{"as_of":"2026-08-13T16:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4192eeefa2b0e87129b9e4e0b5e179e0d1cc9eb527bff02aa3c3acee2145141d","coverage":[{"denominator":57,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":57,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T22:47:07.326630Z","state":"measured"},{"denominator":57,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":57,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2412.03179/citation-record","integrity":"/paper/2412.03179/integrity","json":"/paper/2412.03179/citation-record.json","paper":"/paper/2412.03179"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:47:13.114741Z","title":"Multimae: Multi-modal multi-task masked autoen- coders, 2022","venue":null,"work_id":"049e7097-3deb-486f-8a4a-fd84534fc3d0","year":2022},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.554756Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:7fe73811bb42e9bb99c9703b3086c52d9d94cc6d7e6f5c0214f7deff95d6c135","observation_id":"6e994f92-c9c6-437b-aba7-811bf2f50fc1","resolution":{"observed_at":"2026-08-11T22:47:13.152972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:13.001972Z","title":"Exploring rela- tional context for multi-task dense prediction, 2021","venue":null,"work_id":"fdb1010d-6de7-4bdb-95fd-2f3c3d6eda92","year":2021},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.575787Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:2984d3b1e30639bb14701933fcb58f16a177a95871fde5355675abeb1e1c153e","observation_id":"6da85bf7-9154-4a7e-a3e8-b75ecc6bab40","resolution":{"observed_at":"2026-08-11T22:47:13.033658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:12.834751Z","title":"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks","venue":null,"work_id":"be51b07b-4f5f-4e5a-a7c0-79f3edea9b7e","year":2017},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.604179Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:76db63260d329ad372980ee0bf4780d9afa012178b635d3db341d190d989e5a1","observation_id":"d58f806d-83e4-4c7c-a358-6e9c16010aee","resolution":{"observed_at":"2026-08-11T22:47:12.874747Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:12.678125Z","title":"Schwing, Alexan- der Kirillov, and Rohit Girdhar","venue":null,"work_id":"0bb8f93c-382f-495e-bc46-fc1e73cbc754","year":2022},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.632505Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:9dd8a3095e1903fa96e9c3be3fff6642ec1545feb5a8215d182817430021b14f","observation_id":"4920812a-aeda-4271-8737-a84202411843","resolution":{"observed_at":"2026-08-11T22:47:12.715004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:12.575891Z","title":"Se- mantic image segmentation: Two decades of research, 2023","venue":null,"work_id":"8f1fb094-c9ef-4da3-86bc-3eba759631e6","year":2023},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.654834Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:57ed47896d0ee4f06ebc86b622256e7beffff6af744d18f196496429a7f38671","observation_id":"b96ba6b8-4c24-40b0-b895-75ba8ad164db","resolution":{"observed_at":"2026-08-11T22:47:12.594901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:12.454816Z","title":"Everingham, L","venue":null,"work_id":"48e8ed27-2631-44ff-8c50-dc344bfba231","year":2010},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.694747Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:2d79cd1311473bc984afe0ad0a374777dd6419ec3cae1f600f2749c85726f3fa","observation_id":"30dc2116-42fe-46d0-8695-b9a427d78afc","resolution":{"observed_at":"2026-08-11T22:47:12.499633Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:12.354877Z","title":"When multi-task learning meets partial supervision: A com- puter vision review, 2024","venue":null,"work_id":"da1c09a7-a544-4dbb-819c-98f45554ec9c","year":2024},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.728303Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:898f77b5cfcb20b52e59962edaa0ab14602d6473a9acce9a75abb71e354f8c9f","observation_id":"9e269e70-f6ae-4a5d-a409-71c247fbe5c8","resolution":{"observed_at":"2026-08-11T22:47:12.376020Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1801.08297","last_updated":"2019-04-04T23:24:48Z","snapshot_observed_at":"2026-08-12T06:16:15.693046Z","submitted_at":"2018-01-25T07:38:52Z","title":"NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction","version":4},"cited_work":{"arxiv_id":"1801.08297","doi":null,"metadata_source":"pith","pith_arxiv_id":"1801.08297","snapshot_observed_at":"2026-08-11T22:47:07.812131Z","title":"NDDR-CNN: