{"as_of":"2026-08-13T18:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ecc2e9c3a03d158122210f746c408557cab948d0a2a789f194cca3d62a5a9dcf","coverage":[{"denominator":300,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T20:23:10.525489Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2411.09827/citation-record","integrity":"/paper/2411.09827/integrity","json":"/paper/2411.09827/citation-record.json","paper":"/paper/2411.09827"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:23:10.118455Z","title":"Convolutional neural networks for speech recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.118455Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:ba46e3ce9cf754820473449a487979e398df5063a175c24dc67bee42664c3e54","observation_id":"e11e364b-36a9-4b7c-b3ec-1817e17a14b5","resolution":{"observed_at":"2026-08-12T20:23:10.118455Z","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":"2026-08-12T20:23:10.123535Z","title":"End-to-end en- vironmental sound classification using a 1d convolutional neural network","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.123535Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:32518638562e936f501be946b35a9b5da9584df0376c3c53a9229db190dab0d4","observation_id":"8c5a3761-00fb-405b-8abf-4240443e2e3f","resolution":{"observed_at":"2026-08-12T20:23:10.123535Z","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":"2026-08-12T20:23:10.127774Z","title":"Applications of the generalized fourier transform in numerical linear algebra","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.127774Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:f5b4fa46ac63bf5ae39e537f895e4943138fd529f4e72412c1c5efb2bfa9c7a1","observation_id":"f09fda75-2b11-49e7-8752-d9ae6f20528e","resolution":{"observed_at":"2026-08-12T20:23:10.127774Z","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":"2026-08-12T20:23:10.132036Z","title":"Noether networks: meta-learning useful conserved quantities","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.132036Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:e6c0619bdc711787e4fe039380e7694b7dddc1ad8861fe31d3cdcc7cea90e470","observation_id":"2c279756-1f80-4739-bc36-4aed75f0ade2","resolution":{"observed_at":"2026-08-12T20:23:10.132036Z","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":"2026-08-12T20:23:10.136296Z","title":"Statistical applications for equivariant matrices","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.136296Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:62d36d08c9af2cad6e75f91f2bc0730254d5c8889093fc2fe4b905392530e806","observation_id":"5c1d7ecb-78be-4095-a96a-e05b523966a7","resolution":{"observed_at":"2026-08-12T20:23:10.136296Z","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":"2026-08-12T20:23:10.140657Z","title":"Deep scattering spectrum","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.140657Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:800ad6db43fc5d1ffaccb89c6d6e6b44b4b89d26e8e7eb9cbd1f483a5deefea9","observation_id":"a8075a40-fa03-4594-906f-72a63f930bf2","resolution":{"observed_at":"2026-08-12T20:23:10.140657Z","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":"2026-08-12T20:23:10.145316Z","title":"Unitary evolution recurrent neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.145316Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:58c08b5e1a5595b31162df42b90b372e46f8b34365385688a25bb8164580eced","observation_id":"3bfaa6e3-d7b5-41b3-b643-370f562f7c06","resolution":{"observed_at":"2026-08-12T20:23:10.145316Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1607.06450","last_updated":"2016-07-21T19:57:52Z","snapshot_observed_at":"2026-08-12T08:59:05.030983Z","submitted_at":"2016-07-21T19:57:52Z","title":"Layer Normalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1607.06450","snapshot_observed_at":"2026-08-12T20:23:10.149647Z","title":"Layer normalization","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.149647Z"},"links":{"cited_paper":"/paper/1607.06450","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:2fc9072549e8e4b20ae00a0b3e89bc04c302f3c5fb1576e28e2e3b89bcad941e","observation_id":"718249ed-3d6f-4c8c-b500-382355563e1a","resolution":{"observed_at":"2026-08-12T20:23:10.149647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.00075","last_updated":"2018-10-31T19:24:20Z","snapshot_observed_at":"2026-08-10T23:37:46.162225Z","submitted_at":"2018-10-31T19:24:20Z","title":"The UEA multivariate time series classification archive, 2018","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.00075","snapshot_observed_at":"2026-08-12T20:23:10.154378Z","title":"The uea multivariate time series classification archive, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.154378Z"},"links":{"cited_paper":"/paper/1811.00075","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:74324cd8108776600d8283e205665e6f64a740fbb79f505cd7d1fdc87e8ab2c4","observation_id":"c1aef4fe-4afe-4994-8037-52401c660ae3","resolution":{"observed_at":"2026-08-12T20:23:10.154378Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.0473","last_updated":"2016-05-19T21:53:22Z","snapshot_observed_at":"2026-08-12T12:07:33.202888Z","submitted_at":"2014-09-01T16:33:02Z","title":"Neural Machine Translation by Jointly Learning to Align and Translate","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.0473","snapshot_observed_at":"2026-08-12T20:23:10.158470Z","title":"Neural