{"as_of":"2026-08-16T07:24:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9d67be535c5b5ac3ec7ae75eb02527c0a5730febfc6670d780402e0e2ac0810b","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:04:56.543886Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2507.19077/citation-record","integrity":"/paper/2507.19077/integrity","json":"/paper/2507.19077/citation-record.json","paper":"/paper/2507.19077"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:04:57.080349Z","title":null,"venue":null,"work_id":"ff3108fa-9c34-4682-addc-9727d839dfd7","year":2024},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.367738Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:c6c683b2a5a1d53844cfcbe7e73855a393f4763487352f839ac4212050cb756d","observation_id":"a89b1a34-23ab-4b29-af8b-e5f0fc6c93e4","resolution":{"observed_at":"2026-08-15T18:04:57.083683Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:57.070087Z","title":null,"venue":null,"work_id":"e90d19ae-8033-4349-9dab-1440447609ad","year":2023},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.371970Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:02010f3d816b2708fd62cc388f9b2fd46d13bdee816f1c3daa150032c30afafa","observation_id":"12e3c26f-6e9f-447d-9e07-52bae8791f14","resolution":{"observed_at":"2026-08-15T18:04:57.073669Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:57.059322Z","title":null,"venue":null,"work_id":"86c32c3a-7bd4-4b02-a1a6-f4eec2373be0","year":2021},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.375741Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:2891db1bce0d96bac8febd7cbd18b11d85db309e756fdb380af476010fdd4dc7","observation_id":"b4f7e7a9-c662-4205-9441-458fd325ddd6","resolution":{"observed_at":"2026-08-15T18:04:57.063351Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:57.048904Z","title":null,"venue":null,"work_id":"e8e5e1d5-b795-49fc-8ce0-a4a29b0fa5fe","year":2014},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.379808Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:2b0c69bbf83e4e66516332ce0fb2beba353f1aa0a355d45016f31ae9266133e3","observation_id":"bd93df10-23de-420b-abae-1956de89c5cf","resolution":{"observed_at":"2026-08-15T18:04:57.052450Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:57.038466Z","title":null,"venue":null,"work_id":"2da087d8-9c0c-4736-9848-1a0f2ffe389e","year":2023},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.383412Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:115e8dd1e59a615ba125889f413820eb680b5ff6236e9aa8bb2a671ffa62bcd7","observation_id":"c5d2056f-7cf6-4f4a-b310-e14dddd9d0fe","resolution":{"observed_at":"2026-08-15T18:04:57.041860Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.06066","last_updated":"2024-01-11T17:31:42Z","snapshot_observed_at":"2026-08-13T15:18:04.411100Z","submitted_at":"2024-01-11T17:31:42Z","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.06066","snapshot_observed_at":"2026-08-15T18:04:56.386910Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.386910Z"},"links":{"cited_paper":"/paper/2401.06066","citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:7d66bbe5be6741ec4cc971504991b20ea128e245b78c2a78bb0f84096e326a53","observation_id":"1f7fd909-0798-4760-8917-e4d391fed380","resolution":{"observed_at":"2026-08-15T18:04:56.386910Z","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":"2026-08-15T18:04:56.390542Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.390542Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:c70155009419f834d61f13173329c38391b06e2960d26b3675b1e5909d1c668d","observation_id":"c0db6af7-fa6d-403d-ba3b-5674b276f2f9","resolution":{"observed_at":"2026-08-15T18:04:56.390542Z","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":"2026-08-15T18:04:56.393766Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.393766Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:98dbe6cd398e59d8335cc93cc235d3d89494bcdc9dde8ec2fc66ac165ebf6f75","observation_id":"3477b5b6-5de1-40c2-aece-637735912e63","resolution":{"observed_at":"2026-08-15T18:04:56.393766Z","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":"2026-08-15T18:04:56.400216Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.400216Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:1931718ab3a9f2972303450d9f33821167f8e31e5411700fa06258a3c8bf67bf","observation_id":"bab3c162-7c41-4cc7-ba91-42a51101ac29","resolution":{"observed_at":"2026-08-15T18:04:56.400216Z","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":"2026-08-15T18:04:57.002684Z","title":null,"venue":null,"work_id":"a13214f1-520d-454d-8817-eb37bca2e830","year":2022},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.403586Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:d2102890d2f79fd7472b81571f6e141bc4a66c5071ca9f718da7