{"as_of":"2026-08-08T11:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:15a0077d1e118f5a8bd1405a23748be960698867fa44718a5d0ef59187d713c8","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T17:53:29.400938Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.09702/citation-record","integrity":"/paper/2507.09702/integrity","json":"/paper/2507.09702/citation-record.json","paper":"/paper/2507.09702"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:53:25.907116Z","title":"EVit: Expediting vision transformers via token reorganizations,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:25.907116Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:e4af54c2704640bf50fd2ec64666c8cd24d0df79d1204a0f19150a3dbb3b68db","observation_id":"c917aeac-93ad-4cc3-8220-234813b55a6a","resolution":{"observed_at":"2026-08-06T17:53:25.907116Z","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":"2026-08-06T17:53:25.950294Z","title":"Dynamicvit: Efficient vision transformers with dynamic token sparsification,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:25.950294Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:f43daea65b08405b0a58e3a707c61a9d241ebb7fb066dc29466fc0782925514b","observation_id":"66bc784b-c34d-41e9-8b31-ea949e7eea59","resolution":{"observed_at":"2026-08-06T17:53:25.950294Z","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":"2026-08-06T17:53:32.887291Z","title":"Token cropr: Faster vits for quite a few tasks,","venue":null,"work_id":"cf0abedb-59d8-4720-af71-77ceb1959757","year":2025},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:26.010929Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:0b44a0985c48e876dd69be269bed33394db16a401c81a0a31e7fe13fecbb27da","observation_id":"bf39ae82-2bb0-47d5-9324-f160b4a46846","resolution":{"observed_at":"2026-08-06T17:53:32.957144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:53:32.717264Z","title":"Adaptive token sampling for efficient vision trans- formers,","venue":null,"work_id":"9d807b17-3198-4574-ac62-abaaeac33d09","year":2022},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:26.079885Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:16794ac75a8603c63831701337adc2bfc2117a48d1d99f90e3691789abd5ba6e","observation_id":"303c52b5-4eef-4059-b823-60ce23020226","resolution":{"observed_at":"2026-08-06T17:53:32.771402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:53:32.505126Z","title":"Spvit: Enabling faster vision transformers via latency-aware soft token pruning,","venue":null,"work_id":"916c77c0-0c89-48ec-8d7c-bed99e6a72cc","year":2022},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:26.131712Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:fc503e78e2b2b1b987966b24a6d10ec1b5a5dc07900beceb612e999a0c44e928","observation_id":"91b631ec-01d9-4f2e-b7fd-9e1e91f2438e","resolution":{"observed_at":"2026-08-06T17:53:32.616947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:53:26.194931Z","title":"Token merging: Your ViT but faster,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:26.194931Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:b9cf7bd9260bbcaf2c94fd5fe43743013baa71962e946954bda66dffa6096f84","observation_id":"2a1f77be-8f9c-4eb7-8135-db7994d8ada5","resolution":{"observed_at":"2026-08-06T17:53:26.194931Z","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":"2026-08-06T17:53:26.373778Z","title":"Not all tokens are equal: Human-centric visual analysis via token cluster- ing transformer,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:26.373778Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:79ff681d42a67dd7af3d1642c80862e8a371a0876006dc1c0b1565473a2c2c5e","observation_id":"3c0617de-37b9-4f7b-87d7-a01874c97176","resolution":{"observed_at":"2026-08-06T17:53:26.373778Z","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":"2026-08-06T17:53:32.162631Z","title":"Ac- celerating transformers with spectrum-preserving token merging,","venue":null,"work_id":"755c2fa8-ac4d-4b4a-a3f5-129fa2f90cfe","year":2024},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:26.435482Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:6806a69340e436032a42bbc04a2f7d9737326e72b264586910b1e235c55973ca","observation_id":"6a37da3f-b963-42e0-b554-17b19b5b2fbb","resolution":{"observed_at":"2026-08-06T17:53:32.234718Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:53:31.928034Z","title":"Self-slimmed vision transformer,","venue":null,"work_id":"1868b1f6-4091-4df1-9dbc-d37f36dd3d10","year":2022},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:26.496643Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:7ac896fa6823a7c7c09d7ea28caefceac7d5b0249b1dafdf714c0e22c9a14d38","observation_id":"2f567a39-8f7c-4071-9207-555a1334a347","resolution":{"observed_at":"2026-08-06T17:53:32.044333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:53:31.678950Z","title":"Multi-scale hybrid vision transformer and sinkhorn tokenizer for sewer defect