5036be35f","observation_id":"11836526-7bba-49c6-b17b-f78fd96957b3","resolution":{"observed_at":"2026-08-12T14:46:12.261907Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.13359","last_updated":"2022-05-05T20:48:34Z","snapshot_observed_at":"2026-08-19T18:34:41.904146Z","submitted_at":"2022-04-28T09:06:19Z","title":"Poly-CAM: High resolution class activation map for convolutional neural networks","version":2},"cited_work":{"arxiv_id":"2204.13359","doi":null,"metadata_source":"pith","pith_arxiv_id":"2204.13359","snapshot_observed_at":"2026-08-12T14:46:12.677913Z","title":"Poly-CAM: High resolution class activation map for convolutional neural networks","venue":"cs.CV","work_id":"59935d45-3bd9-402a-9d5a-db943c8247bb","year":2022},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.265382Z"},"links":{"cited_paper":"/paper/2204.13359","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:53d77f310efb2a1136b0b4bec4f82c455da6837e18f3da456d5c34d4eae61d4f","observation_id":"83b77de3-dc28-417a-8b0a-2c3a730730b9","resolution":{"observed_at":"2026-08-12T14:46:12.680743Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.08644","last_updated":"2020-10-16T22:06:43Z","snapshot_observed_at":"2026-08-16T19:12:51.907069Z","submitted_at":"2020-10-16T22:06:43Z","title":"Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labels","version":1},"cited_work":{"arxiv_id":"2010.08644","doi":null,"metadata_source":"pith","pith_arxiv_id":"2010.08644","snapshot_observed_at":"2026-08-12T14:46:12.668049Z","title":"Zoom-CAM: Generating Fine-grained Pixel Annotations from Image Labels","venue":"cs.CV","work_id":"2eb960d7-b6e9-4126-b6b5-7a49d577af1d","year":2020},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.268172Z"},"links":{"cited_paper":"/paper/2010.08644","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:3dd1ecfab150c11dcade7ee5fe5120b682fbde8be08ac563d6e764f8842d4a91","observation_id":"0806dba8-f3c3-40f9-8ec7-9f33c56643dd","resolution":{"observed_at":"2026-08-12T14:46:12.671189Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T14:46:13.051283Z","title":"Recipro-cam: Fast gradient-free visual explanations for convolutional neural networks, 2023","venue":null,"work_id":"ad5f61c2-2e42-4728-9542-94e41a47dd4a","year":2023},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.271068Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:094e6cb6eb33f7aeddf0c6f9af451702db7098cc4012a44b2ee4f7bb33a0a323","observation_id":"c1ef4996-d49b-4c07-90c2-fda28751e9aa","resolution":{"observed_at":"2026-08-12T14:46:13.054193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2008.00299","last_updated":"2020-08-01T17:14:13Z","snapshot_observed_at":"2026-08-10T20:57:27.080865Z","submitted_at":"2020-08-01T17:14:13Z","title":"Eigen-CAM: Class Activation Map using Principal Components","version":1},"cited_work":{"arxiv_id":"2008.00299","doi":null,"metadata_source":"pith","pith_arxiv_id":"2008.00299","snapshot_observed_at":"2026-08-12T14:46:12.657856Z","title":"Eigen-CAM: Class Activation Map using Principal Components","venue":"cs.CV","work_id":"d055839d-13f1-45d5-b287-de9f10790dc3","year":2020},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.273562Z"},"links":{"cited_paper":"/paper/2008.00299","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:429587be6db761f3e46733badc819e67bad72ed2ff39ac889d4bf0dc9aad018e","observation_id":"4cf71907-6636-4b02-958a-29dd79be85da","resolution":{"observed_at":"2026-08-12T14:46:12.660978Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.07421","last_updated":"2018-09-25T18:16:18Z","snapshot_observed_at":"2026-08-16T23:44:59.708767Z","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":"2026-08-12T14:46:12.276412Z","title":"Rise: Randomized input sampling for explanation of black-box models, 2018 