{"as_of":"2026-08-10T13:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1214d57eebaebdb7df95a9d50bc39b80fb492e3404e4e76eec3fa9a5f4054cfa","coverage":[{"denominator":30,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":30,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T18:11:10.267219Z","state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-27T16:49:14.243931Z","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":"2026-07-03T01:07:30.144002Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"cited_work":{"arxiv_id":"2508.15036","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.15036","snapshot_observed_at":"2026-07-03T01:07:30.144002Z","title":"Moecho: Exploiting side-channel attacks to compromise user privacy in mixture-of-experts llms","venue":null,"work_id":"7042b661-0867-45c5-920a-ec23edac60a9","year":2025},"citing_paper":{"arxiv_id":"2603.09002","last_updated":"2026-04-26T14:13:48Z","snapshot_observed_at":"2026-07-06T22:48:26.306802Z","submitted_at":"2026-03-09T22:46:27Z","title":"Security Considerations for Multi-agent Systems","version":2},"reference_index":256,"source":"pdf_text","source_observed_at":"2026-05-15T14:12:14.160789Z"},"links":{"cited_paper":"/paper/2508.15036","citing_paper":"/paper/2603.09002"},"observation_digest":"sha256:617e59394ac2ab6758853447fe53f65dea90a6cd934f150be0d1358e72e7da21","observation_id":"628c1594-0b17-4a05-8337-7aacb8c14fea","resolution":{"observed_at":"2026-05-15T14:15:55.054634Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"cited_work":{"arxiv_id":"2508.15036","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.15036","snapshot_observed_at":"2026-07-03T01:07:30.144002Z","title":"Moecho: Exploiting side-channel attacks to compromise user privacy in mixture-of-experts llms","venue":null,"work_id":"7042b661-0867-45c5-920a-ec23edac60a9","year":2025},"citing_paper":{"arxiv_id":"2606.09038","last_updated":"2026-06-08T05:10:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-06-08T05:10:05Z","title":"Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-27T16:49:14.243931Z"},"links":{"cited_paper":"/paper/2508.15036","citing_paper":"/paper/2606.09038"},"observation_digest":"sha256:d065ba730bd99a94a0574c8d1a62853bb26fc1a221e9f89ea4de9b718a60c23c","observation_id":"6cd9d6f5-0f45-439c-b752-f5b3484cdab0","resolution":{"observed_at":"2026-07-03T01:07:30.145764Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2508.15036/citation-record","integrity":"/paper/2508.15036/integrity","json":"/paper/2508.15036/citation-record.json","paper":"/paper/2508.15036"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T18:11:14.767532Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":"0e8f93b3-7628-456e-924e-0dee201df5ad","year":2016},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:07.495152Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:a03116431890c15756df4d0d12332f26fc96247e5cc42a9eda152032882f25dc","observation_id":"f7d1ab20-78cb-4bf0-91d1-2c023815b789","resolution":{"observed_at":"2026-08-05T18:11:14.905246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T18:11:14.554099Z","title":"CNN Feature Map Augmentation for Single-Source Domain Generaliza- tion","venue":null,"work_id":"1a9b49e2-3ad7-44c4-a3dc-91f8329d702f","year":2023},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:07.559774Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:bcf9d5328a14ea15b2da88b49031014c5e0e46c57a49419fef28549359155b7b","observation_id":"a923ea6e-4bb3-46f4-985b-66148248a957","resolution":{"observed_at":"2026-08-05T18:11:14.644492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T18:11:14.342054Z","title":"Feature Map Augmentation to Improve Rotation Invariance in Convolutional Neural Networks","venue":null,"work_id":"4be0bd88-1596-42c2-9a17-78c8dc0fa708","year":2020},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:07.678577Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:ac23a2445149d5bf411bf03b43c5b3d9c9cd0233d72e7062259bdebaaef66e0d","observation_id":"b1cb0650-4c7b-45f7-80fc-a6005bef8400","resolution":{"observed_at":"2026-08-05T18:11:14.442609Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1311.2901","last_updated":"2013-11-28T23:04:01Z","snapshot_observed_at":"2026-08-05T00:25:16.855832Z","submitted_at":"2013-11-12T20:02:22Z","title":"Visualizing and Understanding