{"as_of":"2026-08-08T20:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1ba47e08fd4810f78a1bafdce3bbd8f19069171eb5044f3cd245c5806356674b","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:20:16.720912Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2506.05607/citation-record","integrity":"/paper/2506.05607/integrity","json":"/paper/2506.05607/citation-record.json","paper":"/paper/2506.05607"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:20:15.793271Z","title":"Ntire 2017 challenge on single image super-resolution: Dataset and study","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:15.793271Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:78ebf3dad395a144350303003477ab7f913e2bb3d2ff3b5d42c51ed819599c5b","observation_id":"985c4449-2714-4ade-83b2-f8dcc282e93a","resolution":{"observed_at":"2026-08-07T10:20:15.793271Z","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":"2026-08-07T10:20:17.874335Z","title":"Optimization of imaging reconnaissance systems using super- resolution: Efficiency analysis in interference conditions.Sensors (Basel, Switzerland), 24(24):7977, 2024","venue":null,"work_id":"75ab7418-81b7-495d-b211-164f98d23ccd","year":2024},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:15.886744Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:13fcf3b220ba6f1f604830ea1c109c2e0b23a56ef909d38b6d1f6b837a51e25f","observation_id":"8cd266de-dfed-41b7-9cae-7e4aee3ecfd1","resolution":{"observed_at":"2026-08-07T10:20:17.881957Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:16.056331Z","title":"Toward real-world single image super-resolution: A new benchmark and a new model","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.056331Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:b393b86125527fbcaba6b5577a59231d972bf4dd50d97c7bd085556659e1120f","observation_id":"72ca3f4e-9370-4358-8502-64ec5658d0a1","resolution":{"observed_at":"2026-08-07T10:20:16.056331Z","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":"2026-08-07T10:20:17.832543Z","title":"Adversarial diffusion compression for real-world image super-resolution","venue":null,"work_id":"5a0a8403-c560-43a3-a9ca-bada515068af","year":2025},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.216559Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:83eb267925f53102c70063b7b64eeb48ade8777d661660c429ead101103654c2","observation_id":"97028fc2-ae36-4c45-ab45-0e37e8336b4f","resolution":{"observed_at":"2026-08-07T10:20:17.839048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:16.378868Z","title":"Hat: Hybrid attention transformer for image restoration.arXiv preprint arXiv:2309.05239, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.378868Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:32f15a5273cc22dad36ff60588a4ba6720c5203d11a2162b37c26568c050e9f9","observation_id":"4d1d8a93-662a-40de-bed5-d048e679e9cf","resolution":{"observed_at":"2026-08-07T10:20:16.378868Z","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":"2026-08-07T10:20:17.806569Z","title":"Multinet++: Multi-stream feature aggregation and geometric loss strategy for multi-task learning","venue":null,"work_id":"4044556f-d1d5-4e46-ae5e-a8a02092cd79","year":2019},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.514169Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:d548f773b42776d9e8b2efe859da427d15adda8cf3b4e5d13779f49d66eebd16","observation_id":"69aabfb2-0dae-4749-9169-c7b712d973e3","resolution":{"observed_at":"2026-08-07T10:20:17.814484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:16.520048Z","title":"Learning a deep convolutional network for image super-resolution","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.520048Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:291722c0634c2e70c2d02c027e437df11ceebb17f324111b5d42cf17bc597595","observation_id":"7e50f9d6-6482-47e8-9ea8-4558613cd23b","resolution":{"observed_at":"2026-08-07T10:20:16.520048Z","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":"2026-08-07T10:20:17.768813Z","title":"Tsd-sr: One-step diffusion with target score distillation for real-world image super- resolution","venue":null,"work_id":"ffd5fbc1-4a3c-4e93-8279-704207d41668","year":2025},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.524915Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:71255ecc65408eb13f2f9e29b2ae9c33c0c54ec88ac40f6b288fa7f933e26e01","observation_id":"c6ef3efc-45b9-4686-8dbb-cc07e8583cfb","resolution":{"observed_at":"2026-08-07T10:20:17.776173Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:17.734450Z","title":"Adadiffsr: Adaptive region-aware dynamic acceleration diffusion model for real-world image super-resolution","venue":null,"work_id":"4b4971d9-12d7-4c32-a70a-68c738cf6bfa","year":2024},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.530215Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:de7d90de6e251ece8e514e339151590ed3c245c01dee402cfbc2df15da93c1fc","observation_id":"95b721d3-05f8-41f4-bed0-9d8cf3ada094","resolution":{"observed_at":"2026-08-07T10:20:17.741152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:16.535280Z","title":"Efficiently