{"as_of":"2026-08-10T02:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1ebbe66b9ab80007ad0db9e78b631ec53d0386db2b362aa03f4a8bbae6ca9b90","coverage":[{"denominator":36,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":36,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T00:23:55.631073Z","state":"measured"},{"denominator":36,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":36,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.14217/citation-record","integrity":"/paper/2506.14217/integrity","json":"/paper/2506.14217/citation-record.json","paper":"/paper/2506.14217"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1806.08049","last_updated":"2018-06-21T02:33:44Z","snapshot_observed_at":"2026-07-06T06:46:01.245927Z","submitted_at":"2018-06-21T02:33:44Z","title":"On the Robustness of Interpretability Methods","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.08049","snapshot_observed_at":"2026-08-07T00:23:50.336227Z","title":"and Jaakkola, T","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:50.336227Z"},"links":{"cited_paper":"/paper/1806.08049","citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:ca972e007e82957bcd01e1267ac2afbed913d8421e0b1d445054612a887e741c","observation_id":"eb904b32-4d1f-4680-bcd0-dea22805649a","resolution":{"observed_at":"2026-08-07T00:23:50.336227Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.11866","last_updated":"2022-06-01T21:25:21Z","snapshot_observed_at":"2026-08-09T10:12:27.784966Z","submitted_at":"2022-06-01T21:25:21Z","title":"A Multi-Policy Framework for Deep Learning-Based Fake News Detection","version":1},"cited_work":{"arxiv_id":"2206.11866","doi":null,"metadata_source":"pith","pith_arxiv_id":"2206.11866","snapshot_observed_at":"2026-08-07T00:23:55.961309Z","title":"A Multi-Policy Framework for Deep Learning-Based Fake News Detection","venue":"cs.CL","work_id":"e5cd71b9-b6c5-4668-938d-bc8a30b28ef2","year":2022},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:50.456187Z"},"links":{"cited_paper":"/paper/2206.11866","citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:7a092f02b498f296e5debd7577ff14ad1a4a159351fae355eaf5b625031148fc","observation_id":"02253864-8304-4404-bc13-70b9bf527633","resolution":{"observed_at":"2026-08-07T00:23:56.026024Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:24:12.675908Z","title":"Transformer interpretability beyond attention visualization","venue":null,"work_id":"721a856c-6bfc-4da4-9568-7704117331ff","year":2021},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:50.627172Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:adb9b9cf0fe1ecf54b67433a46da4daa9192ae39f99dcc4512ec3a6927c94883","observation_id":"a6f0da04-c1cd-4db2-87ab-fbc88093d77a","resolution":{"observed_at":"2026-08-07T00:24:12.679621Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:24:12.658006Z","title":"When are saliency maps trustworthy? In International Conference on Learning Representations (ICLR), 2023","venue":null,"work_id":"dc894c32-2bbf-4031-ba4e-2dad81fb84c1","year":2023},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:50.796398Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:2b5966df57d8e2081e7395277702d322dca913fc7cbac71d866011bc58a2380d","observation_id":"742ac470-09b0-433d-add3-722f44171545","resolution":{"observed_at":"2026-08-07T00:24:12.667441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:24:12.640806Z","title":"and Hein, M","venue":null,"work_id":"d8d8d374-8a9f-4171-bd06-1e98c6f0d575","year":2020},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:50.932126Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:c3055a1c62a5bc141b0c8bc91eb7677f2c147c9d7b50674a66dd16f81a0c8d50","observation_id":"40e80b01-6f7e-40b6-b243-f47953881e8d","resolution":{"observed_at":"2026-08-07T00:24:12.648934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.10265","last_updated":"2018-05-29T09:48:05Z","snapshot_observed_at":"2026-08-02T03:18:47.605415Z","submitted_at":"2018-05-25T17:35:39Z","title":"Training verified learners with learned verifiers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.10265","snapshot_observed_at":"2026-08-07T00:23:51.093805Z","title":"Training verified learners with learned