{"as_of":"2026-08-13T09:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ecaee9f703aa275bad167aa289d66b2d9f60d9bf7bad6a6a97e5bb1f259e9bee","coverage":[{"denominator":71,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":71,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T04:29:20.325100Z","state":"measured"},{"denominator":71,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":71,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2412.01369/citation-record","integrity":"/paper/2412.01369/integrity","json":"/paper/2412.01369/citation-record.json","paper":"/paper/2412.01369"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:29:22.541411Z","title":"Struc- tured pruning of deep convolutional neural networks","venue":null,"work_id":"3ee64305-f34e-4245-b867-a038a11c2a83","year":2017},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.772340Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:1680fc0d3ba2dd1ba88e197d9f357c08c965891e03319eb26e9c3261c98d4aab","observation_id":"ff676e60-7f45-40ee-8f97-f66ed17fb657","resolution":{"observed_at":"2026-08-12T04:29:22.569642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:19.779548Z","title":"Medical image segmentation review: The suc- cess of u-net","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.779548Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:17470b783bada7596fe50dbbd3ef3d5d322e93b7d7afddff703300a3a15c1c87","observation_id":"2f690827-1390-486f-90dc-764a08c3141d","resolution":{"observed_at":"2026-08-12T04:29:19.779548Z","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":"2026-08-12T04:29:22.486667Z","title":"A new backdoor attack in cnns by training set corruption without label poisoning","venue":null,"work_id":"aa2a83e7-cce8-41ac-8988-6d9e6a4aad77","year":2019},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.784483Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:368b21e73c98b83bda3a6d33972a691f7865a2b18438eeebd1c637adbfa77f71","observation_id":"547de60b-c5ef-4dcb-8d4d-b970b7e24725","resolution":{"observed_at":"2026-08-12T04:29:22.493993Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:22.461551Z","title":"Review of image classification algorithms based on convolutional neural networks","venue":null,"work_id":"40430987-403f-4952-b69d-9a48b94aa38d","year":2021},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.789887Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:24a3d248e7d8efb724fb4d85530c9c7071c95e0eb2d757bd931ea526f4f14928","observation_id":"4162d11f-797f-4dd7-80eb-a7b7060e6f5b","resolution":{"observed_at":"2026-08-12T04:29:22.468802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1712.05526","last_updated":"2017-12-15T04:26:26Z","snapshot_observed_at":"2026-07-06T06:14:30.795326Z","submitted_at":"2017-12-15T04:26:26Z","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.05526","snapshot_observed_at":"2026-08-12T04:29:19.795851Z","title":"Targeted backdoor attacks on deep learning systems using data poisoning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.795851Z"},"links":{"cited_paper":"/paper/1712.05526","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:8c7c2c435cbc88251a1a4c757bdfd7f248974936014a75ed34b639e842ebf0af","observation_id":"595da81a-a571-48fe-9216-386b11c3867a","resolution":{"observed_at":"2026-08-12T04:29:19.795851Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.08819","last_updated":"2017-08-23T16:06:20Z","snapshot_observed_at":"2026-07-06T05:52:59.445968Z","submitted_at":"2017-07-27T11:22:22Z","title":"A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.08819","snapshot_observed_at":"2026-08-12T04:29:19.802268Z","title":"A downsampled variant of imagenet as an alternative to the ci- far datasets","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.802268Z"},"links":{"cited_paper":"/paper/1707.08819","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:4c32e2bb971ccca0040559e7c48e0bc2d685a3615d729282a62f03690843f964","observation_id":"a898f3bb-625d-49d5-8297-ba61848b3267","resolution":{"observed_at":"2026-08-12T04:29:19.802268Z","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":"2026-08-12T04:29:22.439120Z","title":"The mnist database of handwritten digit images for machine learning research [best of the web]","venue":null,"work_id":"6e52d415-23d0-4dcf-ae34-ed503a246b06","year":2012},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.807804Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:153c8bbf5a2d1a3b237ee96bb7c5498421c8cf21b0b8298757326e172009c856","observation_id":"6b61e255-9a4d-4249-b2ac-c334c6eaf66e","resolution":{"observed_at":"2026-08-12T04:29:22.448163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-13T02:40:23.887636Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-12T04:29:19.814737Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.814737Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:25b0e89ae6ed6f082d17b9ede5f8ead2708abab4de1471728e47633a69ad240b","observation_id":"4c771c0b-84f7-4638-8f5f-633b1513cf5c","resolution":{"observed_at":"2026-08-12T04:29:19.814737Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:29:19.820917Z","title":"The