{"as_of":"2026-08-10T01:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c5c4d5ba764a791eda8d273cd817c14a5524d21c6f6dbda038e44994b7e2cf0e","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-12T04:51:08.903724Z","state":"measured"},{"denominator":24,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":24,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.03108/citation-record","integrity":"/paper/2607.03108/integrity","json":"/paper/2607.03108/citation-record.json","paper":"/paper/2607.03108"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T04:51:08.903724Z","title":"Implicit regularization in deep matrix factorization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:f257bc6e5aba8a7e477afb3cf67fa1e697c39904418925d623d56a47f103c848","observation_id":"8323e7b4-d4ee-4e63-abb8-0e2e8696644f","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.13478","last_updated":"2021-05-02T16:16:03Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-04-27T21:09:51Z","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.13478","snapshot_observed_at":"2026-07-12T04:51:08.903724Z","title":"Bronstein, Joan Bruna, Taco Cohen, and Petar Veliˇckovi´c","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"cited_paper":"/paper/2104.13478","citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:91e4ecb86c8e4c113b2b415e9516647e57ddc1934fe5ad246127dcaaddc0bdf1","observation_id":"93eb368c-5a05-47e2-a653-5bfc559416ef","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"Group equivariant convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:6f9d8367a44a788a9ba83fecfcb86fc72ec936673c62605a2b0b3327ef32472a","observation_id":"2d912d22-a04c-4107-b996-be4bcd6ac0f6","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"Deep learning on implicit neural representations of shapes","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:0b79b1d48da0ac7528d8c8bfe4e2ee5e445de23e109e6bcc7e554d1abad0b5df","observation_id":"c1cbc51b-6ba5-4636-937a-184c504880f4","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"Automatic symmetry discovery with lie algebra convolutional network","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:1f3a67b4b3ff53ff10c999540b0e66ee6f57a75b5c9430814598f205b062caf3","observation_id":"f1ff247a-dc5d-42c4-8e3c-eef1772e2809","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:f3ed892dd2d32fa29d429f08cc5c7bf997026f8277491abada571f4580fe4ea3","observation_id":"cf744a34-1b13-425f-b1a9-f2edf3f7f3d4","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"On the symmetries of deep learning models and their internal representations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:54cff2509d1a7c7ce9b4c08345d2bfaaea3ae24e8dcef717d4afd459aafdefd1","observation_id":"233fa43d-6204-4192-8485-768d2d46cb7a","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.09841","last_updated":"2024-10-13T13:39:39Z","snapshot_observed_at":"2026-08-03T21:46:04.540336Z","submitted_at":"2024-10-13T13:39:39Z","title":"Symmetry Discovery for Different Data Types","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.09841","snapshot_observed_at":"2026-07-12T04:51:08.903724Z","title":"Symmetry discovery for different data types.arXiv preprint arXiv:2410.09841, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"cited_paper":"/paper/2410.09841","citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:2086e5a9a9388d6f95c31b2cddf6df4ad75019a6986f6c3f9b4c1773b988265e","observation_id":"955f0176-ddde-47c5-b187-eeadf5ff698d","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"Kingma and Jimmy Ba","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:faff49439b62932ad05cb4f5bf437a7a4646eacc46b7ec8b91f2d839771a5423","observation_id":"092c6059-e23a-4884-bc87-ae559a476d0d","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"SGDR: Stochastic gradient descent with warm restarts","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:c2c85f40f4473bda2cdc6b95a60a313b8758957bde90489fef2affe9d47bcb81","observation_id":"06a682f0-2fc8-42b8-abec-89710ce3d96f","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"Srinivasan, Matthew Tancik, Jonathan T","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:57ccd2ef905b89fcff50d25bff26625889581a0f6d7775796108da2e457d7d71","observation_id":"92f5638b-5401-4e65-b38d-2fea033f6fdd","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"Liegg: studying learned lie group