identifying task groupings for multi-task learning.Advances in Neural Information Processing Systems, 34:27503–27516, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.535280Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:454483eedfca250ab6f210ee1853d3c19d5dfc41fd6faa660983aac80b8596af","observation_id":"0763223b-6184-4022-ad1d-817c9bfda5a2","resolution":{"observed_at":"2026-08-07T10:20:16.535280Z","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":"2026-08-07T10:20:17.694448Z","title":"Sample-level weighting for multi-task learning with auxiliary tasks.Applied Intelligence, 54(4):3482–3501, 2024","venue":null,"work_id":"eb4bf373-1f67-4976-a3df-67f987596b3f","year":2024},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.540151Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:1acae8e0b11722afc9591051c6d166fc623bcf054325b10c0bffc94bae986c95","observation_id":"a9331c21-ec23-4134-8342-ef659f4d1638","resolution":{"observed_at":"2026-08-07T10:20:17.703402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:17.670436Z","title":"Blind super-resolution with iterative kernel correction","venue":null,"work_id":"797bf340-8339-4cf0-bee2-218a49dc2a2b","year":2019},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.544755Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:ab9adb760766abe546138f169af96106f041dab79d13b21c5cb7eb2b2214bc3c","observation_id":"e89e65c7-3047-485a-9829-22cd78adf44b","resolution":{"observed_at":"2026-08-07T10:20:17.679122Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:17.646736Z","title":"Dynamic task prioritization for multitask learning","venue":null,"work_id":"e491b4e0-2aa1-475f-a60f-c5ba07100176","year":2018},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.549710Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:065d4281d20ee94fd75b89994b3cf1351e7d0aa52bdda4be87e0fb00041ee5cf","observation_id":"641e43b4-9a64-48b7-8d3a-0165aa3bcab6","resolution":{"observed_at":"2026-08-07T10:20:17.652727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:17.627323Z","title":"Unfolding the alternating optimization for blind super resolution.Advances in Neural Information Processing Systems, 33:5632–5643, 2020","venue":null,"work_id":"b1a2805a-4bdb-4fe9-8878-ec7544879a90","year":2020},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.555267Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:c8ff3d72d7ad43bfb9733cbdc07750f55e189a86eb5679e4dd301daca081be0c","observation_id":"75eaccf0-d4e4-4c07-99cb-7a55e4dc6c0b","resolution":{"observed_at":"2026-08-07T10:20:17.633611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:16.559989Z","title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.559989Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:33a8e091d9cc1a4d3f209deb8a1a7676a978b4391f9e6d4e6db6dac77d083e34","observation_id":"763b9361-e093-4b16-854c-4755851d6db6","resolution":{"observed_at":"2026-08-07T10:20:16.559989Z","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":"2026-08-07T10:20:16.564660Z","title":"Accurate image super-resolution using very deep convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.564660Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:bb2a6cd8d3850163da573772eb7320573a41354ab9902e136f9bb9417aa5de86","observation_id":"1c4b26e3-fdc0-42dd-9288-208140b498ea","resolution":{"observed_at":"2026-08-07T10:20:16.564660Z","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":"2026-08-07T10:20:17.563137Z","title":"Ubernet: Training a universal convolutional neural network for low-, mid-, and high- level vision using diverse datasets and limited memory","venue":null,"work_id":"8f203855-1b31-4a81-a18e-430e5be75c53","year":2017},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.569720Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:31f6473ae326bf9663e10c3d7dcffb4c90c1d4bba9bb27ef98aa42b5c2f039f5","observation_id":"03017ab4-8db3-4c63-ab09-6d48277d2448","resolution":{"observed_at":"2026-08-07T10:20:17.570458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:16.574322Z","title":"Photo-realistic single image super- resolution using a generative adversarial network","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.574322Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:efdd8f68b00c3ea9f92af485c6bd5987fc06bada5afa8c14d0721a865186d3de","observation_id":"dee022d1-797f-40b0-9d38-04a54487f081","resolution":{"observed_at":"2026-08-07T10:20:16.574322Z","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":"2026-08-07T10:20:17.526390Z","title":"Efficient and degradation-adaptive network for real-world image