{"as_of":"2026-08-21T10:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d362e01b59e1ebacf0a9bbf0b6df21086aad53a5335ab0a05f2f7e120b2d2783","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T20:44:25.481054Z","state":"measured"},{"denominator":54,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":54,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2411.09420/citation-record","integrity":"/paper/2411.09420/integrity","json":"/paper/2411.09420/citation-record.json","paper":"/paper/2411.09420"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:44:26.184689Z","title":"Uni4eye++: A general masked image modeling multi-modal pre-training framework for ophthalmic image classification and segmentation","venue":null,"work_id":"aaa18b2a-831d-4af8-86bb-3c6cdfd7bf0a","year":2024},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.270785Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:1402e1a577449dfd6a66a9577198281ac133c4f4a24942eb7c4946e799ecf301","observation_id":"983f661d-3e97-47e0-a7a3-f184317555ec","resolution":{"observed_at":"2026-08-12T20:44:26.189089Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:26.171738Z","title":"End-to- end object detection with transformers, 2020","venue":null,"work_id":"83313fc2-8c8c-4c03-8ddd-81b41a866b74","year":2020},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.275438Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:d4c3a7e85b7952f3f16f431003c3424677c2dbbbf065e46378a005d33803506c","observation_id":"abb8a084-89a2-4846-90d0-3f4338afe7e0","resolution":{"observed_at":"2026-08-12T20:44:26.176248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:26.157947Z","title":"Crossvit: Cross-attention multi-scale vision transformer for image classification","venue":null,"work_id":"dad28fcc-d27c-4a8d-9f75-3c429841631c","year":2021},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.280125Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:b6e02ad708e887694473ee0505c79fa117ff92d8008241a34d33d42a5d6945fb","observation_id":"25bb2213-6e22-44b4-ba4a-3bceb595725f","resolution":{"observed_at":"2026-08-12T20:44:26.162517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:26.145147Z","title":"Chen et al","venue":null,"work_id":"3bd3e191-118a-4731-aee5-339c99c45dee","year":2024},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.284571Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:c82b5a447cdbc1eefc9ff8fcc1b8a123b0f89b3e1d5f99febfd8f548e72f54f9","observation_id":"6916e746-f155-47a7-8159-6490da88204d","resolution":{"observed_at":"2026-08-12T20:44:26.149316Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:26.131810Z","title":"Ef- ficient decoder-free object detection with transformers, 2022","venue":null,"work_id":"fec2b036-e1d9-4816-b168-09522abdd7e2","year":2022},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.288836Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:e4c1848007cc27aa01a3629898e81d93da630c5b91a86c43478bce42fcad359f","observation_id":"7b811392-787c-4e00-99b9-6e382c5d278d","resolution":{"observed_at":"2026-08-12T20:44:26.136200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:26.119089Z","title":null,"venue":null,"work_id":"137f5432-a00e-4ed0-8a0a-7468e7b732ba","year":2019},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.293031Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:5ad4563c68c5c325dccadbf7a928f405c8d01f2a1adf9aca5bb0a08e9f1e7f1c","observation_id":"ba3d82ee-8479-4279-98bd-dfe8bfdbc474","resolution":{"observed_at":"2026-08-12T20:44:26.123192Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:26.106140Z","title":null,"venue":null,"work_id":"2e93c636-375d-4f0a-b351-2ac2cb799ae8","year":2021},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.297480Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:221fa0448cb8c450c997612d87a6ddf90657e9994c437a9095617b5fa35d7f7b","observation_id":"3bd97567-22d2-4d54-aa4a-d514b0957b74","resolution":{"observed_at":"2026-08-12T20:44:26.110677Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:26.093397Z","title":"Remote sens- ing image scene classification: Benchmark and state of the