561ae38633c7","observation_id":"0a407077-4b39-44ed-a0c6-ae4c39382aae","resolution":{"observed_at":"2026-08-15T18:04:57.006498Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.991998Z","title":null,"venue":null,"work_id":"1d3ef824-588e-4670-a87b-0155c20a2b5d","year":2022},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.406926Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:83d75de783616e70f7e2a111f8dcf5f6e4acb1b8534427aabfb85de235bc6126","observation_id":"c7d96dbc-925b-4511-8415-f066cedfad53","resolution":{"observed_at":"2026-08-15T18:04:56.995742Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.981478Z","title":null,"venue":null,"work_id":"4702c634-8bc2-41d3-aa6e-4d840ab88605","year":2024},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.410169Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:6de499241506177136f098553a11db6e0b0be75ff24ef505cdad09cf712c8ecf","observation_id":"e90f3d30-dbb1-408c-91e5-5728a632ceb3","resolution":{"observed_at":"2026-08-15T18:04:56.985095Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.970644Z","title":null,"venue":null,"work_id":"c27ddc83-c955-42de-be5e-609f33254fc8","year":1993},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.413489Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:3a6b1f74db3ac30ec5c0628a33e354048ae1dd5c12eca734e7dbca7a7e32dedb","observation_id":"b0ef806b-4b1f-4251-8977-d7df309e31a6","resolution":{"observed_at":"2026-08-15T18:04:56.974192Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.417199Z","title":null,"venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.417199Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:844a87be20460739b202a700ce33064a02fb70f965cab4604e29307bded66469","observation_id":"cddcb38d-f167-4813-87aa-fbb2164d8817","resolution":{"observed_at":"2026-08-15T18:04:56.417199Z","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":"2026-08-15T18:04:56.953534Z","title":null,"venue":null,"work_id":"7242cd70-a23d-4753-9562-e93a9d1f9fa7","year":2022},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.420660Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:a8bb4e14f5fd598bcb7ffb82a87d7fd73167bd11e40355c6aeac01ff1d44f88e","observation_id":"411e713b-26e5-4555-8399-fd213736011c","resolution":{"observed_at":"2026-08-15T18:04:56.957217Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.943438Z","title":null,"venue":null,"work_id":"3e751c88-538b-4a90-ba73-967992fe6027","year":2024},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.424877Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:124b41ca0c8784c4f0e2750c50be8b776836344f16bde011d8705f70b161dd2f","observation_id":"0881986e-ae1b-4cbd-a2b9-560527d1c2c4","resolution":{"observed_at":"2026-08-15T18:04:56.946917Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.933006Z","title":null,"venue":null,"work_id":"ab7fbef8-6527-41b7-8298-e1f1c9cea322","year":2021},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.428593Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:11a951cc10e910b60865a98f04d317c642db5838d7e5a01f4b7dfaa8f3f05c0a","observation_id":"a044855d-8c58-4022-ac6a-25c905ec6943","resolution":{"observed_at":"2026-08-15T18:04:56.936487Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.922694Z","title":null,"venue":null,"work_id":"83418557-4b49-4e8a-8987-2304880fe074","year":2017},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.431583Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:529124c1d171eaeb4e9111fe85532ef7abd0a2c337e2feaea5c8b8974906ffbe","observation_id":"4ce72f26-646a-4c51-8ea2-8772df4a2a10","resolution":{"observed_at":"2026-08-15T18:04:56.926175Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.912159Z","title":null,"venue":null,"work_id":"faa166c3-ccbe-472e-971b-78d2026cf44b","year":2021},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.434921Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:c51ea9c23b64780cd27112083627b32261060784dceb5cf05733956c12fc00e9","observation_id":"b8f62caf-545c-4de8-8bda-2c2904de6b56","resolution":{"observed_at":"2026-08-15T18:04:56.915865Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.902055Z","title":null,"venue":null,"work_id":"4403666f-1300-479d-9042-a65ca320ef40","year":2022},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.438150Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:2114e0c8c55b003bc92104a45bf9d77abeccbe2e13ee4570c527d30d7fe0c0bb","observation_id":"0193e26f-3d89-4b37-be6e-326b2a9bf8d4","resolution":{"observed_at":"2026-08-15T18:04:56.905460Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.892377Z","title":null,"venue":null,"work_id":"b4eb7f62-4a0f-4b2a-827c-eacd772849f3","year":2022},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.441338Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