{"as_of":"2026-08-20T00:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bd44919fa8d177bb10005baa4bab743d3f62e919ddc29e38695fddaec7726f92","coverage":[{"denominator":126,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T14:54:52.396995Z","state":"measured"},{"denominator":101,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":101,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:55:25.325890Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-16T12:16:17.039197Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"cited_work":{"arxiv_id":"2412.11521","doi":"10.48550/arxiv.2412.11521","metadata_source":"pith","pith_arxiv_id":"2412.11521","snapshot_observed_at":"2026-08-16T12:16:17.039197Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","venue":"cs.LG","work_id":"7f4862e3-238a-4f97-b979-5e04a66dd8d2","year":2024},"citing_paper":{"arxiv_id":"2505.11719","last_updated":"2025-05-16T22:01:46Z","snapshot_observed_at":"2026-08-17T06:22:32.706258Z","submitted_at":"2025-05-16T22:01:46Z","title":"Zero-Shot Visual Generalization in Robot Manipulation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T20:55:25.325890Z"},"links":{"cited_paper":"/paper/2412.11521","citing_paper":"/paper/2505.11719"},"observation_digest":"sha256:a2850fba7f54945cb1ac0bbe5bcb49bc606a3371b4ab4b67c5ea02fb98da5987","observation_id":"3f9133f5-f80f-4161-9961-a5cfe9e9386c","resolution":{"observed_at":"2026-08-15T20:55:26.110062Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.11521/citation-record","integrity":"/paper/2412.11521/integrity","json":"/paper/2412.11521/citation-record.json","paper":"/paper/2412.11521"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:54:52.078284Z","title":"Progress and limitations of deep networks to recognize objects in unusual poses","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.078284Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:6ad69400e6231b0cf8724616ee8e65b738fa1446d4eafb9aafbbeb58e865819a","observation_id":"99c0ba41-44c4-49ec-8c72-9e6a8b868046","resolution":{"observed_at":"2026-08-11T14:54:52.078284Z","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":"2026-08-11T14:54:52.081888Z","title":"Git Re-Basin : Merging models modulo permutation symmetries","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.081888Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:91de08e48fe51f77b36dbca6c68c34c6676668b1aabc51acdae9be362ea3130c","observation_id":"91c77d72-29bf-4b10-b8a5-c1a21e7e0cc7","resolution":{"observed_at":"2026-08-11T14:54:52.081888Z","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":"2026-08-11T14:54:52.085377Z","title":"Strike (with) a pose: Neural networks are easily fooled by strange poses of familiar objects","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.085377Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:61d6ff02a118562798d5f6fd4d5892dd2cad19e4983441e8e866f27ed1635fbc","observation_id":"4eff5d19-d315-4447-a3d1-91efc2cb078b","resolution":{"observed_at":"2026-08-11T14:54:52.085377Z","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":"2026-08-11T14:54:52.089394Z","title":"Symmetry-adapted representation learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.089394Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:ee565f0d9e3d903739cb6d7454e235aae9e252f5a803c762334acc835d6561a4","observation_id":"84ef3a2c-0f55-4b57-a86c-5a84f61b0bbf","resolution":{"observed_at":"2026-08-11T14:54:52.089394Z","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":"2026-08-11T14:54:52.093008Z","title":"Data symmetries and learning in fully connected neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.093008Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:c081f425584b97b35ba10b2d3a6f366dc85183606b492c4b5151738d3c0b0956","observation_id":"04055fbf-d18f-47d6-b301-d1f781cb3a56","resolution":{"observed_at":"2026-08-11T14:54:52.093008Z","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":"2026-08-11T14:54:52.096568Z","title":"On exact computation with an infinitely wide neural net","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.096568Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:dcce6734863c052fbf1129b7034f9042b4f4a7c3c012d0d31e66c958b90048cc","observation_id":"a7bc6831-1d3a-42cb-ba85-eab475ccc1c1","resolution":{"observed_at":"2026-08-11T14:54:52.096568Z","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":"2026-08-11T14:54:52.100438Z","title":"Unified theoretical framework for wide neural network learning dynamics","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.100438Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:38692dbc777a59c4ef7a2dd003555827cc94d3f76eed54e931457d9d8ca46595","observation_id":"6e332fa0-b588-437e-b87b-6a96064ca3d9","resolution":{"observed_at":"2026-08-11T14:54:52.100438Z","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":"2026-08-11T14:54:52.103729Z","title":"Why do deep convolutional networks generalize so poorly to small image transformations? Journal of Machine Learning Research (JMLR), 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.103729Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:daed8256c0daa687cb6055f6cdeaeaa7140f96b795ff4cfaca3a5981247936d6","observation_id":"255ec48a-9027-455d-8348-11010709fabd","resolution":{"observed_at":"2026-08-11T14:54:52.103729Z","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":"2026-08-11T14:54:52.107011Z","title":"Breaking the curse of dimensionality with convex neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.107011Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:0aa256d9211d129bbc83e41bb709c722c2fea5e642c64b3f735e2e29a1395b50","observation_id":"2d2c36cb-664c-4011-adba-2374f5171d56","resolution":{"observed_at":"2026-08-11T14:54:52.107011Z","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":"2026-08-11T14:54:52.110441Z","title":"Explaining neural scaling laws","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.110441Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:9fd9b6d4ed82c823e05b21b6ca91709654b569d42508504d08bc6258aef99b27","observation_id":"d530f323-de98-4332-99c0-49409f0b9083","resolution":{"observed_at":"2026-08-11T14:54:52.110441Z","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":"2026-08-11T14:54:52.113761Z","title":"A