Convolutional Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1311.2901","snapshot_observed_at":"2026-08-05T18:11:07.771874Z","title":"Visualizing and Understanding Convolutional Networks","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:07.771874Z"},"links":{"cited_paper":"/paper/1311.2901","citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:6cd5ad222663e43670116d87e11040c4861b87f61f91bd132541494d737eac3e","observation_id":"0f0c5226-d480-4838-b119-79f5cc7f9672","resolution":{"observed_at":"2026-08-05T18:11:07.771874Z","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":"2026-08-05T18:11:14.198585Z","title":"An Efficient CNN Inference Accelerator Based on Intra- and Inter-Channel Feature Map Compression","venue":null,"work_id":"21c6bdc0-504c-4896-821e-83281d8370e6","year":2023},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:07.875960Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:23874c6de9820a02820f3d459a95995a7b3b983aa31f0ab37d692eb6f53c8c12","observation_id":"b550f29a-9aed-47ac-8969-43e5795d045b","resolution":{"observed_at":"2026-08-05T18:11:14.263166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T18:11:14.030783Z","title":"GACT: Activation Compressed Training for Generic Network Architectures","venue":null,"work_id":"3654d26e-c4fb-4982-9749-8ea38781af29","year":2022},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:07.944951Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:9ead5f887d91af29866bdb0c5a272f9ccbefe7ac7a5317447cd785237ee1b410","observation_id":"1cb32afb-a6f4-4572-a1f2-57717fa5ed7f","resolution":{"observed_at":"2026-08-05T18:11:14.113587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T18:11:13.858413Z","title":"ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training","venue":null,"work_id":"8c369a0d-864c-4e7e-bf0f-42e826cdb1f4","year":2021},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:08.009481Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:3fe98eda580f5d6f36d60dc1b992e1f3898f20d8c7d2682975436d471afa2bde","observation_id":"35e11ed5-b73f-4ec4-9c48-9e9c9486d0e2","resolution":{"observed_at":"2026-08-05T18:11:13.932658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T18:11:13.686991Z","title":"Egeria: Efficient DNN Training with Knowledge-Guided Layer Freezing","venue":null,"work_id":"c41ffb52-986d-440d-af87-32a75ba114cb","year":2023},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:08.127580Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:a215d3202b13a2f18974da324e26f5aa2f7e4326344c048a3322ef8d176690ad","observation_id":"1b26f767-8cc4-4699-99d9-2179e2ce2625","resolution":{"observed_at":"2026-08-05T18:11:13.749562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.16720","last_updated":"2024-01-30T03:34:27Z","snapshot_observed_at":"2026-07-06T17:22:15.248410Z","submitted_at":"2024-01-30T03:34:27Z","title":"SmartFRZ: An Efficient Training Framework using Attention-Based Layer Freezing","version":1},"cited_work":{"arxiv_id":"2401.16720","doi":null,"metadata_source":"pith","pith_arxiv_id":"2401.16720","snapshot_observed_at":"2026-08-05T18:11:10.920329Z","title":"SmartFRZ: An Efficient Training Framework using Attention-Based Layer Freezing","venue":"cs.LG","work_id":"c1450fbc-a97b-40ea-baf9-6c97340f4e3a","year":2024},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:08.215580Z"},"links":{"cited_paper":"/paper/2401.16720","citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:d2d23e366c53907f2fa69607d8e43c4d67494a144e67a56d379a3aca38b9f501","observation_id":"f5463539-7244-4ff3-8ff0-fdd1443d726c","resolution":{"observed_at":"2026-08-05T18:11:11.114496Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T18:11:13.601787Z","title":"Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training","venue":null,"work_id":"3ce92919-891e-4106-875b-d18b2cef5772","year":2022},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:08.315986Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:947d76c5b1e61d6ac54f7ae9c976182945a2c13f8e3e0b7b4afaf16e8191b70e","observation_id":"eaa82b9c-284e-423a-a121-6d8490eec2df","resolution":{"observed_at":"2026-08-05T18:11:13.638915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.01386","last_updated":"2021-04-03T15:08:06Z","snapshot_observed_at":"2026-08-09T08:23:14.998906Z","submitted_at":"2021-02-02T08:35:02Z","title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.01386","snapshot_observed_at":"2026-08-05T18:11:08.387528Z","title":"AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:08.387528Z"},"links":{"cited_paper":"/paper/2102.01386","citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:c18440ff340920f7bcfa23eef0d6303e18c7d42b9b6d91c1c4dbb0f7261bf643","observation_id":"cf59379f-de74-4ea4-9f67-205ba03678da","resolution":{"observed_at":"2026-08-05T18:11:08.387528Z","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":"2026-08-05T18:11:13.414811Z","title":"LayerOut: Freezing Layers in Deep Neural Networks","venue":null,"work_id":"e1f9668c-646e-4fae-9ded-71df206c54bf","year":2020},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:08.475983Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:d0cd5b3d1de509108bb331456637db01a9fb626946572da538cabf842495788d","observation_id":"34031b2b-88d2-4c9b-a088-3f6c6ad03381","resolution":{"observed_at":"2026-08-05T18:11:13.506268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.03090","last_updated":"2019-11-08T07:05:20Z","snapshot_observed_at":"2026-07-06T08:35:28.740170Z","submitted_at":"2019-11-08T07:05:20Z","title":"What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.03090","snapshot_observed_at":"2026-08-05T18:11:08.573875Z","title":"What Would Elsa Do? Freezing Layers During Transformer Fine-Tuning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:08.573875Z"},"links":{"cited_paper":"/paper/1911.03090","citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:d3d24554661ca0aca5186fed4649d17f2f7104580641127c9bbddcfeb9b2a1ae","observation_id":"2384074e-1fc6-4345-bf64-4ff67428de20","resolution":{"observed_at":"2026-08-05T18:11:08.573875Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.04983","last_updated":"2017-06-18T16:15:21Z","snapshot_observed_at":"2026-07-06T05:47:02.250306Z","submitted_at":"2017-06-15T17:35:15Z","title":"FreezeOut: Accelerate Training by Progressively Freezing Layers","version":2},"cited_work":{"arxiv_id":"1706.04983","doi":null,"metadata_source":"pith","pith_arxiv_id":"1706.04983","snapshot_observed_at":"2026-08-05T18:11:10.803191Z","title":"FreezeOut: Accelerate Training by Progressively Freezing Layers","venue":"stat.ML","work_id":"8e0f008a-6202-4a73-9878-362d2ee67ae1","year":2017},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:08.695617Z"},"links":{"cited_paper":"/paper/1706.04983","citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:87ef270f610502f31f6f90c879b9dc2bde580c2a90c7a2af09f004a1804d2bc9","observation_id":"aa7f1628-683d-4f2a-8900-34a66b7513cf","resolution":{"observed_at":"2026-08-05T18:11:10.823484Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.12877","last_updated":"2021-01-15T15:52:50Z","snapshot_observed_at":"2026-08-09T03:59:14.830524Z","submitted_at":"2020-12-23T18:42:10Z","title":"Training data-efficient image transformers & distillation through attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.12877","snapshot_observed_at":"2026-08-05T18:11:08.807726Z","title":"Training data- efficient image transformers & distillation through attention","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:08.807726Z"},"links":{"cited_paper":"/paper/2012.12877","citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:8f6bf710cad49882b0b4dd491cd3fa91319b3e59c04b16044d9300a6908dd3b0","observation_id":"37c2ffe3-2a3e-4707-a57c-152aeee783fd","resolution":{"observed_at":"2026-08-05T18:11:08.807726Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.05785","last_updated":"2025-04-18T04:00:31Z","snapshot_observed_at":"2026-07-06T19:12:40.908608Z","submitted_at":"2024-09-09T16:48:09Z","title":"NeurLZ: An Online Neural Learning-Based Method to Enhance Scientific Lossy Compression","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.05785","snapshot_observed_at":"2026-08-05T18:11:08.898782Z","title":"NeurLZ: On Enhancing Lossy Compression Performance based on Error- Controlled Neural Learning for Scientific Data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:08.898782Z"},"links":{"cited_paper":"/paper/2409.05785","citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:0bfafde7ef51b33fa49442c6bdf4e92e27ee6d5d335f5dff7a5cd3340e0740ad","observation_id":"3df2a5c0-4bc8-4ef1-9259-67d5ae0dca44","resolution":{"observed_at":"2026-08-05T18:11:08.898782Z","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":"2026-08-05T18:11:13.250650Z","title":"A Review of Deep Transfer Learning and Recent