super-resolution","venue":null,"work_id":"771d057f-2f94-4cca-9d00-57d253b3be16","year":2022},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.579182Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:aa33f66210b96809b2228f08975c4b3a2aaed0a9f22db2693c56b0f3200db834","observation_id":"9d59b9ac-ac6c-4a3c-a3ce-c9535f6b2497","resolution":{"observed_at":"2026-08-07T10:20:17.532579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:16.585064Z","title":"Swinir: Image restoration using swin transformer","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.585064Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:e2685cb340a7b0d4b79fd80fe57938cc93c08704a3fa9ac5611a59884ee179f2","observation_id":"dcc0aa80-74f7-40c2-a040-64ba0ea6493c","resolution":{"observed_at":"2026-08-07T10:20:16.585064Z","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":"2026-08-07T10:20:17.483678Z","title":null,"venue":null,"work_id":"5233571d-0df4-4643-a339-16c417779e44","year":2016},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.590552Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:6593656906d839bd9f925a4b264d3a6c66be58f96efebf11221297d9f843c75a","observation_id":"d603f54e-ff2e-4e77-9606-aeb427e1c569","resolution":{"observed_at":"2026-08-07T10:20:17.489967Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.10603","last_updated":"2022-07-27T15:44:33Z","snapshot_observed_at":"2026-08-04T09:16:41.802622Z","submitted_at":"2021-11-20T14:28:32Z","title":"Reasonable Effectiveness of Random Weighting: A Litmus Test for Multi-Task Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.10603","snapshot_observed_at":"2026-08-07T10:20:16.595380Z","title":"Reasonable effectiveness of random weighting: A litmus test for multi-task learning.arXiv preprint arXiv:2111.10603, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.595380Z"},"links":{"cited_paper":"/paper/2111.10603","citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:1f9958492026bed4584f7eb0000d3c271d115c7648f17b88abe84cf219d0fead","observation_id":"8eb7ccda-32aa-4ce8-a931-5fbd297f81a9","resolution":{"observed_at":"2026-08-07T10:20:16.595380Z","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":"2026-08-07T10:20:17.458362Z","title":"End-to-end multi-task learning with attention","venue":null,"work_id":"a1e08196-aacf-4255-917d-c68e1c383771","year":2019},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.600741Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:decc1c4c13efdf769388f748a3f434c1927e41b7980c075e3a48e9e0a546b991","observation_id":"2308ff2d-9a30-4972-9237-d47b017731cb","resolution":{"observed_at":"2026-08-07T10:20:17.466651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:17.434276Z","title":"Cross-stitch networks for multi- task learning","venue":null,"work_id":"39769097-a1f6-4f74-98e2-be31811280b5","year":2016},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.606089Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:741c6eb7bc3c8b4b6d2852cafaccdea5adc0af075505eb2941ab8002b25bdcf5","observation_id":"412dcd16-2109-4ed3-891d-0ab7154c0206","resolution":{"observed_at":"2026-08-07T10:20:17.440592Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:17.412859Z","title":"Metric learning based interactive modulation for real-world super-resolution","venue":null,"work_id":"f936a4f0-9e92-482e-afa3-4e2bcdc03551","year":2022},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.611081Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:10bcd0828a84a49d653b5d57949f38f167f8c5a93659b8b5098c67c5453151e2","observation_id":"8d0e413e-8a51-4121-8e66-4ccf624965e9","resolution":{"observed_at":"2026-08-07T10:20:17.419755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:17.386139Z","title":"Deep learning based autonomous vehicle super resolution doa estimation for safety driving.IEEE Transactions on Intelligent Transportation Systems, 22(7):4301–4315, 2020","venue":null,"work_id":"9dee7832-42ee-477d-986d-196b46cab65b","year":2020},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.615939Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:7f34f48a75f30d08468c5d60b5a414f44373fe0f4acf9a2ef40a13ee0d3e413d","observation_id":"429a5092-15c6-4610-94fe-e31fb8bd7668","resolution":{"observed_at":"2026-08-07T10:20:17.394231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:17.319702Z","title":"Vcisr: Blind single image super-resolution with video compression synthetic data","venue":null,"work_id":"4287269a-b929-4c39-b5b8-e59208e49faa","year":2024},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.620634Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:7c7a444a66b4a9ed2de5a1047814cd5db64cb5114610697bff71f1567d692b7b","observation_id":"e2180207-bc70-4abc-8ac8-415384f132b9","resolution":{"observed_at":"2026-08-07T10:20:17.347688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:17.257353Z","title":"Unsupervised degradation representation learning for blind