b","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.276412Z"},"links":{"cited_paper":"/paper/1806.07421","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:6c04668ef87386d787fe508e225cf534ef76c54f78ec647dcaeaf51d6598020d","observation_id":"5802df91-78b3-4073-9485-1a3ad70ca27d","resolution":{"observed_at":"2026-08-12T14:46:12.276412Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.08485","last_updated":"2019-10-18T16:02:01Z","snapshot_observed_at":"2026-08-18T09:09:37.359122Z","submitted_at":"2019-10-18T16:02:01Z","title":"Understanding Deep Networks via Extremal Perturbations and Smooth Masks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.08485","snapshot_observed_at":"2026-08-12T14:46:12.279082Z","title":"Understanding deep networks via extremal perturbations and smooth masks","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.279082Z"},"links":{"cited_paper":"/paper/1910.08485","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:a4e0821b418e20fd16946ab9eb63d26c258f3fd326932a9556759abd89e567b8","observation_id":"2d22d087-5d87-4be6-a8a2-c0d61e990f60","resolution":{"observed_at":"2026-08-12T14:46:12.279082Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1602.04938","last_updated":"2016-08-09T17:54:52Z","snapshot_observed_at":"2026-08-14T22:10:11.360520Z","submitted_at":"2016-02-16T08:20:14Z","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1602.04938","snapshot_observed_at":"2026-08-12T14:46:12.282205Z","title":"why should I trust you?","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.282205Z"},"links":{"cited_paper":"/paper/1602.04938","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:b67109e4118e2480aa7c0d088d7d9f42b64b50098c1ab02b3cd73de65f775536","observation_id":"b9f7af9b-50cc-4e8a-8451-c224293fabd8","resolution":{"observed_at":"2026-08-12T14:46:12.282205Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.10252","last_updated":"2021-04-20T21:34:24Z","snapshot_observed_at":"2026-08-16T18:30:07.629104Z","submitted_at":"2021-04-20T21:34:24Z","title":"Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis","version":1},"cited_work":{"arxiv_id":"2104.10252","doi":null,"metadata_source":"pith","pith_arxiv_id":"2104.10252","snapshot_observed_at":"2026-08-12T14:46:12.635333Z","title":"Revisiting The Evaluation of Class Activation Mapping for Explainability: A Novel Metric and Experimental Analysis","venue":"cs.CV","work_id":"ff82f8e2-a654-45df-864e-e2cbccbb7ddf","year":2021},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.284658Z"},"links":{"cited_paper":"/paper/2104.10252","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:6132e25867ffab2534b46c7490be6e1d13164cd9b5eb3ac6e8cfd4dcf499a052","observation_id":"3eb075c0-fbca-4c06-b320-7199d37c9699","resolution":{"observed_at":"2026-08-12T14:46:12.638389Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.13291","last_updated":"2022-06-22T12:55:12Z","snapshot_observed_at":"2026-08-16T17:24:40.426954Z","submitted_at":"2022-01-31T14:59:36Z","title":"Metrics for saliency map evaluation of deep learning explanation methods","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.13291","snapshot_observed_at":"2026-08-12T14:46:12.287423Z","title":"Metrics for saliency map evaluation of deep learning explanation methods","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.287423Z"},"links":{"cited_paper":"/paper/2201.13291","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:cf6cf466d405845ec7db3b426b50243edc545b45b553f788f8b542e91c937b1b","observation_id":"7840f774-354e-4f55-bf33-88a894229ce0","resolution":{"observed_at":"2026-08-12T14:46:12.287423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.00507","last_updated":"2016-08-01T17:49:57Z","snapshot_observed_at":"2026-08-14T21:45:54.798820Z","submitted_at":"2016-08-01T17:49:57Z","title":"Top-down Neural Attention by Excitation Backprop","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.00507","snapshot_observed_at":"2026-08-12T14:46:12.290231Z","title":"Top-down neural attention by excitation backprop","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.290231Z"},"links":{"cited_paper":"/paper/1608.00507","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:f374aa445052bb4427fc83bebc80ef6ef60f8d6d0c476e4a9b0a7e27b7cfaad2","observation_id":"1ae36e9f-c1d4-47c3-afeb-84984630064a","resolution":{"observed_at":"2026-08-12T14:46:12.290231Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.06175","last_updated":"2025-09-12T10:28:58Z","snapshot_observed_at":"2026-08-16T16:39:35.959158Z","submitted_at":"2022-08-12T08:50:21Z","title":"The