classification,","venue":null,"work_id":"e0fcbe8a-7306-410a-980d-4d0e5e2e8a37","year":2022},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:26.562695Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:6b2ff7a5d59df8e7dba45486fbc673fbcbcf2ac6796f83fb97b0ec5314f58929","observation_id":"40b915a7-a7b8-4159-afdf-3b1e53e50ced","resolution":{"observed_at":"2026-08-06T17:53:31.800702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.12015","last_updated":"2022-02-24T10:56:17Z","snapshot_observed_at":"2026-08-06T14:20:02.767018Z","submitted_at":"2022-02-24T10:56:17Z","title":"Learning to Merge Tokens in Vision Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.12015","snapshot_observed_at":"2026-08-06T17:53:26.621820Z","title":"Learning to merge tokens in vision transformers,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:26.621820Z"},"links":{"cited_paper":"/paper/2202.12015","citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:6081c982b22b42c550f37c84834ce161b6407457a7da3808092588c128ec766e","observation_id":"06250222-426a-428f-9eb6-6a309faf1aba","resolution":{"observed_at":"2026-08-06T17:53:26.621820Z","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":"2026-08-06T17:53:31.555537Z","title":"Learning to merge tokens via decoupled embedding for efficient vision transformers,","venue":null,"work_id":"f830122c-fcdd-4282-a8ac-52cc2e89d900","year":2024},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:26.706545Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:10ddc27985d6e7a5e23774afaa1c21e41fc3e117c6d72ab53db07b1693ae1a8c","observation_id":"76227289-c98c-4736-b3ae-01dfea308443","resolution":{"observed_at":"2026-08-06T17:53:31.614091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:53:26.795238Z","title":"Token fusion: Bridging the gap between token pruning and token merging,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:26.795238Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:0b9b14ec7938ca68604022f8eef949bc36d270d3fd946ab5d5e9cb03a788ef2e","observation_id":"90f019a3-07c6-4d21-ada9-a614fedeea49","resolution":{"observed_at":"2026-08-06T17:53:26.795238Z","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":"2026-08-06T17:53:31.311547Z","title":"Diffrate: Differentiable compression rate for efficient vision transformers,","venue":null,"work_id":"63af76ff-0f32-435e-b37c-afaf491bb04c","year":2023},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:26.846228Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:386dbfc52e8eb0d85bb899cfe85b594964ed3fce38ef33b817c4bb6aac0e5598","observation_id":"cb0a5cf6-021a-402f-9fb3-8a6a7a2dd66b","resolution":{"observed_at":"2026-08-06T17:53:31.428546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:53:26.884853Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:26.884853Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:d8cb6286a2d701ad4080b8962956f86b858de95574624952974cb97a7bc358db","observation_id":"9567c294-0725-45f8-a984-c2be9d4f9260","resolution":{"observed_at":"2026-08-06T17:53:26.884853Z","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":"2026-08-06T17:53:31.020485Z","title":"End-to-end object detection with transformers,","venue":null,"work_id":"f06d6c15-c665-433d-b2c5-2fd2badea3b8","year":2020},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:26.938863Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:d9369194a1fbbdb128b7294dc094e73c40f213b9f7bbd727db04cc005cd6e4a7","observation_id":"91990994-306b-4e64-b933-e5790e1cb3bb","resolution":{"observed_at":"2026-08-06T17:53:31.156986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:53:27.015898Z","title":"Vivit: A video vision transformer,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:27.015898Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:f3de42a4e0c273b574fba52afef031f275333f1e6d0380033441bfce3dab087e","observation_id":"7e75d30c-a07d-4964-97c9-d5db8ac0c261","resolution":{"observed_at":"2026-08-06T17:53:27.015898Z","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":"2026-08-06T17:53:30.779802Z","title":"Learn- ing transferable visual models from natural language supervision,","venue":null,"work_id":"8ae023d3-b1b2-4da3-b8e4-71efdcbe69ce","year":2021},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:27.084666Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:40d0814c1ce20faa23a91969075f5ca3a67dd321bdae1cb94e46828c9837664e","observation_id":"b86b3981-37e0-453f-9f19-f8ca4603207e","resolution":{"observed_at":"2026-08-06T17:53:30.861889Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:53:27.144976Z","title":"Autoformer: Searching transformers for visual recognition,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:27.144976Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:9060303e37759c4b89062054306131d09e1d5e8a55da8150dd167bce7012b098","observation_id":"3f7bcd5f-7488-4d85-84c6-c33b1b7f1a5a","resolution":{"observed_at":"2026-08-06T17:53:27.144976Z","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":"2026-08-06T17:53:30.610632Z","title":"Elasticvit: Conflict-aware supernet training for deploying fast vi- sion transformer on diverse mobile devices,","venue":null,"work_id":"1cf430c7-996c-4ee0-9a92-269f412aa035","year":2023},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:27.258661Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:9cffd9cb606640e9a6eaf7f57b9698edb8d30aea91b76f4c8302859d94c2d0d1","observation_id":"fecc1481-479b-4b93-9219-34517ec79ea8","resolution":{"observed_at":"2026-08-06T17:53:30.682547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:53:27.321679Z","title":"Revisit