pascal visual object classes (voc) challenge","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.820917Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:93d1c5f85d2e5d11632d049a7ab1390a1146dd8952cfc7a1cc0d84b58b5fd645","observation_id":"bd09c833-a36a-467f-a349-1743e3922b26","resolution":{"observed_at":"2026-08-12T04:29:19.820917Z","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":"2026-08-12T04:29:22.384963Z","title":"Depgraph: Towards any structural pruning","venue":null,"work_id":"7ca7181d-9742-4d28-8a4a-49352436c95f","year":2023},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.826759Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:600213c8f02f26fa86dfffa7209dc70153057521492bbb6452b1f5d5bf43831b","observation_id":"009d982c-ca6c-4f36-9908-939eea2c9fe6","resolution":{"observed_at":"2026-08-12T04:29:22.396194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.00473","last_updated":"2024-03-30T20:43:53Z","snapshot_observed_at":"2026-08-13T00:40:49.520669Z","submitted_at":"2024-03-30T20:43:53Z","title":"Privacy Backdoors: Stealing Data with Corrupted Pretrained Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.00473","snapshot_observed_at":"2026-08-12T04:29:19.834898Z","title":"Privacy backdoors: Stealing data with corrupted pretrained models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.834898Z"},"links":{"cited_paper":"/paper/2404.00473","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:0834f51b4d5b9228ff75d98fee894531c5bc31b29cd00597d55ba7f4eec26b2f","observation_id":"dfc6540e-2ffe-4e4a-8a0e-a13174465311","resolution":{"observed_at":"2026-08-12T04:29:19.834898Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.10760","last_updated":"2020-08-02T08:38:25Z","snapshot_observed_at":"2026-08-09T12:13:44.628029Z","submitted_at":"2020-07-21T12:49:12Z","title":"Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.10760","snapshot_observed_at":"2026-08-12T04:29:19.842379Z","title":"Backdoor attacks and countermeasures on deep learning: A comprehensive review","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.842379Z"},"links":{"cited_paper":"/paper/2007.10760","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:f3f5f65f0d68942d3227719b0065c0a960dfa5fa802a3c8596e4a2b711b607fa","observation_id":"c7e6cb3f-b89f-4290-abc8-03e2e9781145","resolution":{"observed_at":"2026-08-12T04:29:19.842379Z","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":"2026-08-12T04:29:22.329780Z","title":"A survey of quan- tization methods for efficient neural network inference","venue":null,"work_id":"99b58a21-9dd6-4cec-b2c4-12b23935e8f6","year":2022},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.850845Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:9b34f52186de70ba295b81c0f0805a0907bbdf6dccbdca04c4c37f4c036344da","observation_id":"e329991e-7e63-4b69-a444-b22e9abadee7","resolution":{"observed_at":"2026-08-12T04:29:22.359636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:22.237577Z","title":"Badnets: Evaluating backdooring attacks on deep neu- ral networks","venue":null,"work_id":"ce8d6002-9234-48e2-af47-8f89cf2cd59d","year":2019},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.857049Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:a4d85c18da0e909da87fbaf47d23e5d0e81021767e3dd3e8213e7b6c7aadc3bb","observation_id":"c67a5a2d-7edb-4b4b-b6bc-21997f12e035","resolution":{"observed_at":"2026-08-12T04:29:22.272881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:19.862568Z","title":"Optimal brain surgeon and general network pruning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.862568Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:252f9b547186ec12e9481df20a7480f6ac251c0e7b30293f27e5886c24b8a4a2","observation_id":"44a31662-826a-48f8-a5f2-490b41436a40","resolution":{"observed_at":"2026-08-12T04:29:19.862568Z","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":"2026-08-12T04:29:22.129412Z","title":"Zhang, Shaoqing Ren, and Jian Sun","venue":null,"work_id":"58cd8043-4b52-4104-8307-4bb7eb2f4ddb","year":2016},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.869080Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:f65fc031e9856ea00ed51c7d7422c8d9538fb956be397757eaa37bd554a13ebe","observation_id":"64b6666a-a8e0-4b4c-925f-2c4c909b4c53","resolution":{"observed_at":"2026-08-12T04:29:22.167000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:22.055640Z","title":"In- telligent unmanned ground vehicles: autonomous navigation research at Carnegie Mellon","venue":null,"work_id":"82c91a85-fe80-4995-8799-e62897258cf4","year":2012},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.880216Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:6a8c8817ff17628cae44cfcf53a1e1fb267458b023d38cc9ed9e31dc5580dd30","observation_id":"17c9309d-5333-4a74-9aeb-da7282599076","resolution":{"observed_at":"2026-08-12T04:29:22.062553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:22.036432Z","title":"Segment