Layerwise Feature Fusing in Multi-Task CNNs by Neural Discriminative Dimensionality Reduction","venue":"cs.CV","work_id":"84084900-a43c-443c-a5fc-9be0c6d31a4a","year":2018},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.744815Z"},"links":{"cited_paper":"/paper/1801.08297","citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:ed00f894bb1e4da8546934d213e4b7a233d66efc09ebe8a072f50aac35953cdd","observation_id":"2b77314c-2495-489e-9883-6008622b53fa","resolution":{"observed_at":"2026-08-11T22:47:07.827759Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:12.230298Z","title":"R-cnns for pose estimation and action detec- tion, 2014","venue":null,"work_id":"e0cadeac-c6b4-44c3-a937-a347bfaa8c25","year":2014},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.774828Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:d26e1f389a082d6c973f199eac5b0d9529fd048de4286a45b529e7d6eb30156c","observation_id":"a0413e93-549f-4f22-8a4a-ef9f9c585d0d","resolution":{"observed_at":"2026-08-11T22:47:12.256144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:12.124743Z","title":"Dynamic task prioritization for multitask learning","venue":null,"work_id":"23b36e09-a376-4d86-b00c-4f062c7c7eb6","year":2018},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.814744Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:14bd053123dbacf6ef578b41e2416cf272d79ca951a11c6d2bd323d7b8f09d20","observation_id":"1ae49d9c-b776-432f-99a0-58b462ab83a9","resolution":{"observed_at":"2026-08-11T22:47:12.160747Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:12.054746Z","title":"Unit: Multimodal mul- titask learning with a unified transformer, 2021","venue":null,"work_id":"d7f0ecad-7315-4a92-b1c9-cd0f641e19a7","year":2021},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.850460Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:5ae712d1228093343d7afa6874476d29d25882a7e5e760051c84baf4a25aaaa3","observation_id":"a1aca202-042f-47e4-ad60-ba0e13d8397d","resolution":{"observed_at":"2026-08-11T22:47:12.082708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:11.958318Z","title":"Lau, and Thomas S","venue":null,"work_id":"2104af6d-56d6-46da-b397-b0a32e812ed2","year":2019},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.874745Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:1492e799c2281583f4f461fb2037f2128f75ce211271fcdb595010a62ac8a80f","observation_id":"b9f874fd-9d5f-498c-ac79-c89da709a029","resolution":{"observed_at":"2026-08-11T22:47:11.991255Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1705.07115","last_updated":"2018-04-24T06:42:35Z","snapshot_observed_at":"2026-07-06T05:43:25.911696Z","submitted_at":"2017-05-19T17:56:57Z","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.07115","snapshot_observed_at":"2026-08-11T22:47:05.901104Z","title":"Multi-task learning using uncertainty to weigh losses for scene geome- try and semantics","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.901104Z"},"links":{"cited_paper":"/paper/1705.07115","citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:cb4b871110b80a5a63f4ea82d098fd5377791220328d04d8ae1dd804d44fc6e9","observation_id":"19eb5853-e83f-4c75-b825-49bf8113c940","resolution":{"observed_at":"2026-08-11T22:47:05.901104Z","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":"2026-08-11T22:47:11.858636Z","title":"Pushing the boundaries of boundary de- tection using deep learning, 2016","venue":null,"work_id":"5899988c-b8d5-4eae-8c3f-03624f5eb944","year":2016},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.924738Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:9836639d7c1b21d19c3e31c0a8f7d23882ad3c8af097fac82d5a17b5c92321fb","observation_id":"6d0bbed8-f5c6-45d5-a07a-e2955dfa5930","resolution":{"observed_at":"2026-08-11T22:47:11.895634Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02132","last_updated":"2016-09-07T19:35:30Z","snapshot_observed_at":"2026-08-13T01:04:12.519286Z","submitted_at":"2016-09-07T19:35:30Z","title":"UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memory","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02132","snapshot_observed_at":"2026-08-11T22:47:05.960476Z","title":"Ubernet: Training a ’universal’ convo- lutional neural network for low-, mid-, and high-level vi- sion using diverse datasets and limited