art","venue":null,"work_id":"f6283002-aea3-44ae-bf88-f1966701a4de","year":2017},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.301416Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:77c592b0f5506f407b6d5ab5f6494ee7f581e96661a3ef359234283909c967d7","observation_id":"65fd272f-6fa3-405d-8dd2-b4966e090407","resolution":{"observed_at":"2026-08-12T20:44:26.097740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:26.080475Z","title":"Dosovitskiy","venue":null,"work_id":"2fc9aeae-17a1-40b3-a038-bbc14a45e229","year":2020},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.305331Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:fb4e4f1c23356c354c11035e257ec91a2da89c9803a234c131da60e3a9174527","observation_id":"3fb802e3-6cc1-4740-bfe8-1006044c1fc3","resolution":{"observed_at":"2026-08-12T20:44:26.084412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:26.067603Z","title":"Large- scale learnable graph convolutional networks","venue":null,"work_id":"a69dd762-82f9-49dc-a61d-5df31997ad83","year":2018},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.309207Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:2814cfc971c62f252b045fb0c734a6684d93401539e3f9e53f8b38f0b1110ba9","observation_id":"284b5dbc-2b1b-49ea-9314-3cfa494d3ce7","resolution":{"observed_at":"2026-08-12T20:44:26.071912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:26.055282Z","title":null,"venue":null,"work_id":"7d6ef702-06e9-4a21-a878-6508edbbd031","year":2021},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.313045Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:4a504cc749d24ee1e988d3645277cbbecba432024be68afa1fd490f99ca58390","observation_id":"6776a8df-e616-4961-b19e-10f77f03bffd","resolution":{"observed_at":"2026-08-12T20:44:26.059363Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:26.043095Z","title":null,"venue":null,"work_id":"74fc1e69-acd8-4d07-a5d0-bac4a3171e04","year":2021},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.317054Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:bc3a7a0f71d833cd1cb2b755f7cbf8bb7df43131479edf0af2d1386a2a36ebd7","observation_id":"ae6ada0c-adf6-461c-a966-ef5838e263a9","resolution":{"observed_at":"2026-08-12T20:44:26.047195Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:26.030112Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"f13d0ec5-6fe0-43ec-ab28-157bff786a43","year":2016},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.320706Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:3874c75681673de5b81310ee69445e1185bc8706b2faf1e992c20e4bf6386add","observation_id":"bf2e751a-59f7-451a-a9a8-5e9c39d5f92d","resolution":{"observed_at":"2026-08-12T20:44:26.034409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:26.017185Z","title":"Densely connected convolutional net- works","venue":null,"work_id":"2cb29110-d284-4aa8-9a04-56c9e0affcd3","year":2017},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.324449Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:33913ded5a045fd428729dce54f7fbec687e8cf77e6b1a2a102078899925c068","observation_id":"de3d3995-f34f-4159-af34-df505622b63b","resolution":{"observed_at":"2026-08-12T20:44:26.021485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:26.004355Z","title":"Polarformer: A transformer-based method for multi-lesion segmentation in intravascular oct","venue":null,"work_id":"3a7633f1-f1c9-49cb-8dea-1b8502cf82bf","year":2024},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.328440Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:80b12a042c154a9ecece79de9a848f144e37c6f8d355b72e7bbaffc40e0927f6","observation_id":"4b3203a0-c824-4e07-942a-336727bbac09","resolution":{"observed_at":"2026-08-12T20:44:26.008530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.991629Z","title":null,"venue":null,"work_id":"ca52b931-d05f-43f5-a614-af52d42229a7","year":2016},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.332346Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:041d034b237acf20fb75f144baf4d4c3cbf59ec311992c75051bb775d9ce53fc","observation_id":"8a31a3d3-04b4-4ff3-8e82-895c03c9b8ae","resolution":{"observed_at":"2026-08-12T20:44:25.995723Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.978930Z","title":"Iandola, Song Han, Matthew W","venue":null,"work_id":"eb5cc080-6c74-4379-9308-12f57f0dab32","year":2016},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.336101Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:4d3f2b3c7f6e3f14a87e27902c25f8e3b761cc9a8b21b71574abad7398a2010d","observation_id":"7151d80a-451c-41a4-a0c4-930fdde045cd","resolution":{"observed_at":"2026-08-12T20:44:25.983058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.964832Z","title":"Nct-crc-he: Not all histopathological datasets are equally useful, 