{"as_of":"2026-08-21T10:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:35ded72032db609c3d44671eaa41375f659cf99ab3a6edde2f72d557dddf6e9d","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-31T21:53:21.079465Z","state":"measured"},{"denominator":48,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":48,"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/2607.24177/citation-record","integrity":"/paper/2607.24177/integrity","json":"/paper/2607.24177/citation-record.json","paper":"/paper/2607.24177"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-31T21:53:20.832937Z","title":"EMBER: An Open Dataset for Training Static PE Malware Machine Learning Models,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.832937Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:93a84e2c5936fe14d64acad670fd3bbf99b1d5faf52d234dbed51457cce9023b","observation_id":"0703d204-0482-49dc-9234-89099b678b96","resolution":{"observed_at":"2026-07-31T21:53:20.832937Z","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":"2026-07-31T21:53:20.838858Z","title":"Deep neural network based malware detection using two dimensional binary program features,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.838858Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:5c8e13d3f9449e3a14f988417ece20c34dc06c84c3645d203a8e98814cffb40b","observation_id":"4d75c38f-d554-489c-b140-c8d66915a541","resolution":{"observed_at":"2026-07-31T21:53:20.838858Z","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":"2026-07-31T21:53:20.844819Z","title":"Novel feature extraction, selection and fusion for effective malware family classification,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.844819Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:c3041d0ee9344615e0dbc65efd91894484503fafce43f170e353974712e77935","observation_id":"b7d10bde-2f6a-4bbe-9017-059d823ee83c","resolution":{"observed_at":"2026-07-31T21:53:20.844819Z","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":"2026-07-31T21:53:20.850773Z","title":"Malware detection by eating a whole EXE,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.850773Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:8670496024ef4382318f1c38272807d01989f04193c2cdf86d8c17d691f0be62","observation_id":"dd77f27e-2f1f-4551-a391-3aaa028627f8","resolution":{"observed_at":"2026-07-31T21:53:20.850773Z","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":"2026-07-31T21:53:20.857098Z","title":"Deep convolutional malware classifiers can learn from raw executables and labels only,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.857098Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:82be9e96974507700013926665f77c56c1af945c809764d07f6c8a400803a09f","observation_id":"f25e293a-b4a4-4eb8-bd33-5c8a891e7b0e","resolution":{"observed_at":"2026-07-31T21:53:20.857098Z","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":"2026-07-31T21:53:20.862159Z","title":"Activation analysis of a byte-based deep neural network for malware classification,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.862159Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:1c030c1127c9be7adbb8e782e0d0f46214bec2c06eda0fb0ca133641e019c049","observation_id":"6f8e5109-9976-444e-98d5-4ee3829a287f","resolution":{"observed_at":"2026-07-31T21:53:20.862159Z","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":"2026-07-31T21:53:20.867583Z","title":"Auditing static machine learning anti-malware tools against metamorphic attacks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.867583Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:2ae23ddb5ac46d82fbaa616ebd9e272ba745494a770361896e71c8eed7d62a7a","observation_id":"e38a0939-db34-4906-92a2-cb379e6b2d44","resolution":{"observed_at":"2026-07-31T21:53:20.867583Z","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":"2026-07-31T21:53:20.872633Z","title":"Malware images: visualization and automatic classification,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.872633Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:7b05d469ab6bb009d501098f19596fed82251e12a822f8881a163c939bc43a76","observation_id":"3a547b83-8167-484c-a996-65837886fe62","resolution":{"observed_at":"2026-07-31T21:53:20.872633Z","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":"2026-07-31T21:53:20.878729Z","title":"Using convolutional neural networks for classification of malware represented as images,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.878729Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:a4d0ee672648a1a38ac0f55d33e1b1fbaaf7d593605deafbad7d7d2c351a7473","observation_id":"e982fc11-d7fb-4081-a142-d239786c67ea","resolution":{"observed_at":"2026-07-31T21:53:20.878729Z","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":"2026-07-31T21:53:20.883600Z","title":"RS-Del: Edit distance robustness certificates for sequence classifiers via randomized deletion,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.883600Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:370f75c4121c6695c2830d38ed60b87babd1afa2c71c9429ecda08115c755925","observation_id":"3becbb5f-2de1-4e58-8187-857bf3e23497","resolution":{"observed_at":"2026-07-31T21:53:20.883600Z","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":"2026-07-31T21:53:20.888590Z","title":"Towards a practical defense against adversarial attacks on deep learning-based malware detectors via ran- domized smoothing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.888590Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:62093abc81a8740956cdc08b8d66235d6303b70b5564989db9ceefdc3dca7d64","observation_id":"a22639a3-5a01-4bea-a0ce-8eae4f64d322","resolution":{"observed_at":"2026-07-31T21:53:20.888590Z","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":"2026-07-31T21:53:20.893365Z","title":"Certified robustness of static deep learning-based malware detec- tors against patch and append attacks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.893365Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:acbb59870dc4f7b5cd760a848f4603c2160a0b104b8b612175f7c4330083a947","observation_id":"938603c2-5afd-419f-ae5e-31741d79f828","resolution":{"observed_at":"2026-07-31T21:53:20.893365Z","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":"2026-07-31T21:53:20.898924Z","title":"Drsm: De- randomized smoothing on malware classifier providing certified robust- ness,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.898924Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:ca61c9753df2c315e06140fede9ca996f89f073f11d7e64b5075f7f078070356","observation_id":"ca3c23d5-9642-4eab-a337-6fd8713e5bbe","resolution":{"observed_at":"2026-07-31T21:53:20.898924Z","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":"2026-07-31T21:53:20.903864Z","title":"Adversarial robustness of deep learning-based malware detectors via (de)randomized smoothing,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.903864Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:e360014dc2bdee57cca0f4ef09055c5e4af64958b85aa30b9c2c7d4a5731fcd4","observation_id":"e3723a2f-880e-4f27-8509-96f38acf8fff","resolution":{"observed_at":"2026-07-31T21:53:20.903864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.00392","last_updated":"2024-05-01T08:45:57Z","snapshot_observed_at":"2026-08-18T20:14:49.934443Z","submitted_at":"2024-05-01T08:45:57Z","title":"Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothing","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.00392","snapshot_observed_at":"2026-07-31T21:53:20.909079Z","title":"Certified adversarial robustness of machine learning-based malware detectors via (de)randomized smoothing,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.909079Z"},"links":{"cited_paper":"/paper/2405.00392","citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:c8a712014722f35008a4844775ddb85123238acc4fe24dbc7e02cfabcac549c1","observation_id":"63e869bd-ed37-435d-9d72-89a9fd9b42aa","resolution":{"observed_at":"2026-07-31T21:53:20.909079Z","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":"2026-07-31T21:53:20.914782Z","title":"Certified adversarial robustness via randomized smoothing,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.914782Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:02b7d42de86647aad9f77c994490bcc7c0fe038594085019d95025bf95331c9d","observation_id":"c89f9052-57f3-44cc-9184-61389e3c746c","resolution":{"observed_at":"2026-07-31T21:53:20.914782Z","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":"2026-07-31T21:53:20.920951Z","title":"(de)randomized smoothing for certifiable defense against patch attacks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.920951Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:1514f6cb9cc9ef047e4dbffa8a48d85b639a936a3bd0010ef08a3ac6c7382a97","observation_id":"0a8b8d74-48ab-4904-9e7c-afe88bda473b","resolution":{"observed_at":"2026-07-31T21:53:20.920951Z","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":"2026-07-31T21:53:20.926453Z","title":"{TESSERACT}: Eliminating experimental bias in malware classifi- cation across space and time,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.926453Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:485106cd72a8fe5e26a5295833d6110238d3843dbcfbf5a2d47e85b249b36b83","observation_id":"7efa643e-2642-4492-b8fc-5a949b366580","resolution":{"observed_at":"2026-07-31T21:53:20.926453Z","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":"2026-07-31T21:53:20.931992Z","title":"Adversarial malware binaries: Evading deep learning for