{"as_of":"2026-08-16T08:58:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:672f4da0bc52d45a68379eff7cae3942d19a9b5567b8da270a1724f5f08eb0dd","coverage":[{"denominator":67,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":67,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T14:03:59.346316Z","state":"measured"},{"denominator":67,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":67,"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/1908.03884/citation-record","integrity":"/paper/1908.03884/integrity","json":"/paper/1908.03884/citation-record.json","paper":"/paper/1908.03884"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:04:00.019698Z","title":"Real-time monocular depth estimation using synthetic data with do- main adaptation via image style transfer","venue":null,"work_id":"b3b75037-b87b-4839-9046-8c3805674d6c","year":2018},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.108128Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:7a82495b69cecbd6e3436b2a6b425e4b702bf49a94bdf04cda8491acaec62ead","observation_id":"0f5a9be0-7488-4a8c-9b62-45394b44526c","resolution":{"observed_at":"2026-08-14T14:04:00.023720Z","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":"2026-08-14T14:04:00.008600Z","title":"Unsupervised pixel- level domain adaptation with generative adversarial net- works","venue":null,"work_id":"927a0759-223b-4c66-a1e0-8625234209db","year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.112880Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:fa3dc01f2534f24d5821c62e549aedce6fe92d23baf988b85bb4cafe3834becb","observation_id":"01d470ff-f265-45f5-b47e-51a7e0631570","resolution":{"observed_at":"2026-08-14T14:04:00.012456Z","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":"2026-08-14T14:03:59.998585Z","title":"Multitask learning","venue":null,"work_id":"d93804bd-7cb4-417a-a914-03ec35e78be1","year":1997},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.116752Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:15177408b210d454e8e5bd176394524615608ab18e3a2c96e7fe9a1935009d4b","observation_id":"956c0a5a-c6ad-4425-ab35-27f8c3767910","resolution":{"observed_at":"2026-08-14T14:04:00.002219Z","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":"2026-08-14T14:03:59.988688Z","title":"No more discrimi- nation: Cross city adaptation of road scene segmenters","venue":null,"work_id":"6616355e-2ecd-453c-b3ba-760723ebbdfe","year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.121013Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:88f93fef842716c8be512cf3df8279fd62973c82e2f7f1e522c0100768a0a1ea","observation_id":"1b278b5b-4615-45b1-be0b-d131bca4c9c0","resolution":{"observed_at":"2026-08-14T14:03:59.991984Z","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":"2026-08-14T14:03:59.124940Z","title":"The cityscapes dataset for semantic urban scene understanding","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.124940Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:10f4aa4a60504be6646a036a3be5584421f74ee2d61bcdf451959f4501b78466","observation_id":"882f78db-b678-4719-9e8a-c59fc6a6a4ef","resolution":{"observed_at":"2026-08-14T14:03:59.124940Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1702.05374","last_updated":"2017-03-30T15:42:12Z","snapshot_observed_at":"2026-08-14T21:16:00.098867Z","submitted_at":"2017-02-17T15:07:40Z","title":"Domain Adaptation for Visual Applications: A Comprehensive Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1702.05374","snapshot_observed_at":"2026-08-14T14:03:59.128724Z","title":"Domain adaptation for visual applications: A comprehensive survey","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.128724Z"},"links":{"cited_paper":"/paper/1702.05374","citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:1985a7ca853df1194a4dd010446dfc82a1e041ad8445949f5c2e6b8bf48493e2","observation_id":"193eda8f-0bb2-4f1c-b2b6-ae42be878557","resolution":{"observed_at":"2026-08-14T14:03:59.128724Z","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":"2026-08-14T14:03:59.973169Z","title":"Multi-task self- supervised visual learning","venue":null,"work_id":"3f3a539a-5954-4434-9aa2-5f37d10566db","year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.133219Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:de065cdd1a549c8e53c3c2982ad7e1876c6cb9f95100addd2edd66be839aa3d7","observation_id":"90f9d56c-b1c1-43be-a11c-75fef7d0b1d7","resolution":{"observed_at":"2026-08-14T14:03:59.976473Z","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":"2026-08-14T14:03:59.962921Z","title":"Predicting depth, surface nor- mals and semantic labels with a common multi-scale convo- lutional