2024","venue":null,"work_id":"9701f68e-a1b9-439b-8c7c-01577c4983bf","year":2024},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.340000Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:562c952ebd051ae9edc951fc6299556eae7451e81c72b1247493b1cd33105b47","observation_id":"66bdffd6-b056-4528-a2c7-db0245ed8187","resolution":{"observed_at":"2026-08-12T20:44:25.969724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.950650Z","title":null,"venue":null,"work_id":"ef93e492-b98e-4c91-9cb1-070a91b42a8a","year":2021},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.343760Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:488abb72f7faff7fc8e158cc1b8298e95070dc7f2270aa0f50cc30fa87bf67e4","observation_id":"f1356267-e50a-4e8a-b0d2-047beafe4255","resolution":{"observed_at":"2026-08-12T20:44:25.954963Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-12T20:44:25.347574Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.347574Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:f2923e2fa44a7ae81d72d6f8e1072f759d008fdca919da750f663341436de856","observation_id":"510f645e-6a30-49f3-9b07-ffd51d03285a","resolution":{"observed_at":"2026-08-12T20:44:25.347574Z","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":"2026-08-12T20:44:25.937998Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"48a50e28-9bc9-47e3-9c5f-9380540e8eb0","year":2009},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.351908Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:9cd59cc922220547153c091cab35788200b569c092aa6bd9749fbcb4aad2c349","observation_id":"d9d309a3-2c7a-4bcd-b833-251d0c990cac","resolution":{"observed_at":"2026-08-12T20:44:25.942124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.925070Z","title":null,"venue":null,"work_id":"e289d345-84bb-44a0-b8f3-7f830d63080b","year":2017},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.355759Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:bf61f1e89a2f9ad8a93882782c8e70fece7e438a180361357c2c6828cedfe422","observation_id":"f504d416-5f01-48cd-a6ca-b5fd13eb6242","resolution":{"observed_at":"2026-08-12T20:44:25.929167Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.911939Z","title":"Lee, J.S","venue":null,"work_id":"5e45a7f7-4061-4cc4-a6af-c5a98ed68668","year":2024},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.359966Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:c5c9a810fb8eace40b4a842e7c4ebe484db1f837eb24e220bd88324ab2d71ffb","observation_id":"a7d3a0a8-581a-41b0-94f8-e27945567be5","resolution":{"observed_at":"2026-08-12T20:44:25.916234Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.898971Z","title":"Feature pyramid networks for object detection, 2016","venue":null,"work_id":"d36a8c04-3275-40ea-b977-00b54667255d","year":2016},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.363937Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:2ea88f77cdc862f0d74e109adce9019332ed79357f9b7c93fdff4964b3e4b8a8","observation_id":"4e6aefaa-f1ca-4e50-8707-c9ad6f359075","resolution":{"observed_at":"2026-08-12T20:44:25.903329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.367582Z","title":"Feature pyramid networks for object detection, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.367582Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:f9545e4b5aedca3b7d74fd566f02ebef66a71b793e92184cff83f4d21e230a0f","observation_id":"0b9140a9-f850-43e6-aaca-e46a8a30615f","resolution":{"observed_at":"2026-08-12T20:44:25.367582Z","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":"2026-08-12T20:44:25.877955Z","title":null,"venue":null,"work_id":"714420f2-2dad-498f-9c70-cbee091fec15","year":2021},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.371470Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:3b3b41843ed793194787ddb95df97e91c3216582e8127e285ea3a76a98444415","observation_id":"17dd8b49-a639-4e43-846b-6b98844b625f","resolution":{"observed_at":"2026-08-12T20:44:25.881943Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.865051Z","title":"Understanding the effective receptive field in deep convolu- tional neural networks","venue":null,"work_id":"0f3192b8-c99b-4c4f-a1bb-c7a254055dc5","year":2017},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.375294Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:2aaaba00ca8ae43c68d57b4a33ae5484e13bbf54cd71030450cbc914212dd80d","observation_id":"1ff58198-b241-459a-9ecb-2644b85ab323","resolution":{"observed_at":"2026-08-12T20:44:25.869505Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.852619Z","title":"Shufflenet v2: Practical guidelines for efficient cnn architec- ture