machine trans- lation by jointly learning to align and translate","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.158470Z"},"links":{"cited_paper":"/paper/1409.0473","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:c6edde69ac667e98cf1dc4be1384b9cdb2cdee01d4775dc8b6a17e81b9fcba9d","observation_id":"5ce87031-53de-44ae-84fc-684bf0f9648a","resolution":{"observed_at":"2026-08-12T20:23:10.158470Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.01271","last_updated":"2018-04-19T14:32:38Z","snapshot_observed_at":"2026-08-13T10:37:24.864456Z","submitted_at":"2018-03-04T00:20:29Z","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.01271","snapshot_observed_at":"2026-08-12T20:23:10.163212Z","title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.163212Z"},"links":{"cited_paper":"/paper/1803.01271","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:79aee7b9e7d53086c4cf498b49f56ea21836fce7c71c73363c16e6ea92f14844","observation_id":"7cf8222a-1af9-4b97-aa75-c59290f4cb8c","resolution":{"observed_at":"2026-08-12T20:23:10.163212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.06682","last_updated":"2019-03-11T21:37:42Z","snapshot_observed_at":"2026-08-02T04:51:39.379194Z","submitted_at":"2018-10-15T20:50:05Z","title":"Trellis Networks for Sequence Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.06682","snapshot_observed_at":"2026-08-12T20:23:10.167870Z","title":"Trellis networks for sequence mod- eling","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.167870Z"},"links":{"cited_paper":"/paper/1810.06682","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:a109b10176eda4a798c7d005fff57106d38d94b7092791ff7c7b01776922a450","observation_id":"1bf6fe04-0ad3-4190-a56a-86166bc0f8a3","resolution":{"observed_at":"2026-08-12T20:23:10.167870Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.06576","last_updated":"2018-11-11T23:01:58Z","snapshot_observed_at":"2026-08-13T04:38:36.713754Z","submitted_at":"2018-05-17T02:04:54Z","title":"Mad Max: Affine Spline Insights into Deep Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.06576","snapshot_observed_at":"2026-08-12T20:23:10.172111Z","title":"Mad max: Affine spline insights into deep learning","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.172111Z"},"links":{"cited_paper":"/paper/1805.06576","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:2ba1c3d16ef0862674eb43f5f2a1939b527a7c790fcdef7bf8969d4d60c8a241","observation_id":"1c3895bb-42d2-47e2-8ca1-053bc5e874ac","resolution":{"observed_at":"2026-08-12T20:23:10.172111Z","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":"2026-08-12T20:23:10.176147Z","title":"The quickhull algo- rithm for convex hulls","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.176147Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:78b8b6849244b5920c6ed1f05ed07aa3a94410e06ca02c5845cf131341027de4","observation_id":"e5fcb9d9-a912-4245-be0a-fbac6114dd1e","resolution":{"observed_at":"2026-08-12T20:23:10.176147Z","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":"2026-08-12T20:23:10.180429Z","title":"Ai in healthcare: Ethical and privacy challenges","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.180429Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:0c82e7ce824e7ba8e1ff92a245a8b0607d0be0dc01682f9e8f1bd2dab4582150","observation_id":"7a022ede-63b2-4638-98bd-b4abc9a9986f","resolution":{"observed_at":"2026-08-12T20:23:10.180429Z","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":"2026-08-12T20:23:10.184680Z","title":"Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.184680Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:9c0c967b3be862bfa725abe2530397937c533b9c4530df46f61ff6c1be8914d8","observation_id":"0a9a7e34-1043-4d9a-a5a2-4b2af2de6ab1","resolution":{"observed_at":"2026-08-12T20:23:10.184680Z","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":"2026-08-12T20:23:10.188368Z","title":"B-spline {cnn}s on lie groups","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.188368Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:8fc07cf744a14e2b24c951197ac00981b241f906ca8114260a5f01b4f1045213","observation_id":"ea1829e3-bcd2-49d5-893e-5bcb0c82357f","resolution":{"observed_at":"2026-08-12T20:23:10.188368Z","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":"2026-08-12T20:23:10.192012Z","title":"Roto-translation covariant convolutional networks for medical image analysis","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.192012Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:f5b113a879f4c324e5036d9213a93f3b1ce1c7a462dfb3736c187d464ec18ac5","observation_id":"0c153033-1e5e-48b2-ad8b-a5b9143589d1","resolution":{"observed_at":"2026-08-12T20:23:10.192012Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02970","last_updated":"2024-03-15T09:21:33Z","snapshot_observed_at":"2026-08-13T08:02:20.671371Z","submitted_at":"2023-10-04T17:06:32Z","title":"Fast, Expressive SE$(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.02970","snapshot_observed_at":"2026-08-12T20:23:10.195721Z","title":"Fast, expressive se (n) equivariant networks through weight- sharing in position-orientation