{"as_of":"2026-08-08T12:05:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b42d36ae9df55011a7dc4a55756097c9b1b7b6d117542743de3d6b63704ba2f6","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":16,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":16,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":16,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":16,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T19:18:21.979217Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-06-29T17:33:45.399073Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-08-07T19:18:21.979217Z","title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.10490","last_updated":"2025-02-14T13:15:13Z","snapshot_observed_at":"2026-08-07T19:10:57.274990Z","submitted_at":"2025-02-14T13:15:13Z","title":"A Robust Attack: Displacement Backdoor Attack","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T19:18:21.979217Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2502.10490"},"observation_digest":"sha256:33cff38a3bc96f3a48e0a5edf8734a81bc1920ac66fc9093642c079db36a8983","observation_id":"e8bbf724-6b09-4573-bb31-b90086f24b79","resolution":{"observed_at":"2026-08-07T19:18:21.979217Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-08-07T15:25:23.370648Z","title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15308","last_updated":"2025-05-21T09:36:35Z","snapshot_observed_at":"2026-08-07T15:18:07.516589Z","submitted_at":"2025-05-21T09:36:35Z","title":"BadSR: Stealthy Label Backdoor Attacks on Image Super-Resolution","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T15:25:23.370648Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2505.15308"},"observation_digest":"sha256:906bd5bfe91531070e1e33510e556f3b4814711c2ae19d0aac96d6c505883f83","observation_id":"25bb1842-bce3-402d-84e9-25aaa633d04a","resolution":{"observed_at":"2026-08-07T15:25:23.370648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-08-07T13:05:27.893032Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.22829","last_updated":"2026-06-18T15:45:13Z","snapshot_observed_at":"2026-08-07T12:57:10.888209Z","submitted_at":"2025-05-28T20:11:30Z","title":"Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies","version":2},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-07T13:05:27.893032Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2505.22829"},"observation_digest":"sha256:74df6d84e018c3ed4476a9bc7f53a1da8d78c6fa30e3d8c3d21f4428d08a3f40","observation_id":"d71db358-f5da-4866-8e48-5f383609866b","resolution":{"observed_at":"2026-08-07T13:05:27.893032Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-08-07T05:40:15.206330Z","title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07467","last_updated":"2025-06-09T06:21:35Z","snapshot_observed_at":"2026-08-07T05:30:38.997146Z","submitted_at":"2025-06-09T06:21:35Z","title":"Circumventing Backdoor Space via Weight Symmetry","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T05:40:15.206330Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2506.07467"},"observation_digest":"sha256:c6e99d58fde77bcd610fd5431c9266a52a106d0e9c93e8eb05d43ce7afa0b0fc","observation_id":"8ededfff-d14e-495b-8dcb-a1b8b1b13d62","resolution":{"observed_at":"2026-08-07T05:40:15.206330Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-08-06T17:33:49.807827Z","title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.10491","last_updated":"2025-07-14T17:13:06Z","snapshot_observed_at":"2026-08-06T17:27:09.347274Z","submitted_at":"2025-07-14T17:13:06Z","title":"BURN: Backdoor Unlearning via Adversarial Boundary Analysis","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T17:33:49.807827Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2507.10491"},"observation_digest":"sha256:bcf286f7f23f016a3952b6cf4bd1c8f8d63f0747cfe89700761e8fc1428ae0c0","observation_id":"09d81821-9783-465e-a588-f927c20ee1df","resolution":{"observed_at":"2026-08-06T17:33:49.807827Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-08-05T23:24:03.420014Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.05404","last_updated":"2025-08-07T13:56:54Z","snapshot_observed_at":"2026-08-07T06:17:18.078145Z","submitted_at":"2025-08-07T13:56:54Z","title":"NT-ML: Backdoor Defense via Non-target Label Training and Mutual