{"as_of":"2026-08-13T01:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c09f8c9b319564f0fe663334c1d19b7c4055f96c7eac97425e5938da40997899","coverage":[{"denominator":14,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T12:06:06.342647Z","state":"measured"},{"denominator":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+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/2411.17571/citation-record","integrity":"/paper/2411.17571/integrity","json":"/paper/2411.17571/citation-record.json","paper":"/paper/2411.17571"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.10760","last_updated":"2021-06-22T07:53:17Z","snapshot_observed_at":"2026-07-06T11:21:06.741337Z","submitted_at":"2021-06-20T21:52:46Z","title":"On Stein Variational Neural Network Ensembles","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.10760","snapshot_observed_at":"2026-08-12T12:06:06.190105Z","title":"Stroke J","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2411.17571","last_updated":"2025-07-17T12:24:49Z","snapshot_observed_at":"2026-08-12T11:56:16.095495Z","submitted_at":"2024-11-26T16:34:24Z","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T12:06:06.190105Z"},"links":{"cited_paper":"/paper/2106.10760","citing_paper":"/paper/2411.17571"},"observation_digest":"sha256:f57b3fa100d5a92621e26afc0f2927c5fc18f26170ab653a41654099e542a3c5","observation_id":"308c7633-e867-4d5c-869b-a77a5352100a","resolution":{"observed_at":"2026-08-12T12:06:06.190105Z","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":"2026-08-12T12:06:07.150064Z","title":"V olume Only: Only the estimated volume from the SEnt model is used as a feature","venue":null,"work_id":"a81b87a1-49bc-41fc-b814-0abb20d4e9e9","year":null},"citing_paper":{"arxiv_id":"2411.17571","last_updated":"2025-07-17T12:24:49Z","snapshot_observed_at":"2026-08-12T11:56:16.095495Z","submitted_at":"2024-11-26T16:34:24Z","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T12:06:06.283691Z"},"links":{"citing_paper":"/paper/2411.17571"},"observation_digest":"sha256:9612bf6fb5223287aad3d3dd19995f93fdc5d323d1432979e4fa3658fc70efd9","observation_id":"be9c8e27-f337-4da4-af48-ccc4e7c6d82f","resolution":{"observed_at":"2026-08-12T12:06:07.158028Z","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":"2304.03209","last_updated":"2023-07-17T19:52:20Z","snapshot_observed_at":"2026-08-03T20:17:59.578831Z","submitted_at":"2023-04-06T16:44:03Z","title":"Implicit Anatomical Rendering for Medical Image Segmentation with Stochastic Experts","version":2},"cited_work":{"arxiv_id":"2304.03209","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.03209","snapshot_observed_at":"2026-08-12T12:06:06.451260Z","title":"Implicit Anatomical Rendering for Medical Image Segmentation with Stochastic Experts","venue":"cs.CV","work_id":"8097fa08-b31f-44dc-a691-89f56df3ed2a","year":2023},"citing_paper":{"arxiv_id":"2411.17571","last_updated":"2025-07-17T12:24:49Z","snapshot_observed_at":"2026-08-12T11:56:16.095495Z","submitted_at":"2024-11-26T16:34:24Z","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T12:06:06.271474Z"},"links":{"cited_paper":"/paper/2304.03209","citing_paper":"/paper/2411.17571"},"observation_digest":"sha256:dc02da9353d883e94b0a74ec529b8756a6453b1b1893b66423774640fc8f2342","observation_id":"4881236f-3b20-4161-abfa-e3402fe02652","resolution":{"observed_at":"2026-08-12T12:06:06.464176Z","resolver_source":"local_arxiv","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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T12:06:07.114022Z","title":"V olume Only: Only the estimated volume from the SEnt model is used as a feature","venue":null,"work_id":"6a994263-eb37-466d-a38f-30e8a55b88ee","year":null},"citing_paper":{"arxiv_id":"2411.17571","last_updated":"2025-07-17T12:24:49Z","snapshot_observed_at":"2026-08-12T11:56:16.095495Z","submitted_at":"2024-11-26T16:34:24Z","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T12:06:06.295252Z"},"links":{"citing_paper":"/paper/2411.17571"},"observation_digest":"sha256:70605d4eb6eaa01eb782d8dcc167c54e6435fbfddb7902f0ade84c31b8359931","observation_id":"eb61b4ed-a1ec-46f8-ad3f-8296cdf6f385","resolution":{"observed_at":"2026-08-12T12:06:07.122570Z","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":"2026-08-12T12:06:07.084522Z","title":"V