space","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.195721Z"},"links":{"cited_paper":"/paper/2310.02970","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:cc851be8249842fdea13b927a93452b0ee2345c8284a0b482c090e73b3243fa1","observation_id":"fac25b0a-f3c9-4706-b7d7-729506bcba08","resolution":{"observed_at":"2026-08-12T20:23:10.195721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.09925","last_updated":"2020-09-09T18:52:40Z","snapshot_observed_at":"2026-08-12T18:53:58.175023Z","submitted_at":"2019-04-22T15:31:15Z","title":"Attention Augmented Convolutional Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.09925","snapshot_observed_at":"2026-08-12T20:23:10.201427Z","title":"At- tention augmented convolutional networks","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.201427Z"},"links":{"cited_paper":"/paper/1904.09925","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:4b22412568b0d15ce4edb9c79b32e0cc09a54e1d9e3af2caee2cba5fa1e7d3bb","observation_id":"366e2afd-7e77-4b1b-ac28-408771b831dc","resolution":{"observed_at":"2026-08-12T20:23:10.201427Z","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":"2026-08-12T20:23:10.205519Z","title":"Understanding and simplifying one-shot architecture search","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.205519Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:3b6c2df8109ab829539b5d178dd83a029f8e626c91cb4a4b11647feb71bb67b1","observation_id":"1fde48de-1b30-4fc4-bb92-287d385edcd7","resolution":{"observed_at":"2026-08-12T20:23:10.205519Z","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":"2026-08-12T20:23:10.209645Z","title":"Learning long-term depen- BIBLIOGRAPHY 193 dencies with gradient descent is difficult","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.209645Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:289605af7d51f7111d8fe6cbc921b4a0519cd5e12b109edfef724a010912c90d","observation_id":"531fc08f-1262-48c4-a99c-593b3a208dc0","resolution":{"observed_at":"2026-08-12T20:23:10.209645Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1308.3432","last_updated":"2013-08-15T15:19:34Z","snapshot_observed_at":"2026-08-11T05:54:56.124984Z","submitted_at":"2013-08-15T15:19:34Z","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1308.3432","snapshot_observed_at":"2026-08-12T20:23:10.213618Z","title":"Estimating or propa- gating gradients through stochastic neurons for conditional computation","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.213618Z"},"links":{"cited_paper":"/paper/1308.3432","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:69e12a2f7d32f621bfcdc837164954945f8e96ade9f8278715c4dcfee2892e81","observation_id":"ac83db19-af63-4ff4-87d5-365555edbdaa","resolution":{"observed_at":"2026-08-12T20:23:10.213618Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.09336","last_updated":"2021-01-22T21:13:46Z","snapshot_observed_at":"2026-08-07T00:40:56.156835Z","submitted_at":"2021-01-22T21:13:46Z","title":"A Comprehensive Survey on Hardware-Aware Neural Architecture Search","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.09336","snapshot_observed_at":"2026-08-12T20:23:10.218303Z","title":"A comprehensive survey on hardware-aware neural architecture search","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.218303Z"},"links":{"cited_paper":"/paper/2101.09336","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:138787146b1027416afae49bbf3d08f41b6f273625c2f6f4d320d836eefbd186","observation_id":"923d8782-a2fd-443c-98ef-aa2c08b0b9d6","resolution":{"observed_at":"2026-08-12T20:23:10.218303Z","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":"2026-08-12T20:23:10.222543Z","title":"Learning invariances in neural networks from training data","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.222543Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:bca04dd1fc128461468274312e16779b8d69a9f338f1da497349dd5cd09291c2","observation_id":"1ca1973d-9a94-4e6c-b602-d08c4e93b5d4","resolution":{"observed_at":"2026-08-12T20:23:10.222543Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.11831","last_updated":"2020-05-04T10:19:18Z","snapshot_observed_at":"2026-08-13T13:09:11.223767Z","submitted_at":"2019-10-25T16:31:25Z","title":"Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameters","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.11831","snapshot_observed_at":"2026-08-12T20:23:10.226225Z","title":"Stabi- lizing darts with amended gradient estimation on architectural parameters","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.226225Z"},"links":{"cited_paper":"/paper/1910.11831","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:a109862aa946a43a41dc9f448ca4cbef0962a1ee6f74580cb2364c685fb60744","observation_id":"9289d0b8-e9e7-4a2f-8226-e670fdcab652","resolution":{"observed_at":"2026-08-12T20:23:10.226225Z","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":"2026-08-12T20:23:10.230307Z","title":"Spectrotemporal resolution tradeoff in auditory processing as revealed by human auditory brainstem re- sponses and psychophysical indices","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.230307Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:e9d716815b3959f81cd4a3ee13d0f37e0f70c35103585327e5e0b5a786819647","observation_id":"db4db8b7-b92e-44dd-b63f-08e3035031d8","resolution":{"observed_at":"2026-08-12T20:23:10.230307Z","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":"2026-08-12T20:23:10.234264Z","title":"Recognition-by-components: a theory of human image