{"as_of":"2026-08-11T20:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6c05126f4cd3f69474addcc1c0963c9895e715c105ea64127d43f673c2ae8f18","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T07:59:06.281037Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2607.20523/citation-record","integrity":"/paper/2607.20523/integrity","json":"/paper/2607.20523/citation-record.json","paper":"/paper/2607.20523"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T07:59:00.803038Z","title":"Fish-vista: A multi-purpose dataset for understanding & identification of traits from images,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:00.803038Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:0109c27c006f9722bfe8b675afe2b174c46856a699240e945e8271c978d9cc7b","observation_id":"88d8ef8d-3347-4c7c-b82c-016d86e4c960","resolution":{"observed_at":"2026-08-02T07:59:00.803038Z","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":"2026-08-02T07:59:00.843312Z","title":"Autofish: Dataset and benchmark for fine-grained analysis of fish,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:00.843312Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:759729c70a3a8233f26f4d5891dde1d8fb4fc1ad14f472a30684f333aff4eee3","observation_id":"2227548d-6812-4660-8f5c-ae564a8118a6","resolution":{"observed_at":"2026-08-02T07:59:00.843312Z","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":"2026-08-02T07:59:00.984478Z","title":"M4FT: Mamba, migratory, mobile and multiple fish tracking,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:00.984478Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:cc15018ddfb97f0832062ceb472e922ddad4ebb7a219ec2038be389f84551e5a","observation_id":"917d3797-5c4f-4d63-97f8-384bc8fce44d","resolution":{"observed_at":"2026-08-02T07:59:00.984478Z","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":"2026-08-02T07:59:01.068626Z","title":"Fishnet: A large-scale dataset and benchmark for fish recognition, detection, and functional trait prediction,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:01.068626Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:f3685b5b51da55e1731bccf9c59c42af830272ccad53f6c762296d75b07ec28f","observation_id":"21649620-4650-4e85-aa0b-57e442280d21","resolution":{"observed_at":"2026-08-02T07:59:01.068626Z","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":"2026-08-02T07:59:01.217718Z","title":"A realistic fish-habitat dataset to evaluate algorithms for underwater visual analysis,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:01.217718Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:dd6f16c3012a1fbe60df9263e468dbcfddf554ebf197aef5bfc552a967d671f5","observation_id":"06461f61-cdd4-4391-89e0-9c5fa75a3544","resolution":{"observed_at":"2026-08-02T07:59:01.217718Z","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":"2026-08-02T07:59:01.298974Z","title":"The deepfish computer vision dataset for fish instance segmentation, classification, and size estimation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:01.298974Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:b3b7209808287717b34d44499e1e5b63fd111d8cd42f0eb333370f5543872418","observation_id":"245f539b-c075-4f76-bf0b-28e73475ed77","resolution":{"observed_at":"2026-08-02T07:59:01.298974Z","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":"2026-08-02T07:59:01.357742Z","title":"Automatic estuarine fish species classification system based on deep learning techniques,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:01.357742Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:dfa7bd1585906088b77aea16689969d4a147ebb2378c8720ec0c805aa8fbd6ba","observation_id":"1e6c3609-1392-4411-840b-8b4b106811d3","resolution":{"observed_at":"2026-08-02T07:59:01.357742Z","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":"2026-08-02T07:59:01.438687Z","title":"Fish tracking and segmentation from stereo videos on the wild sea surface for electronic monitoring of rail fishing,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:01.438687Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:79a863dfc5eac24d3ae880648a34e6bfd5ebbee3f68252427156c14ee2f758e8","observation_id":"7d053661-5166-48ad-bb7c-28504a4f1dc5","resolution":{"observed_at":"2026-08-02T07:59:01.438687Z","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":"2026-08-02T07:59:01.598701Z","title":"Fish tracking and continual behavioral pattern clustering using novel sillago sihama vid (ssvid),","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:01.598701Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:22cb6662e463a8eeb3ac2188fde46f1ce16339518cea247351aefd876370dc61","observation_id":"e902d9ed-f137-4f92-beec-d8828140746f","resolution":{"observed_at":"2026-08-02T07:59:01.598701Z","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":"2026-08-02T07:59:01.780941Z","title":"Fishnet: Fish visual recognition with one stage multi-task learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:01.780941Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:e9ed73ee2fbd3c4bd70f82a1c553fca6a63309891ded6bb673c0bd05f3e5c325","observation_id":"4ef2d1fc-4692-4abe-87a7-e735c2dceb45","resolution":{"observed_at":"2026-08-02T07:59:01.780941Z","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":"2026-08-02T07:59:01.926811Z","title":"Mtaffb: a multi-task active learning framework for analyzing fish school feeding behavior,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:01.926811Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:8b88741d9bc57f72603fd7bd77c4193c4b55732c649e320cc6072879448409f7","observation_id":"0bfd21b4-4693-46a3-8e26-0ce71d68c102","resolution":{"observed_at":"2026-08-02T07:59:01.926811Z","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":"2026-08-02T07:59:02.102010Z","title":"Exploring simple siamese representation learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:02.102010Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:b3085f88ddbec117e92366a7dd481e78039a5e341f067ee13f7dc03fae9160d5","observation_id":"84731210-b1ba-4255-9c93-ae6d2238490b","resolution":{"observed_at":"2026-08-02T07:59:02.102010Z","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":"2026-08-02T07:59:02.189337Z","title":"Interpretable image classi- fication via non-parametric part prototype learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:02.189337Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:7248e7fcde92ab0362da928aee346be6f8c2da86460aabd93cffca787f122bba","observation_id":"992a7e69-f5a3-4975-891f-775692a0cf31","resolution":{"observed_at":"2026-08-02T07:59:02.189337Z","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":"2026-08-02T07:59:02.263866Z","title":"Multi-task learning using uncer- tainty to weigh losses for scene geometry and semantics,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:02.263866Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:b462fcd200422432d2347bec5c67b79aeea238931759ee2d28f2773934a80ab8","observation_id":"73e488f2-1129-481f-82b7-d596340de9e2","resolution":{"observed_at":"2026-08-02T07:59:02.263866Z","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":"2026-08-02T07:59:02.327717Z","title":"Wildfish++: A comprehensive fish benchmark for multimedia research,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:02.327717Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:7aa563aa65beccebbe34e4c55ffa5c0451239283a1e1d50a9808d8532a51550d","observation_id":"8fb78b08-bc95-478f-9037-961b59ba8866","resolution":{"observed_at":"2026-08-02T07:59:02.327717Z","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":"2026-08-02T07:59:02.474362Z","title":"Fine-grained fish classification from small to large datasets with vision transformers,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:02.474362Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:39787737dee186d6f3934e108684e0391c4afb1cf6c9909a23260635783c6d02","observation_id":"d4834f57-c7ea-4b32-9069-f47e1e7a1107","resolution":{"observed_at":"2026-08-02T07:59:02.474362Z","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":"2026-08-02T07:59:02.653513Z","title":"A lightweight fine-grained pelagic fish recognition algorithm based on object detec- tion,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:02.653513Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:e4955184a5d8a0850ac29fdebbfe028a9f8dd5a5a431898b4a8b5848df7e8f47","observation_id":"7b009a44-4051-4412-a11d-9aa52a4cdbd3","resolution":{"observed_at":"2026-08-02T07:59:02.653513Z","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":"2026-08-02T07:59:02.779797Z","title":"BioCLIP: A vision foundation model for the tree of life,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:02.779797Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:ae30ad4ef5df9bae7ef1843461b425d01ed34282037c57e09206e24b2da83ba3","observation_id":"064ada02-e090-4add-b3d3-1f060f55a16c","resolution":{"observed_at":"2026-08-02T07:59:02.779797Z","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":"2026-08-02T07:59:02.866476Z","title":"Yolo-fd: An accurate fish disease detection method based on multi-task learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:02.866476Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:4867e8a622f48bee043c9d08efff361573c41e9faa2355601fa285854f392e3f","observation_id":"965821ac-aa2d-4bbd-9c99-fb3adc76c7fc","resolution":{"observed_at":"2026-08-02T07:59:02.866476Z","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":"2026-08-02T07:59:02.993318Z","title":"Deepseavision: Enhanced detection and classification of underwater species,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:02.993318Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:0cd14d3c04f02f1ca4230eb1dce5621bfc3e6863b96ad30f802aec9b7b324693","observation_id":"c37ed7a4-cc79-4e3b-b2ea-7810f4e2cfda","resolution":{"observed_at":"2026-08-02T07:59:02.993318Z","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":"2026-08-02T07:59:03.102306Z","title":"Optimizing fish classification with a hybrid sae-svm model: Perfor- mance and evaluation on fish-gres and fish4-knowledge datasets,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:03.102306Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:43de809940ffa517177eeb90d0e0937fb10e49132d004157107513c9b7bb662d","observation_id":"34937711-fb90-4085-9785-21a6b6e48ec9","resolution":{"observed_at":"2026-08-02T07:59:03.102306Z","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":"2026-08-02T07:59:03.245698Z","title":"Which tasks should be learned together in multi-task learning?","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:03.245698Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:1f31051cdc73d7a6176a37d362b928c7cce92f6943d6d3ab0276ad23eb8518d6","observation_id":"50df9c78-105d-4d46-a66d-0e448d03d5a2","resolution":{"observed_at":"2026-08-02T07:59:03.245698Z","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":"2026-08-02T07:59:03.356218Z","title":"Model- protected multi-task learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:03.356218Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:dbca570b9719d11ab754d76dbb0d40bdeab0442f507982cfa1507ab6e783283b","observation_id":"f9ec6579-62c9-4109-b487-c25050c0cef0","resolution":{"observed_at":"2026-08-02T07:59:03.356218Z","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":"2026-08-02T07:59:03.537189Z","title":"Decoupling representation learning and classifier for long- tailed adversarial training,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:03.537189Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:9416f827d2244adb45fb355effc71e2e37a56273567dcedfffee6e77d25a1d70","observation_id":"b98a2d14-3f07-4994-8376-5a97274090cb","resolution":{"observed_at":"2026-08-02T07:59:03.537189Z","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":"2026-08-02T07:59:03.652492Z","title":"Gradient surgery for multi-task learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:03.652492Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:fbf9b8ec2f086860e6d4839a39ce39e5e4aaeeae4393dffe41f59c4651af3a5d","observation_id":"d1f58a78-e959-457a-ac60-587514504997","resolution":{"observed_at":"2026-08-02T07:59:03.652492Z","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":"2026-08-02T07:59:03.804761Z","title":"Individual fish recognition method with coarse and fine-grained feature linkage learning for precision aquaculture,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:03.804761Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:e04df5590614537ca1ae45d6041bb75593ec6e3a1c8e92a824112f554bc1e2d9","observation_id":"a7bf1c75-bc0c-406e-994d-5b865beb31d0","resolution":{"observed_at":"2026-08-02T07:59:03.804761Z","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":"2026-08-02T07:59:03.889940Z","title":"Hierarchical feature attention learning network for detecting object and discriminative parts in fine-grained visual classification,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:03.889940Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:64e43606de1379e13dabb28ffb2e592aa3d76cdb90e8f32e21875caaa2d7a058","observation_id":"1ce631c8-8592-4a1d-a980-7b40b2083103","resolution":{"observed_at":"2026-08-02T07:59:03.889940Z","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":"2026-08-02T07:59:04.070296Z","title":"Concept bottleneck models,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:04.070296Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:444c55f7bda8884cee92643082c887142618b589b17e89928a321f37c5125d7f","observation_id":"f2ebde6a-6ab8-45fe-b290-59b28ada9849","resolution":{"observed_at":"2026-08-02T07:59:04.070296Z","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":"2026-08-02T07:59:04.237242Z","title":"Very