design","venue":null,"work_id":"5af777d0-e2a7-47b0-aa61-d20eb7a3a31f","year":2018},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.379367Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:6d100ed90142cb76b4919d3b95cb40e501daa9b2fa5ab2a4ffe93a6c7a78d2bb","observation_id":"c6377d94-4a79-4413-8f8f-4f61e54d876a","resolution":{"observed_at":"2026-08-12T20:44:25.856836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.840276Z","title":"Mobilevit: Light- weight, general-purpose, and mobile-friendly vision trans- former, 2021","venue":null,"work_id":"00918300-580d-4d6d-894c-32189d2e1008","year":2021},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.383176Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:927bd8fc65691d6a325825b7a492dedba81a137ce798d5f982c6fc060b5b8287","observation_id":"eb7d2557-d003-4db1-9359-a537f8112413","resolution":{"observed_at":"2026-08-12T20:44:25.844482Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.827913Z","title":null,"venue":null,"work_id":"3b8e2c56-3837-462c-b35c-af686958f3c2","year":2018},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.386750Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:cfec3ab8a38d53aed5b9682bed999ee0eca86f71e3973a95655bd1ec44998d6b","observation_id":"2bd26d01-f3c2-4654-b909-36bb1195e151","resolution":{"observed_at":"2026-08-12T20:44:25.831864Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-17T19:17:06.411141Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-12T20:44:25.390613Z","title":"Very deep convo- lutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.390613Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:8b19a70a42462218f16b9219651b2184a172c86458c4d93680257ca6ba790d3e","observation_id":"012c5f7b-1d2a-4208-a68d-da443ccada64","resolution":{"observed_at":"2026-08-12T20:44:25.390613Z","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":"2026-08-12T20:44:25.815497Z","title":"Vidt: An efficient and effective fully transformer-based object detector, 2021","venue":null,"work_id":"bcc5ee08-87e3-4c44-b5c8-fb2981e94590","year":2021},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.394728Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:fd459030d1fc2d85fb558d46218adadc2111032e283f35560e2ae1b65b544203","observation_id":"353c0412-45c4-4210-b066-ecd068b300ba","resolution":{"observed_at":"2026-08-12T20:44:25.819670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.802953Z","title":"Srinivas","venue":null,"work_id":"b5eab210-c0c9-4e83-81bf-3ddc8cbeba11","year":2021},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.398622Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:5a8bd7332277e366c608cffe5feab92244c4a19f6aae9416f628e24049d38166","observation_id":"5cd6935a-e49e-4c54-a827-5529f6925f77","resolution":{"observed_at":"2026-08-12T20:44:25.807041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.790022Z","title":null,"venue":null,"work_id":"e2726f43-6b58-449e-94a9-0b663949ca03","year":2012},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.402455Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:f0b597eb387fb83000a786646d656d8fcae30495dae50f8c7588feba7d5a9f74","observation_id":"e7d8562b-288d-4d27-acd0-614cddcd63c6","resolution":{"observed_at":"2026-08-12T20:44:25.793896Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.777818Z","title":"Going deeper with convolutions","venue":null,"work_id":"70f4ce9e-db27-42ef-9481-a4132f94d9e4","year":2015},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.406291Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:8ebd7a62bcacaf3a6883db6f04e708203fc43d67907be674ed7ff2e0e020425f","observation_id":"ac68f6a4-c6a3-481d-9089-34c437506dbe","resolution":{"observed_at":"2026-08-12T20:44:25.781925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.764453Z","title":"Rethinking the inception archi- tecture for computer vision","venue":null,"work_id":"42401140-47b2-4232-a13c-5d05a295bd31","year":2016},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.410263Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:1ac0f978aebdc52e1215100969c5203df4e4467111473c84f7ac10ac807a3618","observation_id":"fcdfaf01-d5dc-40ec-98ca-323ccbc45e07","resolution":{"observed_at":"2026-08-12T20:44:25.768813Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.752360Z","title":null,"venue":null,"work_id":"96e5ab45-cc65-4f15-b7d7-bac4be4f942b","year":2020},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.414075Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:bc5c1ef3a0b99df5c125e52bcbc5e7466717c2c4fea1bda6aac88d2602152c94","observation_id":"191bf31a-a120-49f8-a0ab-a240e659b6ff","resolution":{"observed_at":"2026-08-12T20:44:25.756288Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.740070Z","title":null,"venue":null,"work_id":"ac8d919e-d683-4c0c-922e-ee8bf3a714f9","year":2021},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.418073Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:5576ba135aa3151107fc7ca26862c0d3a526e011141a7992b3de54c364b36509","observation_id":"bfbdc98f-6979-4036-a55b-9eedd1c99970","resolution":{"observed_at":"2026-08-12T20:44:25.744036Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.727421Z","title":"Category