Weighting Game: Evaluating Quality of Explainability Methods","version":2},"cited_work":{"arxiv_id":"2208.06175","doi":null,"metadata_source":"pith","pith_arxiv_id":"2208.06175","snapshot_observed_at":"2026-08-12T14:46:12.613582Z","title":"The Weighting Game: Evaluating Quality of Explainability Methods","venue":"cs.CV","work_id":"d7a7b4e2-7d48-4372-a265-f6dcab4b2497","year":2022},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.293275Z"},"links":{"cited_paper":"/paper/2208.06175","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:9dfa85cee52e8005e5a8d56257d6942a5464e1ab0f3bbe21bd211acccbab553d","observation_id":"cfa7a902-7923-43d1-9a91-a8a08d8ac781","resolution":{"observed_at":"2026-08-12T14:46:12.616788Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T14:46:12.295808Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.295808Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:0344211713f494bd22c5beb01c02e0026fefcfb749a9bf7f3cd2e890cdc3f9af","observation_id":"9c5f0cd7-6bff-4992-8267-516fe761c419","resolution":{"observed_at":"2026-08-12T14:46:12.295808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1405.0312","last_updated":"2015-02-21T01:48:49Z","snapshot_observed_at":"2026-08-21T02:14:04.953864Z","submitted_at":"2014-05-01T21:43:32Z","title":"Microsoft COCO: Common Objects in Context","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1405.0312","snapshot_observed_at":"2026-08-12T14:46:12.298342Z","title":"Belongie, Lubomir D","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.298342Z"},"links":{"cited_paper":"/paper/1405.0312","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:ba24e8ba62fbcac521d39997d7a77783a8e4b13b5feef530306ec34af4513071","observation_id":"6950ec2b-bd6f-44bd-b2de-1f3013970ba9","resolution":{"observed_at":"2026-08-12T14:46:12.298342Z","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":"2026-08-12T14:46:13.043604Z","title":"Threat of adversarial attacks on deep learning in computer vision: A survey","venue":null,"work_id":"ad9b4251-a187-42c3-b848-c568bf8d6336","year":2018},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.301128Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:0b153c6f28da863b4f6b1cb35236e1bbba1aa95513d7800cef8cfb6908174625","observation_id":"6547326c-6a97-45d6-8c9f-aee21bcf5f2c","resolution":{"observed_at":"2026-08-12T14:46:13.046522Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1707.04131","last_updated":"2018-03-20T10:10:10Z","snapshot_observed_at":"2026-08-14T20:47:52.040006Z","submitted_at":"2017-07-13T13:59:15Z","title":"Foolbox: A Python toolbox to benchmark the robustness of machine learning models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.04131","snapshot_observed_at":"2026-08-12T14:46:12.303939Z","title":"Foolbox v0.8.0: A python toolbox to benchmark the robustness of machine learning models","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.303939Z"},"links":{"cited_paper":"/paper/1707.04131","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:8bdaf4da6aa8287355d81ed90df6645760b840a53c93f4d07d57901e7eee1a10","observation_id":"d66aab4f-8c12-4e0d-90db-33a8965f7bc1","resolution":{"observed_at":"2026-08-12T14:46:12.303939Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.08864","last_updated":"2019-10-17T07:46:53Z","snapshot_observed_at":"2026-08-18T04:02:02.238815Z","submitted_at":"2017-10-24T16:02:19Z","title":"One pixel attack for fooling deep neural networks","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.08864","snapshot_observed_at":"2026-08-12T14:46:12.306609Z","title":"One pixel attack for fooling deep neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.306609Z"},"links":{"cited_paper":"/paper/1710.08864","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:46dacb7b399dbfcdc6be48f87b7f27ac2277c4ff42ff39fac92142806ffaa1c3","observation_id":"cc1eec0f-74bc-490c-9374-eb1dff1a259a","resolution":{"observed_at":"2026-08-12T14:46:12.306609Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.04644","last_updated":"2017-03-22T17:46:16Z","snapshot_observed_at":"2026-08-15T15:16:56.180227Z","submitted_at":"2016-08-16T15:59:35Z","title":"Towards Evaluating the Robustness of Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.04644","snapshot_observed_at":"2026-08-12T14:46:12.309521Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.309521Z"},"links":{"cited_paper":"/paper/1608.04644","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:52d3f22642b35d029e356cb86a739dea41cd5b5737e8a57b0af7479a8a5a6a6d","observation_id":"5ffc6531-e2bf-4b11-819c-a7128df421d9","resolution":{"observed_at":"2026-08-12T14:46:12.309521Z","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":"2018.28742","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T14:46:12.578470Z","title":"Detecting adversarial image examples in deep neural networks with adaptive noise reduction","venue":null,"work_id":"3ef390a5-22ba-481e-a73f-ad38f7babb94","year":2021},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.312115Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:cef9d9f941714dd4df44b5ba47189e11739a81cf8747803724e22c065e61e34c","observation_id":"fcdebc18-d9f9-460d-9ecb-50ba7738fbcb","resolution":{"observed_at":"2026-08-12T14:46:12.582071Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.01155","last_updated":"2017-12-05T23:45:08Z","snapshot_observed_at":"2026-08-19T19:49:58.259825Z","submitted_at":"2017-04-04T18:56:53Z","title":"Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.01155","snapshot_observed_at":"2026-08-12T14:46:12.314674Z","title":"Feature squeezing: Detecting adversarial examples in deep neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.314674Z"},"links":{"cited_paper":"/paper/1704.01155","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:feabf9232a680b9d0ecb9b1915ada8ed06f245e7ff5fab9180eecdfb39d5db68","observation_id":"2827293e-eabd-419d-9825-000cf6cfaf9b","resolution":{"observed_at":"2026-08-12T14:46:12.314674Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.09961","last_updated":"2021-11-18T22:13:43Z","snapshot_observed_at":"2026-08-17T16:41:59.143346Z","submitted_at":"2021-11-18T22:13:43Z","title":"A Review of Adversarial Attack and Defense for Classification Methods","version":1},"cited_work":{"arxiv_id":"2111.09961","doi":null,"metadata_source":"pith","pith_arxiv_id":"2111.09961","snapshot_observed_at":"2026-08-12T14:46:12.520488Z","title":"A Review of Adversarial Attack and Defense for Classification Methods","venue":"cs.CR","work_id":"67dfd6db-8ce1-4b0b-9d3e-3facdb3ae9b0","year":2021},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.317546Z"},"links":{"cited_paper":"/paper/2111.09961","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:1211ae73f1bcc95260f683ccad9e6654175e6a2992d0440ebf0888d489f4f80a","observation_id":"56e3047c-a0d0-481a-8c79-85fdaa4c5bf5","resolution":{"observed_at":"2026-08-12T14:46:12.523120Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-08-19T07:17:20.004918Z","submitted_at":"2014-12-20T01:17:12Z","title":"Explaining and Harnessing Adversarial Examples","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6572","snapshot_observed_at":"2026-08-12T14:46:12.320089Z","title":"Goodfellow, Jonathon Shlens, and Christian Szegedy","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.320089Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:b0235fc518714391fc4a3c4e450e12f01015bfca381f21f1974f620a70234ec0","observation_id":"4bd8baa0-c58a-41b9-a5a4-10678570b2ae","resolution":{"observed_at":"2026-08-12T14:46:12.320089Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.06083","last_updated":"2019-09-04T18:53:10Z","snapshot_observed_at":"2026-08-07T14:27:46.872660Z","submitted_at":"2017-06-19T17:53:11Z","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.06083","snapshot_observed_at":"2026-08-12T14:46:12.322436Z","title":"Towards