{"as_of":"2026-08-13T05:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a436d7e4bcc382e7690f57ab5d9d861887ba4d4df99da95ce91b67c936865edf","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T11:06:09.023142Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-14T06:34:55.089754Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-10T14:15:29.234678Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"cited_work":{"arxiv_id":"2411.18615","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.18615","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2411.18615 (2024) 42","venue":null,"work_id":"e7291489-400d-49c2-829c-efc58cc093ee","year":2024},"citing_paper":{"arxiv_id":"2604.13560","last_updated":"2026-04-15T07:09:05Z","snapshot_observed_at":"2026-08-10T02:24:00.629993Z","submitted_at":"2026-04-15T07:09:05Z","title":"Parameter-efficient Quantum Multi-task Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-10T14:13:39.288961Z"},"links":{"cited_paper":"/paper/2411.18615","citing_paper":"/paper/2604.13560"},"observation_digest":"sha256:c1c1687ee34deafec7b55bbf363cd57433c883cf7b84adc0bde6b1c937d9f4b0","observation_id":"56c69f23-8f3f-4e4c-9209-7964d708943f","resolution":{"observed_at":"2026-05-10T14:15:29.236706Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"cited_work":{"arxiv_id":"2411.18615","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.18615","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2411.18615 (2024) 42","venue":null,"work_id":"e7291489-400d-49c2-829c-efc58cc093ee","year":2024},"citing_paper":{"arxiv_id":"2604.17257","last_updated":"2026-04-21T06:47:04Z","snapshot_observed_at":"2026-08-11T09:18:25.699659Z","submitted_at":"2026-04-19T04:41:55Z","title":"REZE: Representation Regularization for Domain-adaptive Text Embedding Pre-finetuning","version":2},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-05-10T06:14:28.893342Z"},"links":{"cited_paper":"/paper/2411.18615","citing_paper":"/paper/2604.17257"},"observation_digest":"sha256:0b5502de298dcfa4c9ffb824be29f9ae0b14ce1e3e892bf6112d3511412cd12d","observation_id":"7ad50e89-7695-4a26-a9ff-bfc608672555","resolution":{"observed_at":"2026-05-10T06:16:20.959995Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.18615","snapshot_observed_at":"2026-07-14T06:34:55.089754Z","title":"Proactive gradient conflict mitigation in multi-task learning: A sparse training perspective,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.11163","last_updated":"2026-07-13T06:57:02Z","snapshot_observed_at":"2026-08-02T05:26:21.947350Z","submitted_at":"2026-07-13T06:57:02Z","title":"Unified Gradient Projection: Language-Balanced Continual Learning for Multilingual Low-Resource ASR","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-14T06:34:55.089754Z"},"links":{"cited_paper":"/paper/2411.18615","citing_paper":"/paper/2607.11163"},"observation_digest":"sha256:56623bb2a7b38c93d8faa7e0a3c380c7d8f0ee16d15ab3a97adadeed4910176e","observation_id":"7934230b-ffc6-434f-8d8c-9cdc099920b0","resolution":{"observed_at":"2026-07-14T06:34:55.089754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2411.18615/citation-record","integrity":"/paper/2411.18615/integrity","json":"/paper/2411.18615/citation-record.json","paper":"/paper/2411.18615"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T11:06:09.343307Z","title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","venue":null,"work_id":"2f1c6988-f12b-4bf6-be0a-a65621771ff0","year":2017},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.916564Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:c10851042f96b7c14bea3b5e30c2167e8e697e9ca21cebce94162bea18840db3","observation_id":"293aaaa3-c32a-4caa-ae8c-8b8a11fff76a","resolution":{"observed_at":"2026-08-12T11:06:09.346020Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:09.336165Z","title":"Sparse multi-task reinforcement learning","venue":null,"work_id":"30db313c-76c2-483a-bff2-3c73f6082db4","year":2014},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.920391Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:d079430e33e7ccad54c051e569349950c934342da2d15e259b109e420e27e17b","observation_id":"ed0e6c8b-2749-49c0-a754-281a5d64d6e4","resolution":{"observed_at":"2026-08-12T11:06:09.338753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:09.328439Z","title":"Sam