{"as_of":"2026-08-19T19:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:935736501dbfa860ae749e25d2cdb667be62c26c17d316e07de876d2c76e45eb","coverage":[{"denominator":66,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":66,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T05:28:26.293648Z","state":"measured"},{"denominator":66,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":66,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2504.20602/citation-record","integrity":"/paper/2504.20602/integrity","json":"/paper/2504.20602/citation-record.json","paper":"/paper/2504.20602"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:24.788085Z","title":"Small- object detection in remote sensing images with end-to-end edge- enhanced gan and object detector network,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:24.788085Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:7333c23aebc8a9ae0981a995575c5afa7c6d4eab8038c7c45fcdc6711127d659","observation_id":"7d860b1d-a7d8-4fc1-b96b-5060628854db","resolution":{"observed_at":"2026-08-16T05:28:24.788085Z","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":"2026-08-16T05:28:28.391511Z","title":"Cross-layer attention network for small object detection in remote sensing imagery,","venue":null,"work_id":"128a3572-8ea3-4562-9e92-c87e6781b6e3","year":2020},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:24.854481Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:08d0b0c8ab72027ceee23ce513132d6635f4df22133d97bfaa1b5b481ce888de","observation_id":"df8a8235-0f31-4512-9dcf-d90bda3486fe","resolution":{"observed_at":"2026-08-16T05:28:28.420282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:24.859797Z","title":"Small object detection in remote sensing images with residual feature aggregation-based super-resolution and object detector network,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:24.859797Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:cf77fb439d91ab506a53c22ca2cd9f805bb375c466b55ece1d76b204a9f76cf5","observation_id":"e356b4d1-a79d-408b-ad9e-bace7517493e","resolution":{"observed_at":"2026-08-16T05:28:24.859797Z","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":"2026-08-16T05:28:28.358613Z","title":"Exploring feature compensation and cross-level correlation for infrared small target de- tection,","venue":null,"work_id":"8f1e2b7e-e44a-4553-97b5-cd345ead8e92","year":2022},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:24.864214Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:47b7272d79d3c67ed22651f8cbb33cdab4862adcc8a6a00673ba7d174f809c01","observation_id":"1e26ec11-e70a-4eb7-94f1-cafe9fbfff85","resolution":{"observed_at":"2026-08-16T05:28:28.365048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:28.343331Z","title":"Convolutional neural networks for object detection in aerial imagery for disaster response and recovery,","venue":null,"work_id":"fb259abd-1602-48d0-8d1d-c5051199f1bf","year":2020},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:24.868242Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:108744a9f291a1da3da05a4c9df496c336453f7783cc4db499bbe2159c8e9bc3","observation_id":"c5cd58d2-4951-4396-bd04-e13e7540f73e","resolution":{"observed_at":"2026-08-16T05:28:28.348367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:28.313940Z","title":"Self-mimic learning for small-scale pedestrian detection,","venue":null,"work_id":"7eb5bd92-a3e6-462f-b780-3af9915e393b","year":2020},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:24.872387Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:14c91c7c316c7e3dd23456b1d2a53c77cebdb7aa1fec9d2fe77d0ae959d8a020","observation_id":"1eabfd35-2691-4e93-99aa-fb69455591b1","resolution":{"observed_at":"2026-08-16T05:28:28.331552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:24.878277Z","title":"A survey and performance evaluation of deep learning methods for small object detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:24.878277Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:68cd556f2ec2f7d6ee641a856e438ec2b4848b5eea460998df422ac33292e0f3","observation_id":"701df162-2817-418c-8fa7-38e65a1f3378","resolution":{"observed_at":"2026-08-16T05:28:24.878277Z","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":"2026-08-16T05:28:28.225957Z","title":"A survey of the four pillars for small object detection: Multiscale representation, contextual information, super-resolution, and region