verifiers","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:51.093805Z"},"links":{"cited_paper":"/paper/1805.10265","citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:e9989e111462576aff6dffb8dfbf4bef8bf2336b5d6ea9c3c692af6795651d50","observation_id":"1a917d0c-7c5e-40de-b6b2-edd332b8c80f","resolution":{"observed_at":"2026-08-07T00:23:51.093805Z","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":"2026-08-07T00:24:12.626920Z","title":null,"venue":null,"work_id":"0f37b87d-e4fc-40d3-9c61-31c7a06b2cb7","year":2017},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:51.635188Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:f470a0033630f805cbdc8f668fed48b0eea97a42565c0564559ceb5a9f19df7b","observation_id":"b7a22688-f8a2-490e-8eab-79c972306900","resolution":{"observed_at":"2026-08-07T00:24:12.632430Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:24:12.610784Z","title":"AI2 : Safety and robustness certification of neural networks with abstract interpretation","venue":null,"work_id":"6d504824-2add-490c-9882-fac9facb036f","year":2018},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:51.764818Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:2f90ceeebda20e437a90404abde19f227c32842756746c6a84f3837582c2a60d","observation_id":"aa2d56ff-ea84-43de-9866-775e3102d92a","resolution":{"observed_at":"2026-08-07T00:24:12.616916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:24:12.587788Z","title":null,"venue":null,"work_id":"fdce2d4d-2463-48cf-bb5e-8f69ff1cf487","year":2019},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:51.905023Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:27369f8a56cddcb3f02860048f0a86bb349b5706c747f351c1459aa10cfdcb11","observation_id":"ccf92d50-1e96-4b8d-aa57-0d52682469b2","resolution":{"observed_at":"2026-08-07T00:24:12.596279Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6572","last_updated":"2015-03-20T20:19:16Z","snapshot_observed_at":"2026-07-06T04:04:16.777653Z","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":"2026-08-07T00:23:52.020756Z","title":"J., Shlens, J., and Szegedy, C","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:52.020756Z"},"links":{"cited_paper":"/paper/1412.6572","citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:e3b7a7a9157b47419d8ee748f882dee93b909fe8741698288d2d5850629747a3","observation_id":"11a75fc9-f3fe-4607-aae7-178853247fa4","resolution":{"observed_at":"2026-08-07T00:23:52.020756Z","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":"2026-08-07T00:24:12.571813Z","title":"Improving robustness without sacrificing accuracy via learned data augmentation","venue":null,"work_id":"492c4dfd-011b-4192-a88c-3a546252afa5","year":2021},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:52.198905Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:bcc03e974d34abd2c4b79f1ba4f29a9f0fdeba887b1639cf5530c486d65bf133","observation_id":"31cacdb3-022d-4c27-b8e6-c1711fe6c12b","resolution":{"observed_at":"2026-08-07T00:24:12.579389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:24:12.555021Z","title":"The many faces of robustness: A critical analysis of out-of-distribution generalization","venue":null,"work_id":"29173e29-c156-46ea-bc5f-ee26171d5eb8","year":2021},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:52.439422Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:fe04ed7cfc5e3e8a2c948f1f50d4e4a967bc9d7e74c4d57893144bf468710f32","observation_id":"3c16ef11-0287-422d-aab6-ea1957056617","resolution":{"observed_at":"2026-08-07T00:24:12.559277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:24:12.529986Z","title":"A benchmark for interpretability methods in deep neural networks","venue":null,"work_id":"c930839d-1007-4c7e-b2be-492e0048be33","year":2020},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:52.589827Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:29e462fcc1a5900456223002a79bc18370a3c6a2fb8b1d40d60442ed2d24437f","observation_id":"fe1e6bb3-924e-4bd2-9845-6e267b5e2991","resolution":{"observed_at":"2026-08-07T00:24:12.539819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:24:12.504724Z","title":"Benchmark for evaluating saliency methods","venue":null,"work_id":"6a14070d-ad65-483a-b910-5f140ab18162","year":2021},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:52.717268Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:f0e1f5c0359f2df2c23b2c936826b2304fe0197cb72f8094a79245a17652caf4","observation_id":"e2ffd8ab-c0b6-4f89-ab29-25ce1b54fc99","resolution":{"observed_at":"2026-08-07T00:24:12.514638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:24:12.481879Z","title":"The