{"as_of":"2026-08-16T14:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c570665b706b876cabb7f17ccceb3e8d4b24605e25927c58869462a7f81931c1","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T15:43:29.142715Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T04:45:56.542435Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-14T04:45:56.637195Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"cited_work":{"arxiv_id":"1908.00686","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.00686","snapshot_observed_at":"2026-08-14T04:45:56.637195Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","venue":"cs.CR","work_id":"d7813672-a7b2-4fdf-b7b4-dd9079a53653","year":2019},"citing_paper":{"arxiv_id":"1909.02742","last_updated":"2020-08-31T04:14:46Z","snapshot_observed_at":"2026-08-14T10:10:39.195350Z","submitted_at":"2019-09-06T07:11:26Z","title":"Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T04:45:56.542435Z"},"links":{"cited_paper":"/paper/1908.00686","citing_paper":"/paper/1909.02742"},"observation_digest":"sha256:f4f1b78e6445bf825a740df9fdb3c802e8a2323833e497d745cab5152e54dffa","observation_id":"c4be214c-0349-434e-a2df-13ae7eb2da79","resolution":{"observed_at":"2026-08-14T04:45:56.644346Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1908.00686/citation-record","integrity":"/paper/1908.00686/integrity","json":"/paper/1908.00686/citation-record.json","paper":"/paper/1908.00686"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1807.00459","last_updated":"2019-08-06T04:36:45Z","snapshot_observed_at":"2026-08-14T18:56:55.011249Z","submitted_at":"2018-07-02T04:37:43Z","title":"How To Backdoor Federated Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.00459","snapshot_observed_at":"2026-08-14T15:43:28.776675Z","title":"How to backdoor federated learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.776675Z"},"links":{"cited_paper":"/paper/1807.00459","citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:520111c715bba6f232fc05fc4e93cb2d8156789104a9d0fac0620149dc73c183","observation_id":"63d19641-51bd-437d-ace9-55e163a0bce8","resolution":{"observed_at":"2026-08-14T15:43:28.776675Z","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":"2026-08-14T15:43:30.717310Z","title":"Mitigating poisoning attacks on machine learning models: A data provenance based ap- proach","venue":null,"work_id":"fb1e1886-27dc-4d29-803e-94256c866b0a","year":null},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.781600Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:745ecaf29fe31d18ba2ee42bf1a9051805623f250811034195e1c2c13e84b339","observation_id":"7cfdc3af-6827-4753-94da-3841ba01c7c1","resolution":{"observed_at":"2026-08-14T15:43:30.821814Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:30.564869Z","title":"Statistics for experimenters, volume 664","venue":null,"work_id":"bfc9dc68-7576-42b6-80af-308abb3f7799","year":1978},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.785784Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:70c5d4dfd971ab3747d9804dd7830a1a4bb9417343393f22d576961c4be69741","observation_id":"f431349e-0de9-4a77-aceb-eb9ccbd4516d","resolution":{"observed_at":"2026-08-14T15:43:30.641689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:30.514237Z","title":"Detecting backdoor at- tacks on deep neural networks by activation clustering","venue":null,"work_id":"abad5103-abe6-4ba1-ab6a-4fcdac87ac48","year":2019},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.790144Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:d3d92d1105e1c5a26b892500280ab54d5a4ba02fd0e7e1bad3bd1b2d4d2a215a","observation_id":"f6e16c9a-7050-478e-8f33-63d7a7642f5e","resolution":{"observed_at":"2026-08-14T15:43:30.518235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:30.501702Z","title":"Bayesian face revisited: A joint formulation","venue":null,"work_id":"36e2185a-4c91-4090-b085-452e3e38a76e","year":2012},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.794483Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:8d78c226fb2b5e938c439ff53a09ea8da73508d2670fce8870cc0226aec4921c","observation_id":"0c47f921-e306-4a90-b285-1c65fa602e3b","resolution":{"observed_at":"2026-08-14T15:43:30.505707Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:30.488238Z","title":"ZOO: zeroth order optimization based black-box attacks to deep neural networks with- out training