proposal,","venue":null,"work_id":"3d9f1ab7-4cb6-4e93-b717-f297ae0937bc","year":2020},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:24.883410Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:62632800445583c78a6d40ab8be41830483409a4ded718c00ede8f664695bce2","observation_id":"6c99f851-8298-4c54-a1cc-24912d19e878","resolution":{"observed_at":"2026-08-16T05:28:28.249502Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:28.204853Z","title":"Small object detection via pixel level balancing with applications to blood cell detection,","venue":null,"work_id":"bd2b8967-6099-4349-b7b5-77ffdc3aa8ce","year":2022},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:24.963881Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:e578567070cd155b1fedc656343b965d39e7abfb3be3bd5d19067ada499c39e4","observation_id":"46b1a430-40bc-48bf-91a4-b83c50888b6d","resolution":{"observed_at":"2026-08-16T05:28:28.209469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:28.190595Z","title":"Imaging based cervical cancer diagnostics using small object detection-generative adversarial networks,","venue":null,"work_id":"1245f5bb-332b-4439-8156-6088100c3c93","year":2022},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:24.985181Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:6e620fa3d6e9124a038f56ebaed72f672b67b826a8332e47d418e5dd941ccef0","observation_id":"d149009d-8ce9-4512-bcec-b61622ecbae2","resolution":{"observed_at":"2026-08-16T05:28:28.195155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:24.989424Z","title":null,"venue":null,"work_id":null,"year":1982},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:24.989424Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:c0e78e300ddc24b112f9af33894b6e7c77f875750c6a948678056e9fefea6339","observation_id":"242a0ece-6b38-46cd-b7c6-b5244e80fdb9","resolution":{"observed_at":"2026-08-16T05:28:24.989424Z","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":"2026-08-16T05:28:28.167761Z","title":"Feature pyramid networks for object detection,","venue":null,"work_id":"16435caa-b085-4998-b54b-7a9250b2a788","year":2017},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.003234Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:af9748c4eddbe2e4e13e3b729737d56180fb9a47721ce8beaae7aed0f0322f1f","observation_id":"d0569d55-1387-41a9-9321-f30900cb8ed1","resolution":{"observed_at":"2026-08-16T05:28:28.172275Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:25.007362Z","title":"Faster r-cnn: Towards real-time object detection with region proposal networks,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.007362Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:e83783436f05f70beacc9d5580f32f77b6a8c49861980eea742ff5a1da64f11f","observation_id":"b33ea280-969a-4045-ab65-09d08947aca4","resolution":{"observed_at":"2026-08-16T05:28:25.007362Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:25.014651Z","title":"Focal loss for dense object detection,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.014651Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:2ea4d12718311ca4f0e12c3727f3436240540ee7958999175f7a7da88299c2df","observation_id":"5dbb83cb-6ba2-45db-891c-835fb0f16bde","resolution":{"observed_at":"2026-08-16T05:28:25.014651Z","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":"2026-08-16T05:28:28.078049Z","title":"Fcos: Fully convolutional one- stage object detection,","venue":null,"work_id":"ac577849-9967-4d95-b78a-d236768c4969","year":2019},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.019468Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:780251aadc152b7dfc94377975c5e5295b6245af2855b5d0783fb03990130ce7","observation_id":"d50fa3c1-d2c9-48e5-90a6-c952e0331868","resolution":{"observed_at":"2026-08-16T05:28:28.111828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:25.064331Z","title":"End-to-end object detection with transformers,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.064331Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:4653e2fcbd84c3e8097130094578adf751157ff32f5fed048b552f9173f9231d","observation_id":"405ec0a6-acc4-4531-8aa3-67751aa09162","resolution":{"observed_at":"2026-08-16T05:28:25.064331Z","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":"2026-08-16T05:28:28.001505Z","title":"Iou loss for 2d/3d object