memory","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.960476Z"},"links":{"cited_paper":"/paper/1609.02132","citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:46df62b22e6ebe87c6588245840e49b9205919e46354a89d662d1d325bdb59bf","observation_id":"5c3201ca-024b-4811-904c-43a0b0afc483","resolution":{"observed_at":"2026-08-11T22:47:05.960476Z","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":"2026-08-11T22:47:11.772127Z","title":"Learning multi- ple pixelwise tasks based on loss scale balancing","venue":null,"work_id":"2178512b-aed1-41d0-a5c8-d4d81fcf7146","year":2021},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:05.984752Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:bf81cb241f0b878411a09f5b85a99b552c55e65a4d18461bf4bdd4b4f810af06","observation_id":"f7b8eda0-6ce3-4c6a-bfcb-a1386624c087","resolution":{"observed_at":"2026-08-11T22:47:11.796856Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:11.674612Z","title":"Transformed dynamic feature pyramid for small object detection","venue":null,"work_id":"98041e12-4d07-4205-9f64-4b1215a84a2d","year":2021},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.004737Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:d96d96cd1fd705e1478033fc06faa518c36fbc839b246a68978d3dcc59124d75","observation_id":"6053291b-0779-4b32-b1d7-62f43bf5f8e3","resolution":{"observed_at":"2026-08-11T22:47:11.706427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:11.599211Z","title":"Auxiliary tasks in multi- task learning, 2018","venue":null,"work_id":"23379d1d-2c51-4c76-b0a6-da08cd1fea16","year":2018},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.034817Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:46ef41f5d3440a9408c9a5e897e0f6167380b653c9086005defccf8b64d8d0da","observation_id":"56653743-8ea7-4ce0-b9e2-2d4ce429d96a","resolution":{"observed_at":"2026-08-11T22:47:11.625300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:11.547965Z","title":null,"venue":null,"work_id":"3614c017-31fe-4b46-86d6-fedc45d3a176","year":2023},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.073299Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:f58015e6a99066723834144fe11393ca1e8debdb5bea181819d6ec3cd3405ccb","observation_id":"dd83813c-7903-4484-a8d7-412be366cbbd","resolution":{"observed_at":"2026-08-11T22:47:11.565116Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:11.462833Z","title":"Rethinking boundary detection in deep learning models for medical image segmentation, 2023","venue":null,"work_id":"491c0c3d-091c-48aa-a98f-d594dc9a50a5","year":2023},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.103690Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:a254241dec672449913fc4cf42793e5e9581a50adea7ab9cec50998d3e22e4db","observation_id":"756843e4-23d3-44c9-9243-60782e124c02","resolution":{"observed_at":"2026-08-11T22:47:11.504748Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.10704","last_updated":"2019-04-05T05:57:50Z","snapshot_observed_at":"2026-08-12T19:43:03.968931Z","submitted_at":"2018-03-28T16:15:45Z","title":"End-to-End Multi-Task Learning with Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.10704","snapshot_observed_at":"2026-08-11T22:47:06.122012Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.122012Z"},"links":{"cited_paper":"/paper/1803.10704","citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:e132fe0c6c189fe93a084dbaf558c420ac5e8772765163b4f994dd80eef9e480","observation_id":"a26a99cb-74f7-48c3-8e90-80123f8aa882","resolution":{"observed_at":"2026-08-11T22:47:06.122012Z","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":"2026-08-11T22:47:11.391795Z","title":"Swin trans- former: Hierarchical vision transformer using shifted win- dows, 2021","venue":null,"work_id":"34835abd-40d1-46f1-a0db-46bb22a84869","year":2021},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.144750Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:084e3d2408bde737aa12af5acc0cfbda2b3105176211c3e0e33d9803fbdd6254","observation_id":"13c2629d-1020-4b80-885b-cc1f0228faa1","resolution":{"observed_at":"2026-08-11T22:47:11.424968Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:11.294820Z","title":"Cross- task attention mechanism for dense multi-task learning,","venue":null,"work_id":"b42d90d7-d835-4a87-ba9c-4fcd080ae0a4","year":null},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.170741Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:531fffebda962745bd0432582108f986b0cc0f4f91c488aa02d1a0619fba5bd3","observation_id":"4dc1f821-4a00-4a65-bd39-cb5e5da613fb","resolution":{"observed_at":"2026-08-11T22:47:11.324745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:06.194745Z","title":"Decoupled