Learning","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-05T23:24:03.420014Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2508.05404"},"observation_digest":"sha256:e005cffc93d2fd009581933620f9d1fdc1043ed2a0b28ab1d4302b16e089fc15","observation_id":"84ae4f14-53d6-4d1d-b04a-b1df7c024c07","resolution":{"observed_at":"2026-08-05T23:24:03.420014Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-08-05T23:24:48.993186Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.05409","last_updated":"2025-08-07T14:02:34Z","snapshot_observed_at":"2026-08-05T23:24:41.370139Z","submitted_at":"2025-08-07T14:02:34Z","title":"From Detection to Correction: Backdoor-Resilient Face Recognition via Vision-Language Trigger Detection and Noise-Based Neutralization","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-05T23:24:48.993186Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2508.05409"},"observation_digest":"sha256:39721009a929c908fc03adb6f788a1db85bdf6a825d0baaeba5b7b0e5ae690dc","observation_id":"bd113e7f-828a-4b9a-a65c-a6fdb524dadd","resolution":{"observed_at":"2026-08-05T23:24:48.993186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-08-05T14:42:31.441302Z","title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.21004","last_updated":"2025-08-28T17:05:18Z","snapshot_observed_at":"2026-08-07T06:34:15.037429Z","submitted_at":"2025-08-28T17:05:18Z","title":"Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T14:42:31.441302Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2508.21004"},"observation_digest":"sha256:5c4e8335d1ce6b8422cf6afa0236d979db8fa34ff48b6cf3fdf876b9ab5145e6","observation_id":"a614b883-9253-4efe-b958-75e33edea10c","resolution":{"observed_at":"2026-08-05T14:42:31.441302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":"2101.05930","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-06-29T17:33:45.399073Z","title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","venue":null,"work_id":"7cff72c9-26cd-43fe-847c-bc5aa9997177","year":2021},"citing_paper":{"arxiv_id":"2511.22262","last_updated":"2026-04-05T05:36:52Z","snapshot_observed_at":"2026-08-02T06:19:12.090439Z","submitted_at":"2025-11-27T09:39:51Z","title":"Can Protective Watermarking Safeguard the Copyright of 3D Gaussian Splatting?","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-17T05:07:54.119100Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2511.22262"},"observation_digest":"sha256:2a85c844a7974bd0b43671288e030e7afefb169f7bb1397facd6d8e13c7ad56f","observation_id":"d6be84be-3448-418d-af0a-4e418aa94185","resolution":{"observed_at":"2026-05-17T05:09:03.725821Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":"2101.05930","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-06-29T17:33:45.399073Z","title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","venue":null,"work_id":"7cff72c9-26cd-43fe-847c-bc5aa9997177","year":2021},"citing_paper":{"arxiv_id":"2602.07200","last_updated":"2026-04-30T22:02:47Z","snapshot_observed_at":"2026-08-02T05:45:43.617157Z","submitted_at":"2026-02-06T21:20:41Z","title":"BadSNN: Backdoor Attacks on Spiking Neural Networks via Adversarial Spiking Neuron","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-16T06:31:04.036790Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2602.07200"},"observation_digest":"sha256:8cb559e0efc921c68c36c1c6a1f2c897c064b79106e587cd33164230d6a81b87","observation_id":"0ae5997c-5920-4064-a0fd-075e1b8b062b","resolution":{"observed_at":"2026-05-16T06:32:27.436926Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":"2101.05930","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-06-29T17:33:45.399073Z","title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","venue":null,"work_id":"7cff72c9-26cd-43fe-847c-bc5aa9997177","year":2021},"citing_paper":{"arxiv_id":"2604.04800","last_updated":"2026-04-06T16:06:07Z","snapshot_observed_at":"2026-07-30T23:23:10.579340Z","submitted_at":"2026-04-06T16:06:07Z","title":"Forgetting to Witness: Efficient Federated Unlearning and Its Visible