olume Only: Only the estimated volume from the SEnt model is used as a feature","venue":null,"work_id":"030a8b04-89e2-4645-a9f3-4f24b9814b53","year":null},"citing_paper":{"arxiv_id":"2411.17571","last_updated":"2025-07-17T12:24:49Z","snapshot_observed_at":"2026-08-12T11:56:16.095495Z","submitted_at":"2024-11-26T16:34:24Z","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T12:06:06.302250Z"},"links":{"citing_paper":"/paper/2411.17571"},"observation_digest":"sha256:fbcfff1c689cc544742620903136088c076263d755a09804c1c7e074789078fa","observation_id":"87b3d27b-4fb3-4766-9b17-982280f7c540","resolution":{"observed_at":"2026-08-12T12:06:07.097165Z","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":"2026-08-12T12:06:07.050952Z","title":"V olume Only: Only the estimated volume from the SEnt model is used as a feature","venue":null,"work_id":"eebbabb4-b5e7-4ca2-addc-84f8d03408fc","year":null},"citing_paper":{"arxiv_id":"2411.17571","last_updated":"2025-07-17T12:24:49Z","snapshot_observed_at":"2026-08-12T11:56:16.095495Z","submitted_at":"2024-11-26T16:34:24Z","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T12:06:06.314856Z"},"links":{"citing_paper":"/paper/2411.17571"},"observation_digest":"sha256:10a5f3d194fdb9266842bdbfbd672918aaa20b2e56348018219d8b0c2db6790f","observation_id":"7ad9db23-8f4a-4590-86a4-56fe9119f9d9","resolution":{"observed_at":"2026-08-12T12:06:07.061370Z","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":"2026-08-12T12:06:07.016796Z","title":"V olume Only: Only the estimated volume from the SEnt model is used as a feature","venue":null,"work_id":"6956982d-8a79-4b1f-8b31-8cdd5a24ae90","year":null},"citing_paper":{"arxiv_id":"2411.17571","last_updated":"2025-07-17T12:24:49Z","snapshot_observed_at":"2026-08-12T11:56:16.095495Z","submitted_at":"2024-11-26T16:34:24Z","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T12:06:06.329034Z"},"links":{"citing_paper":"/paper/2411.17571"},"observation_digest":"sha256:92ed0430b07930e00f502f532551a122f9954889a508d515c3ab4001fe0f5505","observation_id":"4a25d72d-bc79-413d-bdc5-d4c8e1ede7f3","resolution":{"observed_at":"2026-08-12T12:06:07.024365Z","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":"2026-08-12T12:06:06.987731Z","title":"V olume Only: Only the estimated volume from the SEnt model is used as a feature","venue":null,"work_id":"2f7397ac-c15d-4aa2-b245-b9a606b80899","year":null},"citing_paper":{"arxiv_id":"2411.17571","last_updated":"2025-07-17T12:24:49Z","snapshot_observed_at":"2026-08-12T11:56:16.095495Z","submitted_at":"2024-11-26T16:34:24Z","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T12:06:06.342647Z"},"links":{"citing_paper":"/paper/2411.17571"},"observation_digest":"sha256:3a1338888cd9b1a676eaff7d19d7c4f7a23054ee498d93356194105c3c3f35f7","observation_id":"cde15f83-9835-4c58-8f18-ae0980089886","resolution":{"observed_at":"2026-08-12T12:06:06.994309Z","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":"2026-08-12T12:06:06.238370Z","title":"Stroke 42 (7), 1917–1922","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2411.17571","last_updated":"2025-07-17T12:24:49Z","snapshot_observed_at":"2026-08-12T11:56:16.095495Z","submitted_at":"2024-11-26T16:34:24Z","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification","version":2},"reference_index":2011,"source":"pdf_text","source_observed_at":"2026-08-12T12:06:06.238370Z"},"links":{"citing_paper":"/paper/2411.17571"},"observation_digest":"sha256:5793407b1555d9d2b99cfe5ca7dc5ade5f3095945360c371d99b3ce0a7432521","observation_id":"ac21c7ac-2a4d-47a6-8fbc-3c90c84af23b","resolution":{"observed_at":"2026-08-12T12:06:06.238370Z","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":"2026-08-12T12:06:06.258926Z","title":null,"venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2411.17571","last_updated":"2025-07-17T12:24:49Z","snapshot_observed_at":"2026-08-12T11:56:16.095495Z","submitted_at":"2024-11-26T16:34:24Z","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification","version":2},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-12T12:06:06.258926Z"},"links":{"citing_paper":"/paper/2411.17571"},"observation_digest":"sha256:9de95f36166b52fd93ab3206606dd13b00edaadb1ac53125e3dd49c0d1e7e51e","observation_id":"1297802c-c6c0-4eb5-87b4-9d5c43e17e63","resolution":{"observed_at":"2026-08-12T12:06:06.258926Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.11599","last_updated":"2024-04-17T17:50:24Z","snapshot_observed_at":"2026-08-13T00:27:59.611745Z","submitted_at":"2024-04-17T17:50:24Z","title":"Variational