weight decay regularization, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.194745Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:be6ecd55da611d79b22891897f96a92c93e07c8ced1cc4908bfc8a66233825d4","observation_id":"09aead47-97f8-4a1e-b39b-30793cb2a53c","resolution":{"observed_at":"2026-08-11T22:47:06.194745Z","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":"2026-08-11T22:47:11.097413Z","title":null,"venue":null,"work_id":"72b8d00b-3b49-41a8-b885-da21c1682a42","year":2018},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.221186Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:f48032a5ee2a781c4d4f978e9e6e30584efb2c7603c8cc70e60742e966b3d4db","observation_id":"7ae86475-6967-45d8-bb55-d3d027e83534","resolution":{"observed_at":"2026-08-11T22:47:11.140163Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:11.026056Z","title":"Image seg- mentation using deep learning: A survey, 2020","venue":null,"work_id":"d8eadd52-7783-4f4a-8215-9b4bfd9faa66","year":2020},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.255231Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:637422b155bceb43bf129961cf8a44f29e726117491678d7906ed691378fd29c","observation_id":"30db888f-8742-4b13-ab1d-629ddc26f334","resolution":{"observed_at":"2026-08-11T22:47:11.038496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1604.03539","last_updated":"2016-04-12T19:43:25Z","snapshot_observed_at":"2026-08-05T17:14:52.408260Z","submitted_at":"2016-04-12T19:43:25Z","title":"Cross-stitch Networks for Multi-task Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1604.03539","snapshot_observed_at":"2026-08-11T22:47:06.285077Z","title":"Cross-stitch networks for multi-task learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.285077Z"},"links":{"cited_paper":"/paper/1604.03539","citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:234eb5d155dee17ec4cf748e469797ef69d03647f09ede0c8381dd2a35f1150b","observation_id":"b0aa0f03-de47-40eb-b185-b09e938af08c","resolution":{"observed_at":"2026-08-11T22:47:06.285077Z","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":"2026-08-11T22:47:10.920117Z","title":"Indoor segmentation and support inference from rgbd images","venue":null,"work_id":"9c9e4808-fd0a-488f-b981-819657f9dde1","year":2012},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.334738Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:d28ebdee91adabc005df532f4ea82ffe3d7513673dae3801717b8f69fd18ed59","observation_id":"f06a2746-c4fd-44a2-905a-98c2b07be543","resolution":{"observed_at":"2026-08-11T22:47:10.942126Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:10.807648Z","title":"An overview of multi-task learning in deep neural networks, 2017","venue":null,"work_id":"42ef0151-1439-4ccd-a4de-3019b87e52af","year":2017},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.384748Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:4b5a112b402521f1ec0a83e74b4e6d338d89441959c20060c4c6d4a40890940f","observation_id":"a7e4521b-2587-4ace-ac6d-0993eb1394f6","resolution":{"observed_at":"2026-08-11T22:47:10.851219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:10.694747Z","title":"Latent multi-task architecture learning,","venue":null,"work_id":"6756b64c-5264-4854-a905-172446c1e2b4","year":null},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.424743Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:b32fbed269fe76f55814ef1222f1ccbd73e3db6604d6c1557b28414536854123","observation_id":"d3f2dca9-32cb-402e-a747-3e1c53c58067","resolution":{"observed_at":"2026-08-11T22:47:10.731077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:10.507861Z","title":"Rusu, Neil C","venue":null,"work_id":"4ea2da3d-fb2f-4acd-b414-720e412fb9ed","year":null},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.474748Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:642974f863cf14cf68ffcae452d1ab3ee619ffcb3c6aa995222ddd72b584c313","observation_id":"9fd3fcba-4bc8-4191-8de4-e9c91981033a","resolution":{"observed_at":"2026-08-11T22:47:10.535095Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:10.422593Z","title":null,"venue":null,"work_id":"e86907e9-7b24-42df-9b11-9efcc5839dee","year":2023},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.524747Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:524d010759f873bb1a9c2bf0c67111fdeeb714848f9ca24840ac94066f3747a3","observation_id":"d38cfd2f-80db-4e69-97d7-42c6f8979a52","resolution":{"observed_at":"2026-08-11T22:47:10.446828Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:10.330520Z","title":"Efficient