cookbook of self-supervised learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.113761Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:178e19639c3d675ed29a5c4f66fe818a137d8ddfe7575b4fce06241cccbca600","observation_id":"7d4f3c56-b38a-4229-897a-bf73c4141171","resolution":{"observed_at":"2026-08-11T14:54:52.113761Z","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":"2026-08-11T14:54:52.120736Z","title":"Developmental changes in children’s object insertions during play","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.120736Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:6b5f66d1e0afb3a3d724b96c876e2ba76b6a49258d0684becb79260d209adfff","observation_id":"bbf2afc5-9cfb-4ed8-832e-23ad5c5bc70c","resolution":{"observed_at":"2026-08-11T14:54:52.120736Z","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":"2026-08-11T14:54:52.124731Z","title":"B-spline CNNs on Lie groups","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.124731Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:b0e7344255d27d44526654473c587faf402e672064cd493b4d29bda53229668e","observation_id":"2d0f584f-db43-47d2-99b1-300683e365c1","resolution":{"observed_at":"2026-08-11T14:54:52.124731Z","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":"2026-08-11T14:54:52.127875Z","title":"Learning invariances in neural networks from training data","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.127875Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:8dc6bf9998946902a778da8f69d1c8d51505e7023db4b432638ef8bf886f931d","observation_id":"3b05e403-b7ba-4218-8dc7-a36471543766","resolution":{"observed_at":"2026-08-11T14:54:52.127875Z","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":"2026-08-11T14:54:52.131180Z","title":"Self-consistent dynamical field theory of kernel evolution in wide neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.131180Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:e04a61df4756b48d1a36617ae7aa75c47c875f03e10cd62450abd0ee56ba0326","observation_id":"0e9eeb3d-15f6-4a65-a0e1-fedf8f74e485","resolution":{"observed_at":"2026-08-11T14:54:52.131180Z","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":"2026-08-11T14:54:52.134366Z","title":"Spectrum dependent learning curves in kernel regression and wide neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.134366Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:117c7d3d3ec31bd754433df6fb66092ab540c559dbee5de7cbbdecf5368a1d50","observation_id":"e50e0573-5cba-4a0e-bc9d-a9210678dbab","resolution":{"observed_at":"2026-08-11T14:54:52.134366Z","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":"2026-08-11T14:54:52.137940Z","title":"Addressing the topological defects of disentanglement via distributed operators","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.137940Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:d931f233c5fcf79e3e112f676f419f1939d03af31f401e89bd28bcb99aa820c3","observation_id":"e272fc91-5c69-4621-b34a-9039f2b80bfc","resolution":{"observed_at":"2026-08-11T14:54:52.137940Z","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":"2026-08-11T14:54:52.141606Z","title":"Does equivariance matter at scale? arXiv preprint, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.141606Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:d63df5ce10e664c8141b1db2d6c8776e509220c0d94c488f77f51169e5144b1e","observation_id":"96da175b-420c-4713-b59b-e016ae7ef9fd","resolution":{"observed_at":"2026-08-11T14:54:52.141606Z","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":"2026-08-11T14:54:52.144909Z","title":"Bronstein, Joan Bruna, Taco Cohen, and Petar Veličković","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.144909Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:29ae2e9517c1529524f9bc906b030358e024fda525947bd0364963bcf6d78432","observation_id":"499c2ec1-4b2d-481e-bc6e-799badd07225","resolution":{"observed_at":"2026-08-11T14:54:52.144909Z","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":"2026-08-11T14:54:52.148484Z","title":"Spectral bias and task-model alignment explain generalization in kernel regression and infinitely wide neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.148484Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:c9a7d04353991c17c285f71ba19e3d28b935be12dc87d4448f8aabc4dcb4bad1","observation_id":"d768c008-6a5d-4bc3-ae5c-f7d1d258c479","resolution":{"observed_at":"2026-08-11T14:54:52.148484Z","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":"2026-08-11T14:54:52.151804Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.151804Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:6264f8b97250deb670e8c8527f2231ff8a6346b85f1b3c4681b46169c6967e85","observation_id":"48a8c98a-fe6f-4911-9e23-863d563e3596","resolution":{"observed_at":"2026-08-11T14:54:52.151804Z","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":"2026-08-11T14:54:52.155142Z","title":"Deep reasoning networks for unsupervised pattern de-mixing with constraint reasoning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.155142Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:ed6d1d57328737fd70ff720f97e446e2f8f9b6ec89add0ace248a013e001a8e9","observation_id":"70946239-de03-44ce-8f5c-e466dce4f36c","resolution":{"observed_at":"2026-08-11T14:54:52.155142Z","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":"2026-08-11T14:54:52.158711Z","title":"Chirikjian and Alexander B","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.158711Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:7832c18d87c9f3a180993adf7bfd6feac7f16f54d5baf84fd7bd6b1fa66f4cd6","observation_id":"0ec9fc66-3808-488e-ab94-cfdcaaa651e6","resolution":{"observed_at":"2026-08-11T14:54:52.158711Z","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":"2026-08-11T14:54:52.161500Z","title":"On the global convergence of gradient descent for over-parameterized models using optimal transport","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.161500Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:1ca29c157e6f25d0625c2e2df51b90feb313056ecbe203b68e1f717cafcafd50","observation_id":"88fc3fc9-047b-461e-994d-069fb865626a","resolution":{"observed_at":"2026-08-11T14:54:52.161500Z","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":"2026-08-11T14:54:52.164300Z","title":"Lee, and