under- standing","venue":null,"work_id":null,"year":1987},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.234264Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:1d406e5500aaf3c64f053d1ecb1f5bad8291fe82bbd9f673b7f8d02991c2b0ab","observation_id":"a7e8efa8-3a97-4f91-9302-47702d852f70","resolution":{"observed_at":"2026-08-12T20:23:10.234264Z","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":"2026-08-12T20:23:10.238043Z","title":"Experiment tracking with weights and biases, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.238043Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:dae5b90678073eb399a4d05a227bc75058e63005347c925ede2ced1a409e59ea","observation_id":"95f298cc-99f5-4260-b29f-566c72336c53","resolution":{"observed_at":"2026-08-12T20:23:10.238043Z","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":"2026-08-12T20:23:10.241823Z","title":"The role of temporal structure in human vision","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.241823Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:4491f8d1cf85b788a712dda5b3e821508533b61cb9b40fda8acde3561e59b57f","observation_id":"d3ce473c-b785-4697-9179-b1ac3b44c75a","resolution":{"observed_at":"2026-08-12T20:23:10.241823Z","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":"2026-08-12T20:23:10.245649Z","title":"Lorentz group equivariant neural network for particle physics","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.245649Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:f66bf7cc8a8db6ad091a9fe630454e9b3525b0368a23e8f07b0edcab52ad3ab0","observation_id":"beea3bfb-61ce-4abe-b101-054cc7ab11aa","resolution":{"observed_at":"2026-08-12T20:23:10.245649Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.05344","last_updated":"2017-08-17T16:03:33Z","snapshot_observed_at":"2026-07-06T05:55:43.085839Z","submitted_at":"2017-08-17T16:03:33Z","title":"SMASH: One-Shot Model Architecture Search through HyperNetworks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.05344","snapshot_observed_at":"2026-08-12T20:23:10.249347Z","title":"Smash: one-shot model architecture search through hypernetworks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.249347Z"},"links":{"cited_paper":"/paper/1708.05344","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:04e0be34c296cac45802b4f1c0c6199bfd34cde8ed90a28fb040a838120268b9","observation_id":"01f1b791-838f-49bb-9444-13374bac91b8","resolution":{"observed_at":"2026-08-12T20:23:10.249347Z","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":"2026-08-12T20:23:10.253528Z","title":"Recognition by children of inverted photos of faces","venue":null,"work_id":null,"year":1963},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.253528Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:3547485d74439aa349b2f2838350ab0b1a61260dee5820cee2b4a3899458120c","observation_id":"e54f600e-f2e6-4ccd-92c0-42acdc90d76c","resolution":{"observed_at":"2026-08-12T20:23:10.253528Z","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":"2026-08-12T20:23:10.257610Z","title":"Language models are few-shot learners","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.257610Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:0478436370fc0e9d20bb9eb4f9a42ecf520a455fcb5d73e51c09e3ffd178de86","observation_id":"97ae06ec-b98c-4988-80b1-c1a5ba5a1a13","resolution":{"observed_at":"2026-08-12T20:23:10.257610Z","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":"2026-08-12T20:23:10.261329Z","title":"Recognizing objects and faces","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.261329Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:21bad97f52d1e63806b6c38757216310b3113d9069e617dcdfba64445d642206","observation_id":"9b08bfad-cbfc-4909-8bb1-2fe6eb6645bf","resolution":{"observed_at":"2026-08-12T20:23:10.261329Z","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":"2026-08-12T20:23:10.265406Z","title":"Invariant scattering convolution networks","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.265406Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:cf1245e9c05a39239b483b37b23a99ff4617a9e7b3ed46d685b9154cfb2bba9a","observation_id":"96f0f204-dac4-4842-91ec-b58151da29e4","resolution":{"observed_at":"2026-08-12T20:23:10.265406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00332","last_updated":"2019-02-23T01:36:47Z","snapshot_observed_at":"2026-08-10T08:54:59.663457Z","submitted_at":"2018-12-02T05:29:53Z","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00332","snapshot_observed_at":"2026-08-12T20:23:10.269189Z","title":"Proxylessnas: Direct neural architecture search on target task and hardware","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.269189Z"},"links":{"cited_paper":"/paper/1812.00332","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:85da1a2bf1378cfae6e4feb216e37e31907f615b62e09b5e750cb2e72460ca5d","observation_id":"fc04c7e3-e568-4c48-a9d7-6fe1ad5d1903","resolution":{"observed_at":"2026-08-12T20:23:10.269189Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.09791","last_updated":"2020-04-29T20:49:05Z","snapshot_observed_at":"2026-08-11T01:59:17.823546Z","submitted_at":"2019-08-26T16:46:23Z","title":"Once-for-All: Train One Network and Specialize it for Efficient Deployment","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.09791","snapshot_observed_at":"2026-08-12T20:23:10.273148Z","title":"Once-for- all: Train one network and specialize