{"as_of":"2026-08-09T18:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c88a24561fd2d4c588daeade4eb3d19027bc2b1c48fbe97467e548b99695f14a","coverage":[{"denominator":33,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":33,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T11:01:33.575599Z","state":"measured"},{"denominator":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T11:01:31.085740Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-05T11:01:33.666593Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"cited_work":{"arxiv_id":"2509.03379","doi":null,"metadata_source":"pith","pith_arxiv_id":"2509.03379","snapshot_observed_at":"2026-08-05T11:01:33.666593Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","venue":"cs.CV","work_id":"5f758bb4-fc86-45f2-ba57-7439cc128961","year":2025},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.085740Z"},"links":{"cited_paper":"/paper/2509.03379","citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:1be4ade925227db59c492c6e88db30f77ba127458ac316cf364adc5da9c45777","observation_id":"6d9aaebf-7301-48c4-a87f-e2225da21367","resolution":{"observed_at":"2026-08-05T11:01:33.766233Z","resolver_source":"local_arxiv","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2509.03379/citation-record","integrity":"/paper/2509.03379/integrity","json":"/paper/2509.03379/citation-record.json","paper":"/paper/2509.03379"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:36.057689Z","title":"Un- like convolutional networks, ViTs process all input tokens uniformly with identical computational cost, resulting in quadratic complexity relative to token count","venue":null,"work_id":"c5181313-2415-4e08-8077-cae3ab40c865","year":null},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:30.973846Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:0c8735cb415c4364005b895eab1439cde6af59eadb9d207c7f5dd352edbb043a","observation_id":"b9e16fa5-ca3f-4dee-8ec9-84d995cfa45e","resolution":{"observed_at":"2026-08-05T11:01:36.060701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"cited_work":{"arxiv_id":"2509.03379","doi":null,"metadata_source":"pith","pith_arxiv_id":"2509.03379","snapshot_observed_at":"2026-08-05T11:01:33.666593Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","venue":"cs.CV","work_id":"5f758bb4-fc86-45f2-ba57-7439cc128961","year":2025},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.085740Z"},"links":{"cited_paper":"/paper/2509.03379","citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:1be4ade925227db59c492c6e88db30f77ba127458ac316cf364adc5da9c45777","observation_id":"6d9aaebf-7301-48c4-a87f-e2225da21367","resolution":{"observed_at":"2026-08-05T11:01:33.766233Z","resolver_source":"local_arxiv","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:36.039165Z","title":"Settings We evaluate TinyDrop across ImageNet-1K [19] on state-of- the-art architectures, including Vision Transformer [1, 20], BEiTv2 [3], DeiT3 [4] and DeiT [21]","venue":null,"work_id":"20d9d630-0536-49e3-a2fa-8fa2b338f054","year":null},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.143620Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:a751baf739a39cb214b63e98aaf50146145fdaa79e2b8a6b4c405d665f75173d","observation_id":"1af56d0c-3f7b-496a-a646-62ca51886261","resolution":{"observed_at":"2026-08-05T11:01:36.042528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:36.029851Z","title":null,"venue":null,"work_id":"11a4c723-4d65-4189-a032-171ee8a8af29","year":null},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.209029Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:141277fd4cdb6982a241cf3c04b016eb98f198caa7f99f08c857f2e15c997281","observation_id":"102286c7-89bf-4103-a34c-e020550d9b92","resolution":{"observed_at":"2026-08-05T11:01:36.033169Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.992263Z","title":"Logit standardization in knowl- edge distillation,","venue":null,"work_id":"33725836-4676-4a8f-8e65-96b03c7e290b","year":2024},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.515396Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:38a6718bd3c365b8836678359f2fa8bc13475203fb5d58bea0c0ff4b5e7daf0f","observation_id":"a877ee83-1ee0-4a1b-8006-05337c51a03d","resolution":{"observed_at":"2026-08-05T11:01:35.995233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:36.020317Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":"dcf1257b-92ba-4463-be86-0b0134b5f9a3","year":2021},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.248930Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:55db36de9685c1e90f016aecc68198c022c86271b26341d478e19832aec2bc79","observation_id":"91c88293-aada-4b35-a5a6-b6a93e76bc77","resolution":{"observed_at":"2026-08-05T11:01:36.023444Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:36.011254Z","title":"Swin transformer v2: Scaling up