architecture","venue":null,"work_id":"1b59d303-b04c-40f8-9204-7bdaee856029","year":2015},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.135936Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:2e79043071d4fd67ee09bd0676046c22272bcdacfbb2661ed39c3fd1a71513ec","observation_id":"76a932db-dba8-4649-b9c1-f77862643ec0","resolution":{"observed_at":"2026-08-14T14:03:59.966461Z","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":"2026-08-14T14:03:59.951972Z","title":"Depth map prediction from a single image using a multi-scale deep net- work","venue":null,"work_id":"a3117e9d-1e4e-490b-ae13-9aa4bac8f131","year":2014},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.139537Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:3351722f8ee7cb08fc752c7a3e696f437134a9672ba6b70c4c7279beba65d53c","observation_id":"6efec788-a4eb-495a-987f-7f6ee15bfdfd","resolution":{"observed_at":"2026-08-14T14:03:59.955492Z","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":"2026-08-14T14:03:59.143252Z","title":"Unsupervised domain adaptation by backpropagation","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.143252Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:f48df68536a58901df6518edeabe795ecc426d8b3d14510a8161c74532a227a3","observation_id":"73b719b8-3013-432e-a33d-2f1f7b9bcded","resolution":{"observed_at":"2026-08-14T14:03:59.143252Z","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":"2026-08-14T14:03:59.934088Z","title":"Domain-adversarial train- ing of neural networks","venue":null,"work_id":"bf6e6e80-821f-4dba-96fa-83a2b5a4b8bd","year":2016},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.145910Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:bbb8c48efbbcb089bb8a8e10f62c5675660d89c3e13af94c71a169963560772e","observation_id":"5ecfc014-ead0-427d-8ae4-f9fbb6ee82a0","resolution":{"observed_at":"2026-08-14T14:03:59.938170Z","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":"2026-08-14T14:03:59.921795Z","title":"Bastiaan Kleijn, Mengjie Zhang, and David Balduzzi","venue":null,"work_id":"b91bf42a-bea5-40f8-a60f-e2c8d33a5d78","year":2015},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.149108Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:6fa82c64a868e60eb6356c1964ae5c52e107caf6590c0da9c2f69b2e319f6e90","observation_id":"7782b6df-d088-4864-b7d3-48a31fd8e7a7","resolution":{"observed_at":"2026-08-14T14:03:59.925575Z","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":"2026-08-14T14:03:59.911160Z","title":"Bros- tow","venue":null,"work_id":"a7085329-0e46-4361-b669-484658752fe3","year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.152335Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:62cfb73c9cd92a68f78416ae19ad0425200ad58f220790d6c5f1ea7d5165d73c","observation_id":"f9d1a494-895f-4d37-b068-f9c30231078d","resolution":{"observed_at":"2026-08-14T14:03:59.914211Z","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":"2026-08-14T14:03:59.155483Z","title":"Generative adversarial nets","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.155483Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:e7960f609a2b64865027abc42c196e082540ae81075d9476398d6227f887d966","observation_id":"a794d679-470f-4944-9263-1e0a9d17dc53","resolution":{"observed_at":"2026-08-14T14:03:59.155483Z","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":"2026-08-14T14:03:59.895344Z","title":"Gretton, AJ","venue":null,"work_id":"1a08af4e-9634-452d-855c-e049a0c4b11d","year":null},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.158519Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:66f280c71df0ccd9cf59a999b32771770e4112a7ce6869860c75bb1851bd5693","observation_id":"5e043755-b66f-4d20-90d8-e7e14441f79b","resolution":{"observed_at":"2026-08-14T14:03:59.898302Z","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":"2026-08-14T14:03:59.884295Z","title":"Heterogeneous face attribute estimation: A deep multi-task learning approach","venue":null,"work_id":"0ade76bc-93fa-4ccb-84ab-40211ffef162","year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.162781Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:697c2c5629ee453a0d95767054abe5b8be3be1fab608204fd2a443d08fd4f30c","observation_id":"c1859283-9174-4afb-8e56-ec83a2fb4674","resolution":{"observed_at":"2026-08-14T14:03:59.888144Z","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":{"arxiv_id":"1611.01587","last_updated":"2017-07-24T14:41:16Z","snapshot_observed_at":"2026-08-14T21:31:52.042451Z","submitted_at":"2016-11-05T01:59:29Z","title":"A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.01587","snapshot_observed_at":"2026-08-14T14:03:59.166289Z","title":"A joint many-task model: Growing a neural network for multiple