{"as_of":"2026-08-17T18:13:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6af70b0bc81b7165b4ebd643c81870d89a2603f138fcbeb7e57260bcf73f7376","coverage":[{"denominator":15,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":15,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T15:55:32.890575Z","state":"measured"},{"denominator":15,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":15,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2509.16959/citation-record","integrity":"/paper/2509.16959/integrity","json":"/paper/2509.16959/citation-record.json","paper":"/paper/2509.16959"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:55:33.160506Z","title":null,"venue":null,"work_id":"61193cf0-4ec3-4cc8-ae88-a512dbb6c729","year":null},"citing_paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning","version":5},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T15:55:32.857945Z"},"links":{"citing_paper":"/paper/2509.16959"},"observation_digest":"sha256:8d08d53f2b231a95777979cee53752e453ee43903323bb3ec2acdeecb76e781b","observation_id":"e3eccb46-bc71-4861-ab24-8446894fa94c","resolution":{"observed_at":"2026-08-15T15:55:33.163807Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:55:33.149220Z","title":"This maintains consistent training dynamics across tasks","venue":null,"work_id":"edf885c3-1957-4d50-91b1-2a092eccbe84","year":2018},"citing_paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning","version":5},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T15:55:32.861679Z"},"links":{"citing_paper":"/paper/2509.16959"},"observation_digest":"sha256:cb8ec9eb5e1b878ad9a54a3f869db36999ffd9a15165a22560b32b1633e94be4","observation_id":"693c02af-a86d-4c0e-8e21-5f4d5f1f61d0","resolution":{"observed_at":"2026-08-15T15:55:33.153131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.08730","last_updated":"2018-06-20T16:39:26Z","snapshot_observed_at":"2026-08-17T06:16:47.122449Z","submitted_at":"2018-06-20T16:39:26Z","title":"The Natural Language Decathlon: Multitask Learning as Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.08730","snapshot_observed_at":"2026-08-15T15:55:32.844403Z","title":"odd” element among “even","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning","version":5},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T15:55:32.844403Z"},"links":{"cited_paper":"/paper/1806.08730","citing_paper":"/paper/2509.16959"},"observation_digest":"sha256:a18492bb2de2b83ec6ce9e2f7cae54e200a83636f54ad2a66d9ebf8d37e29243","observation_id":"3596105c-603d-4846-995b-99bb440cdfc0","resolution":{"observed_at":"2026-08-15T15:55:32.844403Z","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":"2026-08-15T15:55:33.062386Z","title":"It uses an online, per-step rule (no pairwise gradient ops), adding negligible overhead while remaining robust to loss-scale differences","venue":null,"work_id":"76928cb8-cb7c-47ec-adb6-e9c79ccb6170","year":2023},"citing_paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning","version":5},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T15:55:32.883247Z"},"links":{"citing_paper":"/paper/2509.16959"},"observation_digest":"sha256:da80941d43eb7fceec9c5845adf8e987064fca95dfdf1c204328f9ba023a7bfc","observation_id":"d0cc8ba6-e08f-49c5-95c0-dec5ec3a4048","resolution":{"observed_at":"2026-08-15T15:55:33.066412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:55:33.048887Z","title":"The parameterα controls the trade-off between average performance and fairness","venue":null,"work_id":"b7747ced-a7be-419e-bdab-c763304c9560","year":2024},"citing_paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning","version":5},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T15:55:32.886497Z"},"links":{"citing_paper":"/paper/2509.16959"},"observation_digest":"sha256:1fa4b4987ada485a59a415eec0f3fcdea20e3465ae09fdafc2a8f97532c38e78","observation_id":"94df40a9-1632-4cda-ada0-e717d32bd07c","resolution":{"observed_at":"2026-08-15T15:55:33.053895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"1127.1337","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T15:55:32.980772Z","title":"Weights are obtained by solving a small inner problem (e.g., via CCP) using the gradient Gram matrix","venue":null,"work_id":"1f95a556-07ea-4c93-a859-58a0421d3dfb","year":2020},"citing_paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning","version":5},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T15:55:32.890575Z"},"links":{"citing_paper":"/paper/2509.16959"},"observation_digest":"sha256:284e48e70b48199b75efd8c4722abd2400ddbb237dcf6ea7d39671449cd0c87d","observation_id":"bfec0c02-fa40-4a16-909d-4bd483f0f8fe","resolution":{"observed_at":"2026-08-15T15:55:32.992085Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:55:33.137781Z","title":null,"venue":null,"work_id":"480d87a1-b57e-4167-81a1-88fe5bc9a2f7","year":2018},"citing_paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning","version":5},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T15:55:32.865593Z"},"links":{"citing_paper":"/paper/2509.16959"},"observation_digest":"sha256:64dd0307d6526b9bec5a6098aa0399068b52d2b93d6dae80dfd1a2b208b5fb20","observation_id":"3a3a2045-0283-406e-b97c-2f9f0632368f","resolution":{"observed_at":"2026-08-15T15:55:33.141674Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:55:33.113664Z","title":null,"venue":null,"work_id":"8f17550e-550d-47f9-a653-fa311d0b38fb","year":2020},"citing_paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning","version":5},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T15:55:32.873024Z"},"links":{"citing_paper":"/paper/2509.16959"},"observation_digest":"sha256:a8d7fbebcbe629b92eea618992733ca5b5def8d9984fbe9d4f0542e006419d95","observation_id":"551b163a-1184-4a2e-908b-c2dac6101070","resolution":{"observed_at":"2026-08-15T15:55:33.118390Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:55:33.097591Z","title":"This