it for efficient deployment","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.273148Z"},"links":{"cited_paper":"/paper/1908.09791","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:3ac07f94b503e39d610daa20b03bd566494b6ef542ab557021f4d1edf967c75a","observation_id":"f95f3091-a08d-45c5-85ae-a4541cf293f9","resolution":{"observed_at":"2026-08-12T20:23:10.273148Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.11492","last_updated":"2019-04-25T17:59:42Z","snapshot_observed_at":"2026-08-04T06:13:02.014683Z","submitted_at":"2019-04-25T17:59:42Z","title":"GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.11492","snapshot_observed_at":"2026-08-12T20:23:10.276979Z","title":"Gcnet: Non- local networks meet squeeze-excitation networks and beyond","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.276979Z"},"links":{"cited_paper":"/paper/1904.11492","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:7c2a6848e277161e4fe7f8ce98e91269d6a20e6d484031f08d2ca375b5824ae3","observation_id":"b9b928a1-4036-4af0-ba1c-c2cfd9299c01","resolution":{"observed_at":"2026-08-12T20:23:10.276979Z","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":"2026-08-12T20:23:10.281666Z","title":"The concept of group and the theory of perception","venue":null,"work_id":null,"year":1944},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.281666Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:3830f351516873492867f6ada59dc51cfe5af8547ed7878ab66724406a77d0e2","observation_id":"b9dc201d-6484-4033-87a1-85bb802ac868","resolution":{"observed_at":"2026-08-12T20:23:10.281666Z","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":"2026-08-12T20:23:10.285833Z","title":"A program to build e (n)- equivariant steerable cnns","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.285833Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:a0e2fbb904675088e06076fb01dbf827f9a66c43ed90b9d231350ead6e8307df","observation_id":"f90e7d69-3b53-4e81-90e6-8de36655b92c","resolution":{"observed_at":"2026-08-12T20:23:10.285833Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.09689","last_updated":"2019-02-26T01:18:46Z","snapshot_observed_at":"2026-07-06T07:35:24.412482Z","submitted_at":"2019-02-26T01:18:46Z","title":"AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.09689","snapshot_observed_at":"2026-08-12T20:23:10.289637Z","title":"Antisymmetri- crnn: A dynamical system view on recurrent neural networks","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.289637Z"},"links":{"cited_paper":"/paper/1902.09689","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:ca1cca0fe949cb295e468c2630a7ade9cecf09de802624a9757b7ba740e204ec","observation_id":"7faac380-5a83-43b0-896c-265d1f182091","resolution":{"observed_at":"2026-08-12T20:23:10.289637Z","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":"2026-08-12T20:23:10.293979Z","title":"Principled weight initialization for hypernetworks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.293979Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:e1987ad686ad51750026efd2a5011fc9d20b8846c812e985b798b8d23542ea1c","observation_id":"6f8fa819-2e6c-472f-b64e-0cf68ca3aa56","resolution":{"observed_at":"2026-08-12T20:23:10.293979Z","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":"2026-08-12T20:23:10.298454Z","title":"Di- lated recurrent neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.298454Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:fe78f106ab47b3b84ce4e35b5fb6dbb2708d5329b46678bebaa60fa940364fe5","observation_id":"f8b5fd7e-62f3-4f50-b884-a7eedf4e92c0","resolution":{"observed_at":"2026-08-12T20:23:10.298454Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.08190","last_updated":"2023-10-05T22:18:23Z","snapshot_observed_at":"2026-08-13T17:33:31.644685Z","submitted_at":"2021-11-16T02:07:20Z","title":"Learning Augmentation Distributions using Transformed Risk Minimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.08190","snapshot_observed_at":"2026-08-12T20:23:10.302548Z","title":"Learning augmentation distributions using transformed risk mini- mization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.302548Z"},"links":{"cited_paper":"/paper/2111.08190","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:5d3533ba5e2aab69b8078c179c9b8daf4918be5dfd0d2a00aa28dcd1757adee8","observation_id":"ca080954-e784-4a7f-8749-7a6becb1bca2","resolution":{"observed_at":"2026-08-12T20:23:10.302548Z","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":"2026-08-12T20:23:10.306477Z","title":"Recurrent neural networks for multivariate time series with missing values","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.306477Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:0efef77036cbe5ceafa016984757424b4b67d24e1256f531d7725030d4d47966","observation_id":"c9d08436-faf7-4d7c-a020-320735762b0d","resolution":{"observed_at":"2026-08-12T20:23:10.306477Z","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":"2026-08-12T20:23:10.310027Z","title":"Linear system theory and design","venue":null,"work_id":null,"year":1984},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.310027Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:92718f3de0c6a28f668c38798f1fa804fbadfff6f24379b808e0ff07afc37120","observation_id":"03d36327-8a89-43c2-8a7e-83c3d937ee74","resolution":{"observed_at":"2026-08-12T20:23:10.310027Z","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":"2026-08-12T20:23:10.314337Z","title":"A