deep convolutional networks for large-scale image recognition,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:04.237242Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:915b1815989d41b33cd53f019b78d472b4d12d62f1a53e468e5c1afa68c6a9ca","observation_id":"0b2e2a82-557c-4777-94be-a68049a7f522","resolution":{"observed_at":"2026-08-02T07:59:04.237242Z","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":"2026-08-02T07:59:04.397305Z","title":"Aggregated residual transformations for deep neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:04.397305Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:b5a042b83f7146425983e4dbb98282c744207c55a7b60b570c39bfa0f4b9e289","observation_id":"2dc14b2d-9312-4878-be2e-d8cca4c57524","resolution":{"observed_at":"2026-08-02T07:59:04.397305Z","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":"2026-08-02T07:59:04.462951Z","title":"Designing network design spaces,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:04.462951Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:55471b327d3d4e1286fa4a5bb042c96ba2dcea50c9c56c7186236fced2c8d463","observation_id":"5fec0695-d4e0-4082-b7f9-ae5b6fcd291a","resolution":{"observed_at":"2026-08-02T07:59:04.462951Z","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":"2026-08-02T07:59:04.590165Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:04.590165Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:4b3f828a37cf9525c23383ac333e71c0105a6d934b9a368b41c5f55416d923eb","observation_id":"edec4767-b757-4a1a-b56b-f29014b29726","resolution":{"observed_at":"2026-08-02T07:59:04.590165Z","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":"2026-08-02T07:59:04.677930Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:04.677930Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:3f1470087bea6b6bb2f7ce89fa72dbf21ad2ebe0c72511812c7fdda1a4fa8d2c","observation_id":"178a73ca-7819-4c43-b7d3-7620d9add345","resolution":{"observed_at":"2026-08-02T07:59:04.677930Z","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":"2026-08-02T07:59:04.743409Z","title":"Maxvit: Multi-axis vision transformer,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:04.743409Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:0e047f8c3a8cc6c70f403f7db10c3d6e224dd7f459bd58aa9cea19c9022a5baa","observation_id":"5c74961f-e2c6-4537-9ae0-ff3177ae06af","resolution":{"observed_at":"2026-08-02T07:59:04.743409Z","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":"2026-08-02T07:59:04.816877Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:04.816877Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:9cb830840cce17b6b5bfe7836d73941c5d86c47f945f4c626f37a8dd1de0d1fb","observation_id":"801c6e3f-6878-4218-9d98-fb97f3d6b46c","resolution":{"observed_at":"2026-08-02T07:59:04.816877Z","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":"2026-08-02T07:59:04.905015Z","title":"DINOv2: Learning robust visual features without supervision,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:04.905015Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:9b47262190d56fed57b24a4d18c67e2efe960d977d450c080704ae60b44c533f","observation_id":"0b3f6f7e-23eb-4512-ad4d-c4870d78882c","resolution":{"observed_at":"2026-08-02T07:59:04.905015Z","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":"2026-08-02T07:59:05.058134Z","title":"A simple interpretable transformer for fine-grained image classification and analysis,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:05.058134Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:39aa5af58213d222cdb4e3af3f00d231d1d943df1e779852736eae20f9db937c","observation_id":"324b9d68-a455-4fac-954a-1f4b566a45ad","resolution":{"observed_at":"2026-08-02T07:59:05.058134Z","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":"2026-08-02T07:59:05.164119Z","title":"Transfg: A transformer architecture for fine-grained recognition,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:05.164119Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:5ecbf5d6dc7795824070b5053a9e5f4813c9a35c2714def3067f7b8d1318a220","observation_id":"a85e8c8a-e3f8-41dc-956b-a9adaad654d5","resolution":{"observed_at":"2026-08-02T07:59:05.164119Z","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":"2026-08-02T07:59:05.229429Z","title":"Pyramid scene parsing network,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:05.229429Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:90f9aecf1adb641447b081500c84a8bfaa65118bb871d06a5a95bc3e38cb06df","observation_id":"e01711c0-4b0c-49f1-8170-32315c3884b7","resolution":{"observed_at":"2026-08-02T07:59:05.229429Z","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":"2026-08-02T07:59:05.383032Z","title":"Encoder- decoder