substitute models","venue":null,"work_id":"8879d382-152d-4b73-bbc8-86660c616be9","year":2017},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.807142Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:f8d6c5b048bf93c101dc2c21df6284843f086f453a405b5cf2c392bb8f793f3f","observation_id":"6c5138b2-9db5-4650-b9dd-0f1ccdf0459e","resolution":{"observed_at":"2026-08-14T15:43:30.493546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:28.813256Z","title":"Targeted backdoor attacks on deep learning systems using data poisoning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.813256Z"},"links":{"cited_paper":"/paper/1712.05526","citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:cd0016b778bc036b41aed04d2543792de69748ed7ca7efa950756852beff2a2a","observation_id":"ca9e7189-01a1-453b-81c1-d2483eb7a51d","resolution":{"observed_at":"2026-08-14T15:43:28.813256Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00292","last_updated":"2020-05-09T08:34:57Z","snapshot_observed_at":"2026-08-14T17:50:04.287896Z","submitted_at":"2018-12-02T00:03:07Z","title":"SentiNet: Detecting Localized Universal Attacks Against Deep Learning Systems","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00292","snapshot_observed_at":"2026-08-14T15:43:28.817605Z","title":"Sentinet: Detecting physical attacks against deep learning systems","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.817605Z"},"links":{"cited_paper":"/paper/1812.00292","citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:9d77fff8d32ebcba3721fd2eb7467a798a89c2a0277880a28a187dacbf0dd2da","observation_id":"9b017ecd-6b23-4124-9b26-abd69b0e26b7","resolution":{"observed_at":"2026-08-14T15:43:28.817605Z","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":"2026-08-14T15:43:30.476576Z","title":"STRIP: a defence against trojan attacks on deep neural networks","venue":null,"work_id":"8182bb65-bf03-4640-925d-df191d3cbe21","year":2019},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.829148Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:eb93695731bd2b9228f63c4ff1f9a19a0146c7b9b5b79e750274f6f81734703c","observation_id":"ab0e4f90-ff4d-4fce-8cb0-b30b421b82ae","resolution":{"observed_at":"2026-08-14T15:43:30.481293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.06733","last_updated":"2019-03-11T20:45:33Z","snapshot_observed_at":"2026-08-12T15:43:59.037380Z","submitted_at":"2017-08-22T17:31:54Z","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.06733","snapshot_observed_at":"2026-08-14T15:43:28.840933Z","title":"Badnets: Identifying vulnerabilities in the machine learning model supply chain","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.840933Z"},"links":{"cited_paper":"/paper/1708.06733","citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:1215f12d3756e98107edf32f56909746a1bafe993aeac750fa15a65cb218ff32","observation_id":"7e1fdca4-5857-4876-a226-677eb74ec238","resolution":{"observed_at":"2026-08-14T15:43:28.840933Z","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":"2026-08-14T15:43:28.853963Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.853963Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:a59fe769b80bc1a73d11d2e8a49ce2ea38ae4978d5977b62e94a682ac648383c","observation_id":"4301301b-287b-48b9-a199-3ab991d95d60","resolution":{"observed_at":"2026-08-14T15:43:28.853963Z","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":"2026-08-14T15:43:30.451335Z","title":"Hodge and Jim Austin","venue":null,"work_id":"5358de91-a1e5-452e-a0e2-c48c528c7144","year":2004},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.868517Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:5bca48b6cb4809bba8ef5f74a7f602e3db1a913f73e666d878b49e2d556e447b","observation_id":"fdd595dd-d2f9-4881-947b-aa961da973d3","resolution":{"observed_at":"2026-08-14T15:43:30.454854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:30.440192Z","title":"Black-box adversarial attacks with limited queries and information","venue":null,"work_id":"d88a2ef2-c922-4db0-b9f0-07d42576faf3","year":2018},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.872073Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:ad6f55fca4354f00dc4f0bb887d10bf29e7aac4557946fb75bfa9a3eecdeb5be","observation_id":"6c0562bc-7486-4450-855e-e29ee7324ce5","resolution":{"observed_at":"2026-08-14T15:43:30.444424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:30.311808Z","title":"Algorithms