Advancements","venue":null,"work_id":"3057cae2-d4ac-4265-82f7-8e202efcf521","year":2023},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:08.991566Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:a899b1a6557a807821e3a3e2f006baaf1d54f3f3f585ee4c4ce32ae1da82b214","observation_id":"8c4062db-bb40-4e01-99b2-f44d534f5494","resolution":{"observed_at":"2026-08-05T18:11:13.315980Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.16954","last_updated":"2024-11-23T02:35:18Z","snapshot_observed_at":"2026-08-07T07:09:47.433281Z","submitted_at":"2024-10-22T12:33:45Z","title":"LoRA-C: Parameter-Efficient Fine-Tuning of Robust CNN for IoT Devices","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.16954","snapshot_observed_at":"2026-08-05T18:11:09.088987Z","title":"LoRA-C: Parameter-Efficient Fine-Tuning of Robust CNN for IoT Devices","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:09.088987Z"},"links":{"cited_paper":"/paper/2410.16954","citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:0dea58c15e89310e992369c7333b3c85132f976e3f0505edd14b1e8e8ccdecf1","observation_id":"8a9e2ef9-cdb5-4cf4-a4e4-f74acfadffe0","resolution":{"observed_at":"2026-08-05T18:11:09.088987Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.01483","last_updated":"2018-06-06T08:50:30Z","snapshot_observed_at":"2026-07-06T06:21:49.379500Z","submitted_at":"2018-02-05T15:58:40Z","title":"Explicit Inductive Bias for Transfer Learning with Convolutional Networks","version":2},"cited_work":{"arxiv_id":"1802.01483","doi":null,"metadata_source":"pith","pith_arxiv_id":"1802.01483","snapshot_observed_at":"2026-08-05T18:11:10.598432Z","title":"Explicit Inductive Bias for Transfer Learning with Convolutional Networks","venue":"cs.LG","work_id":"ec464b84-503e-4fd6-9634-b83c2bd7882c","year":2018},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:09.183434Z"},"links":{"cited_paper":"/paper/1802.01483","citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:933430901cea192723244e591928511ecfc08ddbcc35dc0c145c4be22c55ded3","observation_id":"e1cfb1c2-e7b8-496f-9175-43841837998f","resolution":{"observed_at":"2026-08-05T18:11:10.673543Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T18:11:13.028443Z","title":"Fixed-Rate Compressed Floating-Point Arrays","venue":null,"work_id":"8b1447a6-1d2e-4b10-9fc1-0d3b061d6689","year":2014},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:09.299428Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:b1bdacdace142c50bc3911b6913a999f455b0419564c5decd32002f089621b8f","observation_id":"29cbabf4-a170-486d-a66a-c979486729d8","resolution":{"observed_at":"2026-08-05T18:11:13.123788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T18:11:12.783178Z","title":"A survey on Image Data Augmentation for Deep Learning","venue":null,"work_id":"096f0046-8b39-4be2-9085-0fbdb56d7eb4","year":2019},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:09.396558Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:570e8343e991a6cfca4953859697c0bc21eae288f543f353089ba52bf42acfa5","observation_id":"16d04ccd-ce91-4063-82c0-bbfd73a84067","resolution":{"observed_at":"2026-08-05T18:11:12.899926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.14097","last_updated":"2022-09-28T13:46:24Z","snapshot_observed_at":"2026-08-10T11:06:50.479571Z","submitted_at":"2022-09-28T13:46:24Z","title":"Data Augmentation using Feature Generation for Volumetric Medical Images","version":1},"cited_work":{"arxiv_id":"2209.14097","doi":null,"metadata_source":"pith","pith_arxiv_id":"2209.14097","snapshot_observed_at":"2026-08-05T18:11:10.383358Z","title":"Data Augmentation using Feature Generation for Volumetric Medical Images","venue":"eess.IV","work_id":"e3f8fe1d-9b0d-46c9-8e24-895dc6c22937","year":2022},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:09.490458Z"},"links":{"cited_paper":"/paper/2209.14097","citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:088ff24ebc36c3b3e942100fd4e4b785cc1a4912eeb7c6e9336469e2a17c25aa","observation_id":"f3cddc89-3f7a-4719-8c41-b9c35cdd1fc0","resolution":{"observed_at":"2026-08-05T18:11:10.476442Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T18:11:12.559835Z","title":"(2019, May)","venue":null,"work_id":"fa2d48e0-0d1e-4507-8e5e-a3cf7dd168ad","year":2019},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:09.562428Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:59e76864d4b7021f60fd49b154f09ce034cbedcfa34d45dcc67a1f3611097321","observation_id":"ad231a53-8243