Bayesian Last Layers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.11599","snapshot_observed_at":"2026-08-12T12:06:06.224153Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.17571","last_updated":"2025-07-17T12:24:49Z","snapshot_observed_at":"2026-08-12T11:56:16.095495Z","submitted_at":"2024-11-26T16:34:24Z","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-12T12:06:06.224153Z"},"links":{"cited_paper":"/paper/2404.11599","citing_paper":"/paper/2411.17571"},"observation_digest":"sha256:560be9982c435794d3e7634d3a929189a72e1f11199eba2d7e93004af92b278c","observation_id":"4b994110-76cd-4b5c-9aa7-5c1e59374c79","resolution":{"observed_at":"2026-08-12T12:06:06.224153Z","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":"2026-08-12T12:06:07.179039Z","title":null,"venue":null,"work_id":"db0a3de8-b806-4347-b372-7505cf264a4d","year":2021},"citing_paper":{"arxiv_id":"2411.17571","last_updated":"2025-07-17T12:24:49Z","snapshot_observed_at":"2026-08-12T11:56:16.095495Z","submitted_at":"2024-11-26T16:34:24Z","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-12T12:06:06.251654Z"},"links":{"citing_paper":"/paper/2411.17571"},"observation_digest":"sha256:94bb2e45524d961c888dd59ef090c1ab87004e98c8553c7812c2f0410e790be2","observation_id":"2c61f7e2-1ab0-4310-8661-87e3efe832fe","resolution":{"observed_at":"2026-08-12T12:06:07.190408Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"10.2196/31684","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T12:06:06.403873Z","title":null,"venue":null,"work_id":"e11b1940-88af-41f0-8b51-1ca30d06070a","year":null},"citing_paper":{"arxiv_id":"2411.17571","last_updated":"2025-07-17T12:24:49Z","snapshot_observed_at":"2026-08-12T11:56:16.095495Z","submitted_at":"2024-11-26T16:34:24Z","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-12T12:06:06.199501Z"},"links":{"citing_paper":"/paper/2411.17571"},"observation_digest":"sha256:a61be340c2e72919777cdde4d61661b5c74fb63c015f89a52ee7db09c1ec1c64","observation_id":"872d6354-9ddf-4b45-bb1c-e4183a550ad6","resolution":{"observed_at":"2026-08-12T12:06:06.413498Z","resolver_source":"doi_truncated","status":"malformed_identifier"},"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":"2022.94634","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T12:06:06.863287Z","title":"In: International Conference on Medical Image Computing and Computer-Assisted Intervention","venue":null,"work_id":"c9d50cd7-3efe-4e4d-ad5d-b8d4608552ee","year":2004},"citing_paper":{"arxiv_id":"2411.17571","last_updated":"2025-07-17T12:24:49Z","snapshot_observed_at":"2026-08-12T11:56:16.095495Z","submitted_at":"2024-11-26T16:34:24Z","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-12T12:06:06.209828Z"},"links":{"citing_paper":"/paper/2411.17571"},"observation_digest":"sha256:36b27c99537b39fac671c9619c78c3397f25156ee2d7082b23834e71c09fce36","observation_id":"06aea9c7-c1ca-40cb-b271-cc382c701d67","resolution":{"observed_at":"2026-08-12T12:06:06.880162Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"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"}}],"paper":{"arxiv_id":"2411.17571","last_updated":"2025-07-17T12:24:49Z","latest_version":2,"primary_category":"eess.IV","snapshot_observed_at":"2026-08-12T11:56:16.095495Z","submitted_at":"2024-11-26T16:34:24Z","title":"Uncertainty quantification for White Matter Hyperintensity segmentation detects silent failures and improves automated Fazekas quantification"},"reference_resolution":{"displayed":14,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":5,"verified_exact":1,"verified_fuzzy":6},"total_outbound_references":14},"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 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2411.17571."}