complete verification of neural networks: the eran approach","venue":null,"work_id":"7e4ecda9-9f14-454b-b234-b1fc0f2f90a6","year":2021},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:52.841588Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:8288e24f0829a923c0083cc1d0aa1c2f312baaf4effb21da0ac0de64fc7bd57d","observation_id":"7a575e89-f343-4071-b1b1-558d28fb56ad","resolution":{"observed_at":"2026-08-07T00:24:12.492138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.06506","last_updated":"2022-06-16T21:52:45Z","snapshot_observed_at":"2026-08-03T07:43:37.673449Z","submitted_at":"2021-05-13T18:40:57Z","title":"Sanity Simulations for Saliency Methods","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.06506","snapshot_observed_at":"2026-08-07T00:23:53.035334Z","title":"Sanity simulations for saliency methods","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:53.035334Z"},"links":{"cited_paper":"/paper/2105.06506","citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:a1efd291543118489f7cd8ce38bd04cd5ba87f1dc78070476889d2ba2bf16b1a","observation_id":"13aa7c62-7e58-4ce6-aa04-14893b02f09d","resolution":{"observed_at":"2026-08-07T00:23:53.035334Z","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":"2026-08-07T00:24:12.460723Z","title":"T., Dähne, S., and Erhan, D","venue":null,"work_id":"5a2fa943-dc3b-4d87-a844-789aeb98d6fa","year":2019},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:53.160344Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:2a241712445932433b0ff077c639690af1aee977d3ce7ae92e1b14d194a5a94e","observation_id":"9169b464-fb00-4fa0-9473-dd6b9e0ae639","resolution":{"observed_at":"2026-08-07T00:24:12.471185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"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":"2026-08-07T00:23:53.297134Z","title":"Towards deep learning models resistant to adversarial attacks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:53.297134Z"},"links":{"cited_paper":"/paper/1706.06083","citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:89999da3951a3731173ed240a8f507cdad71298001410c65a392e13ed4b94962","observation_id":"b2121133-f6bf-4206-b2f1-416f426a7661","resolution":{"observed_at":"2026-08-07T00:23:53.297134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13928","last_updated":"2023-05-23T10:53:59Z","snapshot_observed_at":"2026-07-06T15:31:18.144952Z","submitted_at":"2023-05-23T10:53:59Z","title":"A Physics-Based Hybrid Dynamical Model of Hysteresis in Polycrystalline Shape Memory Alloy Wire Transducers","version":1},"cited_work":{"arxiv_id":"2305.13928","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.13928","snapshot_observed_at":"2026-08-07T00:23:55.752803Z","title":"A Physics-Based Hybrid Dynamical Model of Hysteresis in Polycrystalline Shape Memory Alloy Wire Transducers","venue":"eess.SY","work_id":"a4b6e3e0-7075-4cbc-846c-b173fbc5d945","year":2023},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:53.436041Z"},"links":{"cited_paper":"/paper/2305.13928","citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:4c5ad40a7d4e993d127cd28567c558c55f8bc04c44666cb759cea4de1ce706d5","observation_id":"0ab1d656-2a97-4f94-8f73-6122c8d41acc","resolution":{"observed_at":"2026-08-07T00:23:55.809284Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:24:12.389975Z","title":"Centered kernel alignment losses for saliency method faithfulness","venue":null,"work_id":"65c8f8ec-084b-4911-8c4e-418e1e05dd4e","year":2022},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:53.584865Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:5dd9ff42f84267bcf1e05d91c4b1b3f33594dbadfd16f11420667453d2a52372","observation_id":"da320906-879a-4c15-86de-55baef3b6347","resolution":{"observed_at":"2026-08-07T00:24:12.445441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.09404","last_updated":"2017-11-26T15:20:46Z","snapshot_observed_at":"2026-07-06T06:11:12.245010Z","submitted_at":"2017-11-26T15:20:46Z","title":"Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.09404","snapshot_observed_at":"2026-08-07T00:23:53.692184Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:53.692184Z"},"links":{"cited_paper":"/paper/1711.09404","citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:33dac6be055076ae006b8ff90ae69d8f8b0c0bf0f289269a4a947bc5ff0f7279","observation_id":"84fce78b-0391-4050-9b85-89c4ac8ff234","resolution":{"observed_at":"2026-08-07T00:23:53.692184Z","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":"2026-08-07T00:24:12.291792Z","title":"Evaluating