generators","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:37a98e13f6355d06ff81d9fd7fe3b9c147eaa8fa6ad273f26afb944d25b99f99","observation_id":"09aba1a5-6b5b-4131-8cdc-700b1b2f0d11","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"Equivariant architectures for learning in deep weight spaces","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:005a5eec4df6a9ebb396e5bec6afbccecf321b715786d7baf8430c0d9e28d52a","observation_id":"bee0bdcd-ae49-4fc2-bf82-4274ffad8fc1","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"Hamprecht, Yoshua Bengio, and Aaron Courville","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:4f90f46c2940ca05b0f7c84aeb96c161bf44d046e8e38b7dfaab63c7bdf651d0","observation_id":"15c3d6ad-18ca-485a-bce0-c7b64b61f69d","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"Random features for large-scale kernel machines","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:e86a574f6640c84a4b6988835b322f7b0b604a6ec199ca7b21943222912f0625","observation_id":"d22922a5-3370-4948-b2dd-222c0bee8f63","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"E(n) equivariant graph neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:0de11a40724c99487e406e1cf1ce1cd731b9e4d7f07123a32b82a80ac4592072","observation_id":"f524a5c4-59c0-457f-96c6-ebf1df184a5a","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"Saxe, James L","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:fa7a496dcc5f6e1404db0d6d0e200c20c5fd4342b47c08973073b597ec2d8b6a","observation_id":"538cd878-b5de-41ae-9c59-9907cf0636a7","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"Schönemann","venue":null,"work_id":null,"year":1966},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:b2e0438fcaa08f499fb759f3a2516c129ea365945cae26a7d4040e272d3061fd","observation_id":"2a5a2f09-3de2-4a19-94da-226b71f9aabd","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:612930189361e828efd4dc01e8d0c7e7e3846e6f10d80f4f09cae23ea4184816","observation_id":"d95d5725-b966-4695-baa6-f94da3183ed2","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan T","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:48cee964d7e702bb731f15fc546e30b6e5f15147a0e85367b03f8a2759242a9a","observation_id":"c5fee03c-340d-4cc4-91be-771d73df20f4","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"General e(2)-equivariant steerable cnns","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:b91076082ad6e99e9ca78594d252d25125d8385bbda834053a0f2ca167bc1af3","observation_id":"8a4cacd0-c2c7-4153-9d18-3e0035f80266","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"Group representational position embedding","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:d2e18025746566a47c00d431c57fdd074b2ab9208a7c2cea8783e9fc9cabda9a","observation_id":"5e87d653-410b-4765-95b5-6191a88fb2fb","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","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":"2026-07-12T04:51:08.903724Z","title":"Symmetry in neural network parameter spaces.Transac- tions on Machine Learning Research, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:eb25eb34e2443e1488f5b1fd74c5c4a37499f1eab753ba4cb6f4859ea39814d9","observation_id":"a3453fb6-a078-4e92-a8d1-3a926df94e29","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.05300","last_updated":"2025-05-23T17:22:54Z","snapshot_observed_at":"2026-08-09T04:49:29.861223Z","submitted_at":"2025-02-07T20:10:05Z","title":"Parameter Symmetry Potentially Unifies Deep Learning Theory","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.05300","snapshot_observed_at":"2026-07-12T04:51:08.903724Z","title":"Parameter symmetry potentially unifies deep learning theory.arXiv preprint arXiv:2502.05300, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-12T04:51:08.903724Z"},"links":{"cited_paper":"/paper/2502.05300","citing_paper":"/paper/2607.03108"},"observation_digest":"sha256:03b7cb6df30fd6a0c878faac817c26dc5ad69b06ba44ff61f71089101c44f435","observation_id":"c2521a33-80e7-40bc-b476-70eada18c351","resolution":{"observed_at":"2026-07-12T04:51:08.903724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.03108","last_updated":"2026-07-03T08:43:47Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T04:50:02.780514Z","submitted_at":"2026-07-03T08:43:47Z","title":"Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":24},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2607.03108."}