detection,","venue":null,"work_id":"1f45870a-9195-46b5-bd15-c81379637243","year":2019},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.171795Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:7eb50d7b263819db1e77f74add06f0efd60ee813f5b6838e8761b457b00c8557","observation_id":"8662d341-8444-4aca-9746-b3000d0ee1f3","resolution":{"observed_at":"2026-08-16T05:28:28.031563Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:27.987535Z","title":"A jaccard base similarity measure to improve performance of cf based recom- mender systems,","venue":null,"work_id":"eca97804-3060-4ccb-a1b2-5271bcda1f0d","year":2018},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.177418Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:d350121878b2b1397ea0c226e3922235da6df6018581b1b7c700bdd13f432a16","observation_id":"c7a4d824-3c2d-42f6-a949-54aba3ba9700","resolution":{"observed_at":"2026-08-16T05:28:27.992266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:27.971903Z","title":"Rethinking classification and localization for object detection,","venue":null,"work_id":"825b6a0a-66e7-46b7-94d0-30d25e74140f","year":2020},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.181546Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:784555b64fadfe140253a4e5202007821aad7cb4705d3a2e40d5441086b60ad5","observation_id":"e927a0ac-188e-4a02-82df-404e2da55b4a","resolution":{"observed_at":"2026-08-16T05:28:27.977719Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:25.186357Z","title":"Towards large-scale small object detection: Survey and benchmarks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.186357Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:91894a6db5a421bed30421a2ffc024e50fec2f19e8d000a443aeafc17fedc857","observation_id":"efbe7175-a6f4-40c4-b1ff-089c0224e2e4","resolution":{"observed_at":"2026-08-16T05:28:25.186357Z","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":"2026-08-16T05:28:27.904276Z","title":"Tiny object detection in aerial images,","venue":null,"work_id":"90f754a7-c9cc-4eef-ac7e-6c8e86920abc","year":2020},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.191257Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:6caa484d89d943def5dfe535a5f986340ed3789573d4d9ce2179ac5976d4c987","observation_id":"c0a8925a-5698-4b7b-b2a0-ecbdb3f0cba2","resolution":{"observed_at":"2026-08-16T05:28:27.925456Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:25.195004Z","title":"Microsoft coco: Common objects in context,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.195004Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:bbab427b1a1d4f9129b71138a29c66c21d27898d68f69fbe76e0a9116a77dcca","observation_id":"1ebe02d1-c593-40a6-86db-1bd88a637acc","resolution":{"observed_at":"2026-08-16T05:28:25.195004Z","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":"2026-08-16T05:28:27.827649Z","title":"Dynamic head: Unifying object detection heads with attentions,","venue":null,"work_id":"9a658d79-ef92-4ef5-89ff-2ccb7c9f02f8","year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.261034Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:5c00fceb7a718671eaf7565d4762675d6df1fa9d6a22d4d5d90853f4eb054c43","observation_id":"70cb5e29-d10d-4b69-a232-5afcb5d90c88","resolution":{"observed_at":"2026-08-16T05:28:27.849350Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:27.813204Z","title":"Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection,","venue":null,"work_id":"6a7c0e21-3a8b-41ad-9a1c-7adae96b91e6","year":2020},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.383848Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:a167cb619de9b4c8b25902d4f05332b9fc89329e4bae64a4d6cdadfc3540ee4a","observation_id":"e2ef3d4f-c343-4f66-ada7-6fff2a8cc80a","resolution":{"observed_at":"2026-08-16T05:28:27.818252Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:25.389002Z","title":"Cornernet: Detecting objects as paired keypoints,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.389002Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:1774ed0e152510fb89a7cb86ea9fa1bc20812918fe01e49f8d60b05f87d1ee63","observation_id":"8939e27e-db4c-4295-8dae-d2260c75b683","resolution":{"observed_at":"2026-08-16T05:28:25.389002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.07850","last_updated":"2019-04-25T16:20:02Z","snapshot_observed_at":"2026-08-14T16:45:31.678245Z","submitted_at":"2019-04-16T17:54:26Z","title":"Objects as Points","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.07850","snapshot_observed_at":"2026-08-16T05:28:25.393427Z","title":"Objects as