capacity and resolution,","venue":null,"work_id":"67497f49-0009-49ff-9a5f-68f6ac626f6c","year":2022},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.300070Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:568273b39208fe0485455de2ce5c147870adabed9255b17ebf9dc61905e7b835","observation_id":"46776a12-b8d8-4447-ac68-62b8f135166a","resolution":{"observed_at":"2026-08-05T11:01:36.014400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.06366","last_updated":"2022-10-03T11:47:10Z","snapshot_observed_at":"2026-08-04T18:14:09.239336Z","submitted_at":"2022-08-12T16:48:10Z","title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.06366","snapshot_observed_at":"2026-08-05T11:01:31.392569Z","title":"Beit v2: Masked image modeling with vector-quantized visual tokenizers,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.392569Z"},"links":{"cited_paper":"/paper/2208.06366","citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:ee910886dd0ad1515bf284e981aa61e31712c60330a9e8cd66ed1068f8009163","observation_id":"3868b1ea-5102-43d9-85bd-cd722faeaf07","resolution":{"observed_at":"2026-08-05T11:01:31.392569Z","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":"2026-08-05T11:01:36.001426Z","title":"Deit iii: Revenge of the vit,","venue":null,"work_id":"851f2777-6b55-4378-b118-c15160453526","year":2022},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.457589Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:ac69388ee4256fe2933e9e0b3ab41e1c39d383422bc5115e49744f8e9c77360a","observation_id":"b41d44d7-5bea-4ff9-b90c-d68d2bc44372","resolution":{"observed_at":"2026-08-05T11:01:36.004585Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.948693Z","title":"Zero-tprune: Zero-shot token pruning through leveraging of the attention graph in pre-trained transformers,","venue":null,"work_id":"a96bff76-fbe2-4d55-87a4-f2c238b8058e","year":2024},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.909681Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:4b31aec56745cc175b5ac97251b155b3f7016af0582fc2c63a22b5615535ab5b","observation_id":"fb233c0f-b9f4-480e-9b2c-bbb14bdadcec","resolution":{"observed_at":"2026-08-05T11:01:35.951841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:36.048679Z","title":"In addition, Papr reports pri- marily on smaller/earlier backbones, with limited accounting of cost when scaling to large frozen ViTs","venue":null,"work_id":"089e1c0c-2f04-4927-bf39-73982b496d4d","year":null},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.026920Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:788583a530f77e244f058adc6fe020f73f111d29a8b94ce3c32bb0a2ab458721","observation_id":"566a19e4-20dc-4b41-97fb-af14e93d2d5b","resolution":{"observed_at":"2026-08-05T11:01:36.052089Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.983972Z","title":"Low-rank approximation for sparse attention in multi-modal llms,","venue":null,"work_id":"841d1546-5cd8-45da-be91-f7b7e5f6d48a","year":2024},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.564877Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:7a6c6345b8183794192098a2e09039a0d240dec47a814441bff59567c5c17b3b","observation_id":"d6617598-f242-4980-a27e-b43b1ebf22c7","resolution":{"observed_at":"2026-08-05T11:01:35.986744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.975153Z","title":"Token merging: Your vit but faster,","venue":null,"work_id":"00ff8f37-aed4-4d7c-9441-dfdee781d333","year":2023},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.655748Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:58918934a780ea75a178e9a21035e3f28b331c95742ae5e8410690fc6f63971f","observation_id":"380f6841-1388-431e-8ab4-b7c17fa73f8f","resolution":{"observed_at":"2026-08-05T11:01:35.978315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.966472Z","title":"Diffrate: Differentiable com- pression rate for efficient vision transformers,","venue":null,"work_id":"2c6eb5b8-a90d-419f-b46e-922778867eb7","year":2023},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.742730Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:b1580b4669ad501ae2024d98abc0e7cf7a5f882904a2c1839ea907ea3541cb8b","observation_id":"df7ecc73-c373-4042-8357-8c2d9b214390","resolution":{"observed_at":"2026-08-05T11:01:35.969428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.957876Z","title":"Adaptive token sampling for efficient vision transformers,","venue":null,"work_id":"76975640-d858-4263-ba1a-c6d223c094ec","year":2022},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.825968Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:6f18c97a654ac06cf0d156c768934e9a178115ca51b8d5840869f937c393afc9","observation_id":"d2d3f07d-2f80-4298-abfe-93375a295638","resolution":{"observed_at":"2026-08-05T11:01:35.960857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.940154Z","title":"Papr: Training-free