{"as_of":"2026-08-19T21:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cc65417b752c231f42f5a5129b87b9217104ff6af06399fa118dc810a5948a3d","coverage":[{"denominator":23,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":23,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-12T09:00:09.975699Z","state":"measured"},{"denominator":23,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":23,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+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/2607.02612/citation-record","integrity":"/paper/2607.02612/integrity","json":"/paper/2607.02612/citation-record.json","paper":"/paper/2607.02612"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T09:00:09.975699Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:a02cff2800a86baf8150a5561f716f2f9534d7de5b513134b1756f82bf1d0392","observation_id":"aa49cf8a-41a8-4beb-b430-9007225bdce6","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"Training data-efficient image transformers & distillation through attention,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:f39ae6d6a71b203fea136b6f4b1c7c195309f8e622c2569c83669070cce9dea9","observation_id":"b5ecfdc6-a679-4ab7-9335-1535f13bd606","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"DynamicViT: Efficient vision transformers with dynamic token sparsification,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:29a9ef188487f95a96adf83e351556d4b391a71b2d53100214682a08ca06112f","observation_id":"2f66c576-c68a-46e8-899c-f8737102cbb4","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"Not all patches are what you need: Expediting vision transformers via token reorganizations,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:c2bf78160072dbb9964874d57e802868792813b5b12ab0b1d31218a541e8c5f5","observation_id":"fcf34412-8022-4d0c-af52-6d23a06a6d21","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"Token merging: Your ViT but faster,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:0e31cb4a465f18b0893c32dcb372b14fb59a46809addef935fcd36d3ab9055ec","observation_id":"1dfb7f32-d179-43b8-ad62-567aa255b756","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"A-ViT: Adaptive tokens for efficient vision transformer,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:53b52f0818d72790cd44201e132fbc31f6096748853f9b791c71fca83ecadc80","observation_id":"c9f45727-c0ab-4612-b747-442197de61e0","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"LGViT: Dynamic early exiting for accelerating vision transformer,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:f29d57f6163344607b1b22735d1fa100a165656be1ad1c115b2babbf31c24358","observation_id":"a530c299-18bc-4621-8b7d-215c95040410","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"BranchyNet: Fast inference via early exiting from deep neural networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:28478550c191e2d04cbf017e8aa21bef1aab0c3fcbe2a1cccd5377f18715a559","observation_id":"530c97ee-af20-4984-96a1-6013b473772e","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"Token fusion: Bridging the gap between token pruning and token merging,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:5af1ea53b8af257bd3e3325a56f396908268c652000d2567d1aec3081b971f6c","observation_id":"65b736ab-bae8-4bba-9661-32e1abe1de40","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"Adaptive token sampling for efficient vision transformers,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:99bd122f0c69fc4c0b2f445b5b7a8b170af434632232abcace96437920b2435a","observation_id":"672b86ee-57a7-43ab-87a9-1bc9de887963","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"SPViT: Enabling faster vision transformers via latency-aware soft token pruning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:5901d1d047b7a6a59f0f9057926efec20649cb083e707b6571974d8601ad0f20","observation_id":"0f48319b-35d6-46ec-84a3-9c8e06749e3e","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.05832","last_updated":"2022-10-11T23:26:42Z","snapshot_observed_at":"2026-08-16T16:24:59.801396Z","submitted_at":"2022-10-11T23:26:42Z","title":"SaiT: Sparse Vision Transformers through Adaptive Token Pruning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.05832","snapshot_observed_at":"2026-07-12T09:00:09.975699Z","title":"SaiT: Sparse vision transformers through adaptive token pruning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"cited_paper":"/paper/2210.05832","citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:75c29305b69abf51b7cf824a7623f3d4459e278899467b98c35b7ae944086727","observation_id":"21b13af2-e10b-4cdf-ad19-56d1ca1398f3","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"Dynamic token pruning in plain vision transformers for semantic segmentation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:4287f1605af8ac003e74b2ad1873204e0811474114b1b19af4ad7dc505b35d4f","observation_id":"796b2266-8e47-4ed6-80cf-125d037742af","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"CF- ViT: A general coarse-to-fine method for vision transformer,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:4589a45cb63db462efd7408fd94c26d3aa9f737c772622b542134e222476e776","observation_id":"e1224a18-1d1b-4a14-96ce-8fa33d94859a","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"Multi-exit vision transformer with custom fine-tuning for fine-grained image recognition,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:1131dd5f4e4ef0a4d2b580685ecb924555832ac59e4164ffcb8a55c8d7a00a55","observation_id":"2e0a9f01-b0d2-4cf3-82a4-0af6173689bb","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"BERT loses patience: Fast and robust inference with early exit,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:85a83e4cb2268d8162c1518132da752cd721c075c439809d9274f06207bf48dd","observation_id":"f844a009-af67-41a2-9921-af4eafafcb9c","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"PCEE- BERT: Accelerating BERT inference via patient and confident early exiting,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:edee804daeee48146239bb4cbbf325d5c05e90de07b89aee8fa1aa1c5eb602e2","observation_id":"268574ef-c5f6-4a95-96d6-143f4665bad6","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"Learned thresholds token merging and pruning for vision transformers,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:8f5d19641062cb9735e17afd97a9d5be630d5fa090280cb7e4e6f7bb73302cfd","observation_id":"b3caf6cc-24a2-4b8d-9a5f-ed87ba536164","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"AdaViT: Adaptive vision transformers for efficient image recognition,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:e7239497c215182e64d0567ea7286157d406b4d72ccd44c18088ac56ba7da761","observation_id":"93b68836-f25f-41b1-8214-9851ba93b6a4","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"Slimmable neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:4cde2f9f2ea8969bd4242a842ca70c5702253d520f20fda5851546c9b63792bc","observation_id":"a508d804-cda9-44c4-9932-72b75941bb06","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"Distilling the knowledge in a neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:dec2e985c91567e76f80a2e322b3bb8852eb46175cd19ee46cc68ee038655862","observation_id":"f07b62a0-a65c-4b81-a307-ed4986dc8815","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"ImageNet: A large-scale hierarchical image database,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:e2b81c4e5422d00c4bc15b69a09754169f99cbd7ea90ac85b82a0882621d6048","observation_id":"595c8d90-fd77-41fb-b457-81428c2fecee","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","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":"2026-07-12T09:00:09.975699Z","title":"Pytorch image models,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-12T09:00:09.975699Z"},"links":{"citing_paper":"/paper/2607.02612"},"observation_digest":"sha256:4c08cdf4d4f05b6764302e161d412145c1777bd370d3efe519d160c2d004504c","observation_id":"36caf5d9-308d-4b64-a06b-c7652dacb84e","resolution":{"observed_at":"2026-07-12T09:00:09.975699Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.02612","last_updated":"2026-07-01T15:51:25Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T13:59:05.236736Z","submitted_at":"2026-07-01T15:51:25Z","title":"Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers"},"reference_resolution":{"displayed":23,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":23},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 0 inbound Pith citation observations for arXiv:2607.02612."}