nlp tasks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.166289Z"},"links":{"cited_paper":"/paper/1611.01587","citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:ec2e55dc93ded867a4e02ee6ceb8da1bdf1ab85fb6407e5759c1ad0c5e261db6","observation_id":"3fb3f8db-ad24-4d13-8f1d-74d8cc90f5e3","resolution":{"observed_at":"2026-08-14T14:03:59.166289Z","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":"2026-08-14T14:03:59.873661Z","title":"Distilling the knowledge in a neural network","venue":null,"work_id":"50baa39a-a0d9-42d0-bd72-5c37c1c13250","year":2014},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.170998Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:5b3905bb6f421d20338d146ea3c32ff95768f736c3cf5d2c2799d75c4c61dac1","observation_id":"40baecdd-e9db-4b91-8ff6-0a6b9317ad63","resolution":{"observed_at":"2026-08-14T14:03:59.877310Z","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":"2026-08-14T14:03:59.862230Z","title":"Cycada: Cycle-consistent adversarial domain adapta- tion","venue":null,"work_id":"e77e1aab-4ed0-49b6-846e-158307df9ee0","year":2018},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.174703Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:a9576ced62e370d20a7fe44263f79b120ba169b9b8190c32da24355124bc9e7f","observation_id":"3940561f-ac7f-4dad-ae65-cfc13ce549b8","resolution":{"observed_at":"2026-08-14T14:03:59.865740Z","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":{"arxiv_id":"1612.02649","last_updated":"2016-12-08T14:11:10Z","snapshot_observed_at":"2026-08-14T21:26:29.466258Z","submitted_at":"2016-12-08T14:11:10Z","title":"FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1612.02649","snapshot_observed_at":"2026-08-14T14:03:59.178142Z","title":"Fcns in the wild: Pixel-level adversarial and constraint-based adaptation","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.178142Z"},"links":{"cited_paper":"/paper/1612.02649","citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:348d8e6be4bd98a017e30fbef545dbd03d9ff4361b2c97cf442f86b62a570e1d","observation_id":"1b593950-7244-4f3d-8767-2653713ed5de","resolution":{"observed_at":"2026-08-14T14:03:59.178142Z","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":"2026-08-14T14:03:59.182289Z","title":"Conditional generative adversarial network for struc- tured domain adaptation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.182289Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:a391e6846b8be7f8266003f76c5df6ecfe1240fa2dd59decff63da6ba3d7cd17","observation_id":"80dbd298-1c05-4daf-b127-ab72bafc80c6","resolution":{"observed_at":"2026-08-14T14:03:59.182289Z","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":"2026-08-14T14:03:59.844862Z","title":null,"venue":null,"work_id":"a635049c-257c-45dd-b1db-d1343f81488b","year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.185372Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:7f326c15cd1a4932996d891a8e2a26b7e95be7cf77981d842dde8cc3fba98089","observation_id":"4a9dae23-053f-4fb2-a287-e6282c31d86c","resolution":{"observed_at":"2026-08-14T14:03:59.848675Z","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":"2026-08-14T14:03:59.834634Z","title":"Analyzing modu- lar cnn architectures for joint depth prediction and semantic segmentation","venue":null,"work_id":"813f379a-6c2b-433b-b096-8ed5fcd13fa5","year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.188660Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:058f2af4b81c42a5256ea45b5f8f8b2db81539b8c3789cbbbb83bc996d0ffb16","observation_id":"6bf36d0a-b1f7-4d26-9b50-e6f64c62d395","resolution":{"observed_at":"2026-08-14T14:03:59.838087Z","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":"2026-08-14T14:03:59.824778Z","title":"Multi-task learning using uncertainty to weigh losses for scene geome- try and semantics","venue":null,"work_id":"b2b08935-5823-4ef0-9c7f-eb86667a1375","year":2018},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.192384Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:5e3d12fed5dc1356043589d1ad4a7d1700e6453b152b6dc4a75a86b176399a19","observation_id":"893c8f5a-cbaa-41fb-bed0-c0f273569847","resolution":{"observed_at":"2026-08-14T14:03:59.828234Z","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":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-14T18:51:16.666127Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-14T14:03:59.195890Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.195890Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:5dae4352481c6ee000ea15fbfa674e05881a24ec5008b6e024047b953df8d45a","observation_id":"fbcb04f5-3754-470a-866d-a1c44f25cb49","resolution":{"observed_at":"2026-08-14T14:03:59.195890Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1705.07238","last_updated":"2017-12-06T00:05:17Z","snapshot_observed_at":"2026-08-14T20:59:25.297000Z","submitted_at":"2017-05-20T00:49:01Z","title":"Recurrent