malware detection in executables,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.931992Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:9ee3f72b8fba86c1ebd171a2a0849564b8c1a4a07d6aeef33e9e8e7a922a1647","observation_id":"3b1e63cd-cd69-4da3-ae6e-480f0d948343","resolution":{"observed_at":"2026-07-31T21:53:20.931992Z","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":"2026-07-31T21:53:20.936758Z","title":"Malware makeover: Breaking ml-based static analysis by modifying executable bytes,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.936758Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:69fd37a1c350b7693bcfa144a4406af4cbdb6b58431f8871bd7bd8a2b1e3da61","observation_id":"1c66b820-056a-44ef-b0ca-ebee737bcf5b","resolution":{"observed_at":"2026-07-31T21:53:20.936758Z","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":"2026-07-31T21:53:20.942863Z","title":"Adversarial exemples: A survey and experimental evaluation of practical attacks on machine learning for windows malware detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.942863Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:934782e52861d9d1ce67352c157159934d116d657d69519137c394dccd4f4bdf","observation_id":"ce9dfaea-e810-42f9-ac55-843da7c0e3fc","resolution":{"observed_at":"2026-07-31T21:53:20.942863Z","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":"2026-07-31T21:53:20.948823Z","title":"Functionality-preserving black-box optimization of adversarial win- dows malware,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.948823Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:ea2d0af328c0129d1eb8f244438585db0369c43ea4ed05cc9d5bd1d4c92a7404","observation_id":"95a1ebe8-6c36-48de-a390-b932f9aa90ba","resolution":{"observed_at":"2026-07-31T21:53:20.948823Z","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":"2026-07-31T21:53:20.954512Z","title":"Adversarial training for{Raw-Binary}malware classifiers,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.954512Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:93b7cd4db997fa535ce75f925a8669d48e5e54f88153ae00aa5eb5c2efc41b43","observation_id":"f2970cae-0295-464d-951d-5ab7c6e2bf95","resolution":{"observed_at":"2026-07-31T21:53:20.954512Z","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":"2026-07-31T21:53:20.959153Z","title":"Wild patterns: Ten years after the rise of adversarial machine learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.959153Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:4db7b3b9199287794c632b6367348115eb9c1a446b9e7f7fdc1a5e67dbca5324","observation_id":"657e609a-2f5f-4d69-bfaa-46b23d8e5d0e","resolution":{"observed_at":"2026-07-31T21:53:20.959153Z","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":"2026-07-31T21:53:20.964990Z","title":"Attackbench: Evaluating gradient-based attacks for adversarial examples,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.964990Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:06d43bf17299885e73af548460faba2084e2a3dbfd603914330e175ce083cc37","observation_id":"7ddded6e-6dc9-4746-88b9-1f5cbfa682af","resolution":{"observed_at":"2026-07-31T21:53:20.964990Z","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":"2026-07-31T21:53:20.969530Z","title":"Robustbench: a standardized adversarial robustness benchmark,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.969530Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:0515d81774da6bbc8b8d2864641bd1666523f07c00642960d5a18dfa6a563349","observation_id":"8d75e0db-2b07-4e1e-8200-c8f3e0912260","resolution":{"observed_at":"2026-07-31T21:53:20.969530Z","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":"2026-07-31T21:53:20.975217Z","title":"Intriguing properties of adversarial ml attacks in the problem space,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.975217Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:5d15b32a75fe4dab2f8cfd5a1fc44ed377fa3ac345cd2eeaa6923734340cdab1","observation_id":"9ec22f84-d34c-4ef7-a075-1737cdc89b2c","resolution":{"observed_at":"2026-07-31T21:53:20.975217Z","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":"2026-07-31T21:53:20.979988Z","title":"Robust intelligent malware detection using deep learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.979988Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:136b5c877fd7cbc0238ca871b326c48c5ee0ffeb313a3841031835d1fccd1d0f","observation_id":"b2ea6e32-def6-49ad-8a66-6034e3793168","resolution":{"observed_at":"2026-07-31T21:53:20.979988Z","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":"2026-07-31T21:53:20.984856Z","title":"Optimized approaches to malware detection: A study of machine learning and deep learning