:c67438abb3f02efb17ddadf9de00eede841b8b16268771d2c0cf6d8d6be2ba4f","observation_id":"b99f5722-c473-4764-be8b-46cf148bbb6d","resolution":{"observed_at":"2026-08-15T18:04:56.895650Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.882102Z","title":null,"venue":null,"work_id":"210ae4c0-9e49-4382-bdcb-355356e12ede","year":2021},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.444649Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:5924ba2e3361f66fabe07a8f5548f95b1776604a5ee3bb974e2e608e2f16db67","observation_id":"4b0c8cf1-7905-4fba-bffe-1765bee6d15b","resolution":{"observed_at":"2026-08-15T18:04:56.885393Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.872243Z","title":null,"venue":null,"work_id":"2dbf62e5-1e67-43de-9570-9eae1f511fa3","year":2022},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.448089Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:febe39ec4ffd334eb7e49108efad1340e2f1a65585bf5363ab41683da571b5a8","observation_id":"4665408b-4023-4e17-b5eb-50e8ac54c00c","resolution":{"observed_at":"2026-08-15T18:04:56.875742Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.862403Z","title":null,"venue":null,"work_id":"b2367ebc-e96e-49e2-a5f5-87eb20d9b7f4","year":2021},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.450905Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:57c9eee87642ab4955f93a2dd141d33c2f954b2f6055ad1d3ff8baee6453ade8","observation_id":"22be8504-41d2-41a2-b710-5cc2f7858a59","resolution":{"observed_at":"2026-08-15T18:04:56.865729Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.851424Z","title":null,"venue":null,"work_id":"2fdd8bfb-086a-4d3b-bcd9-89ac0dac24f0","year":2024},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.454693Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:2c6988cb825857b2895228cd2ae49ae0bdc0f82520f906e5a01d9404ff8dff34","observation_id":"4c7c84d5-86cf-42e7-8185-2bec6fbf4942","resolution":{"observed_at":"2026-08-15T18:04:56.854842Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.840303Z","title":null,"venue":null,"work_id":"e7df89d6-c328-4bbf-a103-1ba4d1a87d73","year":2021},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.457579Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:7a1487d7603beb9b6d6fede8eff0cf9d2f8f020327cc1417b2173afc537e6959","observation_id":"f15297e9-cc85-488d-9395-ce7efb02de58","resolution":{"observed_at":"2026-08-15T18:04:56.844347Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.829770Z","title":null,"venue":null,"work_id":"9a49f041-c085-4b17-ad6d-868dc4006036","year":2025},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.461415Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:55ad922d4ef353bfa6170967e968c84dc917c8f0059976e2460add521a12f704","observation_id":"c285f9d0-d7d1-4dba-ab0f-3fe1b7f0894e","resolution":{"observed_at":"2026-08-15T18:04:56.833424Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.819551Z","title":null,"venue":null,"work_id":"1e3267da-98f2-4ad5-aec6-e38f7e4c89ba","year":null},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.464680Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:a10cd45d349a1c66cbdbf093e9e7498b68ec49e5c03d01c3500ca24f9e9e55f3","observation_id":"79e00872-8986-40d8-aa76-da5dac570943","resolution":{"observed_at":"2026-08-15T18:04:56.823190Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.797842Z","title":null,"venue":null,"work_id":"b58d70ac-315c-4b70-bf9d-d498910d00ef","year":2012},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.471782Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:669a501cc474b3d3c8586668e61f2ec1eeef0846d709d43c1b9329e9c9fd6237","observation_id":"76d47566-fa98-4579-b1c7-7e3c035090d6","resolution":{"observed_at":"2026-08-15T18:04:56.801546Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.787631Z","title":null,"venue":null,"work_id":"cd7a6e0c-8fb4-4e52-b2ba-09916e5cae3d","year":2019},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.475013Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:5efeb7255d6810f2e52ddaba0b4f791baac950529fcbda5906fc8b02b78392a0","observation_id":"4607cb80-bcbe-474f-85d3-89d6c37209f0","resolution":{"observed_at":"2026-08-15T18:04:56.791022Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.777440Z","title":null,"venue":null,"work_id":"d4667fc9-d647-415b-b728-e53727af0c99","year":2022},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.479128Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:38a852755e61747b77192807a4a32b7299e706d7f94020223b0063a951a9cd92","observation_id":"049058e7-c115-469f-b662-b5c922f12c03","resolution":{"observed_at":"2026-08-15T18:04:56.780951Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.10174","last_updated":"2024-08-26T07:34:46Z","snapshot_observed_at":"2026-08-12T23:01:15.677695Z","submitted_at":"2024-08-19T17:32:15Z","title":"SMILE: Zero-Shot Sparse Mixture of Low-Rank Experts Construction From Pre-Trained Foundation Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.10174","snapshot_observed_at":"2026-08-15T18:04:56.482292Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.482292Z"},"links":{"cited_paper":"/paper/2408.10174","citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:07a6693d61d14f07c57a8aa8f43b91813ac3b630f9cb2f49d1e296da9dee8578","observation_id":"872c1a93-663d-409a-a675-0be78bb63836","resolution":{"observed_at":"2026-08-15T18:04:56.482292Z","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":"2026-08-15T18:04:56.767155Z","title":null,"venue":null,"work_id":"08b405ba-6039-4103-b766-8f14ec85373c","year":2024},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.486132Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:faea0e478c976831e11e3a5fe53b6a5b03f79cd8d82449b0e2b6eb6d9cd5a484","observation_id":"68749034-5921-492b-b805-c0150d531ef3","resolution":{"observed_at":"2026-08-15T18:04:56.770484Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.757743Z","title":"Vandenhende, S","venue":null,"work_id":"3389c4d8-3324-4a72-a60e-70bb46eb435c","year":2022},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.490109Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:457b06453662dd2488386607bb6fff110f17024b95fd4ac554b23a1557cf96b2","observation_id":"7d540b96-b9de-4de8-bce0-429bd2caea26","resolution":{"observed_at":"2026-08-15T18:04:56.761127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.746325Z","title":null,"venue":null,"work_id":"1abdd9ad-0685-4e39-8171-d18be69ae8c5","year":null},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.493674Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:b9c776b797d17d1c0c67062df76f5010558e28829142f4cb631cad5fcb09d3b4","observation_id":"f950e738-5c31-4a70-89b8-0131ecf3c09d","resolution":{"observed_at":"2026-08-15T18:04:56.750893Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.724813Z","title":null,"venue":null,"work_id":"acd3d639-fd37-4af0-80f9-9342e345896e","year":2024},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.502705Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:721943fd82419f4fccff395072ab68954b86f8e7d0516db5028d28110bcdeb2f","observation_id":"df77c5e8-f451-4b2b-9ee3-12a872553df4","resolution":{"observed_at":"2026-08-15T18:04:56.728221Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.714849Z","title":null,"venue":null,"work_id":"c1f7033a-4836-4df6-b6db-d36194ffbe36","year":2018},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.506673Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:ced3c903f473d00b89d938c3a24d467b971667499770314567dc61d82af016e4","observation_id":"2fecb56a-f816-4b65-8f65-0fdae5704760","resolution":{"observed_at":"2026-08-15T18:04:56.718255Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.704377Z","title":null,"venue":null,"work_id":"0c10282c-3bf2-4aa7-985e-ae5b49716c04","year":2024},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.510068Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:9822e13fb935c3c04a79730aaa2a13bea01ebbac89fd1c6d45836893b2cef932","observation_id":"7e16e917-b9c1-49c9-ae5a-281e105c7757","resolution":{"observed_at":"2026-08-15T18:04:56.707888Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.693395Z","title":null,"venue":null,"work_id":"abe0461a-9e9b-4bbb-9593-0ccc4ec7bf9a","year":2023},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.513221Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:4ebfe08dbd9cb9e133c35d0031fddbc3cd3ed78da9ac0d1f831da9c9df20912b","observation_id":"1e7a902c-5bd4-4dd9-bfc1-c7bc93b4fb9b","resolution":{"observed_at":"2026-08-15T18:04:56.697336Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.682149Z","title":null,"venue":null,"work_id":"8004fbcc-d897-4d94-bfa0-ea1851db9b4a","year":2023},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.516133Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:5a1be5e4b4cec00bd2dc7176799016fecdeefd0671df817408361e1271cea098","observation_id":"359ed390-cf0d-4749-abc3-04632082c902","resolution":{"observed_at":"2026-08-15T18:04:56.685708Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.670984Z","title":null,"venue":null,"work_id":"ab52cd6f-2c95-431e-ad8a-3dcd9d87d4fc","year":2023},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.519797Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:c0b1282ff51242a736f95ab294694e3fc93b18f1c5ab8ea2897dd8fb7efaf389","observation_id":"b790da41-f908-4428-9902-49c32fc22cf7","resolution":{"observed_at":"2026-08-15T18:04:56.674668Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.659564Z","title":null,"venue":null,"work_id":"c1c01e76-9f23-4ebc-a051-31cc93cd1ff9","year":2024