Scene Parsing with Perspective Understanding in the Loop","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.07238","snapshot_observed_at":"2026-08-14T14:03:59.199590Z","title":"Recurrent scene parsing with perspective understanding in the loop","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.199590Z"},"links":{"cited_paper":"/paper/1705.07238","citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:f3d9816bb7e2ec397394d93ef6c37511ea54535d07be460f508405355923fb96","observation_id":"5ad5848a-de61-4bd3-90de-a1677bc5c72d","resolution":{"observed_at":"2026-08-14T14:03:59.199590Z","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":"2026-08-14T14:03:59.814442Z","title":"Saliency unified: A deep architecture for simultaneous eye fixation prediction and salient object segmentation","venue":null,"work_id":"3a796a4e-a85b-4ab6-b14e-3996c020c47f","year":2016},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.203889Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:4449337e4c4231548c5d6d2f1904c670d836366317b274f439a11489c0d988e0","observation_id":"6ddffa48-6f39-440c-aad0-2617633d45ef","resolution":{"observed_at":"2026-08-14T14:03:59.817561Z","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":"2026-08-14T14:03:59.805410Z","title":"Unsupervised feature learning of human actions as trajectories in pose embedding manifold","venue":null,"work_id":"dc8acd2e-a36e-459c-84b7-ab4f224ec089","year":2019},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.207125Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:3499da46beba61906bf13b5f2a5c24dd82d6630a870883467a1ea46bdae740d9","observation_id":"afabff43-712f-4521-a4f3-7fcdee512663","resolution":{"observed_at":"2026-08-14T14:03:59.808765Z","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":"2026-08-14T14:03:59.795034Z","title":"Adadepth: Unsupervised content congruent adaptation for depth estimation","venue":null,"work_id":"b25e7d21-cdce-41d7-9cad-295b50cd0b8f","year":2018},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.210442Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:9a5ada82439ec32cfa81c495d44916b19994f80783f08df06a466107ab639238","observation_id":"30f609c9-2cb1-4c8a-9445-ec5ab08be0d2","resolution":{"observed_at":"2026-08-14T14:03:59.798302Z","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":"2026-08-14T14:03:59.784168Z","title":"Deeper depth prediction with fully convolutional residual networks","venue":null,"work_id":"c0767713-768c-44ef-80b8-44c6ea96383b","year":2016},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.213745Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:fa4468a8f4c9e865cd6f74356f42fa3ad36e016aaef10dbe2421d304064f2e63","observation_id":"fd2ff583-42bc-4a40-a423-1aee7b30b425","resolution":{"observed_at":"2026-08-14T14:03:59.787755Z","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":"2026-08-14T14:03:59.774321Z","title":"Refinenet: Multi-path refinement networks for high- resolution semantic segmentation","venue":null,"work_id":"f8b36b79-8c49-4b11-b06b-744c36ba7e52","year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.216852Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:4af6c0690bd3559e1533010913d2ed1eec569059bb4c279cb9bddde266467fc6","observation_id":"574fb21b-81bc-4ed5-b735-9746919d1570","resolution":{"observed_at":"2026-08-14T14:03:59.777859Z","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":"2026-08-14T14:03:59.763828Z","title":"Efficient piecewise training of deep structured models for semantic segmentation","venue":null,"work_id":"3f4e7e3c-2209-46e2-9cc7-d3b990c143fc","year":2016},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.220213Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:4ff2b5174d874fe6674151f8391666bdd4d4ca9a79f3b90be20dc5b610ae7199","observation_id":"e8c75af6-8fc4-4305-813a-94251711a4c3","resolution":{"observed_at":"2026-08-14T14:03:59.767466Z","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":"2026-08-14T14:03:59.754583Z","title":"Deep con- volutional neural fields for depth estimation from a single image","venue":null,"work_id":"ff951871-89cd-4e55-bdf6-4a49064966b3","year":2015},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.223302Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:963e32a20c0d07c17c54568aaaef475a0ad5b59acfce3cbbf3a08b97ca25a844","observation_id":"471317d3-3bb7-43a7-b7ed-1b4982ba5234","resolution":{"observed_at":"2026-08-14T14:03:59.757905Z","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":{"arxiv_id":"1803.10704","last_updated":"2019-04-05T05:57:50Z","snapshot_observed_at":"2026-08-14T19:31:26.784303Z","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":"2026-08-14T14:03:59.227022Z","title":"End- to-end