group-theoretic framework for data augmentation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.314337Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:3f346cbfd7052921f01102981e2b56eafb016d2a9f8904a3ee8f0ae0ffdca391","observation_id":"946d7d2f-108b-48ff-925f-86b2934ea256","resolution":{"observed_at":"2026-08-12T20:23:10.314337Z","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":"2026-08-12T20:23:10.318068Z","title":"Stabilizing differentiable architecture search via perturbation-based regularization","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.318068Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:ad504e9c47671544ff0a526ba929b02045db450ebc63150164373cad03d6c272","observation_id":"b10bd0ad-467a-4600-be74-fca6317d0699","resolution":{"observed_at":"2026-08-12T20:23:10.318068Z","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":"2026-08-12T20:23:10.322648Z","title":"Progressive darts: Bridging the op- timization gap for nas in the wild","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.322648Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:44d56107eceab4944212b706e47906e71a6aac626a91eb2046f8eead88df8a47","observation_id":"e6d06fa6-1a48-4091-b45e-1a6732d267e7","resolution":{"observed_at":"2026-08-12T20:23:10.322648Z","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":"2026-08-12T20:23:10.326847Z","title":"Graph-based global reasoning networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.326847Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:3f33fbbf237a2663ec0007f48093b38f8eb17def939200a8b1fa44af169e41a7","observation_id":"e4c3c6e6-541d-408d-8c1e-7082deea643e","resolution":{"observed_at":"2026-08-12T20:23:10.326847Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1601.06733","last_updated":"2016-09-20T21:20:09Z","snapshot_observed_at":"2026-08-07T16:18:18.396934Z","submitted_at":"2016-01-25T19:25:48Z","title":"Long Short-Term Memory-Networks for Machine Reading","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1601.06733","snapshot_observed_at":"2026-08-12T20:23:10.330603Z","title":"Long short-term memory-networks for machine reading","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.330603Z"},"links":{"cited_paper":"/paper/1601.06733","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:2c5ed4b97c1d1b1e419638c0f911f8ee27251d416634bb22311970eb8361036a","observation_id":"0472f6a8-3af2-487e-97ac-98bae4a8e198","resolution":{"observed_at":"2026-08-12T20:23:10.330603Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.06846","last_updated":"2018-05-17T16:24:51Z","snapshot_observed_at":"2026-07-06T06:39:45.645092Z","submitted_at":"2018-05-17T16:24:51Z","title":"RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks","version":1},"cited_work":{"arxiv_id":"1805.06846","doi":null,"metadata_source":"pith","pith_arxiv_id":"1805.06846","snapshot_observed_at":"2026-08-12T20:23:12.446209Z","title":"RotDCF: Decomposition of Convolutional Filters for Rotation-Equivariant Deep Networks","venue":"cs.CV","work_id":"5c430b13-c294-4876-9fe6-11bac33e5568","year":2018},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.334834Z"},"links":{"cited_paper":"/paper/1805.06846","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:a486fa186dcf73d01285d90a1d62d3cb7634ba6de6bf7dd74a97bc05fb1d61b9","observation_id":"99c56b69-4f1e-4edf-b30a-17205c7d28fd","resolution":{"observed_at":"2026-08-12T20:23:12.450570Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T20:23:10.339403Z","title":"Some experiments on the recognition of speech, with one and with two ears","venue":null,"work_id":null,"year":1953},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.339403Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:1d8fc3c2111ba6dafe489949e97c8305a6f6a8eea5caf526b5b8664d6279d85d","observation_id":"0b164171-9515-43a4-aedf-4000b7240ff0","resolution":{"observed_at":"2026-08-12T20:23:10.339403Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.11417","last_updated":"2021-05-10T22:34:37Z","snapshot_observed_at":"2026-07-06T10:43:43.208984Z","submitted_at":"2021-02-22T23:43:47Z","title":"Parallelizing Legendre Memory Unit Training","version":2},"cited_work":{"arxiv_id":"2102.11417","doi":null,"metadata_source":"pith","pith_arxiv_id":"2102.11417","snapshot_observed_at":"2026-08-12T20:23:12.427644Z","title":"Parallelizing Legendre Memory Unit Training","venue":"cs.LG","work_id":"e3c1eb42-a49e-4ec6-8333-e1fe90a84c24","year":2021},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.343496Z"},"links":{"cited_paper":"/paper/2102.11417","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:e2829a5e3dcdc1e7712afbab0423f01e61911ebaa9f3dba8ad05185b55e0bd21","observation_id":"61108a06-873a-4511-bc9b-273a2f1ec6b5","resolution":{"observed_at":"2026-08-12T20:23:12.431890Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1406.1078","last_updated":"2014-09-03T00:25:02Z","snapshot_observed_at":"2026-07-06T03:45:28.546418Z","submitted_at":"2014-06-03T17:47:08Z","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1406.1078","snapshot_observed_at":"2026-08-12T20:23:10.347506Z","title":"Learning phrase representa- tions using rnn encoder-decoder for statistical machine