Haim Sompolinsky","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.164300Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:791eb05221dcde86063e2d682d68822e14b2f6074e4f0bdfe9d2859a3066a746","observation_id":"dc0861f8-fc1f-4d27-a6de-095db5a5fd20","resolution":{"observed_at":"2026-08-11T14:54:52.164300Z","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":"2026-08-11T14:54:52.166999Z","title":"Group equivariant convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.166999Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:423850ad0aada8ec01d7723597ca55ef7e958e6686c90d6ed892c5b83f12a923","observation_id":"071137f3-de76-4fe6-a274-d28a97866588","resolution":{"observed_at":"2026-08-11T14:54:52.166999Z","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":"2026-08-11T14:54:52.169738Z","title":"Gauge equivariant convolutional networks and the icosahedral CNN","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.169738Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:7ee11a1222fde67aea8edc3c9fd1caf4b27d6781be9cda7606da8fd5f28e6468","observation_id":"fc90508f-4520-47f7-81c2-8d494e80266c","resolution":{"observed_at":"2026-08-11T14:54:52.169738Z","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":"2026-08-11T14:54:52.172929Z","title":"A general theory of equivariant CNNs on homogeneous spaces","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.172929Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:39d8c2b7308328597f7c86067a1392fafd4bc94cdea769923c7c5e97fcb66fcd","observation_id":"f5a65aec-b11c-4ee6-9ed5-9e46b3307d5d","resolution":{"observed_at":"2026-08-11T14:54:52.172929Z","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":"2026-08-11T14:54:52.175894Z","title":"Lee, and Haim Sompolinsky","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.175894Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:f09c7a7c64cd02ca0be02213a19ccb5fa273ae4aff946fb73d772c493cc85867","observation_id":"a21444cd-1d35-4da7-9c00-67746377e1b1","resolution":{"observed_at":"2026-08-11T14:54:52.175894Z","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":"2026-08-11T14:54:52.178660Z","title":"Representing closed transformation paths in encoded network latent space","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.178660Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:872c12c3821b20bcb9c8bccd20bccf629177b4ad0a8fec225b8247a62ad9f94a","observation_id":"02dc8cb6-3608-44b7-9a6c-06a28c7b70ba","resolution":{"observed_at":"2026-08-11T14:54:52.178660Z","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":"2026-08-11T14:54:52.181370Z","title":"Learning internal representations of 3D transformations from 2D projected inputs","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.181370Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:a8e1dbf17f459c6126f0356082147d52bf70b8ab9f59c7988e360e555bd98c19","observation_id":"81e592d8-6352-40d7-bb82-09e61e0d54cc","resolution":{"observed_at":"2026-08-11T14:54:52.181370Z","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":"2026-08-11T14:54:52.184033Z","title":"Lagrangian neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.184033Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:60f43027b4714742f5b453c8a45ea4a7c0c0779ed143741364add2cfad86b44b","observation_id":"50644a86-4e0f-4865-9aed-dbbe19a710b3","resolution":{"observed_at":"2026-08-11T14:54:52.184033Z","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":"2026-08-11T14:54:52.186780Z","title":"Learning transport operators for image manifolds","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.186780Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:4b1778c6cf0f4842352d602cddd44397b24a54c1385af7b01134a6f9886e42cd","observation_id":"39661d56-5209-4071-98e4-b6ce12648303","resolution":{"observed_at":"2026-08-11T14:54:52.186780Z","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":"2026-08-11T14:54:52.189409Z","title":"Convit: Improving vision transformers with soft convolutional inductive biases","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.189409Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:b4b7c052a38dd060d1591bbf06865ddf904bb53ed9b3768c7c8bd811b726a7c3","observation_id":"f1434d68-a7c6-4439-8c75-c32c03290d1e","resolution":{"observed_at":"2026-08-11T14:54:52.189409Z","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":"2026-08-11T14:54:52.192307Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.192307Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:ca12a7d3bd096fc6e3ab926449370ef0e8e615f7d67558a812c226a07cce30a3","observation_id":"69cfc71e-4f45-47aa-ba81-21367d9d25f5","resolution":{"observed_at":"2026-08-11T14:54:52.192307Z","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":"2026-08-11T14:54:52.195393Z","title":"Equivariant neural rendering","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.195393Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:d77a3704b44042b65a9fbb9a642425dec836d7139f272963c601505d1814f6cb","observation_id":"6933842b-9869-4e98-b573-f4c3acc76ec2","resolution":{"observed_at":"2026-08-11T14:54:52.195393Z","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":"2026-08-11T14:54:52.198309Z","title":"Revisiting spatial invariance with low-rank local connectivity","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.198309Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:6384c3fde33ab266b463380cf9e78df2577d9844f44c3af7111b970d6e1fae8d","observation_id":"7faacdbd-3cb5-4062-a596-986632d5e222","resolution":{"observed_at":"2026-08-11T14:54:52.198309Z","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":"2026-08-11T14:54:52.201089Z","title":"Topological obstructions and how to avoid