feature transformer for semantic segmentation, 2023","venue":null,"work_id":"297aa711-f32d-4e8c-a03f-f9f8c15f881c","year":2023},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.421910Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:17e6afe72e7c907ae1a0b3119925e8e49b4b3774039c866c68b54985056032c5","observation_id":"77cc4263-5a40-49c7-9126-c259d3769c52","resolution":{"observed_at":"2026-08-12T20:44:25.731702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.714888Z","title":null,"venue":null,"work_id":"60e182a3-3fdc-43ae-803f-f3e7a4459e88","year":2024},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.425574Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:242571964c2a404fab3d7f75261400bd4954aa563c897574d6517f08cdaad413","observation_id":"fc9eb6a1-0524-4372-a5d9-811258f72609","resolution":{"observed_at":"2026-08-12T20:44:25.718967Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.12877","last_updated":"2021-01-15T15:52:50Z","snapshot_observed_at":"2026-08-18T18:01:26.617156Z","submitted_at":"2020-12-23T18:42:10Z","title":"Training data-efficient image transformers & distillation through attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.12877","snapshot_observed_at":"2026-08-12T20:44:25.429436Z","title":"Training data-efficient image transformers & distillation through at- tention","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.429436Z"},"links":{"cited_paper":"/paper/2012.12877","citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:7ca23fdbe740273a50fdaa7f73f4f07fae9c3aba873f21413620471d7145bfff","observation_id":"ded668ac-8857-488f-8c94-104d28beef4e","resolution":{"observed_at":"2026-08-12T20:44:25.429436Z","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":"2026-08-12T20:44:25.702094Z","title":"Training data-efficient image transformers & distillation through at- tention","venue":null,"work_id":"379a3828-1f18-4810-8ad2-d870c62fdc8e","year":2020},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.433622Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:5f286ab3f2acc3ea9263d74513451eff64244729437583e4f5f1e110260b4ee3","observation_id":"e0f784c9-7cd7-45a1-b891-ccf486bd79ec","resolution":{"observed_at":"2026-08-12T20:44:25.706392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.689339Z","title":null,"venue":null,"work_id":"3fbd0eb2-b922-4256-8448-6df1d3f23c1b","year":2017},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.437409Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:d732fff077a80cb05f14f69d222ff24381cd8519ce5951756742495f0f1e0206","observation_id":"e269bf1a-accd-41c6-9707-e3547ab8bb2a","resolution":{"observed_at":"2026-08-12T20:44:25.693297Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.676896Z","title":"Graph at- tention networks","venue":null,"work_id":"78fc2359-f289-482f-82e0-51558376f6f7","year":2017},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.441672Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:dbfaa6dd738eb9865e7c85cbf26ea1cac25318294e45ec621433ea2a57a2d3d4","observation_id":"5e3bf1af-d61d-49a7-a3d0-41a61f3b4139","resolution":{"observed_at":"2026-08-12T20:44:25.680966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.662344Z","title":"Deep learning inno- vations for underwater waste detection: An in-depth analy- sis, 2024","venue":null,"work_id":"6d1c43c2-a5f3-47fc-bdfe-f4226ad0f561","year":2024},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.445470Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:03e88e55b24973a6da7fe7e51502a18cd7f2fcb26c2d858587e60e3d83c3b37d","observation_id":"f455ac74-9552-4c81-8c8e-b0509a7abb85","resolution":{"observed_at":"2026-08-12T20:44:25.667387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.648785Z","title":"Optimized custom dataset for efficient detection of underwater