multi-task learning with attention","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.227022Z"},"links":{"cited_paper":"/paper/1803.10704","citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:9e64255282aa9d82470ae39601661c8293ce5ba04eac2afc365a945e8b62838c","observation_id":"18926ff1-ab6e-4a34-a215-87ef4c5efb9e","resolution":{"observed_at":"2026-08-14T14:03:59.227022Z","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":"2026-08-14T14:03:59.743429Z","title":"Fully convolutional networks for semantic segmentation","venue":null,"work_id":"3b7aed61-537b-4d15-9c37-f11a5915c1ed","year":2015},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.231908Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:2bf609c52abdee78d81297ba124d34ac755b045d70aacec3b7f3a1bfe0ffd3ff","observation_id":"900a1d59-0854-4eb6-83dc-7a8591706ba0","resolution":{"observed_at":"2026-08-14T14:03:59.747400Z","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":"2026-08-14T14:03:59.734036Z","title":"Learning transferable features with deep adaptation net- works","venue":null,"work_id":"e0ae9c5e-1be1-4e85-bf92-e6a99c023a57","year":2015},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.235733Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:818e138f520e0da782e6f4e98bc666fb3ae13d5cfcc9283e614408fc9b80075d","observation_id":"f8c15ae6-2c5e-4e0c-b7d5-f8ba9b10096f","resolution":{"observed_at":"2026-08-14T14:03:59.737384Z","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":"2026-08-14T14:03:59.725643Z","title":"Unsupervised domain adaptation with residual trans- fer networks","venue":null,"work_id":"07bc9c38-ccac-4f93-9d01-9146298185b6","year":2016},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.239350Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:4c858fdb57bd64cee06a30933b01433e4c70aba791fa51eb31bcda10845b95bd","observation_id":"574d8f4d-444f-45bf-b437-f47a7ba70890","resolution":{"observed_at":"2026-08-14T14:03:59.728420Z","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":"2026-08-14T14:03:59.716087Z","title":"Cross-stitch networks for multi-task learning","venue":null,"work_id":"9d348eb8-e889-4af8-9f28-93fe9ad19d79","year":2016},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.243547Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:52dd6eedbc1a90affe0714b1f640625585aa3dfe5af5dc4740cedfcad453c34b","observation_id":"417a7215-09a8-40a3-899e-1546bc2749e5","resolution":{"observed_at":"2026-08-14T14:03:59.719188Z","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":"2026-08-14T14:03:59.706108Z","title":"Joint semantic segmentation and depth estimation with deep convolutional networks","venue":null,"work_id":"aaa1e043-24db-4ae2-b35b-8afe6e4273b9","year":2016},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.247007Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:c2487c987ec5febbb24712c3ac28cf6e236e1243594274efd1b603e25ae94958","observation_id":"db7cb88c-e6ed-4ade-a2c5-02c267ac1b09","resolution":{"observed_at":"2026-08-14T14:03:59.709350Z","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":"2026-08-14T14:03:59.696103Z","title":"Image to image translation for domain adaptation","venue":null,"work_id":"ab4e73f9-8cfe-4c3c-94fe-82a1ac110fdc","year":2018},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.250296Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:3cdd56c2dc23be2cf724482d12090a55a1acf61e9bc8720a62ec32b31628d0e0","observation_id":"e24be3df-9dd3-45f9-b50a-7ed9320a84e0","resolution":{"observed_at":"2026-08-14T14:03:59.699717Z","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":"2026-08-14T14:03:59.685843Z","title":"Learning features by watching ob- jects move","venue":null,"work_id":"fbd4de92-27d9-4f0b-b933-d6e7ceb463ef","year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.253932Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:9b6dff7ac363e0b6bbb29b6baf0cdc376747a9f274e0c433669842aaf684e348","observation_id":"b9e86d2d-9b4c-452b-b6a4-1286949a7aa9","resolution":{"observed_at":"2026-08-14T14:03:59.689398Z","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":"2026-08-14T14:03:59.675367Z","title":"Geonet: Geometric neural network for joint depth and surface normal