one-step patch pruning with lightweight convnets for faster infer- ence,","venue":null,"work_id":"2b239be2-beb4-462b-9fda-58dfd6322b57","year":2024},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:31.996475Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:aef5b30391a6f4dbbe5c94596e018b4dfb95a40c23e8beae5dcafe195182342f","observation_id":"da21b2d4-1cb9-49b1-ac47-3b7f2790e26a","resolution":{"observed_at":"2026-08-05T11:01:35.943032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.931705Z","title":"Rethinking vision transformers for mobilenet size and speed,","venue":null,"work_id":"5b91153e-9130-4be7-b8de-1b069052749e","year":2023},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:32.075191Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:59ce468ededf237bc95ffcca9d159f8bb7c599c0ea9e6e147c7872674ecfa95f","observation_id":"617ee9ad-bb18-47b8-bfe2-aea864a91af7","resolution":{"observed_at":"2026-08-05T11:01:35.934553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.923179Z","title":"Efficientnetv2: Smaller models and faster training,","venue":null,"work_id":"474583fc-fac4-4675-9835-991cc213939c","year":2021},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:32.147929Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:a9d657b57db5a656f1f0300b9b2f254e1e1d1949866f92cc56ad1a1db93064ec","observation_id":"44ffc52f-0032-45c4-b303-b7ad98aa9dab","resolution":{"observed_at":"2026-08-05T11:01:35.925930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.914112Z","title":"Extracting class ac- tivation maps from non-discriminative features as well,","venue":null,"work_id":"7fd18feb-3f39-46ab-b1fb-ef53e26ed06e","year":2023},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:32.243053Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:9e7e5cca391c4d6ad2bed90a937d61ae588fc7bf21b59f1e7a05a0a53af305a4","observation_id":"841318e6-d3d0-4208-8e93-0b5594d0e958","resolution":{"observed_at":"2026-08-05T11:01:35.917417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.904226Z","title":"Tiny models are the computa- tional saver for large models,","venue":null,"work_id":"93846b4d-9653-4850-8d92-d2b9e2a5a0b1","year":2024},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:32.338528Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:2ab1d6072c2102480e5bb267a11e8874eacd0002a1f32584f8529df74e51e340","observation_id":"49ae7a41-c633-4418-b655-8482f2fc1ce1","resolution":{"observed_at":"2026-08-05T11:01:35.907939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.895002Z","title":"Grad-cam: Visual ex- planations from deep networks via gradient-based local- ization,","venue":null,"work_id":"70d40ce8-5a95-4c57-951d-ebcc6f61301c","year":2017},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:32.447054Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:fe987acd6e45ceb126f6e7f96456ea8821cfc0fe266ccca2849fdcb811fb5916","observation_id":"d1b959b9-7fe0-478a-90b4-8744ee53d73c","resolution":{"observed_at":"2026-08-05T11:01:35.898200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.886113Z","title":"The impact of posi- tional encoding on length generalization in transform- ers,","venue":null,"work_id":"696fefcc-0b01-478f-935a-598bb81b98f1","year":2023},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:32.518089Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:eb6e827794904fc78cf7ac043a892a9723cbb729e8026355b7c65ac85535447b","observation_id":"04c17078-a7b5-4cd3-8fdd-8e594c869fad","resolution":{"observed_at":"2026-08-05T11:01:35.889103Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.876604Z","title":"Rethinking and improving relative po- sition encoding for vision transformer,","venue":null,"work_id":"e4908f3b-384b-49a4-872a-f39cc4353621","year":2021},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:32.667446Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:1b3d2e56f571d7c9fe6e9157765a37532ab35ab6afa1c2c5ae63b2358bb23a1b","observation_id":"4c8ce726-cffd-4295-b1a7-f9978b422a00","resolution":{"observed_at":"2026-08-05T11:01:35.879521Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.859575Z","title":"Imagenet large scale visual recognition challenge,","venue":null,"work_id":"62157a8b-7849-40ef-9265-88af939c4c40","year":2015},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:32.678760Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:f0c97a9d9c6ac244c163c162a50b38bbf8907f803da322fbcdb532c8df62eb59","observation_id":"6c865bd4-1d6d-4c4d-9520-62ab88855168","resolution":{"observed_at":"2026-08-05T11:01:35.869930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.577874Z","title":"How to train your vit? data, augmentation, and regularization in vision