super-resolution","venue":null,"work_id":"2b4fa79e-f677-4f78-8260-a68718cc16d3","year":2021},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.625468Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:c594117ab7ef727dd8f191237d454e293e14df1125789d2ae32ee626bf7a2343","observation_id":"7e14360a-763d-4b13-a7b3-450fc41c7be9","resolution":{"observed_at":"2026-08-07T10:20:17.268446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:16.630876Z","title":"Real-esrgan: Training real-world blind super- resolution with pure synthetic data","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.630876Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:27ea25a50833cc08d8e27785b331dfbae1c7331b03c51df795df3dfa20819101","observation_id":"801e6a2a-fe9c-4ef7-bcce-e67f265d461c","resolution":{"observed_at":"2026-08-07T10:20:16.630876Z","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":"2026-08-07T10:20:17.218475Z","title":"Recovering realistic texture in image super- resolution by deep spatial feature transform","venue":null,"work_id":"1ea47051-7bf0-4199-9fdb-214d6ed96107","year":2018},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.636064Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:a7e122f4fca16b34eb9f08ff422a9dddf2cd1fbe5407544e54948f12545fbd6a","observation_id":"56f7b989-4744-40d1-8012-b2b489e27d14","resolution":{"observed_at":"2026-08-07T10:20:17.224737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:16.640864Z","title":"Sinsr: diffusion-based image super-resolution in a single step","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.640864Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:0b5c97c2a2bd979acb8ecf2570702f874a907059049e164c201a6703c35a3edd","observation_id":"993545a7-6d68-411e-9c96-faa01d215263","resolution":{"observed_at":"2026-08-07T10:20:16.640864Z","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":"2026-08-07T10:20:17.183018Z","title":"Image quality assessment: from error visibility to structural similarity.IEEE transactions on image processing, 13(4):600–612, 2004","venue":null,"work_id":"ea901481-afba-440d-8c23-10bd6b020054","year":2004},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.645717Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:4ce3b8cde29a962deb5e9001440a3b63675d55437119aa9dd26f4a4515ef50bd","observation_id":"5544ac63-f7cb-40e7-b95d-c828f4df22ec","resolution":{"observed_at":"2026-08-07T10:20:17.188069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:17.158071Z","title":"Component divide-and-conquer for real-world image super-resolution","venue":null,"work_id":"8b7d4abc-f86f-4ca1-abad-97acfd35b116","year":2020},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.650939Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:708453147009b7930c0f0c1334c585befc6a14dcec834d23efb4c6420ea225fa","observation_id":"90d55c2a-dd52-4c82-8851-a23b107045a7","resolution":{"observed_at":"2026-08-07T10:20:17.167406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:16.656752Z","title":"One-step effective diffusion network for real-world image super-resolution.Advances in Neural Information Processing Systems, 37:92529–92553, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.656752Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:e67cb50f4f97bebbf436d979744fd20fa25833a0e4edec49251509b7b6379fdc","observation_id":"520b53c6-8d2a-48c0-a671-c2f4969a53b9","resolution":{"observed_at":"2026-08-07T10:20:16.656752Z","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":"2026-08-07T10:20:16.662826Z","title":"Seesr: Towards semantics-aware real-world image super-resolution","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.662826Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:548f4dbf21d6522283e4f486480c2d10639da67161179920a66cc9e8f2d37981","observation_id":"9e874c64-8187-4864-be1f-8fa7ee3958a5","resolution":{"observed_at":"2026-08-07T10:20:16.662826Z","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":"2026-08-07T10:20:16.667723Z","title":"Gradient surgery for multi-task learning.Advances in neural information processing systems, 33:5824–5836, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.667723Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:697dfb0a7a2a7a0acee23635570f1a81ddbd8f2481117bdef01f02a718a4475f","observation_id":"a0df001b-cb1d-4a93-a11a-5ea2048e736d","resolution":{"observed_at":"2026-08-07T10:20:16.667723Z","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":"2026-08-07T10:20:17.095373Z","title":"Resshift: Efficient diffusion model for image super- resolution by residual shifting.Advances in Neural Information Processing Systems, 36:13294–13307, 2023","venue":null,"work_id":"02a63433-a0a0-46d5-98fe-aae8b919dac9","year":2023},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.674154Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:aba4007faa74804187afb72e0bbd9f61eb9684ab63579a84134ce30441f38b55","observation_id":"c789def9-de8b-4957-abda-4ed3b2d04345","resolution":{"observed_at":"2026-08-07T10:20:17.101664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:17.072756Z","title":"Achievement-based