anything model for medical images? Medical Image Analysis, 92:103061, 2024","venue":null,"work_id":"1e55edd9-be85-48bb-b400-85d6211c32f9","year":2024},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.885446Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:0744e1f417f681016becb0a38a622d1d6f4b1285f98e27a2eb507e2f884d80c2","observation_id":"92a5af53-2353-43ac-9df5-5ecd527d666f","resolution":{"observed_at":"2026-08-12T04:29:22.041911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:22.017880Z","title":"Quantized neural networks: Training neural networks with low precision weights and ac- tivations","venue":null,"work_id":"444892a1-6f6b-4730-a06a-ce2a4326e520","year":2018},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.890727Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:2bcb6956053fd9259a8a8cd97039c6714ef3aecd49db1ba7c6068f7d8dcf013e","observation_id":"734a6651-69a8-4f18-80bd-f85175879fdb","resolution":{"observed_at":"2026-08-12T04:29:22.024115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.993431Z","title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference","venue":null,"work_id":"6b578bd6-479d-4541-83fe-6c44f88426a3","year":2018},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.896261Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:6dd6e88cd34cc5c38700f2387360b04832604aac31c9ce3d5bd2ffae571143a6","observation_id":"0938f234-08d0-4bee-a06a-9fccbfc01063","resolution":{"observed_at":"2026-08-12T04:29:22.000033Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.14692","last_updated":"2023-07-27T08:28:58Z","snapshot_observed_at":"2026-08-05T17:47:54.974979Z","submitted_at":"2023-07-27T08:28:58Z","title":"Backdoor Attacks for In-Context Learning with Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.14692","snapshot_observed_at":"2026-08-12T04:29:19.902384Z","title":"Backdoor attacks for in-context learning with language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.902384Z"},"links":{"cited_paper":"/paper/2307.14692","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:935dc5b426c1dedb0adb3fe1aae553192d7ede3b0e6a64b043ebf448bebe5240","observation_id":"6b3988ff-d0cf-4f78-8177-5d4b0629a5d0","resolution":{"observed_at":"2026-08-12T04:29:19.902384Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-12T04:29:19.908599Z","title":"Kingma and Jimmy Ba","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.908599Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:eef9aa7af29f0453958fb9fdea557d5eb8285f4970269fcbee3404a8d4aee9bf","observation_id":"3463ac5d-18ab-44b7-8213-aedd5fd17a56","resolution":{"observed_at":"2026-08-12T04:29:19.908599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.08342","last_updated":"2018-06-21T17:32:46Z","snapshot_observed_at":"2026-07-06T06:46:08.396066Z","submitted_at":"2018-06-21T17:32:46Z","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.08342","snapshot_observed_at":"2026-08-12T04:29:19.914244Z","title":"Quantizing deep convolu- tional networks for efficient inference: A whitepaper","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.914244Z"},"links":{"cited_paper":"/paper/1806.08342","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:a5aa377282436f2f2462812c6b7dc74c40cc287b9686dd80080ec3e4e89b3680","observation_id":"f423d43a-15e6-4219-9238-68b33a755b23","resolution":{"observed_at":"2026-08-12T04:29:19.914244Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:29:19.922973Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.922973Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:7065fe96560f23759adc1393524efca7332b9d9cf97a01249a6de88175462611","observation_id":"f3da22b9-20eb-4423-ac10-bfc608bada98","resolution":{"observed_at":"2026-08-12T04:29:19.922973Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:29:19.929545Z","title":"Imagenet classification with deep convolutional neural net- works","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.929545Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:504121d1ed42929fbd0c550448007640b9f07860e6ffb09285627eaebdaa60bc","observation_id":"0b0b3a03-1b1b-42fa-a279-35daf769b820","resolution":{"observed_at":"2026-08-12T04:29:19.929545Z","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":"2026-08-12T04:29:21.940489Z","title":"Optimal brain damage","venue":null,"work_id":"c8ab0a76-48ae-4705-a903-7d5a18ae8215","year":1989},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.936854Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:4a97226c1a8cecf30ecd6e41e474ef3799b7680dccfb49bb29aee3736c611cd3","observation_id":"05f25963-1c26-47d6-be83-2395322b4030","resolution":{"observed_at":"2026-08-12T04:29:21.947550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08691","last_updated":"2021-09-02T17:34:41Z","snapshot_observed_at":"2026-08-06T15:24:34.790850Z","submitted_at":"2021-04-18T03:19:26Z","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08691","snapshot_observed_at":"2026-08-12T04:29:19.946081Z","title":"The