them","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.201089Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:a53b86f5d44badeea636c339e5963659b89d325382ec1ce7f6b6e1eb746abe79","observation_id":"b778178d-7074-494e-b81d-c93aafad77d6","resolution":{"observed_at":"2026-08-11T14:54:52.201089Z","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":"2026-08-11T14:54:52.204025Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.204025Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:0d1e738f600fe3dd8dce828e38190225114b3bede87b5ac6e4910e3286ae63ec","observation_id":"e23ba2ef-c138-4bdb-b16f-138f5d7c925e","resolution":{"observed_at":"2026-08-11T14:54:52.204025Z","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":"2026-08-11T14:54:52.206823Z","title":"Model-agnostic meta-learning for fast adaptation of deep networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.206823Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:1d4f98eae16f07766114d9a62200913e7e2d6cbddf96e8007bf23a1061dfd7b9","observation_id":"b52e12f5-0558-41aa-ab0e-bcce490519b9","resolution":{"observed_at":"2026-08-11T14:54:52.206823Z","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":"2026-08-11T14:54:52.210194Z","title":"Generalizing convolutional neural networks for equivariance to Lie groups on arbitrary continuous data","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.210194Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:bdcb8893b1445b3d39f30de2fa31090ed42ad6dd03910a8a1b12ccc3e3e2884f","observation_id":"141aa918-48d8-47bc-b3b9-e47c79d9e88a","resolution":{"observed_at":"2026-08-11T14:54:52.210194Z","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":"2026-08-11T14:54:52.213417Z","title":"Deep learning versus kernel learning: An empirical study of loss landscape geometry and the time evolution of the neural tangent kernel","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.213417Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:bcccc7125c5367376f36c65faa82cf4aa0d80006a1047e7b28cc6bbc6ec415f3","observation_id":"08cd933c-3592-4b7c-9cb3-fb5831346b0a","resolution":{"observed_at":"2026-08-11T14:54:52.213417Z","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":"2026-08-11T14:54:52.216581Z","title":"Learning and leveraging world models in visual representation learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.216581Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:06b4c65e288749af2705447d03c862e60cfc125693bd94a396a9fdab068b68d7","observation_id":"4ea684ac-23f3-48c5-8329-1e3cbcf65efb","resolution":{"observed_at":"2026-08-11T14:54:52.216581Z","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":"2026-08-11T14:54:52.220041Z","title":"Disentangling feature and lazy training in deep neural networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.220041Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:a1a6d704a2d216f49dd89a3993ab688ebd30f124fa698daa07e0c6b713a22aa5","observation_id":"8d3dcedc-36f1-49c9-8d8a-0281be431ec0","resolution":{"observed_at":"2026-08-11T14:54:52.220041Z","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":"2026-08-11T14:54:52.223320Z","title":"Deep symmetry networks","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.223320Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:88b67f58cff61e978022efc20381e5df2fd0e74ea7646fed38b76f127eb9d1ba","observation_id":"9ed99ced-16b8-4971-bd16-0b0996b914b4","resolution":{"observed_at":"2026-08-11T14:54:52.223320Z","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":"2026-08-11T14:54:52.226560Z","title":"Probing transfer learning with a model of synthetic correlated datasets","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.226560Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:5bbc440c5141c2f50ce120caeea0f9f9b2af77c9ce92e4f9e9d5e0aaedb86d3a","observation_id":"d4529b96-71c4-44fd-b418-00b8a7de4d3d","resolution":{"observed_at":"2026-08-11T14:54:52.226560Z","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":"2026-08-11T14:54:53.276195Z","title":"Emergent equivariance in deep ensembles","venue":null,"work_id":"95f94bf6-eb84-4668-8a53-196950387285","year":2024},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.229975Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:663d1dffa24b0f2e74c3fb1fa483aa710a41cd5516b7856a23b3619307240a50","observation_id":"3cbbbb5d-3ab6-4a63-937c-2e9c444d9a6d","resolution":{"observed_at":"2026-08-11T14:54:53.278978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.267613Z","title":"Modeling the influence of data structure on learning in neural networks: The hidden manifold model","venue":null,"work_id":"0619d16c-6d86-4d9d-96be-e606a95460e4","year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.233322Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:d50ca234ad119e6fb238f96e09caa8489796cb82bc093cca9aa4dbbc21d38dca","observation_id":"f8cd8354-3032-48f3-bf60-eb146502a683","resolution":{"observed_at":"2026-08-11T14:54:53.270647Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.258307Z","title":"Hamiltonian neural networks","venue":null,"work_id":"1c5ead25-769f-4492-b7c3-c5d525a6cedb","year":2019},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.236476Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:509d820f4e6e69a9a41035086c604ad899cb38d05ad73755bb247c4c04624fe1","observation_id":"b599b688-d227-43af-900f-b0f0626f1c9d","resolution":{"observed_at":"2026-08-11T14:54:53.262127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.248171Z","title":null,"venue":null,"work_id":"9037487b-ea27-49eb-9e7c-160a38a2fbdf","year":1996},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.239485Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:1d2d68c0a5d7c34d2d2369af474353a307deb4a2fef4830eadb48f72e9ffb902","observation_id":"9a6d9353-23d1-4543-9ca4-6a869606a106","resolution":{"observed_at":"2026-08-11T14:54:53.252117Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.238885Z","title":"The Lie derivative for measuring learned equivariance","venue":null,"work_id":"f84b9f96-fc76-43ea-bc5d-d9b49d2ded6f","year":2023},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.242847Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:b89a23f0190ef1bdc5d960b55e0431b442ddda9a97497fd267427a3e2a8b69b1","observation_id":"8ecece21-3cdd-4fd2-8436-f46c9ad4e647","resolution":{"observed_at":"2026-08-11T14:54:53.242421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.228595Z","title":"Dey, Soham Mukherjee, Shreyas