the visualization of what a deep neural network has learned","venue":null,"work_id":"90de272a-75aa-4c6e-ba6a-a0ae148e867c","year":2017},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:53.864399Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:6014aeb4620acf4ccb1a72098bd5c26a089a3e21156a9aff332e1b3397f94e87","observation_id":"f4a70117-7445-4065-bd05-0dcc8167812f","resolution":{"observed_at":"2026-08-07T00:24:12.351917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:24:12.173955Z","title":"Explainable artificial intelligence: Understanding, visualizing and interpreting deep learning models","venue":null,"work_id":"4e995941-acb1-4f7c-9b87-1c20cc020b60","year":2022},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:53.981029Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:cafda74ab8835aa68a878fa5acadb4b57086bab6b696eb9124f7045d3642b770","observation_id":"f0b6bc5a-fb32-417c-a18a-49305be9a3f2","resolution":{"observed_at":"2026-08-07T00:24:12.231022Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:24:12.035356Z","title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","venue":null,"work_id":"7e9dda40-3af0-44d8-bdc5-dc236581ca53","year":2014},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:54.132802Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:65813675dc9562643e98159a3f959385f108735ed432cf9208f9dd60c4ee4022","observation_id":"a474b5ab-a71b-4f5a-bfe8-3d84dcd887a5","resolution":{"observed_at":"2026-08-07T00:24:12.107351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:24:10.852448Z","title":"An abstract domain for certifying neural networks","venue":null,"work_id":"5d74dd91-a451-4402-91e8-5905801bffef","year":2019},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:54.264491Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:c209ea82d2a5d78807ebe0d5680630b5a7b5fc674a6490bde479f3506f890edc","observation_id":"32335874-5767-406d-b366-b223bfa15e12","resolution":{"observed_at":"2026-08-07T00:24:11.798922Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:23:57.920114Z","title":"and Feizi, S","venue":null,"work_id":"6ed2005d-f715-40cc-8ed7-0f27a8cf23dd","year":2019},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:54.418349Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:ba730c45e12d1dcd30caf369a542b7955c7290202190f95c7d7d26f106719447","observation_id":"14e7e4d0-bd27-4421-9855-49f0bc20f01f","resolution":{"observed_at":"2026-08-07T00:23:58.066255Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.03825","last_updated":"2017-06-12T19:53:30Z","snapshot_observed_at":"2026-07-06T05:46:32.599765Z","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":"2026-08-07T00:23:54.525011Z","title":"Smoothgrad: removing noise by adding noise","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:54.525011Z"},"links":{"cited_paper":"/paper/1706.03825","citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:947b9afdc1d012a90e413c1268951b691d198f4a407cc84fef3ec16bd05d4300","observation_id":"53ef675c-c601-4d15-899a-bbe80524a2f1","resolution":{"observed_at":"2026-08-07T00:23:54.525011Z","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":"2026-08-07T00:23:57.532060Z","title":"Axiomatic attribution for deep networks","venue":null,"work_id":"2b270b13-752e-4598-8601-619a3bacaf5d","year":2017},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:54.625004Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:33b81e00abf3910d67957eb0f50c0a74773932945dcc40aa4e4ecd77bba88066","observation_id":"01327b5a-d2d6-4ac8-8245-6149e3fb6039","resolution":{"observed_at":"2026-08-07T00:23:57.742593Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:23:57.195561Z","title":"Z., Lin, C.-J., and Hsieh, C.