translation","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.347506Z"},"links":{"cited_paper":"/paper/1406.1078","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:6a2cf47740a3cb7adf30349d26999a0336a936463deead22c6ad8230c742bfe7","observation_id":"2c180617-0208-4fad-9993-e06e4e12776c","resolution":{"observed_at":"2026-08-12T20:23:10.347506Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.00298","last_updated":"2016-06-01T14:18:08Z","snapshot_observed_at":"2026-08-07T14:33:06.607361Z","submitted_at":"2016-06-01T14:18:08Z","title":"Automatic tagging using deep convolutional neural networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.00298","snapshot_observed_at":"2026-08-12T20:23:10.351700Z","title":"Automatic tagging using deep convolutional neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.351700Z"},"links":{"cited_paper":"/paper/1606.00298","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:13f2408649859675be93e9cb729ccf45c82d0454f2a16947cbda4fbc2258966f","observation_id":"3ee003e8-7265-4653-a6ad-85376ba81c18","resolution":{"observed_at":"2026-08-12T20:23:10.351700Z","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":"2026-08-12T20:23:10.355972Z","title":"Xception: Deep learning with depthwise separable convolu- tions","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.355972Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:b9096da6d254ea7d08cbe13f1a4a0691f1d284683fc34a2091d5df17f83b8c04","observation_id":"a1cc09c7-763d-41a6-9b77-e5b766b7a5fe","resolution":{"observed_at":"2026-08-12T20:23:10.355972Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.14794","last_updated":"2022-11-19T12:45:21Z","snapshot_observed_at":"2026-08-12T04:58:34.201421Z","submitted_at":"2020-09-30T17:09:09Z","title":"Rethinking Attention with Performers","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.14794","snapshot_observed_at":"2026-08-12T20:23:10.360056Z","title":"Rethinking attention with performers","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.360056Z"},"links":{"cited_paper":"/paper/2009.14794","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:a0ba29e09aa8e7328466494b56ca4eb933d567cd92578c859d62e6a47f6b3b91","observation_id":"b07b342c-1cb2-4ae3-bffc-a7f7a180558b","resolution":{"observed_at":"2026-08-12T20:23:10.360056Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.02311","last_updated":"2022-10-05T06:02:24Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-05T16:11:45Z","title":"PaLM: Scaling Language Modeling with Pathways","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.02311","snapshot_observed_at":"2026-08-12T20:23:10.365028Z","title":"Palm: Scaling language modeling with pathways","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.365028Z"},"links":{"cited_paper":"/paper/2204.02311","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:acacc0a110d8f73e43a604dd98d99df1576997640930bf641eb370c3db7e943f","observation_id":"ffb39d39-ca2c-4139-b428-0fc591d52337","resolution":{"observed_at":"2026-08-12T20:23:10.365028Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1707.08819","last_updated":"2017-08-23T16:06:20Z","snapshot_observed_at":"2026-07-06T05:52:59.445968Z","submitted_at":"2017-07-27T11:22:22Z","title":"A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.08819","snapshot_observed_at":"2026-08-12T20:23:10.369321Z","title":"A downsampled variant 196 BIBLIOGRAPHY of imagenet as an alternative to the CIFAR datasets","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.369321Z"},"links":{"cited_paper":"/paper/1707.08819","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:a4d4c6df55c3158b202a252fa358d342325ba778d8df614ef5f3853221bda110","observation_id":"5c68012d-9973-4249-8a6c-4edcfadbd853","resolution":{"observed_at":"2026-08-12T20:23:10.369321Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.01027","last_updated":"2021-01-15T07:58:11Z","snapshot_observed_at":"2026-07-06T09:52:13.518430Z","submitted_at":"2020-09-02T12:54:13Z","title":"DARTS-: Robustly Stepping out of Performance Collapse Without Indicators","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.01027","snapshot_observed_at":"2026-08-12T20:23:10.373217Z","title":"Darts-: robustly stepping out of performance collapse without indicators","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.373217Z"},"links":{"cited_paper":"/paper/2009.01027","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:c7a7f4c0a43ea5be6ea0d69f19f4d6cb25f0b2f34a149eb160a5ad894d3ce0c4","observation_id":"7ba3c284-c5ba-4b6a-a70d-6edc7ac1caaa","resolution":{"observed_at":"2026-08-12T20:23:10.373217Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.3555","last_updated":"2014-12-11T06:46:53Z","snapshot_observed_at":"2026-08-13T10:35:27.214652Z","submitted_at":"2014-12-11T06:46:53Z","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.3555","snapshot_observed_at":"2026-08-12T20:23:10.377326Z","title":"Empir- ical evaluation of gated recurrent neural networks on sequence modeling","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.377326Z"},"links":{"cited_paper":"/paper/1412.3555","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:d36b8ee8016ddcc1fbc205af7bfc509beceebf5b7e57e68653a7e3f37dfe1357","observation_id":"2a479731-90e5-45b3-8a88-aca88b77e431","resolution":{"observed_at":"2026-08-12T20:23:10.377326Z","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":"2026-08-12T20:23:10.381782Z","title":"An