power of scale for parameter-efficient prompt tuning.arXiv preprint arXiv:2104.08691, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.946081Z"},"links":{"cited_paper":"/paper/2104.08691","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:3cac27f7c53a294764e91519b395a5f9b0f29a32cfd498868cdf3d8784b5d529","observation_id":"8c5a7bdc-a125-4fda-bfe5-b684b067b130","resolution":{"observed_at":"2026-08-12T04:29:19.946081Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1605.04711","last_updated":"2022-11-20T14:21:55Z","snapshot_observed_at":"2026-08-13T07:38:25.973071Z","submitted_at":"2016-05-16T10:21:25Z","title":"Ternary Weight Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1605.04711","snapshot_observed_at":"2026-08-12T04:29:19.952851Z","title":"Ternary weight networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.952851Z"},"links":{"cited_paper":"/paper/1605.04711","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:49483e4b95b72f615daaa0b287194594521e67b3f3c2d6e06c99f51b19252e1e","observation_id":"9a51847f-6c39-4b14-b18f-c09363565a65","resolution":{"observed_at":"2026-08-12T04:29:19.952851Z","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":"2026-08-12T04:29:21.916878Z","title":"Blip: Bootstrapping language-image pre-training for unified 10 vision-language understanding and generation","venue":null,"work_id":"d0aa2c27-e986-4cc9-9ac5-1fef0648f76f","year":2022},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.961999Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:525bc1aee431fb5b6ba8122447fcbf56d71e98a5e3d6834fe666d11ac9750805","observation_id":"327440a2-f4b8-4dd5-9902-809164dd9cea","resolution":{"observed_at":"2026-08-12T04:29:21.923059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:19.967914Z","title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.967914Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:4f5d50f90e687b519e39045fbe6e97ee3a7e912debf894ea14ddd005cfe7d27c","observation_id":"5d358208-773c-40dd-8521-19d529fbde74","resolution":{"observed_at":"2026-08-12T04:29:19.967914Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00190","last_updated":"2021-01-01T08:00:36Z","snapshot_observed_at":"2026-08-12T12:37:28.207761Z","submitted_at":"2021-01-01T08:00:36Z","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00190","snapshot_observed_at":"2026-08-12T04:29:19.976190Z","title":"Prefix-tuning: Optimiz- ing continuous prompts for generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.976190Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:6622cfe55cbe80fba91b556d3af630921394642a84ea0462bf77f40b66d927c6","observation_id":"b27081f1-2e34-46da-b685-849654580f43","resolution":{"observed_at":"2026-08-12T04:29:19.976190Z","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":"2026-08-12T04:29:21.786035Z","title":"Celeb-df: A large-scale challenging dataset for deep- fake forensics","venue":null,"work_id":"c560a345-8c01-407a-abec-0f0a679e139c","year":2020},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.992168Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:3b810a67b8de80325e78657506abccc6f2fe79176987fa36ff8249039153cb20","observation_id":"e228cae1-f08f-4149-9e59-0cbef5d42fcc","resolution":{"observed_at":"2026-08-12T04:29:21.835271Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:19.999170Z","title":"Invisible backdoor attack with sample- specific triggers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:19.999170Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:3343785d7c306bcf3342f87327af3d1ce1185ea365963b92534c85767e16833f","observation_id":"d4979089-602e-4428-a6c2-3ff3998837d7","resolution":{"observed_at":"2026-08-12T04:29:19.999170Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11473","last_updated":"2024-02-18T06:31:05Z","snapshot_observed_at":"2026-08-13T04:16:50.609771Z","submitted_at":"2024-02-18T06:31:05Z","title":"Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11473","snapshot_observed_at":"2026-08-12T04:29:20.005642Z","title":"Poisoned forgery face: Towards backdoor attacks on face forgery detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.005642Z"},"links":{"cited_paper":"/paper/2402.11473","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:80efc98c390a606e7a2156fe4eedc0197c8191d206e52a48c041bf4e5ba26f9f","observation_id":"ad675452-3e85-4843-817f-b84f436526c6","resolution":{"observed_at":"2026-08-12T04:29:20.005642Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.18844","last_updated":"2024-12-16T06:59:33Z","snapshot_observed_at":"2026-08-12T23:34:01.672638Z","submitted_at":"2024-06-27T02:31:03Z","title":"Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.18844","snapshot_observed_at":"2026-08-12T04:29:20.013969Z","title":"Revisiting back- door attacks against large vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.013969Z"},"links":{"cited_paper":"/paper/2406.18844","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:eec3e518224d6ce4c162170c02636fe256ec5ea73db506339ba40e60b565dfa6","observation_id":"3cf15d90-1f22-41a2-a2af-86197eb32f6d","resolution":{"observed_at":"2026-08-12T04:29:20.013969Z","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":"2026-08-12T04:29:21.636315Z","title":"Girshick, Kaiming