trash","venue":null,"work_id":"8d3f97e6-ef10-4475-a5a3-e12a75ce911a","year":2023},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.449323Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:cd4a582c830e4a2596e425d54d9c75cc7d3a3c3ff3e9d754afe27417beff0940","observation_id":"40a6bbc7-eca8-4b39-ade2-c3d103d50d3e","resolution":{"observed_at":"2026-08-12T20:44:25.653065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.636022Z","title":"Non-local neural networks","venue":null,"work_id":"87e1ce37-c5f3-4e7d-836a-e8511e984694","year":2018},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.453221Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:10372bff9e464c5e1d73362843c29d011a8ab9d963d731d35eae1f1c4317f485","observation_id":"a3fc2678-ce7e-480e-ba2d-bbb280fb8653","resolution":{"observed_at":"2026-08-12T20:44:25.640056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.622045Z","title":null,"venue":null,"work_id":"c179221a-33f4-4664-a059-83e3ecf64943","year":2021},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.457085Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:c08ea23c1f8c6c65201e0ce64a43db178f57b0a43a1c6ea7eb0dd30d272bbe01","observation_id":"c2f10580-6b6b-4c86-8e8a-fc19a43ecc41","resolution":{"observed_at":"2026-08-12T20:44:25.627049Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.609193Z","title":null,"venue":null,"work_id":"7256caa5-b529-442d-a92a-b711cdf2f3c1","year":2019},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.461166Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:d32d725729c06162e33c261f05ac54543f0b2b42a4041dfe841a73e14bd27e0d","observation_id":"2d9f27ba-9c6e-45db-93f7-89d2b453595b","resolution":{"observed_at":"2026-08-12T20:44:25.613319Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.595241Z","title":"Multi-label chest x-ray image classification with single positive labels","venue":null,"work_id":"e4667160-c0b3-4f9c-9008-e3b9457231ac","year":2024},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.465026Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:3da5cef8c6ac583e501f020f3e67a3f16aae7a33fe21328e5a49df6f14857de1","observation_id":"85f723d8-0bbe-450a-b710-318ecef25471","resolution":{"observed_at":"2026-08-12T20:44:25.600506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.468727Z","title":"Alvarez, and Ping Luo","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.468727Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:21a4f8c632196da5d6dfabf5f69d5a2da5fd4c8414e640fd141d98e2cb39a339","observation_id":"bf1b2f89-7be9-4c78-935d-5bc9aa34d2a6","resolution":{"observed_at":"2026-08-12T20:44:25.468727Z","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":"2026-08-12T20:44:25.574414Z","title":null,"venue":null,"work_id":"07e06589-4c7a-41f6-9fa9-f62bcd34f4ca","year":2021},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.472970Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:53fc9a7881c355b5a22d7280fbb9fed6bdaad32385283cc8f02a389ff0e90c58","observation_id":"9a9c5e20-e47a-4bdb-8ce5-e7a878ef949a","resolution":{"observed_at":"2026-08-12T20:44:25.578708Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.561445Z","title":null,"venue":null,"work_id":"28bd28e0-bade-4ba2-816c-8a6d9c6e8899","year":2024},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.477122Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:e34d1ecff5e32501f5d621ad58c8f17876c460ba0343b7853171c77857fdd84a","observation_id":"c787f9c4-9aff-434a-9eb9-4fbd542d710a","resolution":{"observed_at":"2026-08-12T20:44:25.565578Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-12T20:44:25.547515Z","title":null,"venue":null,"work_id":"067fc59b-b783-49a2-9724-2aad78f155c7","year":2021},"citing_paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T20:44:25.481054Z"},"links":{"citing_paper":"/paper/2411.09420"},"observation_digest":"sha256:04f10f7984c5ae4e58259964abc74f4c4d4433fc10cdbe7f33ef5f70b81722f0","observation_id":"23a0b415-a994-4b99-8482-ccfe209a0a08","resolution":{"observed_at":"2026-08-12T20:44:25.552606Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.09420","last_updated":"2025-01-08T04:31:16Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-20T23:10:30.161309Z","submitted_at":"2024-11-14T13:15:27Z","title":"SAG-ViT: A Scale-Aware, High-Fidelity Patching Approach with Graph Attention for Vision Transformers"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":0,"verified_fuzzy":30},"total_outbound_references":54},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 0 inbound Pith citation observations for arXiv:2411.09420."}