points,","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.393427Z"},"links":{"cited_paper":"/paper/1904.07850","citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:fc0f7dfcb1640da7a05c7740977106aaf23ade26d68fc9860c0acb789f1200df","observation_id":"4fc2b7b4-88f0-4b64-91ac-12859883d833","resolution":{"observed_at":"2026-08-16T05:28:25.393427Z","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":"2026-08-16T05:28:27.787522Z","title":"Reppoints: Point set representation for object detection,","venue":null,"work_id":"54a46c0d-975e-4129-838d-65a0986de225","year":2019},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.398419Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:c769673520d7cb9d8beada25ad13c0e99dcdec739aca0655f45e0c91574709ce","observation_id":"92c7784f-ea85-443a-b424-69effe4dd774","resolution":{"observed_at":"2026-08-16T05:28:27.792376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.04159","last_updated":"2021-03-18T03:14:26Z","snapshot_observed_at":"2026-08-13T17:54:01.724774Z","submitted_at":"2020-10-08T17:59:21Z","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.04159","snapshot_observed_at":"2026-08-16T05:28:25.402917Z","title":"Deformable detr: Deformable transformers for end-to-end object detection,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.402917Z"},"links":{"cited_paper":"/paper/2010.04159","citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:b82464ffbc68c43df2623e7d0132e48f3f4fdca837d2eb0819c1439bd140d062","observation_id":"97276a2f-e7bc-47ec-acd1-ae8fd98482ce","resolution":{"observed_at":"2026-08-16T05:28:25.402917Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.07296","last_updated":"2019-02-19T21:47:31Z","snapshot_observed_at":"2026-08-14T17:14:08.755202Z","submitted_at":"2019-02-19T21:47:31Z","title":"Augmentation for small object detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.07296","snapshot_observed_at":"2026-08-16T05:28:25.408555Z","title":"Aug- mentation for small object detection,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.408555Z"},"links":{"cited_paper":"/paper/1902.07296","citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:33ca91085280e6d8aba4d5c67152fe41baaa7a8399f4509b416e270e7c4acc27","observation_id":"286a8507-0228-414b-9fe4-40b023e1faa5","resolution":{"observed_at":"2026-08-16T05:28:25.408555Z","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":"2026-08-16T05:28:27.772349Z","title":"Learning data augmentation strategies for object detection,","venue":null,"work_id":"612e732a-bb23-4d1f-b3d1-839b8132e489","year":2020},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.413471Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:6095400302f93559f4cd95275246d9a4739419da9e2605bb3840b846c1956f81","observation_id":"cffe7205-0927-4fa0-8671-630d4a1e4f63","resolution":{"observed_at":"2026-08-16T05:28:27.776561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:27.713938Z","title":"Scale match for tiny person detection,","venue":null,"work_id":"d51e75d5-6bee-4270-a379-e0ae1260ab7b","year":2020},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.422990Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:b81e572e4dfa5b9daebdaea6e8ffcadcb37b515871663331785c0d5ab8f795fb","observation_id":"37dfc9b7-e636-487e-945c-3eb9fcddad92","resolution":{"observed_at":"2026-08-16T05:28:27.761732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:27.629076Z","title":"Sod-mtgan: Small object detection via multi-task generative adversarial network,","venue":null,"work_id":"682c07a3-d871-4fe4-a1e5-69f5dd86d561","year":2018},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.557887Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:af1d5d2c8ad908846e24cdd090ff6b25fa3494762668374fd0cfefeb58778406","observation_id":"4a3ebeef-5c38-4db1-8912-b4ee5670d644","resolution":{"observed_at":"2026-08-16T05:28:27.633702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:27.614009Z","title":"Better to follow, follow to be better: Towards precise supervision of feature super-resolution for small object detection,","venue":null,"work_id":"22fd81fc-6aac-4546-aba2-67a8383e6c4a","year":2019},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.597462Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:b761e6ea9530546eadb8f23ba914664b92e2ae6564f8477ee2080f3e30cc2cb1","observation_id":"fd4b354b-0a61-4d0c-b2fb-437725b0fa67","resolution":{"observed_at":"2026-08-16T05:28:27.619675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:25.602123Z","title":"Effective