He, and Piotr Doll´ar","venue":null,"work_id":"0a12a05c-741f-40f4-abb3-7389c708245c","year":2017},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.023367Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:840203551f35185ce1eebe6b49231975fa6eef6642636ac02b6b626f92ea563c","observation_id":"7e21a0d8-4d2b-4d7d-91b4-8539109e95f2","resolution":{"observed_at":"2026-08-12T04:29:21.707843Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.13824","last_updated":"2023-02-17T13:17:52Z","snapshot_observed_at":"2026-07-06T12:12:39.412868Z","submitted_at":"2021-11-27T06:20:53Z","title":"FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.13824","snapshot_observed_at":"2026-08-12T04:29:20.031345Z","title":"Fq-vit: Post-training quantization for fully quantized vision transformer","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.031345Z"},"links":{"cited_paper":"/paper/2111.13824","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:378bbd79787463d5c34a3c9df6cc973da6c1cdf2491e743afa6e2f94c16ddb4d","observation_id":"dfed0eda-b151-4b48-bcd7-971143a5a032","resolution":{"observed_at":"2026-08-12T04:29:20.031345Z","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":"2026-08-12T04:29:21.563751Z","title":"Harnessing percep- tual adversarial patches for crowd counting","venue":null,"work_id":"78139e1f-9019-458a-9238-d6fe77e40cc9","year":2022},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.038561Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:ae7e2033f392170cd1ff58ea6608c6b6bd49e8cc0f02d06e82d1eb8b421be3cd","observation_id":"0d8d8a4d-a3ab-4cb7-a586-b6f3b81f3eef","resolution":{"observed_at":"2026-08-12T04:29:21.569854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.546314Z","title":"Post-training quantization for vision trans- former","venue":null,"work_id":"2c7ab9aa-a3ad-48ba-a856-d9c89c10ac0b","year":2021},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.044315Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:791a408075a045293ec34cd1941762fcd3764a2bdadc0ca13997b38cd0fa0ac7","observation_id":"fbbc3e62-124f-41c6-a4ba-91119cad2107","resolution":{"observed_at":"2026-08-12T04:29:21.552352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.526830Z","title":"A gentle introduction to deep learning in medical image processing","venue":null,"work_id":"acc76cc9-9a5d-43b4-9b2a-cdae11b76f4d","year":2019},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.049289Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:c6b06e7e65cb87027cc78d6e8aa057b2326a97a558491e7a4715ba0fd6878c73","observation_id":"3063a3ee-ef22-4889-94ac-0d3e3908f74b","resolution":{"observed_at":"2026-08-12T04:29:21.532538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.06440","last_updated":"2017-06-08T19:53:26Z","snapshot_observed_at":"2026-08-07T07:29:29.524604Z","submitted_at":"2016-11-19T22:48:30Z","title":"Pruning Convolutional Neural Networks for Resource Efficient Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.06440","snapshot_observed_at":"2026-08-12T04:29:20.055733Z","title":"Pruning convolutional neural networks for re- source efficient inference","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.055733Z"},"links":{"cited_paper":"/paper/1611.06440","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:d802f1842d8751b68c10d22e1b00fc224e22d3671e991e75939cbcbc25c343f5","observation_id":"f337b78d-e022-413a-94d4-be56b0142e3e","resolution":{"observed_at":"2026-08-12T04:29:20.055733Z","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":"2026-08-12T04:29:21.506129Z","title":"Importance estimation for neural net- work pruning","venue":null,"work_id":"f5ddc6df-3380-4478-9f5b-c5c77198aac2","year":2019},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.062363Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:5929735331f5e8f335e52b55584c4e2e99d0a5b7f04128e5893a2deebc083f63","observation_id":"3faa8e01-8090-4d3a-993b-660299b312f9","resolution":{"observed_at":"2026-08-12T04:29:21.512770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.08295","last_updated":"2021-06-15T17:12:42Z","snapshot_observed_at":"2026-08-02T11:19:40.664702Z","submitted_at":"2021-06-15T17:12:42Z","title":"A White Paper on Neural Network Quantization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.08295","snapshot_observed_at":"2026-08-12T04:29:20.071971Z","title":"A white paper on neural network quantization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.071971Z"},"links":{"cited_paper":"/paper/2106.08295","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:d9b917e507420ada73b09f5f558a0b1189e70da8e9345dcb44f3619e282d455d","observation_id":"5d4e3638-cbff-4552-8751-5785b9b72140","resolution":{"observed_at":"2026-08-12T04:29:20.071971Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.10369","last_updated":"2021-03-04T04:09:38Z","snapshot_observed_at":"2026-08-02T13:52:44.392403Z","submitted_at":"2021-02-20T15:25:36Z","title":"WaNet -- Imperceptible Warping-based Backdoor Attack","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.10369","snapshot_observed_at":"2026-08-12T04:29:20.081305Z","title":"Wanet–imperceptible warping- based backdoor attack","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.081305Z"},"links":{"cited_paper":"/paper/2102.10369","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:e5339b58d733b5412691571242ca4ef0885f834641c9c31efe85f3714bbce749","observation_id":"44d31f79-a481-4ddd-8ea6-2a5058a6e737","resolution":{"observed_at":"2026-08-12T04:29:20.081305Z","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":"2026-08-12T04:29:21.485272Z","title":"Input-aware dynamic backdoor attack","venue":null,"work_id":"fa815d5a-74ad-497d-bee7-508a1fad2694","year":2020},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.103114Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:e09d6e6e8b2a611b169263b4d684f0b1d4770fdac63b7bb72a1b84e567edc6e2","observation_id":"ca44d452-b097-4ead-b3b8-9d5424835478","resolution":{"observed_at":"2026-08-12T04:29:21.490845Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.407877Z","title":"Deep learning for medical image processing: Overview, challenges and the future","venue":null,"work_id":"f95406fa-e1f1-4bee-b726-e8c7391c3565","year":2018},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.114284Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:370ea7ecb843acaec3e7470dc795869338487f7ee8038d94992a60cb22f0b244","observation_id":"3c7b85d1-f21d-461c-891c-1eec1dc9bc61","resolution":{"observed_at":"2026-08-12T04:29:21.450519Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.383299Z","title":"Girshick, and Jian Sun","venue":null,"work_id":"a7e47c7b-cd6e-4b8f-bc9e-dd73a6e8ab57","year":2015},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.120551Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:3c1de47dfe1987965e0b5c52f1ef4ece8ba8128b38595f025e8326df0901be38","observation_id":"8426e01e-daaa-4cf1-a98e-e25a321d1fe5","resolution":{"observed_at":"2026-08-12T04:29:21.390217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:20.136063Z","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.136063Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:b80fe5d6c3d6c3543f36c8c9aa01c2cd5c09ebb19cbd4937a47999e1f8a9c65f","observation_id":"09e8099d-15b2-4668-a655-2bfcf8387b44","resolution":{"observed_at":"2026-08-12T04:29:20.136063Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:29:20.142203Z","title":"Nipq: Noise proxy- based integrated pseudo-quantization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.142203Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:88117a62339a390818b4e57e518ad7ece7b679c747e6db1937c3359f319e003c","observation_id":"9849ff4c-a4ed-498e-84e0-23c4a5b11950","resolution":{"observed_at":"2026-08-12T04:29:20.142203Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-12T14:19:29.389332Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-12T04:29:20.148819Z","title":"Very deep convo- lutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.148819Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:810706a9bef8ea695a4061f9462fb7386a194578a0033fd6b814627c95a0a220","observation_id":"91a06741-570e-4282-a149-0dc35588440f","resolution":{"observed_at":"2026-08-12T04:29:20.148819Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T04:29:20.155198Z","title":"Going deeper with convolutions","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.155198Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:ebb7b59b57733831d41b2ab0f7d2413cfcf5c2fa68f79f6ae6913d245d24552c","observation_id":"251bb0cd-82bb-4db9-b528-090c8b0fe6cb","resolution":{"observed_at":"2026-08-12T04:29:20.155198Z","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":"2026-08-12T04:29:21.311883Z","title":"Convolutional neural networks for medical im- age analysis: Full training or fine tuning? IEEE transactions on medical imaging, 35(5):1299–1312, 2016","venue":null,"work_id":"1a703db6-07bb-479c-b1d0-7a92e6f1edd4","year":2016},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.162150Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:b5a6cfecb68d2e0a324a3bc3ecfc05bd7e05ef59c41b363f77133374cad08abc","observation_id":"713a4891-32b0-49f4-be69-a1eec6b1920f","resolution":{"observed_at":"2026-08-12T04:29:21.318933Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.289045Z","title":"Towards real-world x-ray security inspection: A high-quality benchmark and lateral inhibition module for prohibited items detection","venue":null,"work_id":"40db0167-001a-4c55-bf5e-56eeb1e3617a","year":2021},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.169936Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:3e3957d56fa35bdba23900f20474be5d64973eb8075bed562ef75b84c07bb3f1","observation_id":"638e7685-a8dc-4638-bb5a-ee22325df62f","resolution":{"observed_at":"2026-08-12T04:29:21.296216Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.267165Z","title":"Exploring