fails to segment anything? – sam- adapter: Adapting sam in underperformed scenes: Camou- flage, shadow, and more, 2023","venue":null,"work_id":"4e9f3a8c-c941-4ec5-94d4-1d3502c136fb","year":2023},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.923161Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:cb2b9c9ddffe0d350d424b27dad6031ba6625ab052fe3b54e1ddaa9db2dd2971","observation_id":"342ed0c3-9247-4d99-b9f9-661ba6d96b59","resolution":{"observed_at":"2026-08-12T11:06:09.331697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:09.320389Z","title":"Just pick a sign: Optimizing deep multitask models with gra- dient sign dropout","venue":null,"work_id":"720bc462-7709-496a-aa7c-f43f536eef26","year":2020},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.925822Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:9cebabca19e1da745aa356758becde2766a461566daa728af17cd1b3e7f167a6","observation_id":"9e269cd5-a0d9-4418-874c-0c57594c95c5","resolution":{"observed_at":"2026-08-12T11:06:09.323190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:08.928598Z","title":"The cityscapes dataset for semantic urban scene understanding","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.928598Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:e23d883c562328476ee11f4548a467976c3988e29e1eda961204db8c74fb3175","observation_id":"e5d3a967-e3d4-4cd4-8415-ca5c459cc05f","resolution":{"observed_at":"2026-08-12T11:06:08.928598Z","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":"2026-08-12T11:06:09.307477Z","title":"Indoor semantic segmentation using depth in- formation, 2013","venue":null,"work_id":"c54fa7ad-011d-4487-addf-632c3bcadef3","year":2013},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.931478Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:0c99433280b506ca7121664009dff41a95c270ea57c3f740ba0f0e9120c5a1df","observation_id":"63a10601-9a4f-4992-bd7b-75afc00ee6c4","resolution":{"observed_at":"2026-08-12T11:06:09.311046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:09.299033Z","title":"Imagenet: A large-scale hierarchical im- age database","venue":null,"work_id":"ba1067cd-798c-4b65-8233-4e1f34421815","year":2009},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.934566Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:a777aab52b0b4fb391070963e99d13484ec5d586a1ff0fe913177752df32587a","observation_id":"537e07c1-47da-4bb3-923d-b92757493df8","resolution":{"observed_at":"2026-08-12T11:06:09.302230Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-13T02:40:23.887636Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-12T11:06:08.937239Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.937239Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:f90765eb39cd34217988a4c33779b3726ac9033671b3e30007432e91b7ed8a58","observation_id":"e833b021-5560-4e4d-88e4-735ca7b39cc5","resolution":{"observed_at":"2026-08-12T11:06:08.937239Z","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":"2026-08-12T11:06:09.290671Z","title":"On interpretability of artificial neural networks: A survey","venue":null,"work_id":"1499b457-7df1-4d5e-ad47-ca049eec5685","year":2020},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.940255Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:bcbf4f2726a241c65fa0b1b9af56e5d0be462c9a7dbe73c075f4d5ee64c7839b","observation_id":"c0650d54-1ccd-42d3-87de-6ec3e61f21f4","resolution":{"observed_at":"2026-08-12T11:06:09.293860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1803.03635","last_updated":"2019-03-04T15:51:11Z","snapshot_observed_at":"2026-08-05T23:54:27.386622Z","submitted_at":"2018-03-09T18:51:28Z","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.03635","snapshot_observed_at":"2026-08-12T11:06:08.943008Z","title":"The lottery ticket hy- pothesis: Finding sparse, trainable neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.943008Z"},"links":{"cited_paper":"/paper/1803.03635","citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:ed4c853205214669faf6e96442a66e6d554f449fcebda8b0d13f16cd555f881c","observation_id":"76a03b92-5b83-430f-8d16-9d261104fd57","resolution":{"observed_at":"2026-08-12T11:06:08.943008Z","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":"2026-08-12T11:06:08.945960Z","title":"On