fusion factor in fpn for tiny object detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.602123Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:bdcfbce6ea258b8744b2f58423d8d7f1bddd45a1c89eb7303d6aa514d31819a3","observation_id":"cf4b5168-cfeb-4065-a8d0-762e6899d3be","resolution":{"observed_at":"2026-08-16T05:28:25.602123Z","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":"2026-08-16T05:28:27.468846Z","title":"Sspnet: Scale selection pyramid network for tiny person detection from uav images,","venue":null,"work_id":"b63a714f-021b-4c53-9ebd-0fecae5a49ff","year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.607534Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:517fec41b1426ec1014d3a4567a078602b0841bd5dd18dec5800b91d75ffc6f0","observation_id":"039bdd82-3256-4895-9fda-ce8e6fb0fbcb","resolution":{"observed_at":"2026-08-16T05:28:27.595490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:27.395542Z","title":"Rethinking rotated object detection with gaussian wasserstein distance loss,","venue":null,"work_id":"af274417-4f40-4e5d-8d06-c0642ed1bd51","year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.614418Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:a12316954b6d5d9b5e246f228f0bdb91d99cb48d1e3ff80609fc1268494879e2","observation_id":"843077a8-ca22-494a-b1c0-dafebc8341db","resolution":{"observed_at":"2026-08-16T05:28:27.400298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.13389","last_updated":"2022-06-14T12:58:44Z","snapshot_observed_at":"2026-08-16T17:46:35.539315Z","submitted_at":"2021-10-26T03:43:17Z","title":"A Normalized Gaussian Wasserstein Distance for Tiny Object Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.13389","snapshot_observed_at":"2026-08-16T05:28:25.618716Z","title":"A normalized gaussian wasserstein distance for tiny object detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.618716Z"},"links":{"cited_paper":"/paper/2110.13389","citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:61a75e96d00fc2ac12def1d99265a319288d4ad6b77552c8f470699771bee146","observation_id":"52e5065f-f861-4cb0-8188-5dd7be75f9c5","resolution":{"observed_at":"2026-08-16T05:28:25.618716Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:25.622777Z","title":"Rfla: Gaussian receptive field based label assignment for tiny object detection,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.622777Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:42331a701112be967a37fa001c00a5b7ebde1deffabaee55aec02d2206370b4a","observation_id":"24a1336a-d0a6-47e4-8dc4-a90a91a25bc2","resolution":{"observed_at":"2026-08-16T05:28:25.622777Z","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":"2026-08-16T05:28:27.368164Z","title":"Dynamic coarse-to-fine learning for oriented tiny object detection,","venue":null,"work_id":"2becad06-b533-4b10-8385-b4bd3b8644f1","year":2023},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.626951Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:4e54f29d9d293d12e35e2903be9c78bc947e84073938aefbc15c253da863564d","observation_id":"5a09765a-b72b-4d8f-b00f-2fc1b978425f","resolution":{"observed_at":"2026-08-16T05:28:27.373749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:27.353627Z","title":"Small object detection via coarse-to-fine proposal generation and imitation learning,","venue":null,"work_id":"a079845c-c1b5-4bfe-8e07-2ff31b15a487","year":2023},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.631196Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:a063ca207fb1801aaa5a9b0f470bede64a551ea1b6ef2e351c39421837684796","observation_id":"1c0e60cb-62c0-4e43-b569-0d70fa02d5a9","resolution":{"observed_at":"2026-08-16T05:28:27.358635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:27.214993Z","title":"Feature selective anchor-free module for single-shot object detection,","venue":null,"work_id":"f57b24a6-7130-423b-bdae-c032a26cf608","year":2019},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.634988Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:95cb8fe3f5fe346c3ba420da2a6879e2659a7fb7a327920e22ac36c5bfa6881a","observation_id":"5d908967-dfab-4bc4-b84a-4af5e0e109f0","resolution":{"observed_at":"2026-08-16T05:28:27.276738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:27.186491Z","title":"Ota: Optimal transport assignment for object