endogenous shift for cross-domain detec- tion: A large-scale benchmark and perturbation suppression network","venue":null,"work_id":"01e8ca13-d323-496c-8cff-457408069954","year":2022},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.177040Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:4f30272f0d8c2dc1bfd0e1d9be482265eaed309d76a700392049691d2e1d4f13","observation_id":"7bcc4e13-5399-49d9-ba73-7e64d244d575","resolution":{"observed_at":"2026-08-12T04:29:21.274684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.248040Z","title":"Few-shot x-ray prohibited item detection: A benchmark and weak-feature enhancement net- work","venue":null,"work_id":"902256d0-24f2-4fcc-948d-820838f88e88","year":2012},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.183064Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:448ce88899cdc3bb572cd81e8a6744378d6ecb7593285ad48305c0589a737adb","observation_id":"26a91a11-6c41-4a45-b616-d1f21d1f4562","resolution":{"observed_at":"2026-08-12T04:29:21.254604Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:20.189201Z","title":"Visualizing data using t-sne","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.189201Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:71bd890a907bf7e6c007561c306127c7d96a503bc35c89910a315d8296dd2860","observation_id":"7037306a-5f5d-4a5a-8dfc-2b40bb8789b0","resolution":{"observed_at":"2026-08-12T04:29:20.189201Z","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":"2026-08-12T04:29:21.186669Z","title":"Uni- versal adversarial patch attack for automatic checkout using perceptual and attentional bias","venue":null,"work_id":"2c425e28-c1e8-4155-b58a-c717b483a5c3","year":2021},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.196002Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:aad3ad85ea714777f19a72549b58f7257cc961b52e53c71b1d415a358ab6a7bf","observation_id":"c0a3fe95-11a1-4b9d-83e5-c4aef5566fef","resolution":{"observed_at":"2026-08-12T04:29:21.192905Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.165781Z","title":"Dual attention suppression attack: Generate adversarial camouflage in physical world","venue":null,"work_id":"3d6559e1-41b1-4ebc-93ad-cc956c6ec207","year":2021},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.204717Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:fd5f32b9a7c24652d2005dd61cc57a3bcc1073b49e305207718065e4f8029c96","observation_id":"f1cbb13b-0b79-464c-941e-840a6c091a1f","resolution":{"observed_at":"2026-08-12T04:29:21.172794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.145563Z","title":"De- fensive patches for robust recognition in the physical world","venue":null,"work_id":"14d2d18b-d283-4494-b7af-6ea6f7bfc449","year":2022},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.219976Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:92fff707b3fd7d13927f26aa9d32294fd88c40f9b2c9e9cd82cd47aef9fb6d0e","observation_id":"adc123d8-711e-484c-bf25-89cf5e435eae","resolution":{"observed_at":"2026-08-12T04:29:21.151910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.124260Z","title":"Gener- ate transferable adversarial physical camouflages via triplet attention suppression","venue":null,"work_id":"d5dd3bf0-bc4b-439c-a9b1-5ddebc560e6b","year":2024},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.227311Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:2ef3a116592f701d300533dbabbbf9f95e81f3bfd137e472f7ac4487fd1db3d3","observation_id":"34943ca7-7a56-4aa3-abe1-28aea462bcde","resolution":{"observed_at":"2026-08-12T04:29:21.130891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.100572Z","title":null,"venue":null,"work_id":"5ac31c46-6dab-4448-a7d0-aa5c3dad7a9c","year":2020},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.232988Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:3073a1014d4e79403682a260cf44acbae86e9924e37eb2c479113587f052bbf0","observation_id":"6b27b070-9329-4f5a-ab9a-8899a2ec6b83","resolution":{"observed_at":"2026-08-12T04:29:21.109067Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.080991Z","title":"Grow- ing a brain: Fine-tuning by increasing model capacity","venue":null,"work_id":"0ea6a5a3-dbe7-4bc8-85e8-2aece55cbf92","year":2017},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.238930Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:aa3c84b9764d5c744c324e9114fa20babcf1895b9c413ff4e5485c4ab4f03950","observation_id":"f3025a7a-c546-4970-a22e-eb45ff1d6843","resolution":{"observed_at":"2026-08-12T04:29:21.086567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.059086Z","title":"Convo- lutional neural network pruning with structural redundancy reduction","venue":null,"work_id":"45f690ee-d117-4473-b114-1658d0b91568","year":2021},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.248366Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:5dde1a10466eb7c9da1a7c1c6f73a6791baa8c6ba276f5c61183a79a5a711798","observation_id":"faa0d9bb-fc43-406a-a2e1-5c6b13cfe470","resolution":{"observed_at":"2026-08-12T04:29:21.064874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.040783Z","title":"Napguard: Towards detecting naturalistic ad- versarial patches","venue":null,"work_id":"3cb4db3e-cb85-46d7-bfaf-f766202cad20","year":2024},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.258884Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:a9e9930c9d65073fdc3a62cc4a744ff46e61f140a139eb3d3641e9a02afea8a1","observation_id":"a2780293-fde4-4d94-8cd0-f63923e34bd0","resolution":{"observed_at":"2026-08-12T04:29:21.046508Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:21.019081Z","title":"A comprehensive overview of backdoor attacks in large language models within communi- cation networks","venue":null,"work_id":"08aebca7-582f-4815-b0c0-5c1952b6bb8d","year":2024},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.265277Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:dd620c862c13119a4e65f03dfbb78ae3a9f11a61a980f52a611f281934b5615d","observation_id":"38837741-6d50-4d8e-b381-dddf05aa7e06","resolution":{"observed_at":"2026-08-12T04:29:21.025843Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:20.994402Z","title":"Im- proving deepfake detection generalization by invariant risk minimization","venue":null,"work_id":"acb98b6a-50a6-4029-a6d3-5ba06af6ea12","year":2024},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.281543Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:aee2177b09c7785041739d65cd3b967212e44ba9ddb0e92705fa14ab9ebe5b68","observation_id":"4cda4958-26ba-42c2-9d07-e080cd846e79","resolution":{"observed_at":"2026-08-12T04:29:20.999964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:20.292349Z","title":"Ptq4vit: Post-training quantization for vision transformers with twin uniform quantization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.292349Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:eea58d957d91cec74a5446f3f09a9da03ba6abd65a3a4d66bace4e5d0283384b","observation_id":"bed87e46-91a1-4a0a-b870-0c93d7d32a56","resolution":{"observed_at":"2026-08-12T04:29:20.292349Z","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":"2026-08-12T04:29:20.957018Z","title":"A study on key technologies of unmanned driving","venue":null,"work_id":"5af46632-6be1-448e-af09-02127c88f64a","year":2016},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.298248Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:a0b232de2d16ad6679df194681f1aee3682bbb3188245f964692aed85aca296b","observation_id":"8484327c-079f-46e4-9286-7c165625bec0","resolution":{"observed_at":"2026-08-12T04:29:20.963152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T04:29:20.932997Z","title":"Diversifying sample generation for accurate data-free quantization","venue":null,"work_id":"d804e3f0-8d97-4d20-b4f3-3e6f38043076","year":2021},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.307694Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:63099bab975a72f04651acacb223a36540d66f385cfe71ac30b157a58ae2618e","observation_id":"1300ed92-ad7a-4a17-b168-d1706d60038b","resolution":{"observed_at":"2026-08-12T04:29:20.944265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.06160","last_updated":"2018-02-02T01:43:54Z","snapshot_observed_at":"2026-07-06T05:00:35.763958Z","submitted_at":"2016-06-20T15:02:31Z","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.06160","snapshot_observed_at":"2026-08-12T04:29:20.316099Z","title":"Dorefa-net: Training low bitwidth convo- lutional neural networks with low bitwidth gradients","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.316099Z"},"links":{"cited_paper":"/paper/1606.06160","citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:d9301cc963a8e2dba2335375f887e9b95eb96d0859a6fcf39f53567321ab5874","observation_id":"ddf508ce-46d8-4aa6-9f24-643712747af1","resolution":{"observed_at":"2026-08-12T04:29:20.316099Z","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":"2026-08-12T04:29:20.903793Z","title":"Object detection in 20 years: A survey.Proceed- ings of the IEEE, 111(3):257–276, 2023","venue":null,"work_id":"b71a4ead-6e5c-4d03-a4dc-00b6bfad13f5","year":2023},"citing_paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-12T04:29:20.325100Z"},"links":{"citing_paper":"/paper/2412.01369"},"observation_digest":"sha256:91e66c07d6008ace7355aa71c179ac3eaf7b1534b5c5ad2e6ac65379edefe71e","observation_id":"5bb7ed91-1737-416f-a496-3bf8e1e482a1","resolution":{"observed_at":"2026-08-12T04:29:20.913130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.01369","last_updated":"2024-12-02T10:54:02Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T08:40:38.492553Z","submitted_at":"2024-12-02T10:54:02Z","title":"Behavior Backdoor for Deep Learning Models"},"reference_resolution":{"displayed":71,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":32,"verified_exact":0,"verified_fuzzy":39},"total_outbound_references":71},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 71 of 71 outbound references and 0 inbound Pith citation observations for arXiv:2412.01369."}