with atrous separable convolution for semantic image segmen- tation,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:05.383032Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:50d139c3ca55be190da07355ca6642c931d5d361b8541d4a9c44885c0839dd77","observation_id":"dc1cc907-ecbf-4cd6-a773-4d62a9190cc6","resolution":{"observed_at":"2026-08-02T07:59:05.383032Z","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":"2026-08-02T07:59:05.526199Z","title":"Per-pixel classification is not all you need for semantic segmentation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:05.526199Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:b574f2f569fdd303d682deba11436da07236f30ba1e5e11e3a2551d2c804e768","observation_id":"8544c592-6102-483f-adae-100041641881","resolution":{"observed_at":"2026-08-02T07:59:05.526199Z","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":"2026-08-02T07:59:05.629838Z","title":"Yolov8: A novel object detection algorithm with enhanced performance and robustness,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:05.629838Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:efe39d0e80342487587f9e8197123102b05f672b4bd20d3559fe3f5813d5f200","observation_id":"c1155fca-ef0e-4a35-96d5-014f555efba0","resolution":{"observed_at":"2026-08-02T07:59:05.629838Z","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":"2026-08-02T07:59:05.747083Z","title":"Molmo and pixmo: Open weights and open data for state-of-the-art vision-language models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:05.747083Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:dc6217e54ed6503070c931419e17f2140f178088b2aa1b53e1dfbaf7e9cfcaf1","observation_id":"26cf4d4c-d10d-4343-b222-8245081dada4","resolution":{"observed_at":"2026-08-02T07:59:05.747083Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.10834","last_updated":"2021-07-22T17:49:25Z","snapshot_observed_at":"2026-07-06T11:31:39.278344Z","submitted_at":"2021-07-22T17:49:25Z","title":"Query2Label: A Simple Transformer Way to Multi-Label Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.10834","snapshot_observed_at":"2026-08-02T07:59:05.891955Z","title":"Query2label: A simple transformer way to multi-label classification,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:05.891955Z"},"links":{"cited_paper":"/paper/2107.10834","citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:852dbc290bc78b65b412c280585a5eda620b9f6e12b0f056bdc688d058c00c5d","observation_id":"847ddeb8-f7c0-4154-aa92-34fa6ff11d11","resolution":{"observed_at":"2026-08-02T07:59:05.891955Z","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":"2026-08-02T07:59:06.038105Z","title":"GradNorm: Gradient normalization for adaptive loss balancing in deep multitask networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:06.038105Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:31c3766a814f2ef62795246f1aec9088fc09f3ea1417e3e12e1a3284f32c90e5","observation_id":"fbbaaaba-a5f1-4f1d-88f1-267bd602c73e","resolution":{"observed_at":"2026-08-02T07:59:06.038105Z","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":"2026-08-02T07:59:06.175700Z","title":"Grad-cam: Visual explanations from deep networks via gradient-based localization,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:06.175700Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:d357e464f8f7042947ef6147fd1376e3098b04852807d7fef997d3ca2599d15e","observation_id":"1730a3b3-024f-4f18-865f-4282985ff0ae","resolution":{"observed_at":"2026-08-02T07:59:06.175700Z","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":"2026-08-02T07:59:06.281037Z","title":"Visualizing data using t-sne","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-02T07:59:06.281037Z"},"links":{"citing_paper":"/paper/2607.20523"},"observation_digest":"sha256:5a756b73d760b9e8089de05f943860d4caaf5e114f4ed34e0e67cefc9043cffd","observation_id":"87b09d6c-e106-4f59-8e40-167ce69fc818","resolution":{"observed_at":"2026-08-02T07:59:06.281037Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.20523","last_updated":"2026-07-09T06:30:11Z","latest_version":1,"primary_category":"q-bio.QM","snapshot_observed_at":"2026-08-02T07:58:56.500568Z","submitted_at":"2026-07-09T06:30:11Z","title":"FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":47,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":47},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2607.20523."}