detection,","venue":null,"work_id":"b89fe67b-19e4-49d0-9cc5-cbc132ccf924","year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.657003Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:318c57a54afbfbeba89c14b58c38a5cac330823bbd8e38ab45df7e7f0e8141ec","observation_id":"c3319451-15c6-4936-a49a-8e9251c2fca7","resolution":{"observed_at":"2026-08-16T05:28:27.191385Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:27.172969Z","title":"Freeanchor: Learning to match anchors for visual object detection,","venue":null,"work_id":"7297b40c-373c-4806-9603-959d308e6d95","year":2019},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.758863Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:cc122adafd651cb476fb7ce38073cffcfd08beb80452ca851a601f4ac6b5c69d","observation_id":"50e53125-4176-45c7-83a7-8b5bde010773","resolution":{"observed_at":"2026-08-16T05:28:27.177260Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:25.804886Z","title":"High-frequency component helps explain the generalization of convolutional neural networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.804886Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:3e021e15463c18063d222bb7d6a92fca42bf5ebcbe541467c79cf2b0ebd068b0","observation_id":"00776557-94a0-408a-b29e-be7cf1a97d5d","resolution":{"observed_at":"2026-08-16T05:28:25.804886Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:25.842539Z","title":"Learning in the frequency domain,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.842539Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:44f2bdbbc4106309a2eaf5bb514c8e1d3ae936c18ab92bf54ce499c0aa31b56a","observation_id":"343dcf9e-5f8a-48b2-a164-2893a2ee5f02","resolution":{"observed_at":"2026-08-16T05:28:25.842539Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:25.880383Z","title":"Invertible image rescaling,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.880383Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:e175f8a7495cc105f3f1f3013266d87b34246fa6b45d806c981a342f021cfcbf","observation_id":"e2981989-62d2-4c1e-9099-8b001595bc2f","resolution":{"observed_at":"2026-08-16T05:28:25.880383Z","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":"2026-08-16T05:28:27.028688Z","title":"Detect- ing camouflaged object in frequency domain,","venue":null,"work_id":"19183ae5-107c-4f3c-80a3-13098b9f2368","year":2022},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.884504Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:8e68cbe98cf7c8a9cf7c80dee6791bd544a756d9cdcd85a16c22181bc49e6a6c","observation_id":"f19b0ba4-695e-4b4c-b1c0-4cc36a3adbcc","resolution":{"observed_at":"2026-08-16T05:28:27.056808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:25.889016Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.889016Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:09cb579cce5637a4bc211fd3f53d3edb236230d187cef206315bd824f5120b80","observation_id":"2a3a8a74-a264-46b6-9d7b-594c7ea47554","resolution":{"observed_at":"2026-08-16T05:28:25.889016Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:25.893468Z","title":"Aggregated residual transformations for deep neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.893468Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:9a6536f64868a2784277412fd46e5d8ea39bd0767bcd9d204eebfcb0763517e3","observation_id":"f1796168-8e80-46cb-9b2b-af5f5ade06c2","resolution":{"observed_at":"2026-08-16T05:28:25.893468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:25.897795Z","title":"Sparse r-cnn: End-to-end object detection with learnable proposals,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.897795Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:0d8900561883ca9fb71251bfd47f180782f4beab3159206a5c68485e19bf8edb","observation_id":"b68453e8-910e-4bfa-94a2-1eacc068427a","resolution":{"observed_at":"2026-08-16T05:28:25.897795Z","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":"2026-08-16T05:28:26.988290Z","title":"Cascade rpn: Delving into high-quality region proposal network with adaptive convolution,","venue":null,"work_id":"21ec105f-6bc0-450c-add0-07fae925dd00","year":2019},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.902215Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:14914f3734bd947638c2bce4628902c655b0e33abe51da30e8c0c8dd25802e26","observation_id":"8d45fd15-da5f-4b52-8181-906fc04ae0e4","resolution":{"observed_at":"2026-08-16T05:28:26.993222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.08430","last_updated":"2021-08-06T03:22:14Z","snapshot_observed_at":"2026-08-19T15:19:25.831687Z","submitted_at":"2021-07-18T12:55:11Z","title":"YOLOX: Exceeding YOLO Series in 2021","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.08430","snapshot_observed_at":"2026-08-16T05:28:25.909368Z","title":"Yolox: Exceeding yolo series in 2021,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.909368Z"},"links":{"cited_paper":"/paper/2107.08430","citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:cb091d3cb97cfddf7a41a1ce89b4523cf4516becbff874663aeaa4f8528db0e5","observation_id":"0365f0e8-099f-43e5-893c-e446bdac6386","resolution":{"observed_at":"2026-08-16T05:28:25.909368Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.03496","last_updated":"2020-11-25T15:57:47Z","snapshot_observed_at":"2026-08-18T00:55:11.296757Z","submitted_at":"2020-07-07T14:32:21Z","title":"AutoAssign: Differentiable Label Assignment for Dense Object Detection","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.03496","snapshot_observed_at":"2026-08-16T05:28:25.913690Z","title":"Autoassign: Differentiable label assignment for dense object detection,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.913690Z"},"links":{"cited_paper":"/paper/2007.03496","citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:54fe9b5b09bca7024a6a91e69c4f66063c07c264ba417f6320d8ffeb134e907e","observation_id":"af838b3f-614e-471f-b4f7-63508b0305f1","resolution":{"observed_at":"2026-08-16T05:28:25.913690Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:25.918265Z","title":"Cascade r-cnn: Delving into high quality object detection,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:25.918265Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:c209173b33593de11e11cd94fdb92d7476c37bdca4fdfc28dc2a2af50678ef95","observation_id":"53c7fcac-cce2-456d-b441-79dcc5ca890a","resolution":{"observed_at":"2026-08-16T05:28:25.918265Z","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":"2026-08-16T05:28:26.847935Z","title":"Dot distance for tiny object detection in aerial images,","venue":null,"work_id":"7be1837a-0aab-48c1-aae4-2a0521ca9284","year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:26.007183Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:bbf7bcf2908955f1156579a9f5d0aae4b7d71e54e601ddba936873508ba6ee3a","observation_id":"cb7a9d38-7af7-48b4-a8f0-d88a240f534c","resolution":{"observed_at":"2026-08-16T05:28:26.969385Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12329","last_updated":"2022-03-30T16:04:38Z","snapshot_observed_at":"2026-08-16T17:25:09.013446Z","submitted_at":"2022-01-28T18:51:09Z","title":"DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.12329","snapshot_observed_at":"2026-08-16T05:28:26.045486Z","title":"Dab-detr: Dynamic anchor boxes are better queries for detr,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:26.045486Z"},"links":{"cited_paper":"/paper/2201.12329","citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:8320b7c69fb1a5f35eee44a39ade5b9ac72fd6676274a7005fb127d4a941ba58","observation_id":"f0ef8d29-5e29-41f3-a132-8d39b9c2cd2a","resolution":{"observed_at":"2026-08-16T05:28:26.045486Z","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":"2026-08-16T05:28:26.710114Z","title":"Detectors: Detecting objects with recursive feature pyramid and switchable atrous convolution,","venue":null,"work_id":"e5cc9d15-9153-42db-9228-97d0efabc00a","year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:26.050674Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:fdde6328a4a917fcb4ffb12911e0e9c590aea17082c26a61239e384e26472ddf","observation_id":"c5e86919-0b58-412e-bf4c-588da56ef7e1","resolution":{"observed_at":"2026-08-16T05:28:26.763290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.07155","last_updated":"2019-06-17T17:58:12Z","snapshot_observed_at":"2026-08-16T03:32:25.570081Z","submitted_at":"2019-06-17T17:58:12Z","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.07155","snapshot_observed_at":"2026-08-16T05:28:26.054533Z","title":"MMDetection: Open mmlab detection toolbox and benchmark,","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:26.054533Z"},"links":{"cited_paper":"/paper/1906.07155","citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:5ab22050f120a06b934fcb076ef4991dd03af4fb139d2b4ddf60468efe5ccd29","observation_id":"ca649474-22bc-4ecc-b0c3-1f0741e04ace","resolution":{"observed_at":"2026-08-16T05:28:26.054533Z","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":"2026-08-16T05:28:26.697226Z","title":"Mask