Evaluation","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-10T20:26:25.834943Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2604.04800"},"observation_digest":"sha256:52e6fa9a557d0867202ff02ee60eb04546059c656d64831de130a7a1a01d9d4b","observation_id":"79deb729-9fee-4621-89bf-5340a636fd8e","resolution":{"observed_at":"2026-05-10T21:55:52.770023Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":"2101.05930","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-06-29T17:33:45.399073Z","title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","venue":null,"work_id":"7cff72c9-26cd-43fe-847c-bc5aa9997177","year":2021},"citing_paper":{"arxiv_id":"2604.09651","last_updated":"2026-03-30T03:54:04Z","snapshot_observed_at":"2026-08-07T01:26:00.994535Z","submitted_at":"2026-03-30T03:54:04Z","title":"FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-14T22:20:35.818770Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2604.09651"},"observation_digest":"sha256:2e77ea842bd7ec25c25a65eca7325b14ecc8fb26df883c9012d959606b22338b","observation_id":"da00cdc8-e604-45c6-b4af-316125d3ec7f","resolution":{"observed_at":"2026-05-14T22:23:03.754274Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":"2101.05930","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-06-29T17:33:45.399073Z","title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","venue":null,"work_id":"7cff72c9-26cd-43fe-847c-bc5aa9997177","year":2021},"citing_paper":{"arxiv_id":"2604.24162","last_updated":"2026-04-27T08:18:30Z","snapshot_observed_at":"2026-07-06T23:10:16.426836Z","submitted_at":"2026-04-27T08:18:30Z","title":"Defusing the Trigger: Plug-and-Play Defense for Backdoored LLMs via Tail-Risk Intrinsic Geometric Smoothing","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-08T03:09:43.879809Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2604.24162"},"observation_digest":"sha256:71344570ac8e0cedacd74a51b4cfa9259da89bd238c81fa843a7d85feb8de817","observation_id":"5103b30f-eb97-4377-9587-a4fa4e857b3c","resolution":{"observed_at":"2026-05-11T22:16:25.236082Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":"2101.05930","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-06-29T17:33:45.399073Z","title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","venue":null,"work_id":"7cff72c9-26cd-43fe-847c-bc5aa9997177","year":2021},"citing_paper":{"arxiv_id":"2605.21146","last_updated":"2026-05-20T13:19:27Z","snapshot_observed_at":"2026-07-06T23:31:37.061253Z","submitted_at":"2026-05-20T13:19:27Z","title":"Detecting Trojaned DNNs via Spectral Regression Analysis","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-21T04:03:36.586890Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2605.21146"},"observation_digest":"sha256:56ca40a5b82191fce1dbab55d472994349442ae87ea3d0157f632959b90324dc","observation_id":"4552479d-9936-4398-a84f-885a1ec9d003","resolution":{"observed_at":"2026-05-21T04:03:56.639562Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":"2101.05930","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-06-29T17:33:45.399073Z","title":"Neural attention distillation: Erasing backdoor triggers from deep neural networks","venue":null,"work_id":"7cff72c9-26cd-43fe-847c-bc5aa9997177","year":2021},"citing_paper":{"arxiv_id":"2605.27148","last_updated":"2026-06-01T21:00:09Z","snapshot_observed_at":"2026-07-06T23:36:53.330986Z","submitted_at":"2026-05-26T15:10:35Z","title":"Landseer: Exploring the Machine Learning Defense Landscape","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-06-29T17:27:29.241219Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2605.27148"},"observation_digest":"sha256:51d75423c5334dd0098654e3dbf727f667c0c2778e8503b53c3fd1095cb7484c","observation_id":"4c4eb55a-78e2-4188-9d38-fa1ecd3c197e","resolution":{"observed_at":"2026-06-29T17:33:45.400960Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.05930","snapshot_observed_at":"2026-08-01T11:29:56.213287Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.19894","last_updated":"2026-07-22T08:29:06Z","snapshot_observed_at":"2026-08-07T08:28:40.661843Z","submitted_at":"2026-07-22T08:29:06Z","title":"Defense Against LLM Backdoors using Critical Neuron Isolation Pruning","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-01T11:29:56.213287Z"},"links":{"cited_paper":"/paper/2101.05930","citing_paper":"/paper/2607.19894"},"observation_digest":"sha256:40a806f288e1827d43e31318b809c77a39b2db9772855ee79ca4b38b7980e552","observation_id":"ba7d909d-3799-4b4f-b17d-ea1d7bdd4e79","resolution":{"observed_at":"2026-08-01T11:29:56.213287Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2101.05930/citation-record","integrity":"/paper/2101.05930/integrity","json":"/paper/2101.05930/citation-record.json","paper":"/paper/2101.05930"},"outbound":[],"paper":{"arxiv_id":"2101.05930","last_updated":"2021-01-27T06:23:25Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T10:32:42.591643Z","submitted_at":"2021-01-15T01:35:22Z","title":"Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 16 inbound Pith citation observations for arXiv:2101.05930."}