N","venue":null,"work_id":"b649a982-90aa-4e6f-b2f6-27fa8044c1e5","year":2023},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.246162Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:f00c5a0a1664a03a147faedd743a8f9bac4cd8594418b232c5b9fdbd74a277ea","observation_id":"b9a0a97a-0600-4937-b243-d5d05e588cc0","resolution":{"observed_at":"2026-08-11T14:54:53.232591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.218320Z","title":"Towards a definition of disentangled representations","venue":null,"work_id":"e08de856-53b4-49c9-9b46-afbcea4c4562","year":2018},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.249400Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:156020b84887ae777d2bc2f3f314dffd9b20c61639d1b2771947c7dcf1afc392","observation_id":"815c4505-2e9d-4901-b2d3-59c9b11de27f","resolution":{"observed_at":"2026-08-11T14:54:53.222400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.208381Z","title":"Deep networks always grok and here is why","venue":null,"work_id":"4a1a7708-5d42-4971-94f9-23a8fb4fa14f","year":2024},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.252518Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:99530cf8ec9e4fa8956207a6c66d28b26cbde6482a4aea54eb697f4f7d5e8848","observation_id":"f2978702-18e4-4bf6-8d9a-141149d4b3e6","resolution":{"observed_at":"2026-08-11T14:54:53.212046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.198138Z","title":"Robust self-supervised learning with Lie groups","venue":null,"work_id":"7facca8c-6ac3-4c33-9ed0-457ccee999a7","year":2022},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.255851Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:826cf2a3656588a6edd5dcaf8a3dcd054d800b65a4a66aa31c8af21eaae2a251","observation_id":"7fcc629d-e6aa-408f-b9e8-eb0cf231a596","resolution":{"observed_at":"2026-08-11T14:54:53.201848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.188119Z","title":"Morcos, and Diane Bouchacourt","venue":null,"work_id":"ece2d83f-decc-48d2-b654-0c2a68ef9b26","year":2023},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.259216Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:70793e8e1dab6c0202298cf0403ac6f390e8aa3128a334064e1dd750c0b02489","observation_id":"4556e396-0d20-4b9c-b482-d070f6563b91","resolution":{"observed_at":"2026-08-11T14:54:53.191701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.178211Z","title":"van der Ouderaa, Gunnar R\\\" a tsch, Vincent Fortuin, and Mark van der Wilk","venue":null,"work_id":"58453320-d0b7-402a-82a6-2be32a31e05a","year":2022},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.262399Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:8ae49edcaef9082011348ff8252f7b1340d26c3f057e598e4c0111c517e92a81","observation_id":"09a727fe-3943-436c-ac1d-84573bf2343e","resolution":{"observed_at":"2026-08-11T14:54:53.181781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.167731Z","title":"Neural tangent kernel: Convergence and generalization in neural networks","venue":null,"work_id":"3063d46f-7385-4575-8657-ae3b40e69760","year":2018},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.265152Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:3d853ddf417d67d4ae530624f49c03733fe42970ab84a040e841ba58bbc4c60c","observation_id":"6392ca17-8c67-4e86-a2bd-40bc229ff358","resolution":{"observed_at":"2026-08-11T14:54:53.171410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.157323Z","title":"How DNN s break the curse of dimensionality: Compositionality and symmetry learning","venue":null,"work_id":"6ff5224a-9f3d-48b7-ab53-5fb10cb32a2e","year":2025},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.267980Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:b20602a3af4d7579dccad2f5deef297da15b8df62cd721f0a20dad4386f44540","observation_id":"bd74e73f-0af2-424b-aa8b-60e95bfd9493","resolution":{"observed_at":"2026-08-11T14:54:53.160974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.146695Z","title":"Spatial transformer networks","venue":null,"work_id":"4e813c51-7966-412e-93c5-c6c799dcbe0c","year":2015},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.270931Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:7adc5ee7164fc49db1590fe0765135cb7058f8de4307a6262d15f5b0d1d1b58c","observation_id":"3ee05dfa-a5cb-461d-adb3-911a2a62b06b","resolution":{"observed_at":"2026-08-11T14:54:53.150549Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.135379Z","title":"Symmetry breaking and equivariant neural networks","venue":null,"work_id":"ba4350cd-d057-4081-9c8a-784bcc1b91e0","year":2023},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.273709Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:2644f84044447803b57c23dc5b9711e23e8383e06e7bf1f4394b8281581866eb","observation_id":"01866553-d9b2-487c-adb3-e2c6dbb91b38","resolution":{"observed_at":"2026-08-11T14:54:53.139518Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.124620Z","title":"Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei","venue":null,"work_id":"9093cc85-9ab5-4e58-8e14-13a6da9e0ca0","year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.276524Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:f9086621cc5b88fc8a75d25c7a00df89c0ee1375a26f6dabd7887045bccdee6f","observation_id":"ee3b96cd-c9a5-4b12-bc0c-3aa6681769bc","resolution":{"observed_at":"2026-08-11T14:54:53.128853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.115244Z","title":"Anderson Keller and Max Welling","venue":null,"work_id":"13add4ed-5469-4819-b506-d3af0e0e703f","year":2021},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.279194Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:d63fec137628a3ac3cda1f907c9d16525cdccee308e191a1d92b787983422849","observation_id":"2976c591-2772-4945-856a-d9b6a3ee94c0","resolution":{"observed_at":"2026-08-11T14:54:53.118147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.105831Z","title":"Anderson Keller and Max Welling","venue":null,"work_id":"7d4f84e4-a773-44cf-875e-4ee8b60e926b","year":2021},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.282059Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:7a98d9ac5535e363ea40d9c3b8495eb90ce1607b8b7b8c3142ac00580da06d1d","observation_id":"2470bf8f-2e36-4450-8b9f-930323e2e1d6","resolution":{"observed_at":"2026-08-11T14:54:53.108905Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.096575Z","title":"The