the effectiveness of parameter-efficient fine-tuning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.945960Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:b9194cffdcabb363969a53c0977d7fea38d40c08809c52519846f4e4b31ff2fa","observation_id":"f18fc1aa-a899-4ad0-b6af-7fb9b365f283","resolution":{"observed_at":"2026-08-12T11:06:08.945960Z","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":"2026-08-12T11:06:08.949271Z","title":"Learn- ing to branch for multi-task learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.949271Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:bc985cb7dd95b9d3d76722899cce61ff0fedb61154e5c484d274a014e59990d9","observation_id":"e84766de-a6c3-4a1c-8290-751d4c4bbbda","resolution":{"observed_at":"2026-08-12T11:06:08.949271Z","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":"2026-08-12T11:06:09.275557Z","title":"Learn- ing both weights and connections for efficient neural net- work","venue":null,"work_id":"f20b8596-3c9c-4aa0-893c-7d7498063ace","year":2015},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.952346Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:4046ced332f13aebd1fa7a7f77da3ead7115fa888c8000cf63550bf6b0d81103","observation_id":"3d08b2a1-de3a-4883-a7dd-e121b9d56582","resolution":{"observed_at":"2026-08-12T11:06:09.278329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:08.955002Z","title":"Multi-task learning using uncertainty to weigh losses for scene geome- try and semantics","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.955002Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:ae730b9faa52d257fb8734da10a55acb74455caa945de888208bf12e34b891cd","observation_id":"934774f6-5d2f-4b49-9eec-523940a6fa30","resolution":{"observed_at":"2026-08-12T11:06:08.955002Z","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":"2026-08-12T11:06:08.957997Z","title":"Segment any- thing","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.957997Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:a14d6bcd76da46205d571cc6421540f9986984937725cccbfc636eac9d3cdcd7","observation_id":"8ee95ccb-df8e-4970-870b-30857eddb52a","resolution":{"observed_at":"2026-08-12T11:06:08.957997Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.04838","last_updated":"2021-09-10T12:46:32Z","snapshot_observed_at":"2026-08-10T23:35:07.182089Z","submitted_at":"2021-09-10T12:46:32Z","title":"Block Pruning For Faster Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.04838","snapshot_observed_at":"2026-08-12T11:06:08.960534Z","title":"Block pruning for faster transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.960534Z"},"links":{"cited_paper":"/paper/2109.04838","citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:9e319ffaf38957ccbf77423a76f45a2559eeeaed95c3f721ebe8debca3fadc65","observation_id":"4d3bca07-8ad6-457f-9959-00a481216acc","resolution":{"observed_at":"2026-08-12T11:06:08.960534Z","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":"2026-08-12T11:06:09.258118Z","title":"Conflict-averse gradient descent for multi-task learn- ing","venue":null,"work_id":"01150a8a-97e2-4c0b-9b95-76ad4ded9a8b","year":2021},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.963308Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:4b7a07063e789e8c8bbaff78e52870154897f42de22eea37f6b3883071e375c7","observation_id":"0bffadae-1918-4ee6-9f4c-dd3fbe987376","resolution":{"observed_at":"2026-08-12T11:06:09.261263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:09.249196Z","title":"Famo: Fast adaptive multitask optimization, 2023","venue":null,"work_id":"c68916ca-8840-4ad1-9959-de959a2073c5","year":2023},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.965715Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:74e5c7b1c2ac4f969d8b5e8cc14f074d200cd3535a1724d7441977363aa4fcdd","observation_id":"7d01e526-b8f8-42a3-ad6f-40e8caead4d4","resolution":{"observed_at":"2026-08-12T11:06:09.252488Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:09.240244Z","title":"Towards impartial multi-task