deep learning models resistant to adversarial attacks, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.322436Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:43145f6cd05e412bdac028ad9a24ad43d1b8debcd9a6876797302cadf0c7b714","observation_id":"1163b655-7ca3-40e1-b81b-fe201d04cb8c","resolution":{"observed_at":"2026-08-12T14:46:12.322436Z","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":"2026-08-12T14:46:13.036118Z","title":"A computational approach to edge detection","venue":null,"work_id":"1cc80a64-fc3b-4239-95c8-27642025fc45","year":1986},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.325198Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:9135a765932d2411f808876e279bcbf745c673952be37e1c153faa8ac60c9b4d","observation_id":"e08961cd-622a-4bc0-832a-2fe8d0ed0cee","resolution":{"observed_at":"2026-08-12T14:46:13.038983Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T14:46:13.028521Z","title":"Sanity checks for saliency maps","venue":null,"work_id":"6a6b2ce6-2c2d-47de-ab40-6c755d4b951d","year":2018},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.327458Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:8dabc646cd0b89b6d26a1eb72792cb1d7f13606943ad79a940f9928a7dd3da03","observation_id":"7af3cafe-4e94-4c27-81b0-b657baed84ca","resolution":{"observed_at":"2026-08-12T14:46:13.031370Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T14:46:12.330026Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.330026Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:478954561d9405c7b48db776291b8ffd1fb19ec3cb5287b25f5fb3fd09e6531d","observation_id":"4398dce1-8cdf-4717-a339-59f96161676a","resolution":{"observed_at":"2026-08-12T14:46:12.330026Z","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":"2026-08-12T14:46:12.332881Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.332881Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:de5a8baebe7cc11d9e0fe0b0a6b1ebc23ab02d30439392e566f4692bcd86267c","observation_id":"9eb6b619-f7c8-411f-b990-904d16a931b9","resolution":{"observed_at":"2026-08-12T14:46:12.332881Z","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":"2026-08-12T14:46:13.017121Z","title":null,"venue":null,"work_id":"eaff33fd-0a35-4f55-91a6-5b2bc175093a","year":2017},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.335583Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:20539c529e04b3c85be7efebaf5d870d48a27b2fa887d9d52d27e0c24d126870","observation_id":"c7241323-0eaa-4247-a6a8-e9db72631248","resolution":{"observed_at":"2026-08-12T14:46:13.019824Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1512.03385","last_updated":"2015-12-10T19:51:55Z","snapshot_observed_at":"2026-07-06T04:39:28.429064Z","submitted_at":"2015-12-10T19:51:55Z","title":"Deep Residual Learning for Image Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.03385","snapshot_observed_at":"2026-08-12T14:46:12.338184Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.338184Z"},"links":{"cited_paper":"/paper/1512.03385","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:fa8600eb36d317c5d25a60a78d93add54071db6422a40bbfd0201343419f58e5","observation_id":"4fea1195-2792-434a-a9be-90396d6cebd0","resolution":{"observed_at":"2026-08-12T14:46:12.338184Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.06993","last_updated":"2018-01-28T17:12:02Z","snapshot_observed_at":"2026-08-14T21:42:53.838437Z","submitted_at":"2016-08-25T00:44:55Z","title":"Densely Connected Convolutional Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.06993","snapshot_observed_at":"2026-08-12T14:46:12.341287Z","title":"Weinberger","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.341287Z"},"links":{"cited_paper":"/paper/1608.06993","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:499eaf67e38851c4d239543c1277dc57846543beb700c403ac87efd27dae711b","observation_id":"dbcd47a8-ccba-4301-858a-050b2a2e271c","resolution":{"observed_at":"2026-08-12T14:46:12.341287Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.03545","last_updated":"2022-03-02T15:08:16Z","snapshot_observed_at":"2026-08-18T10:36:46.789607Z","submitted_at":"2022-01-10T18:59:10Z","title":"A