formation and transformation of the perceptual world","venue":null,"work_id":"3e86d1c6-24b6-4e2b-b0e6-5f5650e94842","year":1963},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.284701Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:c8c2a407b9ab4471d2b2f6debc709e66fd140b3bd37ae1fa6f1d20db398a9ded","observation_id":"c6f0bc1c-f20e-467b-a209-180cd8ff2e8c","resolution":{"observed_at":"2026-08-11T14:54:53.099707Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.287477Z","title":"LeCun, L","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.287477Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:4d612e5298a93008840016a5c52a5caa321c8ade2685cc56cb6ebd9d0a87480f","observation_id":"d6b6140d-01b2-4338-a11d-af73ea12f322","resolution":{"observed_at":"2026-08-11T14:54:52.287477Z","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":"2026-08-11T14:54:53.080056Z","title":"Deep neural networks as Gaussian processes","venue":null,"work_id":"921829fa-7f3f-42f6-9a45-1ef28e5fee0b","year":2018},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.290260Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:ce872e482b13b7ccf3a4cfb54cc70fdc78a2417b08b01c255cdab3653346726a","observation_id":"65b4ce52-7ae8-4ae1-aeb4-84ce240f9444","resolution":{"observed_at":"2026-08-11T14:54:53.083780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.069751Z","title":"How diffusion models learn to factorize and compose","venue":null,"work_id":"b8f254cc-71a8-4b68-ae67-a923c31eaf90","year":2024},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.293274Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:f42dfdcacad5d74295c55da7f69e1f1b37bd5a8938873b5960e259c70cdc9b5f","observation_id":"e26e368d-64b6-46a9-9dfd-91ca2133be81","resolution":{"observed_at":"2026-08-11T14:54:53.073563Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.059353Z","title":"When does compositional structure yield compositional generalization? A kernel theory","venue":null,"work_id":"ecbd4c55-447a-4d15-b2a7-6c75086e60c8","year":2025},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.296062Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:0b0eaff7b7e69ceca15756d64aacbc39882cd918be20ce99e3135f7a5b7f5c82","observation_id":"1574801a-3c8d-4441-abab-ca6947b47d6c","resolution":{"observed_at":"2026-08-11T14:54:53.063198Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.049098Z","title":"When and how convolutional neural networks generalize to out-of-distribution category–viewpoint combinations","venue":null,"work_id":"b028eb24-1bd5-43b8-9669-a3b7d4bb8d4b","year":2022},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.298764Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:e6ed9413aaf8b5c4f3257022408000fe2b2f9055388e0599766eaf1ae37a4899","observation_id":"e2b67b8d-4b50-446c-bdb0-63fedec4a090","resolution":{"observed_at":"2026-08-11T14:54:53.052656Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.038053Z","title":"In-distribution adversarial attacks on object recognition models using gradient-free search","venue":null,"work_id":"5e71f370-8cb7-434c-b7c6-8fb2d083a9c8","year":2025},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.301761Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:ce4e252877fbeb4ccd9afe76fad03e24f3227d6e8e4dd24479e9690f41f8e1e0","observation_id":"b17b9d4a-b8db-4e5e-8d31-d34f6e34ce2f","resolution":{"observed_at":"2026-08-11T14:54:53.042030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.026926Z","title":"Harmonics of learning: Universal fourier features emerge in invariant networks","venue":null,"work_id":"000169fc-e1fc-4241-b047-f9ff2747f7d9","year":2024},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.304592Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:1ebe728eb0f608a8bcb1257d8bacc97dee3103c5431158fd0330f72d34aaaf97","observation_id":"b2365ad3-af16-4ad4-b1a4-3228c42ac43e","resolution":{"observed_at":"2026-08-11T14:54:53.030683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.016473Z","title":"A mean field view of the landscape of two-layer neural networks","venue":null,"work_id":"b3f9d21b-c9dc-44b4-81ae-e455b59ef993","year":2018},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.307385Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:646c2357b6e3326963772547f594ee89d60878f64820e5373c986c96d5801089","observation_id":"bf51d45d-6181-4674-ac47-17722b53dc03","resolution":{"observed_at":"2026-08-11T14:54:53.020263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:53.006618Z","title":null,"venue":null,"work_id":"75b977ab-720e-419b-8684-80a2a0bf0485","year":2021},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.310492Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:f6f394e52dd7cd2043f42f14bb4dd7600ef3f28de8eb4ba41750195965a3f9d0","observation_id":"fe864674-bbd7-4278-a65a-555d46280b27","resolution":{"observed_at":"2026-08-11T14:54:53.009561Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.997769Z","title":"Symmetry-induced disentanglement on graphs","venue":null,"work_id":"6fdcb4c6-f7cb-48a8-bd6d-a651517e7366","year":2022},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.313350Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:8dba49d479a4af58efac8f802ce4a4b0cd8e78c5ac0a435799e367ab887ebb57","observation_id":"a883e6ff-ed95-427a-90e0-0ac12e87b94b","resolution":{"observed_at":"2026-08-11T14:54:53.000826Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.988705Z","title":"Smeulders","venue":null,"work_id":"27117d70-dbba-4e8f-ab70-289c19912ad1","year":2023},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.316979Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:7384feff4d4f6d97789b7ac6094c3bc4122cc5423f39fad1730eaebd7694a893","observation_id":"ed918246-9c34-4b25-9996-bbb878923ad7","resolution":{"observed_at":"2026-08-11T14:54:52.991902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.320707Z","title":null,"venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.320707Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:0b531f329aa87ba17691387f12f8097a83892eaef35e77fc80a9a2841eb4504f","observation_id":"84bd565c-3d72-4548-a621-6d57c69bdf79","resolution":{"observed_at":"2026-08-11T14:54:52.320707Z","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":"2026-08-11T14:54:52.973704Z","title":null,"venue":null,"work_id":"6169486d-9a82-4cf8-bdde-cffd5b3fb55a","year":1918},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.324341Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:c5f441d639f313cd185d3492cb7b500ac837ca90a30e776efe24cbf32e804ee0","observation_id":"35e1f539-7ffc-40ef-b785-9a46bd179881","resolution":{"observed_at":"2026-08-11T14:54:52.976599Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.964535Z","title":"Ensembles