multitask dense predictor via binarization, 2024","venue":null,"work_id":"16f0cd14-4295-4f1b-b1c2-2f23d7591c14","year":2024},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.564740Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:9686146c4e2512ca33442f07b0af5314625d311f99c82faa9d503aea3ca4f7dc","observation_id":"3b167a4b-0d78-4c50-8001-a9784173c267","resolution":{"observed_at":"2026-08-11T22:47:10.354749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:10.241034Z","title":"Learning to multi-task by active sampling,","venue":null,"work_id":"7e15ff83-631c-4185-8a50-e362e6d884ba","year":null},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.593260Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:6767ef73ff3a5e7775703746e5a912945cbcfc5d495f0fc2fad05a57bac5e52b","observation_id":"88d0b00c-c949-4afa-ab7b-cb63b9eb7b0a","resolution":{"observed_at":"2026-08-11T22:47:10.263131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:10.130524Z","title":"Usb: Universal-scale object detection bench- mark, 2021","venue":null,"work_id":"fe9a9002-d38f-4776-8214-5d76eeeb422e","year":2021},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.621461Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:3e9da0177b7238219da78899137c0e4d85afb1ddcab8ea737429e2468351adf9","observation_id":"5b3de09f-4ded-4660-984d-9d3aec85deb2","resolution":{"observed_at":"2026-08-11T22:47:10.154849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:10.043221Z","title":"Indoor segmentation and support inference from rgbd images","venue":null,"work_id":"c1d04a22-fecb-41e4-ab29-75736743f40c","year":2012},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.644744Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:2243cfcf8fb1e5c8657e06abae81e357bf443c52289ba2798d2ce17cf61cacd8","observation_id":"316e0546-348c-4279-890a-073472087e4a","resolution":{"observed_at":"2026-08-11T22:47:10.074776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:09.936368Z","title":"Training data-efficient image transformers and distillation through at- tention, 2021","venue":null,"work_id":"3926767e-7059-41b6-846e-851c3c50438b","year":2021},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.677857Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:daefcc06d5976b703ce4b15052b519c3941e64be6b6d309ee471d28e8ef56121","observation_id":"c785fd1d-f5cf-48dc-9aee-8fa5c63f1061","resolution":{"observed_at":"2026-08-11T22:47:09.976649Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:09.854790Z","title":"Multi-task learning for dense prediction tasks: A sur- vey","venue":null,"work_id":"cde617b2-9360-4378-a3c3-842b599eaae1","year":2021},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.717832Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:36a7eb8b32c4ed036998288cf524e007f3f717146e350a2f8a5fa7bd3f444d26","observation_id":"de0dfe7a-4490-43a3-9625-e3236cfee6a1","resolution":{"observed_at":"2026-08-11T22:47:09.884828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:09.715260Z","title":"Mti-net: Multi-scale task interaction networks for multi-task learning, 2020","venue":null,"work_id":"07a082ad-7edc-4fd4-939a-cbb83c25a079","year":2020},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.744895Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:66329dd29e1549ca6d924f34ddb60b068102b7daca0c4288f451b6ea4b5136ac","observation_id":"f5356f05-4e71-46cd-be3d-61328b767274","resolution":{"observed_at":"2026-08-11T22:47:09.775199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:09.484752Z","title":"Internim- age: Exploring large-scale vision foundation models with deformable convolutions, 2022","venue":null,"work_id":"d3e5a9df-f1df-4516-9df2-5bffdde33c2e","year":2022},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.784925Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:2c391926e49bc123144183b8780aa20113da97aa039471f08b99e891d1eb0b9f","observation_id":"d9076cb1-f9d5-49ae-9ed6-5816aeeeee03","resolution":{"observed_at":"2026-08-11T22:47:09.534739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:09.336087Z","title":"Pyra- mid vision transformer: A versatile backbone for dense pre- diction without convolutions, 