r-cnn,","venue":null,"work_id":"696f622e-0ee8-428c-9978-189e104c09ca","year":2017},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:26.059420Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:f67c0d21c4c497d9a0e230d7aecdc23206cdbac977507dd4c87c57ec963e042c","observation_id":"04d5f51f-4270-4ba1-a8ad-f0a93874a142","resolution":{"observed_at":"2026-08-16T05:28:26.701403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:26.675698Z","title":"Libra r-cnn: Towards balanced learning for object detection,","venue":null,"work_id":"a174e1fa-d9eb-48b0-9b39-9a3200d0d889","year":2019},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:26.064061Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:79dc21fa41da0bf855f79724fbd13ba7d6872151023f137966cf4a1e7fe6a31d","observation_id":"b11065c4-01ef-4c5d-a1b9-705d5b3ee4a7","resolution":{"observed_at":"2026-08-16T05:28:26.680336Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:26.661300Z","title":"Region proposal by guided anchoring,","venue":null,"work_id":"9e3a4c10-fd5b-4019-980e-f8ed34b2a249","year":2019},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:26.068690Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:70386ac4b683ae4ef021217610bcf6a7bbc770a5bf51ed0dc01f614fe8f39763","observation_id":"19e3359c-6fb8-43dc-a48b-21a003118cc3","resolution":{"observed_at":"2026-08-16T05:28:26.666289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:26.520542Z","title":"R3det: Refined single-stage detector with feature refinement for rotating object,","venue":null,"work_id":"d7e4f3be-7a32-4baa-83a4-bd10c37c89be","year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:26.073473Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:2e067125789075547aa5db4b947f82f0bd0e6a6d40832588cbd224ce3ec8c204","observation_id":"29bb62a1-fc44-426b-b9e7-cd0ccbb49c47","resolution":{"observed_at":"2026-08-16T05:28:26.612516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:26.157806Z","title":"Align deep features for oriented object detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:26.157806Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:27e9f4f44408c6af0c81caab2aa687944d86050072b7ddb22ab68002196d99b1","observation_id":"174dc060-e3ee-4f67-93b4-0e6746fa524e","resolution":{"observed_at":"2026-08-16T05:28:26.157806Z","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":"2026-08-16T05:28:26.464461Z","title":"Redet: A rotation-equivariant detector for aerial object detection,","venue":null,"work_id":"2b2ddfe3-bf56-4a0d-87ff-9b88a4c44ea3","year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:26.285231Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:e4d46a6b3e59b09d62dd8b9b8a94c0f971823a229176e00ff559c763078a4882","observation_id":"8163e992-73f2-4257-a784-9795ca6c4eb8","resolution":{"observed_at":"2026-08-16T05:28:26.469500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:26.448977Z","title":"Gliding vertex on the horizontal bounding box for multi-oriented object detection,","venue":null,"work_id":"afac39cf-7dd4-43a6-8db2-941ee1db30a3","year":2020},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:26.289294Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:51dc77b0d238ce1ae1478c47b6b9c757bf30689252eec0a13a5890823e0257e6","observation_id":"17065fd3-2247-4c59-a6ef-d9fd1fb4ced4","resolution":{"observed_at":"2026-08-16T05:28:26.454360Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:28:26.434024Z","title":"Oriented r-cnn for object detection,","venue":null,"work_id":"5d8a27d0-07ac-4b9c-83be-8eb5dcb5ffe7","year":2021},"citing_paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-16T05:28:26.293648Z"},"links":{"citing_paper":"/paper/2504.20602"},"observation_digest":"sha256:71ca2ff34e8804bb87c20cea6ed96566e10ba2e4b2f5d40a270fa9fcc30cfd87","observation_id":"3d07892a-c054-4a11-993d-36792c2ca296","resolution":{"observed_at":"2026-08-16T05:28:26.439416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2504.20602","last_updated":"2025-04-29T10:11:03Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T05:22:35.970773Z","submitted_at":"2025-04-29T10:11:03Z","title":"Purifying, Labeling, and Utilizing: A High-Quality Pipeline for Small Object Detection"},"reference_resolution":{"displayed":66,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":28,"verified_exact":0,"verified_fuzzy":38},"total_outbound_references":66},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 0 inbound Pith citation observations for arXiv:2504.20602."}