for mining distancebased outliers in large datasets","venue":null,"work_id":"37361273-8907-42e7-9931-94cdeb0c2eab","year":1998},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.875486Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:205a2376626c4ef5bf2c5c57606c4283d9431002aa2d0dce465a70ac91b555ab","observation_id":"f9e6f3be-83a5-4a47-9fbe-30537e595372","resolution":{"observed_at":"2026-08-14T15:43:30.369717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:30.185975Z","title":"Parameter estimation and hypothesis testing in linear models","venue":null,"work_id":"16c2f1c5-68a2-4e25-8217-83f768808f1f","year":1988},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.879275Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:4b2230b6c37fffd87aa196a295f0292dd396e943ba405e53435e594fbe0ad7eb","observation_id":"725bb6ef-d60a-4373-ae2e-1b0af3b327ec","resolution":{"observed_at":"2026-08-14T15:43:30.249569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:30.137484Z","title":"Understanding black- box predictions via influence functions","venue":null,"work_id":"1df7965d-67eb-4879-ab53-5c2c29c3db41","year":2017},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.883742Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:0c14b5e2f95c5f627c46511df192be37f63e8987ee35b6ccbcc3b4114dca4026","observation_id":"a9d54593-1a7f-432b-ae1c-d5aab8abdcc9","resolution":{"observed_at":"2026-08-14T15:43:30.141092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:30.125562Z","title":"Quantifiable data mining using principal component analysis","venue":null,"work_id":"d24eaff8-649a-4580-9cf4-f83c5e36c0bd","year":1998},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.886987Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:91dfb849495ff3d9834fb6d3d431e4d4788b4ac56e671efaa73e781903cb0177","observation_id":"2936a901-ac3b-47cf-8891-1b273c33a244","resolution":{"observed_at":"2026-08-14T15:43:30.129534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:30.114621Z","title":"Learning multi- ple layers of features from tiny images","venue":null,"work_id":"ab737e16-8a8c-4118-8dca-3d5a62ebdfe1","year":2009},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.890250Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:94421c5b6efc0bfb31f26833e690d4de828f9e826ee650362171c1780a5e06b5","observation_id":"b218ac15-7eb3-4b12-963c-85c227f596d5","resolution":{"observed_at":"2026-08-14T15:43:30.118289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:30.102687Z","title":"Gradient-based learning applied to document recognition","venue":null,"work_id":"eb460709-e265-4a68-b16a-251f86177c40","year":1998},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.893821Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:571fefaa2b21dca538df32a7cd0542256ef6155acd7a11365152b2bc794f8650","observation_id":"4c080cc9-a1dd-48d0-a7eb-f02b9c6c329e","resolution":{"observed_at":"2026-08-14T15:43:30.107220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:28.896968Z","title":"Detecting outliers: Do not use standard deviation around the mean, use absolute deviation around the median","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.896968Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:2b211053d3493f260380a395d6522f5b51541685d2086565376fec86e14f07e8","observation_id":"56a03e3a-a9ae-4eec-b9d1-c47b8e1855b0","resolution":{"observed_at":"2026-08-14T15:43:28.896968Z","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":"2026-08-14T15:43:30.084747Z","title":"Printracker: Fingerprinting 3d printers using commodity scanners","venue":null,"work_id":"bb0be60c-56b7-4924-b8f6-44830054e7ea","year":2018},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.900033Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:9b1ec4f000ad829937c7e46c4814bae1da323d47198cf8c9b76fdcd0f1109ef8","observation_id":"99b2737d-6b24-48d1-8c26-2fde07520d50","resolution":{"observed_at":"2026-08-14T15:43:30.088857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:30.074377Z","title":"Fine-pruning: Defending against backdooring attacks on deep neural networks","venue":null,"work_id":"f32bb01a-fa69-4a37-adc6-411df43cea51","year":2018},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.903793Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:1b0781e1be259e9c5f04a9d8f875f31ae3e4ee644b0c7f9a3895dacb88af7ded","observation_id":"0cc2da76-2946-4538-8f73-302fecf02ff8","resolution":{"observed_at":"2026-08-14T15:43:30.077838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:30.063768Z","title":"ABS: scan- ning neural networks for back-doors by artificial brain stimulation","venue":null,"work_id":"9661ada7-2caa-4c2c-bf49-cc25963b6fe6","year":2019},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.907750Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:c5861c95d71c8c728859ecc1203b57b31c66fdccef12e4da17fb5e54c5744b08","observation_id":"621b5f87-806e-441c-8b6b-04460faa57ab","resolution":{"observed_at":"2026-08-14T15:43:30.067185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:30.053216Z","title":"Trojaning attack on neural networks","venue":null,"work_id":"489d67b8-1859-4b1d-9e90-1e2780d43ebe","year":2018},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.910807Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:91acbd29b1777fe1ad7524486bbaba77927ee167510b22475557fb8d65d1716a","observation_id":"1a7a2155-497c-47ee-9b95-d9bc78a73043","resolution":{"observed_at":"2026-08-14T15:43:30.056525Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.993558Z","title":"Fisher dis- criminant analysis with kernels","venue":null,"work_id":"302c01a5-6a35-4950-9888-7355dd00af06","year":1999},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.914260Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:e97b6a52d7c23df7aae33576cac30dfb89f63e181e19cf0710fed6732d5078b2","observation_id":"4d2a2d6f-1b1e-4dda-9986-510b8c45d999","resolution":{"observed_at":"2026-08-14T15:43:30.045629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.829125Z","title":"A system for the analysis of jet engine vibration data","venue":null,"work_id":"e8496722-3162-4131-a0a1-9fc120bd37cd","year":1999},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.917250Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:1f8a9b3fa1fa3505f44c27fe39e3e956e98e23d7aca8bc3d42074a7d95e76eeb","observation_id":"aeba5016-e084-4ce7-8db0-8a84523551af","resolution":{"observed_at":"2026-08-14T15:43:29.895572Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.689384Z","title":"Level playing field for million scale face recognition","venue":null,"work_id":"246735cf-de27-44a9-bb62-8b66dee447e5","year":2017},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.920139Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:24fcc66e744968ce9d62d370439daf8f135b50ae16048df7d77c5f36b069119f","observation_id":"be374c72-6ba2-40cf-be01-00850f335d43","resolution":{"observed_at":"2026-08-14T15:43:29.757635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.642744Z","title":"Misleading learn- ers: Co-opting your spam filter","venue":null,"work_id":"788758f2-1627-4a10-a0f2-7bb464f33e09","year":2009},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.924159Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:632fe3bc84b89590ed7007433f219a31afae60164c7b672c8f9fefa73615d963","observation_id":"e3918918-7354-4493-86d6-1d4e3bdb3ba9","resolution":{"observed_at":"2026-08-14T15:43:29.646730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.631467Z","title":"A data-driven ap- proach to cleaning large face datasets","venue":null,"work_id":"b4743498-c977-4258-8178-b50b6075ca02","year":2014},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.928702Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:4da50a2e8408740ae15bf68549827c5cb0620f87bea25c1a1de01cdc49965174","observation_id":"5465e3a4-0625-4046-a7c2-6f72211d1fdb","resolution":{"observed_at":"2026-08-14T15:43:29.635352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.620051Z","title":"Defending neu- ral backdoors via generative distribution modeling","venue":null,"work_id":"ce2fc5b4-2645-40bf-ae12-496c14b1a4c8","year":2019},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.932695Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:d83dbf6a78a9f934688d64a655069dfcbb262d1402d670f4e1b8a169710373df","observation_id":"f63ffce7-8ddd-4fb3-bdb9-5710f2659079","resolution":{"observed_at":"2026-08-14T15:43:29.623772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.608471Z","title":"Berg, and Li