techniques,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.984856Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:095af201780f7c20f9cb45eb44b5ec615d983efba34d2fc6897745d72aca7008","observation_id":"c9899227-e3d2-490a-9a1b-723b2d7816d4","resolution":{"observed_at":"2026-07-31T21:53:20.984856Z","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":"2026-07-31T21:53:20.989433Z","title":"Evaluating realistic adversarial attacks against machine learning models for windows pe malware detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.989433Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:f088b1bf8f4549cbf8d2df94889892de0bbc65f5f8bbe431873f24bb05ba7b26","observation_id":"8afc5b03-5920-4e5b-86db-2892be95a49f","resolution":{"observed_at":"2026-07-31T21:53:20.989433Z","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":"2026-07-31T21:53:20.994825Z","title":"A comparison of adversarial malware generators,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.994825Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:9da193b9405ba83dac95bfe681eec263d6da5826c3455c149456f77e7efb2077","observation_id":"2c02504b-38e5-4b48-8758-bb3a9af11223","resolution":{"observed_at":"2026-07-31T21:53:20.994825Z","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":"2026-07-31T21:53:20.999794Z","title":"The robust malware detection challenge and greedy random accelerated multi-bit search,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:20.999794Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:36804918c2d0b32171af38502586c180c093fdcd9c9bb3bd90675e3b3f212cee","observation_id":"0e4443c0-64d5-4a76-983d-4b62ad3137d6","resolution":{"observed_at":"2026-07-31T21:53:20.999794Z","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":"2026-07-31T21:53:21.004831Z","title":"Fast minimum-norm adversarial attacks through adaptive norm constraints,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.004831Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:0c194761e4963c1d4e181f3f76ce565c8a8ef418605f8f1ec64252a836e9504e","observation_id":"e24569ce-fcf5-4884-84e3-fe097859ddaa","resolution":{"observed_at":"2026-07-31T21:53:21.004831Z","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":"2026-07-31T21:53:21.009550Z","title":"Quo vadis: hybrid machine learning meta-model based on contextual and behavioral malware representations,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.009550Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:8f89fbb161029ce569d22bae52606d8eae294135c91d577a2d17f152eaa78ffb","observation_id":"ae529dd3-a850-45f0-9be8-5fb7aa2b8da9","resolution":{"observed_at":"2026-07-31T21:53:21.009550Z","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":"2026-07-31T21:53:21.014858Z","title":"Greedy function approximation: a gradient boosting machine,","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.014858Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:2cd4f36c7ede6fbb46db17689a2446daeb408e93b842011292990d74f0eb6e24","observation_id":"ea3ea3a9-1d68-4056-aef2-768e88ab103e","resolution":{"observed_at":"2026-07-31T21:53:21.014858Z","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":"2026-07-31T21:53:21.020466Z","title":"Lightgbm: A highly efficient gradient boosting decision tree,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.020466Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:3b1aeb213453e5e2a1bd3945824c048a7534b759dc43ecc8bc4dd4dbc211fd4b","observation_id":"856f7768-d114-4dc1-9ba4-ef91cfa3a4db","resolution":{"observed_at":"2026-07-31T21:53:21.020466Z","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":"2026-07-31T21:53:21.025483Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.025483Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:2db1bf73a33e126aa740214ba5e92df8d11c142f24029e160b67dae207dc66da","observation_id":"04adb692-8862-42c4-ac8d-d9fcca3bc93d","resolution":{"observed_at":"2026-07-31T21:53:21.025483Z","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":"2026-07-31T21:53:21.030263Z","title":"Pytorch: An imperative style, high-performance deep learning library,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.030263Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:a6a31e8678589d9db3c8795bf8bee058b1a12bfad396440b72a38c55e76a7c3a","observation_id":"9ae1f8f8-ab18-417a-b2ed-c3827f24e7a9","resolution":{"observed_at":"2026-07-31T21:53:21.030263Z","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":"2026-07-31T21:53:21.035151Z","title":"Why do adversarial attacks transfer? explaining transferability of evasion and poisoning attacks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.035151Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:904fc6f20e81310629be9652eb0ebc1158efa1db7fc5ba5fae056c49e42a6e1f","observation_id":"4d293ae2-1dec-4812-83e3-18d219c1d4c4","resolution":{"observed_at":"2026-07-31T21:53:21.035151Z","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":"2026-07-31T21:53:21.040103Z","title":"The