estimation","venue":null,"work_id":"0b58ae49-d524-46de-8e6b-c612947ae50a","year":2018},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.257838Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:885622ddda8a27f10113d72ad5930572f8dc3c2745c565044b8ddb314318caf6","observation_id":"7200c1ac-bbd8-4692-bd2a-be52656210c6","resolution":{"observed_at":"2026-08-14T14:03:59.679113Z","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":"2026-08-14T14:03:59.664027Z","title":"Hy- perface: A deep multi-task learning framework for face de- tection, landmark localization, pose estimation, and gender recognition","venue":null,"work_id":"41e9d54c-ae02-4e02-8b2b-cf9fc95c8ec0","year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.261655Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:95ae694fc38d88fdc0dd6fb69a107b914202ddd15dcda2f549b251898cdba1c6","observation_id":"aa4ef38c-6f74-4d5f-ad44-ce8a33b46be2","resolution":{"observed_at":"2026-08-14T14:03:59.667509Z","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":"2026-08-14T14:03:59.652940Z","title":"Faster r-cnn: Towards real-time object detection with region proposal networks","venue":null,"work_id":"ac6e5385-7f85-44d2-9be2-9ff3e0ac0cc9","year":2015},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.265156Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:0f2432f044cfe4bda4cc43aeab9556bd138076268fff8624a6bfcd207c5dfada","observation_id":"ccb05152-23ab-47e0-a1bc-173f106d0d8c","resolution":{"observed_at":"2026-08-14T14:03:59.656235Z","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":"2026-08-14T14:03:59.643316Z","title":"Cross-domain self- supervised multi-task feature learning using synthetic im- agery","venue":null,"work_id":"05d1d8f4-40ca-4a6a-8be8-bc51f2e99c35","year":2018},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.268709Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:b83079bd9371da389f20fce347cf18197e83f646726bf853a02e241297e1b922","observation_id":"8bee40b3-70d3-4b6f-9070-d63d55c828c9","resolution":{"observed_at":"2026-08-14T14:03:59.646676Z","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":"2026-08-14T14:03:59.633137Z","title":"Playing for data: Ground truth from computer games","venue":null,"work_id":"d4cb8bb2-071e-4d42-9e18-31f3330c7f8a","year":2016},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.272665Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:9a4179d28488b8f9ed835179b848816e400d06d31c2c643db0b88cd8f02290ac","observation_id":"66e7fc1b-066f-44a7-ad19-9c65cff8b4b4","resolution":{"observed_at":"2026-08-14T14:03:59.636388Z","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":"2026-08-14T14:03:59.622845Z","title":"Monocular depth esti- mation using neural regression forest","venue":null,"work_id":"38b73604-870e-46f8-87f1-5cbd0d4b577a","year":2016},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.275564Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:01bad551ef1062f645f8a6c46cb2592976f4c543c24dbe9b82617675eaefbabe","observation_id":"90ebf9ea-c2ef-4a45-8d84-4ed39b45f75c","resolution":{"observed_at":"2026-08-14T14:03:59.626099Z","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":"2026-08-14T14:03:59.611919Z","title":"Imagenet large scale visual recognition challenge","venue":null,"work_id":"05c82e44-1067-4820-ac10-5a75c994c939","year":2015},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.279328Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:0fd3877c35f1857097478eb3dfb1a52abd9950c454cf5f3b24912b5fec125919","observation_id":"866753d8-2259-494d-94d5-19521fdea0ca","resolution":{"observed_at":"2026-08-14T14:03:59.615311Z","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":"2026-08-14T14:03:59.602535Z","title":"Improved techniques for training gans","venue":null,"work_id":"239a6b0d-435a-4649-b8dd-f22bcbf7bed2","year":2016},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.283085Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:2dae5a1f69b589a54a562f4798603d413aac40b1e46083df4e73162717855553","observation_id":"dd7252e3-9077-43a9-a10c-059bdce88d85","resolution":{"observed_at":"2026-08-14T14:03:59.605811Z","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":"2026-08-14T14:03:59.592217Z","title":"Learning from synthetic data: Addressing domain shift for semantic segmentation","venue":null,"work_id":"9817ee0c-34c2-4964-95cc-f6ac05a7ab21","year":2018},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.286701Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:07604d7fa55d33c03ed460f138b3c3900aa5ad307b5deadf7d014d861baf8175","observation_id":"1dd2d662-dd53-4296-b436-364b04f6b2f4","resolution":{"observed_at":"2026-08-14T14:03:59.595727Z","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":"2026-08-14T14:03:59.581446Z","title":"Make3d: Learning 3d scene structure from a single still