multimodal meta-learning through the lens of multi-task learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:27.321679Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:ff6da284383d01bac6bb8b055b03165971ec09e11ca06c76d084ed4bc6174383","observation_id":"6c57c364-ddee-4dfe-9c33-e32ef61a0829","resolution":{"observed_at":"2026-08-06T17:53:27.321679Z","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":"2026-08-06T17:53:27.406658Z","title":"Vct: A video compression transformer,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:27.406658Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:9f4c96d2ddf2e33f1ac37733ed4c767338934f24c644afdcc52776b37a70e14c","observation_id":"05247dab-19c9-49db-a882-e9291e14c59d","resolution":{"observed_at":"2026-08-06T17:53:27.406658Z","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":"2026-08-06T17:53:27.533921Z","title":"Highly parallel rate-distortion optimized intra-mode decision on multicore graphics processors,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:27.533921Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:358e272512634dd087e0a7f5ae27cd151ab948f052d2a14e3e26a5adca576508","observation_id":"28b16230-1395-4927-a880-ad616e314363","resolution":{"observed_at":"2026-08-06T17:53:27.533921Z","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":"2026-08-06T17:53:30.440501Z","title":"On-device scalable image-based localization via prioritized cascade 5 search and fast one-many ransac,","venue":null,"work_id":"88b86b30-47f1-43a9-83ef-084d5b214ebc","year":2018},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:27.620016Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:358a1007b1201993556158305b31a074a97a77af486df709b9705e2a664184e4","observation_id":"2c55b6a2-edef-4805-ac11-6f67401c5568","resolution":{"observed_at":"2026-08-06T17:53:30.470844Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.15014","last_updated":"2025-01-28T20:29:44Z","snapshot_observed_at":"2026-07-06T20:25:58.814961Z","submitted_at":"2025-01-25T01:37:03Z","title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.15014","snapshot_observed_at":"2026-08-06T17:53:27.672710Z","title":"On accelerating edge ai: Optimiz- ing resource-constrained environments,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:27.672710Z"},"links":{"cited_paper":"/paper/2501.15014","citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:6764b8d24d7b4b730c713f3f741334390a524a87d31132923752aa5333bf2ddc","observation_id":"1e3af81f-46f6-4f84-bf14-2b32bb6ec881","resolution":{"observed_at":"2026-08-06T17:53:27.672710Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.14294","last_updated":"2024-07-19T04:47:36Z","snapshot_observed_at":"2026-07-06T18:03:47.096406Z","submitted_at":"2024-04-22T15:53:08Z","title":"A Survey on Efficient Inference for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.14294","snapshot_observed_at":"2026-08-06T17:53:27.843310Z","title":"A survey on efficient inference for large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:27.843310Z"},"links":{"cited_paper":"/paper/2404.14294","citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:6527d6fbb14e7bb7c13fe19ca1c37e266cada3af5d00027e9c9c12a8ad7576cf","observation_id":"641e6118-09b8-41e6-8cdc-811107b6a0f5","resolution":{"observed_at":"2026-08-06T17:53:27.843310Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.17639","last_updated":"2026-06-16T03:02:33Z","snapshot_observed_at":"2026-08-07T21:39:08.232650Z","submitted_at":"2025-06-21T08:45:32Z","title":"RLRC: Reinforcement Learning-based Recovery for Compressed Vision-Language-Action Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.17639","snapshot_observed_at":"2026-08-06T17:53:27.970825Z","title":"Rlrc: Reinforcement learning- based recovery for compressed vision-language-action models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:27.970825Z"},"links":{"cited_paper":"/paper/2506.17639","citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:555dc72b362dd0ef4c5f3843a5d3b9bcffdb8418ca32bc5e6601abe5492cb209","observation_id":"774558c3-3b82-4344-bf88-e578ddd294d2","resolution":{"observed_at":"2026-08-06T17:53:27.970825Z","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":"2026-08-06T17:53:28.086534Z","title":"Nvit: Vision transformer compression and parameter redistribution,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:28.086534Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:fc647a32bc57ea94806b68fe2d035e914d18702aa389b41c53db6ede1f37492e","observation_id":"1e54d633-1641-4df0-a91f-929796d6b195","resolution":{"observed_at":"2026-08-06T17:53:28.086534Z","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":"2026-08-06T17:53:28.128321Z","title":"Width & depth pruning for vision