{"as_of":"2026-08-09T09:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f74ec2e45a38b9eaecf6e3d1bedf4c76fb6f66d592fdab56996e10606272552b","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":5,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":5,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":5,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T18:01:08.726844Z","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":"2026-05-13T06:57:27.323110Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2010.02432","last_updated":"2021-02-25T22:38:35Z","snapshot_observed_at":"2026-08-04T03:00:18.680368Z","submitted_at":"2020-10-06T02:06:52Z","title":"A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02432","snapshot_observed_at":"2026-08-06T23:35:36.065493Z","title":null,"venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.17621","last_updated":"2025-06-21T07:13:14Z","snapshot_observed_at":"2026-08-06T23:28:12.796721Z","submitted_at":"2025-06-21T07:13:14Z","title":"Exploiting Efficiency Vulnerabilities in Dynamic Deep Learning Systems","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-06T23:35:36.065493Z"},"links":{"cited_paper":"/paper/2010.02432","citing_paper":"/paper/2506.17621"},"observation_digest":"sha256:826cc0382db252b98d39f0ae6267fa5fe2dcc1acea50c06f8e195f61d6f75569","observation_id":"ee98d712-1642-42af-addf-98e2655e604e","resolution":{"observed_at":"2026-08-06T23:35:36.065493Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02432","last_updated":"2021-02-25T22:38:35Z","snapshot_observed_at":"2026-08-04T03:00:18.680368Z","submitted_at":"2020-10-06T02:06:52Z","title":"A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference","version":2},"cited_work":{"arxiv_id":"2010.02432","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2010.02432","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A panda? no, it’s a sloth: Slowdown attacks on adaptive multi-exit neural network inference","venue":null,"work_id":"3a9f8172-5f03-43de-973d-9f77ee22c0ad","year":2010},"citing_paper":{"arxiv_id":"2605.10987","last_updated":"2026-05-09T09:16:49Z","snapshot_observed_at":"2026-08-02T13:30:31.146998Z","submitted_at":"2026-05-09T09:16:49Z","title":"AESOP: Adversarial Execution-path Selection to Overload Deep Learning Pipelines","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-13T06:56:46.429371Z"},"links":{"cited_paper":"/paper/2010.02432","citing_paper":"/paper/2605.10987"},"observation_digest":"sha256:cd72f744a6fbc8f8d3c5ac1738c5b708782595e41b6b9f19014b170588b683cc","observation_id":"af6d8339-8fcb-4c73-885a-148a9e73e661","resolution":{"observed_at":"2026-05-13T06:57:27.326335Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02432","last_updated":"2021-02-25T22:38:35Z","snapshot_observed_at":"2026-08-04T03:00:18.680368Z","submitted_at":"2020-10-06T02:06:52Z","title":"A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02432","snapshot_observed_at":"2026-08-05T06:00:04.080994Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.03902","last_updated":"2026-08-04T16:29:35Z","snapshot_observed_at":"2026-08-09T04:27:50.402455Z","submitted_at":"2026-08-04T16:29:35Z","title":"When Efficiency Becomes Fragility: Exploiting Dynamic Routing Vulnerabilities in Adaptive UAV Tracking","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T06:00:04.080994Z"},"links":{"cited_paper":"/paper/2010.02432","citing_paper":"/paper/2608.03902"},"observation_digest":"sha256:3ab4b4838c4fad0a1a8bab321abf631d6d4b286681f941ce9ff55b9eb73dc9df","observation_id":"d69d47bc-cf21-4801-94c9-c5d4d6136332","resolution":{"observed_at":"2026-08-05T06:00:04.080994Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02432","last_updated":"2021-02-25T22:38:35Z","snapshot_observed_at":"2026-08-04T03:00:18.680368Z","submitted_at":"2020-10-06T02:06:52Z","title":"A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02432","snapshot_observed_at":"2026-08-06T19:08:28.375787Z","title":"A panda? no, it’s a sloth: Slowdown attacks on adaptive multi-exit neural network inference,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.04680","last_updated":"2026-08-05T10:47:58Z","snapshot_observed_at":"2026-08-08T23:12:16.654516Z","submitted_at":"2026-08-05T10:47:58Z","title":"MOAT: Model-Agnostic Randomized Transformations for preventing Efficiency Degradation Attacks on ViTs","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T19:08:28.375787Z"},"links":{"cited_paper":"/paper/2010.02432","citing_paper":"/paper/2608.04680"},"observation_digest":"sha256:7f4f1eba3b091f982ed91eb87770e2f8ac770e4947e431ff8995996f317f5fe1","observation_id":"228cf454-02ed-4dcc-8d1a-2dbf7525f19f","resolution":{"observed_at":"2026-08-06T19:08:28.375787Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02432","last_updated":"2021-02-25T22:38:35Z","snapshot_observed_at":"2026-08-04T03:00:18.680368Z","submitted_at":"2020-10-06T02:06:52Z","title":"A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02432","snapshot_observed_at":"2026-08-08T18:01:08.726844Z","title":"A panda? no, it’s a sloth: Slowdown attacks on adaptive multi-exit neural network inference,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.05217","last_updated":"2026-08-05T10:29:06Z","snapshot_observed_at":"2026-08-09T09:09:57.651224Z","submitted_at":"2026-08-05T10:29:06Z","title":"A Survey of Adversarial Efficiency Degradation for Vision Transformer by Exploiting Input-adaptive Optimization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-08T18:01:08.726844Z"},"links":{"cited_paper":"/paper/2010.02432","citing_paper":"/paper/2608.05217"},"observation_digest":"sha256:94ae178bc967f8b1539bb23fc99a085d1ac6f5e64759b475b65231bfa5888715","observation_id":"28a4cd23-0cf9-4772-be78-06a3e0444a21","resolution":{"observed_at":"2026-08-08T18:01:08.726844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2010.02432/citation-record","integrity":"/paper/2010.02432/integrity","json":"/paper/2010.02432/citation-record.json","paper":"/paper/2010.02432"},"outbound":[],"paper":{"arxiv_id":"2010.02432","last_updated":"2021-02-25T22:38:35Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T03:00:18.680368Z","submitted_at":"2020-10-06T02:06:52Z","title":"A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:2010.02432."}