ConvNet for the 2020s","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.03545","snapshot_observed_at":"2026-08-12T14:46:12.344565Z","title":"A convnet for the 2020s","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.344565Z"},"links":{"cited_paper":"/paper/2201.03545","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:883bd947bb8a1943f7702963f887f9217870aa4e026f4ce9cc745042ee3e4639","observation_id":"9ca60266-d840-44bb-8678-27ade01131d0","resolution":{"observed_at":"2026-08-12T14:46:12.344565Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.03697","last_updated":"2021-03-29T13:02:36Z","snapshot_observed_at":"2026-08-16T18:53:11.030440Z","submitted_at":"2021-01-11T04:46:11Z","title":"RepVGG: Making VGG-style ConvNets Great Again","version":3},"cited_work":{"arxiv_id":"2101.03697","doi":null,"metadata_source":"pith","pith_arxiv_id":"2101.03697","snapshot_observed_at":"2026-08-12T14:46:12.400372Z","title":"RepVGG: Making VGG-style ConvNets Great Again","venue":"cs.CV","work_id":"aeaafe7b-c2d2-43d9-bde3-fd1125190e58","year":2021},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.347977Z"},"links":{"cited_paper":"/paper/2101.03697","citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:c28943169a7562569112558f586c668f5cd3627101446369b4a8784c2fc684a3","observation_id":"f69a5874-5e6b-4a73-9351-217b7cf8f562","resolution":{"observed_at":"2026-08-12T14:46:12.404161Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T14:46:13.009561Z","title":"Torchcam: class activation explorer","venue":null,"work_id":"15df1258-bfb3-4bf4-8a2e-d5ac226e4372","year":2020},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.350817Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:e634e098b5741dd46aefb39247efc9fe1837b92d6f29862135bb930a9722ed8e","observation_id":"d6db856e-2210-47a3-80fb-49d46418c746","resolution":{"observed_at":"2026-08-12T14:46:13.012369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T14:46:13.001203Z","title":"Saliency library","venue":null,"work_id":"3848410a-36cf-453b-8c68-d93fae4ea7ee","year":2022},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.353466Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:1edeeb5749dd54b2d93baf2693e5a10e6dd3b88a753eb5c609ec364cde605b45","observation_id":"06da81c1-aa4c-44f6-928f-d2bdb49e03c8","resolution":{"observed_at":"2026-08-12T14:46:13.004347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1177/1536867x0200200103","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T14:46:12.381181Z","title":"nonparametric","venue":null,"work_id":"d8c1a233-99d4-40fe-a060-019464bcf243","year":2002},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.356205Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:08816f8afa17451a23de7b748ddbd0b884efab20650668f7a8d56412361fc72a","observation_id":"846325ef-80f3-437d-ac40-24f047018e40","resolution":{"observed_at":"2026-08-12T14:46:12.384963Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T14:46:12.359134Z","title":"Towards deep learning models resistant to adversarial attacks, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-12T14:46:12.359134Z"},"links":{"citing_paper":"/paper/2411.14946"},"observation_digest":"sha256:4895b402c7306ac060d73b47f09320f9517678934eedb07308231feb28530200","observation_id":"d4e8f7fa-1d16-4464-a196-7ec540aef69a","resolution":{"observed_at":"2026-08-12T14:46:12.359134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.14946","last_updated":"2024-11-22T13:57:56Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T20:53:19.083386Z","submitted_at":"2024-11-22T13:57:56Z","title":"Reliable Evaluation of Attribution Maps in CNNs: A Perturbation-Based Approach"},"reference_resolution":{"displayed":61,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":39,"verified_exact":9,"verified_fuzzy":12},"total_outbound_references":61},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 0 inbound Pith citation observations for arXiv:2411.14946."}