trans- formers,","venue":null,"work_id":"4e583e22-2975-492a-a02f-8f2ce37b8cce","year":2022},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:32.707404Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:7d46fdcf75dd410cafb91dd5f17558e36e0767d7733c7f624bd958f125311075","observation_id":"bb7d6307-360a-4533-8b16-cf73b5510b70","resolution":{"observed_at":"2026-08-05T11:01:35.741807Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.358289Z","title":"Training data-efficient image transformers & distillation through attention,","venue":null,"work_id":"09733337-db67-435a-84e4-4c0e0e0731f8","year":2021},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:32.841269Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:2ce9ce69a0237e5faa3da83690859d8778877479f07802192e3fc64f9e35c182","observation_id":"8d4826b8-7b71-4137-a129-24e62df15e60","resolution":{"observed_at":"2026-08-05T11:01:35.465648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.173319Z","title":"Pytorch image mod- els,","venue":null,"work_id":"3da5a918-61dd-4e6d-9e3c-98e7b1dbc250","year":2019},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:32.961713Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:b514055407bfcc900d7af52a0cfb0c947cca8de0dd3ad044ba38a54ce2f97628","observation_id":"0a7e5008-635a-4cea-9e68-05717c22006c","resolution":{"observed_at":"2026-08-05T11:01:35.262118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:35.045967Z","title":"Token fusion: Bridging the gap between token pruning and token merging,","venue":null,"work_id":"b2135de3-b291-4068-b3a0-fcd6960339c6","year":2024},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:33.115986Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:d64bb36b5bfa7262c29fc95bc65c8da98e4f09e746b864212c6f834cf0bc2e68","observation_id":"a4337302-c209-4a08-93bf-743e2787269c","resolution":{"observed_at":"2026-08-05T11:01:35.090129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:34.841065Z","title":"Cf-vit: A general coarse-to- fine method for vision transformer,","venue":null,"work_id":"06a9d4cf-56cb-4fb3-a5ff-6e4056e6fa26","year":2023},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:33.232490Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:301119f5c39db1c353aaf4a4f12a4b4290db329c7736336b0c04847763c47d89","observation_id":"2ac72dac-d14d-4738-934d-4821829cb560","resolution":{"observed_at":"2026-08-05T11:01:34.948533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:34.539618Z","title":"Dynamic perceiver for efficient vi- sual recognition,","venue":null,"work_id":"0b1b2edd-581f-4fae-a285-2e8311f7cab0","year":2023},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:33.332301Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:cb15e34463ebb2dd6a5b7b75809870129807f2e86758e1f5696846244255d4fd","observation_id":"f3d046e2-95bc-4e13-8a36-571e0be04a9e","resolution":{"observed_at":"2026-08-05T11:01:34.712878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:34.344570Z","title":"Msnet: Multi-resolution synergis- tic networks for adaptive inference,","venue":null,"work_id":"06a54983-6f10-463a-8ff0-3d51018907ae","year":2009},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:33.433066Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:d49eb50cb0fe302a1114383ee37f4a3d99551ca5047248bf7602c4876e2fc719","observation_id":"5867d583-96e3-4ded-9527-a3bd6ea5f35c","resolution":{"observed_at":"2026-08-05T11:01:34.472772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:34.093468Z","title":"A panda? no, it’s a sloth: Slow- down attacks on adaptive multi-exit neural network in- ference,","venue":null,"work_id":"8c8ced67-4abb-4c7a-a41b-0137155f50c7","year":2021},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:33.520302Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:10771ee0be567cae21afe7556a8ab391a83111e9dd78e9812ebe6dd75a91e359","observation_id":"50c1da2c-0daa-4d60-9740-802093bc8cd5","resolution":{"observed_at":"2026-08-05T11:01:34.204879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T11:01:33.866527Z","title":"Not all images are worth 16x16 words: Dynamic transformers for efficient image recog- nition,","venue":null,"work_id":"06d6303c-c3a2-47e1-9bab-9a210f69666a","year":2021},"citing_paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T11:01:33.575599Z"},"links":{"citing_paper":"/paper/2509.03379"},"observation_digest":"sha256:323b72f8d56785170115062e0e77761f2421d235d2198b7165a4525a329765f4","observation_id":"a39e5890-bf4f-4608-9638-fa322f1d7246","resolution":{"observed_at":"2026-08-05T11:01:33.983266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.03379","last_updated":"2025-09-03T14:55:49Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T16:35:30.443534Z","submitted_at":"2025-09-03T14:55:49Z","title":"TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":2,"verified_exact":0,"verified_fuzzy":30},"total_outbound_references":33},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 1 inbound Pith citation observation for arXiv:2509.03379."}