Fei-Fei","venue":null,"work_id":"1a0773b3-49c8-4f96-a56b-a6881421f600","year":2015},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.936460Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:cb4127468345a10bb7a7b44d0376e5ec5233d8db264131fa5344a7c7e07596c3","observation_id":"c8e63038-70f2-4664-8b57-c7f06d8fd679","resolution":{"observed_at":"2026-08-14T15:43:29.612425Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.595627Z","title":"Poison frogs! targeted clean-label poisoning at- tacks on neural networks","venue":null,"work_id":"3f671a25-7fa6-44d7-bb1b-16e99ea169ce","year":2018},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.940408Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:588e4856028e659fd366b8c20e1e0aa2e57e94b37a9824112266561861f87f60","observation_id":"de6856a4-fdec-40d5-bcd7-32907353f21a","resolution":{"observed_at":"2026-08-14T15:43:29.600100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.584034Z","title":"Very deep con- volutional networks for large-scale image recognition","venue":null,"work_id":"09684564-90a0-4a7a-acdd-739999f89cae","year":2015},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.944227Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:9da9f529f7e4bab4776a52bd584f8e3f38d5b7f6ed811572d5d6e7fedfc45d6d","observation_id":"1ea6727f-0d98-4c4e-94de-d43233abf413","resolution":{"observed_at":"2026-08-14T15:43:29.588515Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.06430","last_updated":"2018-05-31T20:05:27Z","snapshot_observed_at":"2026-08-14T19:44:46.968870Z","submitted_at":"2018-02-18T19:39:28Z","title":"DARTS: Deceiving Autonomous Cars with Toxic Signs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.06430","snapshot_observed_at":"2026-08-14T15:43:28.948193Z","title":"DARTS: de- ceiving autonomous cars with toxic signs","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.948193Z"},"links":{"cited_paper":"/paper/1802.06430","citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:0f08f90afc072db0f32b2ed1382083ddf51b255e12416b650fb3dd9c62417903","observation_id":"1f1ccc03-efb4-4d31-93ef-5eaec9819a69","resolution":{"observed_at":"2026-08-14T15:43:28.948193Z","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":"2026-08-14T15:43:29.476431Z","title":null,"venue":null,"work_id":"1a4ae805-d057-4577-8277-622be733381a","year":2012},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.951741Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:c2251cda69f9e36c226571e36b8d3ac7981ba38a02f71325ebde3c4e60cac010","observation_id":"3df7f62f-5a00-4765-86cf-7b89b4572821","resolution":{"observed_at":"2026-08-14T15:43:29.537742Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:28.955200Z","title":"Inception-v4, inception-resnet and the impact of residual connections on learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.955200Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:22bd077efe45220d805eb988407d4e9ae9ae2c4ea82e073dbb8f27dee2ca1c8c","observation_id":"df83ce90-cf8e-4732-9c9a-72ae398e82e6","resolution":{"observed_at":"2026-08-14T15:43:28.955200Z","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":"2026-08-14T15:43:29.351295Z","title":"Going deeper with convolutions","venue":null,"work_id":"e98106a5-9c19-462a-98c1-8327ce84a943","year":2015},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.958516Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:d7bb0fbe69def969c9863c1bb6e2ad2066ada15b8e45b064d9bc586f63cc9a50","observation_id":"54428433-67b8-46a6-8439-6f06faf43edc","resolution":{"observed_at":"2026-08-14T15:43:29.374017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.315384Z","title":"Goodfellow, and Rob Fergus","venue":null,"work_id":"1ba3530b-4f7b-4c87-989c-b99b07765d13","year":2014},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.961960Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:5e25a4786f75364c3f003f9d907ef06ed975283b2d06d9ba8a418cb9057d0bf3","observation_id":"0e66835c-aa9f-49de-91ad-1393877b1b77","resolution":{"observed_at":"2026-08-14T15:43:29.318951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.304744Z","title":"Deep learning approach for network intrusion detection in software de- fined networking","venue":null,"work_id":"055fa6ac-42d3-4425-ae22-463e5fc58e8f","year":2016},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.965075Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:993e8bdd917ac1afd7ce2a50d7086a027af73dda1f44418fa7f04f555492b467","observation_id":"6f26f573-bcdd-4fb7-a774-ba2813b735dc","resolution":{"observed_at":"2026-08-14T15:43:29.308409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.293422Z","title":"Spectral