{"as_of":"2026-08-22T22:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:69e5ca811064993262f6578f6850ed853573e4c4655d5647875b202230f95aa0","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":6,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":6,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+00:00","state":"measured"},{"denominator":6,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":6,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T10:55:03.151001Z","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":"2026-08-05T10:40:01.451420Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2209.13802","last_updated":"2023-07-06T10:49:33Z","snapshot_observed_at":"2026-08-19T21:06:02.997436Z","submitted_at":"2022-09-28T03:07:32Z","title":"Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.13802","snapshot_observed_at":"2026-08-12T14:22:07.440191Z","title":"Adaptive sparse vit: Towards learnable adaptive token pruning by fully exploiting self-attention","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.15446","last_updated":"2024-11-23T04:25:16Z","snapshot_observed_at":"2026-08-20T11:18:55.716736Z","submitted_at":"2024-11-23T04:25:16Z","title":"freePruner: A Training-free Approach for Large Multimodal Model Acceleration","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T14:22:07.440191Z"},"links":{"cited_paper":"/paper/2209.13802","citing_paper":"/paper/2411.15446"},"observation_digest":"sha256:7bbd4d03065e8e278f581e34cf12afbab915f2c3c1ebf2473da6ec79a40835eb","observation_id":"c4207409-16a7-4de0-a389-0ee3bb088653","resolution":{"observed_at":"2026-08-12T14:22:07.440191Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.13802","last_updated":"2023-07-06T10:49:33Z","snapshot_observed_at":"2026-08-19T21:06:02.997436Z","submitted_at":"2022-09-28T03:07:32Z","title":"Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.13802","snapshot_observed_at":"2026-08-11T22:42:33.536591Z","title":"Adap- tive Sparse ViT: Towards Learnable Adaptive Token Prun- ing by Fully Exploiting Self-Attention","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.03248","last_updated":"2025-07-29T08:19:36Z","snapshot_observed_at":"2026-08-20T16:31:45.393157Z","submitted_at":"2024-12-04T11:47:57Z","title":"AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T22:42:33.536591Z"},"links":{"cited_paper":"/paper/2209.13802","citing_paper":"/paper/2412.03248"},"observation_digest":"sha256:da57d8c2cdf9b8f8173ef00ce18b5caf50fe6ae965ae3efe2f0dd82a5a8aa18a","observation_id":"040a0f2b-e501-42b1-85f5-12aa6a7fb64c","resolution":{"observed_at":"2026-08-11T22:42:33.536591Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.13802","last_updated":"2023-07-06T10:49:33Z","snapshot_observed_at":"2026-08-19T21:06:02.997436Z","submitted_at":"2022-09-28T03:07:32Z","title":"Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.13802","snapshot_observed_at":"2026-08-16T10:55:03.151001Z","title":"Adaptive sparse vit: Towards learnable adaptive token pruning by fully exploiting self-attention","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.17040","last_updated":"2025-05-10T22:42:28Z","snapshot_observed_at":"2026-08-18T15:49:00.345741Z","submitted_at":"2025-04-23T18:38:18Z","title":"DyMU: Dynamic Merging and Virtual Unmerging for Efficient VLMs","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T10:55:03.151001Z"},"links":{"cited_paper":"/paper/2209.13802","citing_paper":"/paper/2504.17040"},"observation_digest":"sha256:ed09cb576e79469f18541c1911bb4c893493482cc65cbf87931f59e50f3fc0c7","observation_id":"aa365a45-6471-41cc-8b00-a5ed8959deea","resolution":{"observed_at":"2026-08-16T10:55:03.151001Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.13802","last_updated":"2023-07-06T10:49:33Z","snapshot_observed_at":"2026-08-19T21:06:02.997436Z","submitted_at":"2022-09-28T03:07:32Z","title":"Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.13802","snapshot_observed_at":"2026-08-07T13:54:46.053397Z","title":"Adaptive sparse vit: Towards learnable adaptive token pruning by fully exploiting self-attention.arXiv preprint arXiv:2209.13802,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.20698","last_updated":"2025-05-27T04:07:23Z","snapshot_observed_at":"2026-08-20T12:07:19.669872Z","submitted_at":"2025-05-27T04:07:23Z","title":"Sparsified State-Space Models are Efficient Highway Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:54:46.053397Z"},"links":{"cited_paper":"/paper/2209.13802","citing_paper":"/paper/2505.20698"},"observation_digest":"sha256:4bb593fd109bbe0dec025002d51815f8a80d38686fec1ccee20abea3afb9f636","observation_id":"71ce04f2-68ba-4f82-8422-ae1bb3e22d27","resolution":{"observed_at":"2026-08-07T13:54:46.053397Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.13802","last_updated":"2023-07-06T10:49:33Z","snapshot_observed_at":"2026-08-19T21:06:02.997436Z","submitted_at":"2022-09-28T03:07:32Z","title":"Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.13802","snapshot_observed_at":"2026-08-07T10:29:06.482067Z","title":"Adaptive sparse vit: Towards learnable adaptive token pruning by fully exploiting self-attention.arXiv preprint arXiv:2209.13802,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.05709","last_updated":"2025-06-06T03:18:11Z","snapshot_observed_at":"2026-08-20T16:39:23.501723Z","submitted_at":"2025-06-06T03:18:11Z","title":"Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T10:29:06.482067Z"},"links":{"cited_paper":"/paper/2209.13802","citing_paper":"/paper/2506.05709"},"observation_digest":"sha256:e4959827bd3bf985ac540885ca67dd43937b48eb85daff8422717e7c6031c93b","observation_id":"860ec1a7-aee1-403f-8680-eb4b3b6ebb18","resolution":{"observed_at":"2026-08-07T10:29:06.482067Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.13802","last_updated":"2023-07-06T10:49:33Z","snapshot_observed_at":"2026-08-19T21:06:02.997436Z","submitted_at":"2022-09-28T03:07:32Z","title":"Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention","version":2},"cited_work":{"arxiv_id":"2209.13802","doi":null,"metadata_source":"pith","pith_arxiv_id":"2209.13802","snapshot_observed_at":"2026-08-05T10:40:01.451420Z","title":"Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention","venue":"cs.CV","work_id":"5c794a0d-b6e4-4a6b-a379-fcf9d8d0f9ba","year":2022},"citing_paper":{"arxiv_id":"2509.03872","last_updated":"2025-09-04T04:18:46Z","snapshot_observed_at":"2026-08-12T19:55:04.856026Z","submitted_at":"2025-09-04T04:18:46Z","title":"Focus Through Motion: RGB-Event Collaborative Token Sparsification for Efficient Object Detection","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T10:39:58.511749Z"},"links":{"cited_paper":"/paper/2209.13802","citing_paper":"/paper/2509.03872"},"observation_digest":"sha256:0a3c1071dffa83f551ebbe5b53f6aa85c6d908acb0996cec9393d715c8ab8714","observation_id":"2cf702b0-02e6-496d-bee0-0793b13f3f0a","resolution":{"observed_at":"2026-08-05T10:40:01.454814Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2209.13802/citation-record","integrity":"/paper/2209.13802/integrity","json":"/paper/2209.13802/citation-record.json","paper":"/paper/2209.13802"},"outbound":[],"paper":{"arxiv_id":"2209.13802","last_updated":"2023-07-06T10:49:33Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-19T21:06:02.997436Z","submitted_at":"2022-09-28T03:07:32Z","title":"Adaptive Sparse ViT: Towards Learnable Adaptive Token Pruning by Fully Exploiting Self-Attention"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 6 inbound Pith citation observations for arXiv:2209.13802."}