learning","venue":null,"work_id":"abca05f0-8e4d-4c3a-95a4-0a8320163739","year":2021},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.968457Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:a9f1629996562beae567e724508dcda385dd59667cfc9da9db369b6f23c18938","observation_id":"67d4af19-60ce-4753-9508-2602a8e1278c","resolution":{"observed_at":"2026-08-12T11:06:09.243061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:09.231572Z","title":"End- to-end multi-task learning with attention","venue":null,"work_id":"b18c9608-6e13-4e0a-aa8d-e860c5ea3e48","year":2019},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.970858Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:a9297f926f7df214d3c811851831ab3a45770bc2973bf2e45cb8848f1a3434e6","observation_id":"322945b6-fab6-4acf-a699-ae5fbb5f7cba","resolution":{"observed_at":"2026-08-12T11:06:09.235160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:08.973303Z","title":"Deep learning face attributes in the wild","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.973303Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:9c048ddbb40371727b64039c4cf1984f5aa5fe04653462fd2056200a7a20a0b2","observation_id":"96cd3366-1cfa-406e-ac5a-a11a980fc945","resolution":{"observed_at":"2026-08-12T11:06:08.973303Z","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":"2026-08-12T11:06:09.217319Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":"8ef5a0b8-8a2e-455f-aa9d-2384d51d86fe","year":2021},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.975739Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:5d9295094da074ad49f6a4cba168b9769b29a1c76acb10f4d9328aa956656bc3","observation_id":"7621df7c-b601-4902-8448-24aa303ee30f","resolution":{"observed_at":"2026-08-12T11:06:09.221220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:09.208568Z","title":"Attentive single-tasking of multiple tasks","venue":null,"work_id":"2cc1d576-a838-4268-9330-b9aac88a1bf1","year":2019},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.978159Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:d84e6fde66e68a0bad5052cf3f20e4e9da8680f89b43b32a069e83e23b511ec9","observation_id":"664ab58e-c6a3-447b-9c98-38d3b04d703b","resolution":{"observed_at":"2026-08-12T11:06:09.211935Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:09.200276Z","title":"Cross-stitch networks for multi-task learning","venue":null,"work_id":"06456ed6-937d-4790-8dbf-780c6be7619f","year":2016},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.980533Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:a88794fffdb7720570fdde4b180f5b6858097013c422c163998037a8273fdc00","observation_id":"ff7d9a49-a812-46d6-8ab2-d67a2df7be77","resolution":{"observed_at":"2026-08-12T11:06:09.203403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:09.191062Z","title":"Parameter efficient train- ing of deep convolutional neural networks by dynamic sparse reparameterization","venue":null,"work_id":"12e3bf71-42d0-4502-bc48-99faa29ce6aa","year":2019},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.983116Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:e69df4b5ca9fb5fe9a4928a37f53814a7398d676059020bae46b60b8ddabde88","observation_id":"852c5bd6-2f88-498b-8e2d-d5f02d2ea999","resolution":{"observed_at":"2026-08-12T11:06:09.194003Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:09.183135Z","title":"Multi- task learning as a bargaining game, 2022","venue":null,"work_id":"a650f01a-83dd-4427-aa68-344707f2821f","year":2022},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.985487Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:056ec65cfc1798079acdbc252496bc6e21036c3e97cd418f557c6ea60d6df371","observation_id":"16df5d8e-c638-4bac-9aad-d2b344629ab8","resolution":{"observed_at":"2026-08-12T11:06:09.186015Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:09.174648Z","title":"Movement pruning: Adaptive sparsity by fine-tuning","venue":null,"work_id":"db48e676-b0c3-4784-8bfc-971a46f484cf","year":2020},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.987912Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:d1d30a9e90d2675d3a45cbed8836954a7f1f08c680408d310ca034be5e4e700a","observation_id":"060eb3b6-a794-4db9-bb20-c429f7e9f16d","resolution":{"observed_at":"2026-08-12T11:06:09.177651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:09.165534Z","title":"Multi-task