image","venue":null,"work_id":"c85fccde-26d2-465d-9403-cb1b1cc0122b","year":2009},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.290806Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:8da04026adb6b0606b016954e68b80fa5245dce278a7a8fd2d51e3d60bafb43f","observation_id":"8d8f994a-290f-4d69-9903-6c1ea4b47efa","resolution":{"observed_at":"2026-08-14T14:03:59.584792Z","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":"2026-08-14T14:03:59.571288Z","title":"Indoor segmentation and support inference from rgbd images","venue":null,"work_id":"6e04d732-2ba2-4a48-83ed-de0082c3f457","year":2012},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.294294Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:4a63ba38433077f60cc05b2b82b43e00e195e6f4675c12892655a9b7cfc8d8aa","observation_id":"eb718ca8-0674-468e-8787-86510e5b5b6e","resolution":{"observed_at":"2026-08-14T14:03:59.574674Z","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":"2026-08-14T14:03:59.298154Z","title":"Deep coral: Correlation alignment for deep domain adaptation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.298154Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:e02a3ea15e162f4b0dde5ad75b614bc02ecd480e30f3dabeba054e79b6a3189e","observation_id":"3ac025c7-ad39-43c7-baff-5b3f3d920f82","resolution":{"observed_at":"2026-08-14T14:03:59.298154Z","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":"2026-08-14T14:03:59.555608Z","title":"Tsai, W.-C","venue":null,"work_id":"3c313a44-65f9-493a-8555-6b0fe20e9921","year":2018},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.302403Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:bf37c12a242ecb60298bc09c30e87107bfbb64023556b5afddb5f1eef831cc15","observation_id":"cbbaf1df-dad0-4631-a42d-a520fa42e615","resolution":{"observed_at":"2026-08-14T14:03:59.558782Z","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":"2026-08-14T14:03:59.545984Z","title":"Simultaneous deep transfer across domains and tasks","venue":null,"work_id":"47d34138-0ea1-47ba-995d-b6532ce34f81","year":2015},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.305414Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:0bb8b838d482ef67261dba11e8280242c4f1769ed53acd373a34ab36f0a36dc1","observation_id":"1d5c1b1a-53ea-4314-a313-efeb0f15d6d4","resolution":{"observed_at":"2026-08-14T14:03:59.549325Z","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":"2026-08-14T14:03:59.535461Z","title":"Adversarial discriminative domain adaptation","venue":null,"work_id":"8c9e9625-f63d-420b-910b-cb5c233054d1","year":null},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.308695Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:25f6ebe10086f85afcfccaa813a9570c4a899e8d293d73cc97cf9b3140ee9820","observation_id":"a27a9f9b-3848-4c4a-b692-cefab0dc4416","resolution":{"observed_at":"2026-08-14T14:03:59.539477Z","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":{"arxiv_id":"1412.3474","last_updated":"2014-12-10T21:20:54Z","snapshot_observed_at":"2026-08-14T23:08:06.157493Z","submitted_at":"2014-12-10T21:20:54Z","title":"Deep Domain Confusion: Maximizing for Domain Invariance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.3474","snapshot_observed_at":"2026-08-14T14:03:59.312822Z","title":"Deep domain confusion: Maximizing for domain invariance","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.312822Z"},"links":{"cited_paper":"/paper/1412.3474","citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:08c0fc4eb814f6dca4c3f8d88add3dc70f22841b1090cad19366f6cc65c2c6ca","observation_id":"bc3fc5eb-eee6-4573-a9b5-6944722ffaef","resolution":{"observed_at":"2026-08-14T14:03:59.312822Z","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":"2026-08-14T14:03:59.525651Z","title":"Towards unified depth and seman- tic prediction from a single image","venue":null,"work_id":"0cadf633-6896-439d-82bb-f2063e5d08b0","year":2015},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.316235Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:8ce46670ac5fc08f6c6720bde6360005ce457299422a6e4c1b5dcf71b5842075","observation_id":"8ff0a676-1473-4d84-9ceb-efb461ad69f1","resolution":{"observed_at":"2026-08-14T14:03:59.528935Z","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":"2026-08-14T14:03:59.515568Z","title":"Design- ing deep networks for surface normal estimation","venue":null,"work_id":"4d0dc9d1-ddf6-4c87-a0a9-1a9e45a426ee","year":null},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.319238Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:4f23af1e89a39f2413f9903126fd5ed0006fbce56f23251a8d9e95d4bc25a376","observation_id":"e1f17ccc-5c15-4f67-9f19-04feb146c44b","resolution":{"observed_at":"2026-08-14T14:03:59.519005Z","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":"2026-08-14T14:03:59.505003Z","title":"Holistically-nested