provably learn equivariance through data augmentation","venue":null,"work_id":"9795944e-b5f1-4107-8502-3fd6dd077645","year":2024},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.327961Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:2c0c1536a692fae1fddee79eb6ae82809b809672a90bdc7df567ba6bd58427eb","observation_id":"ed5c878d-e734-474a-8c5f-4b693606672e","resolution":{"observed_at":"2026-08-11T14:54:52.967520Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.956102Z","title":"Alemi, Jascha Sohl-Dickstein, and Samuel S","venue":null,"work_id":"7f58ffb9-1848-4277-9fa6-80329d784336","year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.331507Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:04277cd89140fd256269ef07d1a3de29d25ebf29784822f9f76dfcad08ff4b19","observation_id":"2b23169f-1bd2-471c-9808-037b0cb4ee58","resolution":{"observed_at":"2026-08-11T14:54:52.959101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.946499Z","title":"A comparison between humans and AI at recognizing objects in unusual poses","venue":null,"work_id":"f943f342-7a06-4f8c-8a24-1e75d1183882","year":2025},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.334954Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:06d083ce20971d4e04b8181587bb5dee7aac3725defd50026dce90a49865d253","observation_id":"6ad189f5-450b-4aa8-94a9-5df3474beaf6","resolution":{"observed_at":"2026-08-11T14:54:52.950263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.936160Z","title":"Neural anisotropy directions","venue":null,"work_id":"91917c58-590c-46ad-9bf1-1c2ead514dc0","year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.338537Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:6cdcbbfef9ced8873799831420641b2b9eb3952d1e2b8a2c2358dca79cc41228","observation_id":"3ffd66cc-a638-4f1b-99fc-c1be5766d393","resolution":{"observed_at":"2026-08-11T14:54:52.939647Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.925919Z","title":"Breaking the symmetry: Mirror discrimination for single letters but not for pictures in the visual word form area","venue":null,"work_id":"07ce9b0e-7d24-41ff-9b7e-4c1a9be047e2","year":2011},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.342130Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:83a399ac248de653a881efd67294668ba61d92472e7fa083bc1c91118e1a770c","observation_id":"bccb5c8b-6454-4338-904a-1a1442d060f2","resolution":{"observed_at":"2026-08-11T14:54:52.929916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.914635Z","title":"Suppression of mirror generalization for reversible letters: Evidence from masked priming","venue":null,"work_id":"6b4b38c9-5df5-4ac2-ae8d-62db6ebd29e2","year":2011},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.345776Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:6cc36dc039c56554e187b6e938d4f53aee9f7552fd5de68681e08c398e47cabf","observation_id":"b5b40bb3-e882-479c-bcb4-8157ebd5d9a4","resolution":{"observed_at":"2026-08-11T14:54:52.918235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.904783Z","title":"Equivariant representation learning in the presence of stabilizers","venue":null,"work_id":"76f5184d-0c9a-4fc9-aa64-b704214b1665","year":2023},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.349110Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:118751c9af49957c6398e6b384fbd9ee8a845a9336110b097d11fc793690f2ab","observation_id":"3a2752e8-3ca7-4c24-a364-23be8e72fe15","resolution":{"observed_at":"2026-08-11T14:54:52.908360Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.895386Z","title":"Disentangling by subspace diffusion","venue":null,"work_id":"ad5dd0d2-aafe-43ac-b649-38ed376532e6","year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.352556Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:76fec3023054bff763367240dc1735bb15d94a314249af187eb2e89753d0aefe","observation_id":"3c7aae7d-42f3-4fa8-ad14-4e2cb492545a","resolution":{"observed_at":"2026-08-11T14:54:52.898857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.885622Z","title":"Grokking: Generalization beyond overfitting on small algorithmic datasets","venue":null,"work_id":"39a8eb02-096a-4169-97ef-4a4f4f2742ed","year":2022},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.355749Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:8deef00ebdf15ee45110b26184b085c74ac0df125d290f6f28d1df2a0e92b052","observation_id":"392be3de-9ca3-4a13-8de8-24c3893b2518","resolution":{"observed_at":"2026-08-11T14:54:52.888996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.876073Z","title":"Dynamic routing between capsules","venue":null,"work_id":"c1d7fab0-4a11-4212-ba45-bb9ae4b88f93","year":2017},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.358851Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:7efaef97eaa21d3297ef5729d9f5ef6e8789b3289ed38c82839711eb306fb6a7","observation_id":"88e0556c-2f73-4fd2-a0d3-0da4f872bd32","resolution":{"observed_at":"2026-08-11T14:54:52.879542Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.867176Z","title":"An analytical theory of curriculum learning in teacher-student networks","venue":null,"work_id":"af666e2d-452b-4e7f-a0ea-a94417186134","year":2022},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":89,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.362167Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:766f242d16697b0784212b0c448848449184d0d3d845e98950e2d28769882629","observation_id":"a5d3e30a-6023-427a-8eb5-d251aeaa706a","resolution":{"observed_at":"2026-08-11T14:54:52.870460Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.859185Z","title":null,"venue":null,"work_id":"a2c5a7c1-d8bf-4cd4-8b5c-5f0b997ba5c7","year":2023},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.365390Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:db7f9817bce9c236cac576056771ca1103dc445a5047c8e52af980c3e8ea32c5","observation_id":"b66a3000-6918-43eb-9358-f155a3b143c9","resolution":{"observed_at":"2026-08-11T14:54:52.861748Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.850678Z","title":"Saxe, James