learning as multi-objective optimization","venue":null,"work_id":"4ceab743-bf05-4e88-b54b-5b6b75f1a9e4","year":2018},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.990642Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:8e67daf092ff5d756bc40156e7f28fcc40cf67563604c5c3c4b58c0156bc772e","observation_id":"251838c5-8ad6-428f-8ac1-b18df44a9ef5","resolution":{"observed_at":"2026-08-12T11:06:09.168744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.11289","last_updated":"2023-02-22T11:14:16Z","snapshot_observed_at":"2026-08-08T17:16:39.405514Z","submitted_at":"2023-02-22T11:14:16Z","title":"Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.11289","snapshot_observed_at":"2026-08-12T11:06:08.993379Z","title":"Recon: Reducing conflicting gradi- ents from the root for multi-task learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.993379Z"},"links":{"cited_paper":"/paper/2302.11289","citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:b7e51f67159a55ba82c8f5227c54b75f3e6eadf95253209529f32b11b1d3bb55","observation_id":"b4c87c19-dd74-40a7-81a6-467a9f7c8980","resolution":{"observed_at":"2026-08-12T11:06:08.993379Z","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":"2026-08-12T11:06:09.156254Z","title":"Learning sparse sharing architectures for multiple tasks","venue":null,"work_id":"e00e76ba-fc40-4670-854d-9f6e27b6d3d2","year":2020},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.996366Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:bdb6db8c6bae0c3ddcc414502a2bc97a1d25f08b985f2409309921ea28d19bd9","observation_id":"16b64028-2e64-4f45-8f13-aa6f846bcb56","resolution":{"observed_at":"2026-08-12T11:06:09.159680Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:08.999074Z","title":"Multi-task learning for dense prediction tasks: A survey","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:08.999074Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:1f737ab3d180e20f25223227b4a5e56421218f09c4e51c03a5b7cb2a184291b2","observation_id":"aa76ab45-a0a0-46c5-9756-0cdb40b7937d","resolution":{"observed_at":"2026-08-12T11:06:08.999074Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.14509","last_updated":"2022-03-04T18:14:27Z","snapshot_observed_at":"2026-07-06T11:52:39.902598Z","submitted_at":"2021-09-29T15:44:26Z","title":"PAC-Bayes Information Bottleneck","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.14509","snapshot_observed_at":"2026-08-12T11:06:09.001625Z","title":"Pac-bayes information bottleneck","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:09.001625Z"},"links":{"cited_paper":"/paper/2109.14509","citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:7c4bc04909f42eb005b246ece841783b2ee47b504fdf1e5915bba63b1a16287c","observation_id":"3917a510-ef47-4ad5-a86d-b4c719afb59f","resolution":{"observed_at":"2026-08-12T11:06:09.001625Z","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":"2026-08-12T11:06:09.142177Z","title":"Pad-net: Multi-tasks guided prediction-and-distillation net- work for simultaneous depth estimation and scene parsing","venue":null,"work_id":"832f03d9-8a00-4ea6-889a-9a6396c5c513","year":2018},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:09.004464Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:c5a719132828231ce2239e21a2f287e9bef3e0ab50b732765d7f6545db86a72c","observation_id":"52292be9-3762-46a9-8091-b9cd093dc10f","resolution":{"observed_at":"2026-08-12T11:06:09.145114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.05687","last_updated":"2021-09-13T03:39:52Z","snapshot_observed_at":"2026-08-05T01:06:28.807438Z","submitted_at":"2021-09-13T03:39:52Z","title":"Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.05687","snapshot_observed_at":"2026-08-12T11:06:09.006926Z","title":"Raise a child in large language model: Towards effective and generalizable fine-tuning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:09.006926Z"},"links":{"cited_paper":"/paper/2109.05687","citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:86328642282ab41c66ff2e48798de8d1c6fe4cd48d2dd6fed808302bac5f843f","observation_id":"b1412fd6-421e-4df1-853c-aa690408d661","resolution":{"observed_at":"2026-08-12T11:06:09.006926Z","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":"2026-08-12T11:06:09.133884Z","title":"Gradient