-J","venue":null,"work_id":"665def4b-3f84-4901-b6d0-e0add7dae792","year":2021},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:54.744897Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:18c8a01a1f218832a07dea9a81c767c31cab894836dc5730eda27c62f205f941","observation_id":"be47ed0b-734e-4678-bd83-c11df9f4ea8c","resolution":{"observed_at":"2026-08-07T00:23:57.366971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:23:56.768780Z","title":null,"venue":null,"work_id":"208a3128-9c57-4074-8d85-b8e0ea99f88c","year":2021},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:54.863311Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:076347ef134866817ded95df863c1143a678e756357c3917d8d197e08b34a787","observation_id":"c1437161-04f4-4240-a3b2-afe4b087c443","resolution":{"observed_at":"2026-08-07T00:23:56.982814Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:23:56.586737Z","title":null,"venue":null,"work_id":"91410cde-7cad-4431-9abe-7f623f6c41c2","year":2020},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:55.038042Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:036847358d7dc73714d7eb1635ab9e7ddd0d34db4473c39e097ae536673555d4","observation_id":"ff62d5c9-91f8-4aed-bf53-420cd11bfd5c","resolution":{"observed_at":"2026-08-07T00:23:56.679493Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:23:56.421086Z","title":"On the faithfulness and reliability of saliency explanations","venue":null,"work_id":"cb2782da-913f-4b61-9975-da5a091b81a8","year":2023},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:55.213701Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:38d0d565698893ce9736fad9492ad705af59b63a0d99ee310600a49e044457ed","observation_id":"160cdfae-401e-43e6-8afe-0796c08fa585","resolution":{"observed_at":"2026-08-07T00:23:56.506184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:23:56.293447Z","title":"Efficient neural network verification with Auto-LiRPA : Towards scalable certified defense","venue":null,"work_id":"59bef0a1-5d8a-4e36-a2a0-4028ade11744","year":2020},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:55.307095Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:64118de96dd8423fa44408017cbf66ebd19e70a6fcc6b5edb9c63e77821aae2e","observation_id":"f9686b0f-ca16-4c0e-bbea-d8d96e18e1da","resolution":{"observed_at":"2026-08-07T00:23:56.359398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.06316","last_updated":"2019-11-27T11:03:27Z","snapshot_observed_at":"2026-08-09T12:49:41.224969Z","submitted_at":"2019-06-14T17:44:40Z","title":"Towards Stable and Efficient Training of Verifiably Robust Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.06316","snapshot_observed_at":"2026-08-07T00:23:55.459642Z","title":"Z., Wang, S., and Weng, T.-W","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:55.459642Z"},"links":{"cited_paper":"/paper/1906.06316","citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:35cf6926461327fdfefc3e7ebd898c46da6193d29a88146514743aa3c9ed33b4","observation_id":"8e026bc7-219d-48e8-8936-3668d2e2f9ba","resolution":{"observed_at":"2026-08-07T00:23:55.459642Z","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":"2026-08-07T00:23:56.123434Z","title":"Towards certified robustness of real-world neural networks","venue":null,"work_id":"038e7e4a-590c-46b1-a337-3fc92e193750","year":2022},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:55.610255Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:33302f4ef14a09f828f58170e51005250c2fb8d18e553bf9c35a02672298fa62","observation_id":"baa955b1-d652-40dd-bea7-941c02cc91fe","resolution":{"observed_at":"2026-08-07T00:23:56.210835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T00:23:55.631073Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T00:23:55.631073Z"},"links":{"citing_paper":"/paper/2506.14217"},"observation_digest":"sha256:2fed27ce5bc664d0aab43a556b33700df835afa36e80b430b7bf24381d77fc13","observation_id":"a9dc3ee3-ba89-4f3f-85d2-13141a4814c2","resolution":{"observed_at":"2026-08-07T00:23:55.631073Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.14217","last_updated":"2025-06-17T06:12:36Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T06:24:59.533165Z","submitted_at":"2025-06-17T06:12:36Z","title":"TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift"},"reference_resolution":{"displayed":36,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":13,"verified_exact":0,"verified_fuzzy":21},"total_outbound_references":36},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2506.14217."}