-4471-a82e-7bb793b53862","resolution":{"observed_at":"2026-08-05T18:11:12.676691Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T18:11:12.337939Z","title":null,"venue":null,"work_id":"229fe933-8d1e-46df-9f9c-1a44d04b98d4","year":2019},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:09.655293Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:f238f39ad0fdcbd7f7ac065d35ffe15fb77e3dd551dba3135ee7878d792ebe53","observation_id":"8eb0e4a7-5c49-41fe-a278-c5c2c33d08c6","resolution":{"observed_at":"2026-08-05T18:11:12.417729Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.02008","last_updated":"2021-04-05T16:58:09Z","snapshot_observed_at":"2026-08-10T09:28:28.538323Z","submitted_at":"2021-04-05T16:58:09Z","title":"Domain Generalization with MixStyle","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.02008","snapshot_observed_at":"2026-08-05T18:11:09.753746Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:09.753746Z"},"links":{"cited_paper":"/paper/2104.02008","citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:6817f77b73fe2f65d10f0aaf43955a5f08e510fec70b0edd608e4bb37eb3ea47","observation_id":"d9d5c042-6a1d-4e07-ad3c-cad9aaeccb9f","resolution":{"observed_at":"2026-08-05T18:11:09.753746Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.12047","last_updated":"2021-02-28T14:47:36Z","snapshot_observed_at":"2026-08-09T21:39:27.876617Z","submitted_at":"2020-02-27T11:46:33Z","title":"FMix: Enhancing Mixed Sample Data Augmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.12047","snapshot_observed_at":"2026-08-05T18:11:09.846446Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:09.846446Z"},"links":{"cited_paper":"/paper/2002.12047","citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:5750debecfef501e74a3956fcb979a3ccd61fe0ed0b48b763e0d57af84c1fd4c","observation_id":"e62bac5c-c7c6-44c5-bfcf-5746fa0d04f1","resolution":{"observed_at":"2026-08-05T18:11:09.846446Z","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":"2026-08-05T18:11:12.045588Z","title":null,"venue":null,"work_id":"153ae6f8-b172-4a38-965a-a063b809ccb7","year":2021},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:09.968832Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:81567be302222bfc5483e46022058eb11978cf6a2f82f8a15511ea9227c900de","observation_id":"5ba0e415-f9bd-48bc-9205-bf2dae980f4a","resolution":{"observed_at":"2026-08-05T18:11:12.159229Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T18:11:11.734854Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":"0b162c9c-f0e8-4e95-982c-8f67a54f89ba","year":2009},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:10.086766Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:cbefb48e655519954c28fb825e42617b852e85d3f36fea4ab0767fd7bc3152b7","observation_id":"41cf56c1-d920-4a27-bf88-29ce8bac3b55","resolution":{"observed_at":"2026-08-05T18:11:11.887895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T18:11:11.480618Z","title":"[Online]","venue":null,"work_id":"8b2ae46f-f177-417c-b90c-b73b11aa741c","year":2024},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:10.177216Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:4562e6a172c7e1cf7c3ed4ed66f6db134d1d224776ee8a70db1233ad79150c4b","observation_id":"904e9445-a497-4bcb-9fed-faf8dc9f8500","resolution":{"observed_at":"2026-08-05T18:11:11.575641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T18:11:11.279152Z","title":"ImageNet: A large-scale hierarchical image database,","venue":null,"work_id":"102cf263-651d-4877-99b2-9ce35cf82757","year":2009},"citing_paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T18:11:10.267219Z"},"links":{"citing_paper":"/paper/2508.15036"},"observation_digest":"sha256:3001aca84a5ce6363009ee370ab98e2eb741949fada5e38b4a8991afb9762818","observation_id":"888a9d26-c822-4295-9f78-ac3dfccb501b","resolution":{"observed_at":"2026-08-05T18:11:11.404288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.15036","last_updated":"2025-08-20T20:02:35Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-08T01:51:47.464406Z","submitted_at":"2025-08-20T20:02:35Z","title":"MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs"},"reference_resolution":{"displayed":30,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":4,"verified_fuzzy":16},"total_outbound_references":30},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 2 inbound Pith citation observations for arXiv:2508.15036."}