rise of machine learning for detection and classification of malware: Research developments, trends and challenges,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.040103Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:c6c03b17704c1b988d8afb42acb545a8cdaa3d1a3d25c3db91e6896c96ba2ceb","observation_id":"05772be9-4337-4cfb-aa07-55421aef50aa","resolution":{"observed_at":"2026-07-31T21:53:21.040103Z","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":"2026-07-31T21:53:21.044754Z","title":"Sorel-20m: A large scale benchmark dataset for malicious pe detection,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.044754Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:42fd72e645b8d23d2ef62441304ce0cd6d0d125c94275708987b15ad25fc81db","observation_id":"ba49f6b1-360d-4eea-b4fe-ebb63d9d6a9d","resolution":{"observed_at":"2026-07-31T21:53:21.044754Z","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":"2026-07-31T21:53:21.049642Z","title":"Ember2024-a benchmark dataset for holistic evaluation of malware classifiers,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.049642Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:adf2a1b0482e11da88e2df5e32a7fd9d8d70b3938e0d102cc116d594c0bfb04e","observation_id":"7c3e30ba-49c8-4b0a-a20c-3545789750b9","resolution":{"observed_at":"2026-07-31T21:53:21.049642Z","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":"2026-07-31T21:53:21.054196Z","title":"Beyond raw bytes: Towards large language models,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.054196Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:0461ff0255bcc1f08ed9b00a927539bc57e16616f57f180a0f09e466cb8edb99","observation_id":"bb3b448f-0748-44a2-920b-53bc11c2cbc9","resolution":{"observed_at":"2026-07-31T21:53:21.054196Z","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":"2026-07-31T21:53:21.059149Z","title":"Guided malware sample analysis based on graph neural networks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.059149Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:17de36e564d3ef977379e620420b7bfef3155436ee595ccbf343a48b9e3bfe14","observation_id":"8d9f75d9-bfdc-488c-9a51-faa381461411","resolution":{"observed_at":"2026-07-31T21:53:21.059149Z","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":"2026-07-31T21:53:21.064235Z","title":"Training robust ml-based raw-binary malware detectors in hours, not months,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.064235Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:6584422c3431560145efb8d0b92ca0513e61c46e01cdf028cdbce09ecbb893e4","observation_id":"318d8e34-4546-46d0-a6bb-7cab94e0c1ac","resolution":{"observed_at":"2026-07-31T21:53:21.064235Z","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":"2026-07-31T21:53:21.069202Z","title":"Updating windows mal- ware detectors: Balancing robustness and regression against adversarial exemples,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.069202Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:8a629bde0c1532f92e71680fd336031333fb7897421ef0b84afe20b365e54b59","observation_id":"2f3665b1-6c74-4788-800c-f11c8607ba91","resolution":{"observed_at":"2026-07-31T21:53:21.069202Z","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":"2026-07-31T21:53:21.074185Z","title":"Mab- malware: A reinforcement learning framework for blackbox generation of adversarial malware,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.074185Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:40480a92b0649f81ce958ccbb1b1b59673bf74646ab65073ea0220c5eb0e46d7","observation_id":"dd1e21e7-e3b5-4b7a-9d53-48f126a22726","resolution":{"observed_at":"2026-07-31T21:53:21.074185Z","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":"2026-07-31T21:53:21.079465Z","title":"Creating valid ad- versarial examples of malware,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-31T21:53:21.079465Z"},"links":{"citing_paper":"/paper/2607.24177"},"observation_digest":"sha256:b4844bff67461a329a5174844a2247258ca41ef747572eb679f484dfb2e54067","observation_id":"72b6ffa1-20fd-47c8-9466-7735748c9051","resolution":{"observed_at":"2026-07-31T21:53:21.079465Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.24177","last_updated":"2026-07-27T09:02:56Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-21T07:24:47.509234Z","submitted_at":"2026-07-27T09:02:56Z","title":"EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":47,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":48},"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 48 of 48 outbound references and 0 inbound Pith citation observations for arXiv:2607.24177."}