proves more nuanced modifications to gradients than binary projection","venue":null,"work_id":"92cfc77e-bff7-4fdc-bde3-5e3359540232","year":2021},"citing_paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning","version":5},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T15:55:32.876366Z"},"links":{"citing_paper":"/paper/2509.16959"},"observation_digest":"sha256:ccc8c9cdeb835fb6889c41fa24ed11e2b781a33fb06300c832772479ef49fb7f","observation_id":"9eab2c51-d3bc-48df-b1ca-b1ab3485d02a","resolution":{"observed_at":"2026-08-15T15:55:33.102730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:55:33.074347Z","title":null,"venue":null,"work_id":"0db0671a-ed13-4b7d-9b35-32fe097f2bae","year":2023},"citing_paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning","version":5},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T15:55:32.879783Z"},"links":{"citing_paper":"/paper/2509.16959"},"observation_digest":"sha256:38444bb82d769f1101838d96bb94cca61d38d831cfdeea6107fb80866ef4f18d","observation_id":"e1138b99-6401-47eb-8167-1adb520b39a3","resolution":{"observed_at":"2026-08-15T15:55:33.079459Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.05098","last_updated":"2017-06-15T21:38:12Z","snapshot_observed_at":"2026-08-13T21:53:02.384757Z","submitted_at":"2017-06-15T21:38:12Z","title":"An Overview of Multi-Task Learning in Deep Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.05098","snapshot_observed_at":"2026-08-15T15:55:32.848324Z","title":"Transfer learning: even/odd MNIST","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning","version":5},"reference_index":2004,"source":"pdf_text","source_observed_at":"2026-08-15T15:55:32.848324Z"},"links":{"cited_paper":"/paper/1706.05098","citing_paper":"/paper/2509.16959"},"observation_digest":"sha256:b9fd10b185e723844e56b10d7fd15f029b7521ab19c28865c1c7d05b8f0a402c","observation_id":"fc0fe487-bb54-4fc2-97e6-e5fd61e6da4a","resolution":{"observed_at":"2026-08-15T15:55:32.848324Z","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":"2026-08-15T15:55:33.126492Z","title":"36 K.2 State-of-the-art models","venue":null,"work_id":"3ba32482-f297-4b6e-a468-cbaa660f46b4","year":2000},"citing_paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning","version":5},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-15T15:55:32.869469Z"},"links":{"citing_paper":"/paper/2509.16959"},"observation_digest":"sha256:6d1fee8814f4182495ca2039ab972f78d23fb22e0196a87dd7ed8c16665f4cb0","observation_id":"d26eb3cc-fff2-4a69-bba6-eccc97bab4c0","resolution":{"observed_at":"2026-08-15T15:55:33.130321Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T15:55:33.170275Z","title":"J.2 CIF AR-10 The CIFAR-10 (Krizhevsky et al., 2009) dataset contains 60,00032× 32color images across 10 generic classes","venue":null,"work_id":"7aa871cd-b64e-4ff3-8475-c9570e0ca6d5","year":2009},"citing_paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning","version":5},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-15T15:55:32.853494Z"},"links":{"citing_paper":"/paper/2509.16959"},"observation_digest":"sha256:39bb650d289db43777f4364851e4b0f4e5f2fd1332a9ab8a9bf270c04878d4e9","observation_id":"b6d1012c-49fd-413b-9537-f69e85095cf0","resolution":{"observed_at":"2026-08-15T15:55:33.173904Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1512.03385","last_updated":"2015-12-10T19:51:55Z","snapshot_observed_at":"2026-07-06T04:39:28.429064Z","submitted_at":"2015-12-10T19:51:55Z","title":"Deep Residual Learning for Image Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.03385","snapshot_observed_at":"2026-08-15T15:55:32.840193Z","title":"Valerio Guarrasi, Fatih Aksu, Camillo Maria Caruso, Francesco Di Feola, Aurora Rofena, Filippo Ruffini, and Paolo Soda","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning","version":5},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-15T15:55:32.840193Z"},"links":{"cited_paper":"/paper/1512.03385","citing_paper":"/paper/2509.16959"},"observation_digest":"sha256:0839d67f77812cd4422c6d488b11aa160e08d682159f2f75e8c65ec51835aee9","observation_id":"1c751349-b699-4d22-9be0-e4d8d755fed0","resolution":{"observed_at":"2026-08-15T15:55:32.840193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1801.02143","last_updated":"2019-11-23T08:36:48Z","snapshot_observed_at":"2026-08-14T19:57:23.255421Z","submitted_at":"2018-01-07T06:06:31Z","title":"Deep Bidirectional and Unidirectional LSTM Recurrent Neural Network for Network-wide Traffic Speed Prediction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.02143","snapshot_observed_at":"2026-08-15T15:55:32.835363Z","title":"Sanjoy Dasgupta and Anupam Gupta","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning","version":5},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-15T15:55:32.835363Z"},"links":{"cited_paper":"/paper/1801.02143","citing_paper":"/paper/2509.16959"},"observation_digest":"sha256:440e4351c8c1b2af3a58df8a6263b110e0d888cd461d959c22b908ac99fa8a75","observation_id":"c0ec671d-e25d-4f90-b41c-912806629ddc","resolution":{"observed_at":"2026-08-15T15:55:32.835363Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.16959","last_updated":"2026-06-29T19:33:01Z","latest_version":5,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T15:46:39.418749Z","submitted_at":"2025-09-21T07:45:53Z","title":"Graph Coloring for Multi-Task Learning"},"reference_resolution":{"displayed":15,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":6},"total_outbound_references":15},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2509.16959."}