2021","venue":null,"work_id":"ff2164b6-f725-4606-b57d-f44b017f8489","year":2021},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.814743Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:940362a1b722cf5f98bb618093f9d633d25d8d76acffb9735b0a213d17385541","observation_id":"be80829f-6691-4538-8a44-0e96455682b5","resolution":{"observed_at":"2026-08-11T22:47:09.356242Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:09.256351Z","title":"PVT v2: Improved baselines with pyramid vision transformer","venue":null,"work_id":"d6b8e2d2-26c6-4d3b-8a5d-cd8fd932bf95","year":2022},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.854747Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:e6e11b685156aaddcc0bc127cbe829f6a9626b19e2deb8e9863f608042b38bc0","observation_id":"05856433-5099-44b2-b9f9-73f10049ebfd","resolution":{"observed_at":"2026-08-11T22:47:09.284738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:09.184862Z","title":"Gradient vaccine: Investigating and improving multi-task optimization in massively multilingual models","venue":null,"work_id":"b0e23b64-8360-49a2-b75a-60771027b0c8","year":2021},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.894746Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:73d6cab2459003d700249c23c5acfd67d559a23ac028c3492dbf8490bbbb34a9","observation_id":"66520c3d-0a95-4fe4-8d3e-0536f41758d5","resolution":{"observed_at":"2026-08-11T22:47:09.207033Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:06.957795Z","title":"Cbam: Convolutional block attention module, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.957795Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:eb74d63646c2f2a0a63c18a32b7fb7407170a08dba0f4c93756d126a484f7f9d","observation_id":"f4412664-11d0-44c6-bb00-dfd86c0f4ee2","resolution":{"observed_at":"2026-08-11T22:47:06.957795Z","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":"2026-08-11T22:47:08.954750Z","title":"Pad-net: Multi-tasks guided prediction-and-distillation net- work for simultaneous depth estimation and scene parsing,","venue":null,"work_id":"6fb6cc89-3ef3-4c40-9f26-c63548abccca","year":null},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:06.974262Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:33d0a0d431ebff991d3b3b4c1198d32e45d3e2c5c0a58b11cf04193f487eb835","observation_id":"3071582b-90cd-4a03-b636-1b29efba0d6e","resolution":{"observed_at":"2026-08-11T22:47:09.001644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:08.774746Z","title":"Mtformer: Multi-task learning via transformer and cross-task reasoning","venue":null,"work_id":"2401e5aa-ef82-4a14-b2cb-8c2be6584b7d","year":2022},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:07.005956Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:1a04d9360176ae8e2add85ed0418d12e2db4567aab95bf5d2f569a46d67f86e3","observation_id":"940cdf01-c110-44ee-98c0-5d57b992c833","resolution":{"observed_at":"2026-08-11T22:47:08.823443Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:08.614743Z","title":"Demt: De- formable mixer transformer for multi-task learning of dense prediction, 2023","venue":null,"work_id":"a4618fa0-64b9-4e81-bd14-c7c3eaae55b3","year":2023},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:07.031074Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:da17a25517bd852ab323128d7b050cad92872858601ee41c7ac61231a1957888","observation_id":"7ba9d275-7638-49e9-acb1-b547db21438c","resolution":{"observed_at":"2026-08-11T22:47:08.654748Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:08.516963Z","title":"Depth anything: Unleashing the power of large-scale unlabeled data, 2024","venue":null,"work_id":"f8d11b72-3c4d-4480-95a3-f61cf88643db","year":2024},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:07.055260Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:3f5d1146425071f8c6a1beca5ab53b8c870fc64de72b276275164f988baefae3","observation_id":"d7b79ecd-dd80-4bd2-9d54-78d3e5766ada","resolution":{"observed_at":"2026-08-11T22:47:08.538836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:08.414823Z","title":"Multi-task dense prediction via mixture of low-rank experts, 2024","venue":null,"work_id":"f1a5962e-2ed1-4b36-b5ad-246f30fa6843","year":2024},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:07.094199Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:037ca0ee92f8102ba5b14e3081dadfc830581bd25d66e7cd511c280c017cac91","observation_id":"23770d2a-6d36-46ff-9c15-ffc441eae5eb","resolution":{"observed_at":"2026-08-11T22:47:08.436998Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:08.304816Z","title":"Invpt: Inverted pyramid multi-task transformer for dense scene