edge detection","venue":null,"work_id":"c96519d2-3aed-4e61-99b0-0631d492b678","year":2015},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.323559Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:8716c3000d6cfce63bda362e2894829b5f2ef4bb291c854c001ca33b0a44702f","observation_id":"9aee02a3-2b3b-4241-ac28-cee5b9010593","resolution":{"observed_at":"2026-08-14T14:03:59.508032Z","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":"2026-08-14T14:03:59.493542Z","title":"Describing the scene as a whole: Joint object detection, scene classification and semantic segmentation","venue":null,"work_id":"67e74edc-2d24-4d62-970f-ff841cdf1ecb","year":2012},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.326558Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:bbbaf6cb5f36fd74e97fb4dcab2ac009ea8e25c5a81931c3c76fbb189f24d975","observation_id":"a9b8e8d8-8c31-4b70-90a5-cc21d5121a6f","resolution":{"observed_at":"2026-08-14T14:03:59.497352Z","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":"2026-08-14T14:03:59.483430Z","title":"Curricu- lum domain adaptation for semantic segmentation of urban scenes","venue":null,"work_id":"a2e3dc75-4085-4090-a972-a5ccb9e649a9","year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.330204Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:03a2916b6e4a036d31e906fb809bddc4bd1cd855cc18dc6cc159376f9a659a7f","observation_id":"3626fb3e-7509-48ef-a97e-ea8cd23a3b64","resolution":{"observed_at":"2026-08-14T14:03:59.486618Z","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":"2026-08-14T14:03:59.472520Z","title":"Physically-based rendering for indoor scene understanding using convolutional neural networks","venue":null,"work_id":"a40ac90d-e037-45bf-b1a3-b25598d95262","year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.333674Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:78200ea5ee4c3b2e7eb7ef0b254a52338236799f328daf4d07329fef0a8b6fdc","observation_id":"6f47f890-a75e-403f-be12-d21b3c7550ba","resolution":{"observed_at":"2026-08-14T14:03:59.476146Z","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":"2026-08-14T14:03:59.461696Z","title":"Energy- based generative adversarial network","venue":null,"work_id":"e283d1af-77a2-4c16-b744-7fb1662ecca0","year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.336244Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:1b6fb658610d107cb751f3701a6ccbf0e0009f3dc2916003bca50d2e9e13d9f4","observation_id":"9f50cc5a-372d-416e-a456-13004917e4ab","resolution":{"observed_at":"2026-08-14T14:03:59.465216Z","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":"2026-08-14T14:03:59.450286Z","title":"Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks","venue":null,"work_id":"50f722bf-393b-45dd-8f93-47e80e96ac07","year":2018},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.339891Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:19ccf3e5bc7218dddadb21b553df4d9886fd1cbe819e3ccc3f7c68fe8a11829f","observation_id":"b4ce2321-2b23-4c4a-aa52-6d01b65d4fc7","resolution":{"observed_at":"2026-08-14T14:03:59.453831Z","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":"2026-08-14T14:03:59.437115Z","title":"Unsupervised learning of depth and ego-motion from video","venue":null,"work_id":"f438da67-0fb3-48dc-8eb1-ae3ee78fd5ce","year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.343261Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:e4fbb6da3218158dbf0e4ccdd50869deed0461c12ff9911917ba71d4adaa4a80","observation_id":"df5333ef-8059-415e-9fe7-692b07bac571","resolution":{"observed_at":"2026-08-14T14:03:59.442762Z","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":"2026-08-14T14:03:59.346316Z","title":"Unpaired image-to-image translation using cycle- consistent adversarial networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-14T14:03:59.346316Z"},"links":{"citing_paper":"/paper/1908.03884"},"observation_digest":"sha256:e4648cf35ce6da49e2e131d7810b49cda2cc060465be644f8fe577d89be2fcd2","observation_id":"bbc7ec7d-8ba9-4414-9329-a2532499cb66","resolution":{"observed_at":"2026-08-14T14:03:59.346316Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"1908.03884","last_updated":"2019-09-16T12:03:44Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T13:57:03.000682Z","submitted_at":"2019-08-11T10:52:07Z","title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation"},"reference_resolution":{"displayed":67,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":53},"total_outbound_references":67},"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 67 of 67 outbound references and 0 inbound Pith citation observations for arXiv:1908.03884."}