training progress balancing for multi-task learning","venue":null,"work_id":"8b72c588-41f7-47d8-94ba-6af591b6804b","year":2023},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.680025Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:741b0a18b6a74cf0fb8ba4c2ed6c52b2564bea53e87e2193e8794e15cf5edd66","observation_id":"3364acfb-3bf2-4e01-b65e-bac235cc2306","resolution":{"observed_at":"2026-08-07T10:20:17.079354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:16.684840Z","title":"Taskonomy: Disentangling task transfer learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.684840Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:d27aa5bc5e937b1256b38933d09f23afd16953bc0208c8e6282b5499c127c0c9","observation_id":"9826d30a-90ea-4bcc-8be1-3df13bcecada","resolution":{"observed_at":"2026-08-07T10:20:16.684840Z","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":"2026-08-07T10:20:16.690456Z","title":"Designing a practical degradation model for deep blind image super-resolution","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.690456Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:075095d887ee37f32c1c0561f904b53c72c69e33e910584701860eec2f1c8e1b","observation_id":"72c3b45d-9ca7-4338-bd59-e52e42970a38","resolution":{"observed_at":"2026-08-07T10:20:16.690456Z","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":"2026-08-07T10:20:17.021773Z","title":"Learning a single convolutional super-resolution network for multiple degradations","venue":null,"work_id":"71a229bc-a089-4897-8acb-b8f2ec89cc28","year":2018},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.695655Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:d93dae9c36e39407d017501d4793896f399c8207d878b2ce9691c6d9a72875c3","observation_id":"17eb912d-4bb2-404e-b829-a136502d0944","resolution":{"observed_at":"2026-08-07T10:20:17.028115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:16.700551Z","title":"The unreasonable effectiveness of deep features as a perceptual metric","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.700551Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:9ab2ac14a61ec84f702627431f4569f569555eec5b94cfd541ac7ce581cfc00c","observation_id":"ac2db0a4-680d-48e7-a4f2-86dcb06f3645","resolution":{"observed_at":"2026-08-07T10:20:16.700551Z","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":"2026-08-07T10:20:16.986523Z","title":"Real-world image super-resolution as multi-task learning.Advances in Neural Information Processing Systems, 36:21003–21022, 2023","venue":null,"work_id":"7759f187-fcca-488b-80ee-a5018f0d7d38","year":2023},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.705657Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:46577c4174ef2b98d3d57f37ed8d4fe0da3e10fa3ca3c70914ee714f34ddc959","observation_id":"a65b21c2-a737-492d-b738-640301f6a8d3","resolution":{"observed_at":"2026-08-07T10:20:16.993221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T10:20:16.710435Z","title":"Image super-resolution using very deep residual channel attention networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.710435Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:c821b5d3c2c15a60a09d61b71324d6406fe388cfd110093205146bae1e83369c","observation_id":"d15c356b-74e6-4e8d-873e-58a593fcab7c","resolution":{"observed_at":"2026-08-07T10:20:16.710435Z","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":"2026-08-07T10:20:16.715586Z","title":"Residual dense network for image super-resolution","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.715586Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:65d9071530abd56acaf7f808d6fb3f72309a39053cb44b3d8b0282e5567e02ef","observation_id":"b8575674-e7e0-47d0-a873-19a19b4815a3","resolution":{"observed_at":"2026-08-07T10:20:16.715586Z","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":"2026-08-07T10:20:16.930832Z","title":"Csrgan: medical image super-resolution using a generative adversarial network","venue":null,"work_id":"239361c1-62e7-4ed3-95ce-6f8e6d34db2e","year":2020},"citing_paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T10:20:16.720912Z"},"links":{"citing_paper":"/paper/2506.05607"},"observation_digest":"sha256:e7eeae1abac72a2b9105c3c7c2643aa33f49a176734c157e7d98c3be4b4daac3","observation_id":"107ae0a5-98d5-4900-8028-5c6e44be82d4","resolution":{"observed_at":"2026-08-07T10:20:16.938427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.05607","last_updated":"2025-06-05T21:40:21Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T10:11:30.391976Z","submitted_at":"2025-06-05T21:40:21Z","title":"Controlled Data Rebalancing in Multi-Task Learning for Real-World Image Super-Resolution"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":0,"verified_fuzzy":25},"total_outbound_references":46},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2506.05607."}