understanding","venue":null,"work_id":"e03304d5-cce2-4bdf-ac95-581c4d88650b","year":2022},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:07.130814Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:972113a845c8d4a0375f9a87d68781b8b89be33a317f1b03f61a433cff9f94e5","observation_id":"d81fce45-f2ba-45bf-a8e2-00d733cd16dd","resolution":{"observed_at":"2026-08-11T22:47:08.344744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:08.204741Z","title":"Taskprompter: Spatial-channel multi-task prompting for dense scene understanding","venue":null,"work_id":"832e971d-c6a8-4c26-9851-15d6d87ddce7","year":2023},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:07.160870Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:c880710985017903b9225adc3c4bd3578428063bb30b6a5025f34e83d3b3d422","observation_id":"3a1786be-0114-4e44-952f-5e704064e305","resolution":{"observed_at":"2026-08-11T22:47:08.227199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:08.128507Z","title":"Gradient surgery for multi-task learning, 2020","venue":null,"work_id":"de4e4cfd-308e-4515-9920-1808d62baeac","year":2020},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:07.204746Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:09e87b714f6fa71042454a29fa78cf63f9227075b19dd566e1f424c628ea3e66","observation_id":"539b0df1-ad6e-483f-a8d9-a27069b0cac4","resolution":{"observed_at":"2026-08-11T22:47:08.141058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:08.067202Z","title":"A survey on multi-task learn- ing","venue":null,"work_id":"c879c09b-7d4e-44ea-9a25-4c622c756ebf","year":2022},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:07.235898Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:e1be0e428616f1c229f7a1679485af0716e358fa4e28000d5214ad67bf9367a8","observation_id":"a29f99ca-11d3-4891-aecd-337042b37f27","resolution":{"observed_at":"2026-08-11T22:47:08.086816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:08.031254Z","title":"Pattern-affinitive propagation across depth, surface normal and semantic segmentation, 2019","venue":null,"work_id":"009cdb28-61e4-434a-94ba-046bdd75f1da","year":2019},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:07.254767Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:33f0d07eaf6e157ffc708626ce40246c3dbcd3afda90ca8f6344f9b56b81aa70","observation_id":"7ea28770-1cb1-4505-a7b0-e2bc3b889861","resolution":{"observed_at":"2026-08-11T22:47:08.042229Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:07.979384Z","title":"Semantic under- standing of scenes through the ade20k dataset, 2018","venue":null,"work_id":"3ba1ea5a-98eb-48b3-bce5-b8a5e71fd709","year":2018},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:07.274742Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:c642b17b085d9e61d2cd2855c30c789e1d12cd749a71e2c299b2d8c0f009a5aa","observation_id":"f2fecd18-cfd5-4dbd-99f4-a52a9ab84ff0","resolution":{"observed_at":"2026-08-11T22:47:07.995999Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:07.923398Z","title":null,"venue":null,"work_id":"2c65891a-0954-4ed8-a80e-05b6975c9b0e","year":2020},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:07.294227Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:1cca0c0ae5179b6e97ec21a40720effe76edee2781d859d0820d8e5c4c4f0640","observation_id":"e93976f2-df70-48ad-89f0-047b8f45a994","resolution":{"observed_at":"2026-08-11T22:47:07.943241Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T22:47:07.872219Z","title":"Vlprompt: Vision-language prompting for panoptic scene graph gener- ation, 2024","venue":null,"work_id":"f047b339-d7a2-4b5f-8561-e60aa3d9cacf","year":2024},"citing_paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T22:47:07.326630Z"},"links":{"citing_paper":"/paper/2412.03179"},"observation_digest":"sha256:e496bdea18bb357d72fbd5388a2f603bcffa1259190e56ce075b299e8bbb704f","observation_id":"c4c2aa2c-5a95-4328-89a9-e05a89a8bf76","resolution":{"observed_at":"2026-08-11T22:47:07.889128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.03179","last_updated":"2024-12-04T10:05:47Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T06:16:13.274967Z","submitted_at":"2024-12-04T10:05:47Z","title":"Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization"},"reference_resolution":{"displayed":57,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":1,"verified_fuzzy":46},"total_outbound_references":57},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 0 inbound Pith citation observations for arXiv:2412.03179."}