surgery for multi-task learning","venue":null,"work_id":"0be04916-a351-4504-93f5-0b6a0daef42d","year":2020},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:09.009977Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:409c3bbf269a618ae514d8b4805b6ea7070d7f0f53250b49aa1510c2bb452e4a","observation_id":"229bfbcd-9d35-4079-ac96-05320bc55e18","resolution":{"observed_at":"2026-08-12T11:06:09.137122Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.04867","last_updated":"2020-02-21T13:36:15Z","snapshot_observed_at":"2026-08-09T06:48:42.729935Z","submitted_at":"2019-10-01T17:06:29Z","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.04867","snapshot_observed_at":"2026-08-12T11:06:09.012657Z","title":"A large-scale study of representation learning with the visual task adaptation benchmark","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:09.012657Z"},"links":{"cited_paper":"/paper/1910.04867","citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:16232eb83ab45e66a1c0061cae858387ce13aa42278be187af52523f2e0a8f94","observation_id":"5f85dab9-6d0c-439f-a9ca-fd9bee716163","resolution":{"observed_at":"2026-08-12T11:06:09.012657Z","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":"2026-08-12T11:06:09.124997Z","title":"A survey on multi-task learning","venue":null,"work_id":"fc02f82e-ee10-407c-9384-80cc8655464b","year":2021},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:09.015298Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:41bef2ed615fdbf206bcca73f0d771b3fcc18688d57302783c0a59d76fee69b9","observation_id":"fd272273-1c0c-4526-bc54-5e085b9dcd70","resolution":{"observed_at":"2026-08-12T11:06:09.128010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:09.115772Z","title":"Joint task-recursive learning for semantic segmentation and depth estimation","venue":null,"work_id":"fd446dab-942d-4dc8-83e7-d5c56732f274","year":2018},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:09.018115Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:b57f265801560d15cccfcb6bea2b9d31d3812172646faacdc0493a9e6d59e2cb","observation_id":"f51cabe0-20ac-4e7a-bac0-e18eff2315c3","resolution":{"observed_at":"2026-08-12T11:06:09.119327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-12T11:06:09.105095Z","title":"Pattern-affinitive propagation across depth, surface normal and semantic segmentation","venue":null,"work_id":"ec806161-3bcd-4772-9dba-35d7fcf9a156","year":2019},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:09.020647Z"},"links":{"citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:ddff4afa245c9d0fc9c1b86206366d72ef58da8d03daaf99d269e60a9d6d1af3","observation_id":"b217b1f7-aaec-4c7c-a885-42ed73691068","resolution":{"observed_at":"2026-08-12T11:06:09.109763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.10136","last_updated":"2024-06-11T22:45:49Z","snapshot_observed_at":"2026-08-13T05:00:43.204753Z","submitted_at":"2023-12-15T18:59:05Z","title":"Gradient-based Parameter Selection for Efficient Fine-Tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.10136","snapshot_observed_at":"2026-08-12T11:06:09.023142Z","title":"Gradient- based parameter selection for efficient fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T11:06:09.023142Z"},"links":{"cited_paper":"/paper/2312.10136","citing_paper":"/paper/2411.18615"},"observation_digest":"sha256:e43e2ecd6be581b2d22b491db6013daa1dd62890c05e0f7a13bd0242d65c75ba","observation_id":"04a4403c-ac7a-4b23-abcd-0acd4517857d","resolution":{"observed_at":"2026-08-12T11:06:09.023142Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.18615","last_updated":"2024-11-27T18:58:22Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T16:55:42.227012Z","submitted_at":"2024-11-27T18:58:22Z","title":"Proactive Gradient Conflict Mitigation in Multi-Task Learning: A Sparse Training Perspective"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":25},"total_outbound_references":40},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 3 inbound Pith citation observations for arXiv:2411.18615."}