},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.522868Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:0b32d9d8fc4b2564423d06fe33e84347a456a403f82f417c52ba63230825b0ad","observation_id":"43e51741-5bcb-400b-889c-eee5d9ab6c5e","resolution":{"observed_at":"2026-08-15T18:04:56.663786Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.648323Z","title":null,"venue":null,"work_id":"6e418cc3-4e19-496a-a2c1-e71b6601d083","year":2025},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.526076Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:274c210f27766d9e61dd301d85db6b9e60c8131ec31dcb4c1e3119393a100c62","observation_id":"5abb0c7a-e92d-4f6c-b8e5-3161ab2dbe9c","resolution":{"observed_at":"2026-08-15T18:04:56.652386Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.637085Z","title":null,"venue":null,"work_id":"a3ab5711-883c-416e-b287-1b73760d9649","year":2022},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.529863Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:246ca57503f730579d073c6185625b72137435d822e6af42ed1275ec6ca90f11","observation_id":"cc6792c5-1408-4bb7-84e9-b98e836f1ac4","resolution":{"observed_at":"2026-08-15T18:04:56.640961Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.532986Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.532986Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:5857da0f4008ad58f36908ce9bc778cc9481f9e1baaf0efa7cdc07e489b3e13d","observation_id":"6495f1fb-1718-45d0-b490-5303414b6290","resolution":{"observed_at":"2026-08-15T18:04:56.532986Z","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":"2026-08-15T18:04:56.619144Z","title":null,"venue":null,"work_id":"7d30d5e5-9c5e-4700-89ef-2fa1292616ac","year":2023},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.536763Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:7457140c67befe9fb33ecee9c14ab509997c91a871b484c6d39e412566f42403","observation_id":"ffeb29e4-68b0-4e1b-9492-72d49c4b8f2f","resolution":{"observed_at":"2026-08-15T18:04:56.623013Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.606089Z","title":null,"venue":null,"work_id":"11f19c0b-cd70-45c8-adb1-10766a5cf999","year":2024},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.540404Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:5daf731f394fb812b90047300ad4b16907c353b4563e7b597b4beb79dacdbf05","observation_id":"2f88a3d3-ffbb-4cd3-bcb0-dc10ef2ebbc4","resolution":{"observed_at":"2026-08-15T18:04:56.611253Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.591985Z","title":null,"venue":null,"work_id":"8c936560-7567-4f87-af7e-15973e8e7e23","year":2022},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.543886Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:7abb4ade08437814ee183666f67b46e7c4bd96273bd542a7b0d22c972847d423","observation_id":"9107728e-7c43-4157-81ed-cd69f0f53bc9","resolution":{"observed_at":"2026-08-15T18:04:56.597166Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.735257Z","title":"In European Conference on Computer Vision","venue":null,"work_id":"c4f74fdd-ad14-47d3-b552-a74719d48b02","year":null},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.497527Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:fec577b97326a0de97b3f92e9271d26f676de2a313db037158fe777b0cf53a15","observation_id":"4c11839b-9aac-4089-b017-199a45d1b3c4","resolution":{"observed_at":"2026-08-15T18:04:56.739591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T18:04:56.397062Z","title":"In International conference on machine learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.397062Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:c12104622d7c9d8838287bfe716d520529e13f5b2afe93da3a25fdcd966b793b","observation_id":"0f336d9e-1284-427e-9b1e-ad9589e44bb3","resolution":{"observed_at":"2026-08-15T18:04:56.397062Z","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":"2026-08-15T18:04:56.808610Z","title":"In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition","venue":null,"work_id":"cf1e38ac-4724-4d5f-9ada-e72297195268","year":null},"citing_paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T18:04:56.467890Z"},"links":{"citing_paper":"/paper/2507.19077"},"observation_digest":"sha256:4cba8ccb9af755b3f7310fd9d63252046980df76d1120646ef8ba5f0235f59e0","observation_id":"80c24797-c5ff-436b-8967-b5436b13e576","resolution":{"observed_at":"2026-08-15T18:04:56.812564Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.19077","last_updated":"2025-07-25T08:59:30Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T17:59:06.562126Z","submitted_at":"2025-07-25T08:59:30Z","title":"Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":48,"verified_exact":0,"verified_fuzzy":3},"total_outbound_references":51},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2507.19077."}