transformers,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:28.128321Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:4b8ce28f373334e159442d55a6ccbd8c9cfb5a08e8583c8210626512eb45bafb","observation_id":"9be91c68-efb8-4f45-b462-6efde717b120","resolution":{"observed_at":"2026-08-06T17:53:28.128321Z","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":"2026-08-06T17:53:30.233395Z","title":"Revisiting label smoothing and knowledge distillation compatibility: What was missing?","venue":null,"work_id":"091f33f8-8489-4acd-b4bc-8c6e24af2ca9","year":2022},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:28.273809Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:c1fd0bde5e15a03fef2a1be5dfbd763555f0d562f61eead1d61ebde649449354","observation_id":"c7f218e3-45ec-4f69-96b0-00ae361c1662","resolution":{"observed_at":"2026-08-06T17:53:30.295861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-06T17:53:28.417264Z","title":"Distilling the knowledge in a neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:28.417264Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:e43d9f16104a2c4afe7b57cdb16981b07517e6757d0748bd28f42196b96a3590","observation_id":"a6046838-30fb-488b-8e8c-cf710c122d23","resolution":{"observed_at":"2026-08-06T17:53:28.417264Z","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":"2026-08-06T17:53:28.554175Z","title":"Searching the search space of vision transformer,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:28.554175Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:e505670805e7d443086b49e6b275aeeed89bac709fd6e51e002d074b8dcc724b","observation_id":"32f8f9c4-6c85-4b5e-a48b-3821f59517cb","resolution":{"observed_at":"2026-08-06T17:53:28.554175Z","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":"2026-08-06T17:53:28.753738Z","title":"Nasvit: Neural architecture search for efficient vision transformers with gradient conflict-aware supernet training,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:28.753738Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:a0f8ed4ff8b1e9cc975c57e0391cbe3c451806f05b74c12b404916bb6da9dd16","observation_id":"c97944a2-5ac3-4dfc-9aca-8c246711a92a","resolution":{"observed_at":"2026-08-06T17:53:28.753738Z","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":"2026-08-06T17:53:28.896734Z","title":"Vitas: Vision transformer architecture search,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:28.896734Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:47007ece42a4dcfc5e9fc9e054e1eb82daf2bfa38d04d4e9edc239987dd56416","observation_id":"bbf2d92d-b3e7-484e-afba-6f4621fdc9ef","resolution":{"observed_at":"2026-08-06T17:53:28.896734Z","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":"2026-08-06T17:53:30.036030Z","title":"Which tokens to use? investigating token reduction in vision transformers,","venue":null,"work_id":"7df3545e-b7c0-4816-b3ef-b138e17e59b7","year":2023},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:29.047790Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:95e4018aa5753e6173a3b817f6aa6373d222e4d107d2cc63534636276a02f2fc","observation_id":"63adba2c-ac20-4529-9d81-c02e587840b2","resolution":{"observed_at":"2026-08-06T17:53:30.117351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:53:29.840576Z","title":"Spvit: Enabling faster vision transformers via latency-aware soft token pruning,","venue":null,"work_id":"fbbb5e65-7d35-4946-806e-bd587c759885","year":2022},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:29.187146Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:04430870e5848efc1239e4d4aa5d4c8d69cd2f9c6e028e4340ee6dc7f09944a1","observation_id":"b7d28318-bd84-4719-b765-41d3dd0a1e50","resolution":{"observed_at":"2026-08-06T17:53:29.957935Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:53:32.345207Z","title":"Token pooling in vision transformers for image classification,","venue":null,"work_id":"de584ac7-3390-478e-a2ca-b5d2ccb6963e","year":2023},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:29.274039Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:9d70f304756af7426e8686140ebd6ded6db95d62eb0c6ee8faa6e9831cd7bb4e","observation_id":"b6929117-3273-4c44-88dc-c55c69a2bc84","resolution":{"observed_at":"2026-08-06T17:53:32.421317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T17:53:29.580528Z","title":"Not all tokens are equal: Human-centric visual analysis via token cluster- ing transformer,","venue":null,"work_id":"dfa39f92-040d-46df-abb9-2233f6500bae","year":2022},"citing_paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T17:53:29.400938Z"},"links":{"citing_paper":"/paper/2507.09702"},"observation_digest":"sha256:11d938750ec464a5e69f898739eba15e649ede30171693bf80c2873a5b584d0c","observation_id":"843c6e41-c705-4e23-8564-1d22cf2c679a","resolution":{"observed_at":"2026-08-06T17:53:29.691991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.09702","last_updated":"2025-07-13T16:26:05Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T10:39:43.082405Z","submitted_at":"2025-07-13T16:26:05Z","title":"Token Compression Meets Compact Vision Transformers: A Survey and Comparative Evaluation for Edge AI"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":0,"verified_fuzzy":17},"total_outbound_references":38},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2507.09702."}