signatures in backdoor attacks","venue":null,"work_id":"b0d2ff72-06ce-42e4-9c4a-283eadbf44fd","year":2018},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:28.968192Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:9754ece308f6b6676054a31c7b5be888c489fcabcc7143c4649d7d1171de8670","observation_id":"ded39325-bb96-43f0-9752-02a6b0c73b87","resolution":{"observed_at":"2026-08-14T15:43:29.297222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.08313","last_updated":"2021-11-15T17:54:50Z","snapshot_observed_at":"2026-08-04T01:57:41.760585Z","submitted_at":"2020-02-19T17:51:21Z","title":"NNoculation: Catching BadNets in the Wild","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.08313","snapshot_observed_at":"2026-08-14T15:43:29.001856Z","title":"Nnoc- ulation: Broad spectrum and targeted treatment of back- doored dnns","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:29.001856Z"},"links":{"cited_paper":"/paper/2002.08313","citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:0241c015e5ef77663a47ff7ad35a13714f14e40c9ffb685f391a453a5bd147c4","observation_id":"a2754a0b-ca1d-4053-b73d-7bef7a3fe521","resolution":{"observed_at":"2026-08-14T15:43:29.001856Z","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":"2026-08-14T15:43:29.280962Z","title":null,"venue":null,"work_id":"e95b0e56-7987-4b4b-9161-d64043414848","year":2019},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:29.075987Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:88ae98a698015066707660aa34a4a076cd98c32c7cd4607f5e88345552817ffc","observation_id":"128692de-3b95-485b-b14a-1b7f9e9ea676","resolution":{"observed_at":"2026-08-14T15:43:29.285100Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.269030Z","title":"Adversary resistant deep neural networks with an appli- cation to malware detection","venue":null,"work_id":"23e08cea-3816-467a-9376-83fa472d3544","year":2017},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:29.131922Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:20b2d71c3821c981e76fad58394c5db3587e22975031f120802160487f467a33","observation_id":"2107d3ff-efbb-4f91-9684-5a6b458d7e99","resolution":{"observed_at":"2026-08-14T15:43:29.273032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.258818Z","title":"A unified framework for subspace face recognition","venue":null,"work_id":"7c1c9149-8b21-4790-85ba-dff4b9845561","year":2004},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:29.135952Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:933cd166e7cc76926a7d81de3471090c9357335fd9dae43ab09d5503d301a4a3","observation_id":"3dd8b4e6-1f0b-4900-aff6-681cbfde6f4f","resolution":{"observed_at":"2026-08-14T15:43:29.262441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.246342Z","title":"Chi-squared distribution — Wikipedia, the free encyclopedia, 2019","venue":null,"work_id":"9be637e3-e605-458b-8801-bfa3ef2fa171","year":2019},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:29.139309Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:b29bf76f30b2c849e33ebdf3751fd26a33209e0b64cd23ff011b320dc24a696d","observation_id":"58d76a00-30b9-459d-9cca-4ee5e2155a40","resolution":{"observed_at":"2026-08-14T15:43:29.251704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T15:43:29.233014Z","title":"The large-sample distribution of the likelihood ratio for testing composite hypotheses","venue":null,"work_id":"6b525f20-c284-44d5-98de-0d286f21b218","year":1938},"citing_paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T15:43:29.142715Z"},"links":{"citing_paper":"/paper/1908.00686"},"observation_digest":"sha256:d21da2a7a97ce9c46ddc90cd45bab212547e45afda96e059b0cb12dfe992ed43","observation_id":"33aec0b2-3691-4d80-9d62-496f3364f49c","resolution":{"observed_at":"2026-08-14T15:43:29.238147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.00686","last_updated":"2020-12-10T09:03:53Z","latest_version":2,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-14T15:35:51.153992Z","submitted_at":"2019-08-02T02:50:37Z","title":"Demon in the Variant: Statistical Analysis of DNNs for Robust Backdoor Contamination Detection"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":0,"verified_fuzzy":35},"total_outbound_references":46},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 1 inbound Pith citation observation for arXiv:1908.00686."}