L","venue":null,"work_id":"01eaa33d-3aeb-468f-9ba7-d0da21f4f0ca","year":2019},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.368578Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:36b62956ba193a3e3df7f7991e8a73ba60857a914d9b8df32076d641c7f3e0cf","observation_id":"86471740-040b-46c7-a0a1-eb0fe559e507","resolution":{"observed_at":"2026-08-11T14:54:52.853447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.842120Z","title":"u gelgen, Frederik Tr \\","venue":null,"work_id":"87196599-7d78-4db7-ab34-6356575f14a4","year":2022},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":92,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.372097Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:7eeff65c034b59c57d24bc6758c3e430b12c06c290492335ac24c25e733ce631","observation_id":"91cd2aa6-c58b-4a94-8a39-94b7b1cbf3f7","resolution":{"observed_at":"2026-08-11T14:54:52.844978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.832525Z","title":"Laion-5b: An open large-scale dataset for training next generation image-text models","venue":null,"work_id":"08acb35f-2d5c-4d31-955f-ca646b013283","year":2022},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.375200Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:a83665a0563201a3a2e0590434bccc802378439ef460337083424725bc521175","observation_id":"88f7eaef-919d-4c94-9750-ad30d3b945cc","resolution":{"observed_at":"2026-08-11T14:54:52.835540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.823648Z","title":"The pitfalls of simplicity bias in neural networks","venue":null,"work_id":"d9ae2d51-0d28-4aa2-9152-a1913ae82fd0","year":2020},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":94,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.378629Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:ade4a6db8d47befac742c609b5be7b46e902cf76156e840e9611608aafbaba03","observation_id":"3d251193-8efe-4dd2-b8f8-5b4de7936c91","resolution":{"observed_at":"2026-08-11T14:54:52.826670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.814107Z","title":"Shepard and Jacqueline Metzler","venue":null,"work_id":"35ffe8ab-23e7-45b6-ace1-c695b66fbe0d","year":1971},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.381873Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:1970a9a6b5df62f0b943018794914e601a39062d7e7a97e6ebc199c7354340d9","observation_id":"3c9cd70a-9721-4c37-9dcb-b80b16da5404","resolution":{"observed_at":"2026-08-11T14:54:52.817404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.803556Z","title":"Investigating the nature of 3D generalization in deep neural networks","venue":null,"work_id":"fc59ac31-98f6-407a-9725-0262080b0c47","year":2023},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":96,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.385418Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:14a9e6b72180de2a2741ac3349d3d29fbc7f9a599f087ef5237461521a99d655","observation_id":"dd9ebf38-52c4-45c4-a7fb-a27186c4b013","resolution":{"observed_at":"2026-08-11T14:54:52.807672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.793339Z","title":"Geometry of the loss landscape in overparameterized neural networks: Symmetries and invariances","venue":null,"work_id":"94971d5e-a20b-4e5c-acd7-6c8877e9b0a5","year":2021},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":97,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.388269Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:5d51a6f997c7a1b0837d3649486c678dcf891497c88cd571f4ad76afe5120ba1","observation_id":"b47681c1-84dd-460b-ad2c-8dcdd6723855","resolution":{"observed_at":"2026-08-11T14:54:52.797049Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.783718Z","title":"Revisiting weakly supervised pre-training of visual perception models","venue":null,"work_id":"98f79b07-fc24-4607-a670-737f4a858196","year":2022},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":98,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.390975Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:1837713643bc9b07746d443c604223cf8cb05552deccfd6c8d083037a6ef1a5d","observation_id":"fbb63719-a0b0-40a3-a35b-6d08b4968377","resolution":{"observed_at":"2026-08-11T14:54:52.787192Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.773267Z","title":"Olshausen","venue":null,"work_id":"9fdbda4e-8308-45e6-b067-a4c60df2af3d","year":2017},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":99,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.393842Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:5053ef606a14a87e7cc03d9243649e2a85beb334f1cafb628779247ef012e1ef","observation_id":"f38dc5d9-fb94-4373-8643-792cbdf1f385","resolution":{"observed_at":"2026-08-11T14:54:52.776617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-11T14:54:52.763614Z","title":"Neural representational geometry underlies few-shot concept learning","venue":null,"work_id":"49750ee6-5d62-42ab-bc56-4789a5d7bb94","year":2022},"citing_paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory","version":2},"reference_index":100,"source":"arxiv_source","source_observed_at":"2026-08-11T14:54:52.396995Z"},"links":{"citing_paper":"/paper/2412.11521"},"observation_digest":"sha256:59ee71dac7855afbc0af6221e251eec5f2a7a3ff62e01f0e2f8eb67d5fa7a6c3","observation_id":"cbb9313d-fe76-4269-bc37-bd66043d67c3","resolution":{"observed_at":"2026-08-11T14:54:52.767061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.11521","last_updated":"2025-06-26T15:02:44Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T04:48:35.772604Z","submitted_at":"2024-12-16T07:56:54Z","title":"On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":52,"verified_exact":0,"verified_fuzzy":48},"total_outbound_references":126},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 100 of 126 outbound references and 1 inbound Pith citation observation for arXiv:2412.11521."}