analysis of single-layer net- works in unsupervised feature learning","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.381782Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:8847e43540aa5e7a4a3804a481402704c6fe087a2d838a93f8b3d046bdd63f09","observation_id":"ae880d73-27cc-4c8a-85da-15417e609983","resolution":{"observed_at":"2026-08-12T20:23:10.381782Z","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":"2026-08-12T20:23:10.385638Z","title":"Group equivariant convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.385638Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:528c38828dcef4d5676aaf9287f57a47480cd209649609999c67c9aafcc78437","observation_id":"30430f16-40b0-41a0-b80c-89218409347d","resolution":{"observed_at":"2026-08-12T20:23:10.385638Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1612.08498","last_updated":"2016-12-27T04:38:28Z","snapshot_observed_at":"2026-08-13T00:07:55.869360Z","submitted_at":"2016-12-27T04:38:28Z","title":"Steerable CNNs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1612.08498","snapshot_observed_at":"2026-08-12T20:23:10.389534Z","title":"Steerable cnns","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.389534Z"},"links":{"cited_paper":"/paper/1612.08498","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:6de7162db64d3ce3450cc606441b4d1c65e9cb19546eb6d72ccc3ff59a8ab13f","observation_id":"c4c49952-7e89-49b5-b3d7-c36a7183fb27","resolution":{"observed_at":"2026-08-12T20:23:10.389534Z","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":"2026-08-12T20:23:10.393801Z","title":"Spherical cnns","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.393801Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:da07797a0bb0f8f745e374e2be62f66508fda25020b8a898caa416637ce94d82","observation_id":"6771c2d1-9075-4bd8-8d39-4c8f8ba57742","resolution":{"observed_at":"2026-08-12T20:23:10.393801Z","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":"2026-08-12T20:23:10.398182Z","title":"A general theory of equivariant cnns on homogeneous spaces","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.398182Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:9accfe716cb249c2e73a117513ab73a91cb10777dbc401d46b5280c1cc91c42c","observation_id":"720a63ed-8347-4639-b377-8a6e610996a1","resolution":{"observed_at":"2026-08-12T20:23:10.398182Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.04615","last_updated":"2019-05-13T23:03:52Z","snapshot_observed_at":"2026-08-09T17:17:13.630798Z","submitted_at":"2019-02-11T17:01:05Z","title":"Gauge Equivariant Convolutional Networks and the Icosahedral CNN","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.04615","snapshot_observed_at":"2026-08-12T20:23:10.402833Z","title":"Gauge equivariant convolutional networks and the icosahedral cnn","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.402833Z"},"links":{"cited_paper":"/paper/1902.04615","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:b3ecc13f64fefc156e28212adac3a9cce17d7d2341a82f74d5b85fd2b7eb3a9e","observation_id":"93ddeaa5-588a-4f53-9048-85818da78118","resolution":{"observed_at":"2026-08-12T20:23:10.402833Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.01781","last_updated":"2017-01-27T12:49:11Z","snapshot_observed_at":"2026-07-06T04:58:57.726406Z","submitted_at":"2016-06-06T15:14:50Z","title":"Very Deep Convolutional Networks for Text Classification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.01781","snapshot_observed_at":"2026-08-12T20:23:10.407162Z","title":"Very deep con- volutional networks for text classification","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.407162Z"},"links":{"cited_paper":"/paper/1606.01781","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:438e73508380d9dc57f7c247898b9d2974aee7926f8e8528aa208dbc64cb001b","observation_id":"23355ce8-3027-4611-b0ef-11041b49178f","resolution":{"observed_at":"2026-08-12T20:23:10.407162Z","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":"2026-08-12T20:23:10.411545Z","title":"Fast construction of k-nearest neighbor graphs for point clouds","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.411545Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:64e74e4ba4464f995b5f8e387ddcf5f23feb17f9997ee0e56f2db20ec36a2c77","observation_id":"1c766b1e-b57b-4394-8ea1-c6cb6b51f954","resolution":{"observed_at":"2026-08-12T20:23:10.411545Z","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":"2026-08-12T20:23:10.415118Z","title":"On the relation- ship between self-attention and convolutional layers","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.415118Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:9d3fe59dd7655f7c2dbcc32834c5a8313ba99b3fe06bff3855fd475a747ab677","observation_id":"9359e152-c650-4dbf-8c21-35e804b5cab8","resolution":{"observed_at":"2026-08-12T20:23:10.415118Z","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":"2026-08-12T20:23:10.418937Z","title":"A volumetric method for building complex models from range images","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.418937Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:384bba44828ea21b7cfbdcd9b3ffcb54c1523c374c5e48acaceeb55cb34489a9","observation_id":"d31bdbf7-7048-4743-840a-e7bc28a75578","resolution":{"observed_at":"2026-08-12T20:23:10.418937Z","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":"2026-08-12T20:23:10.422479Z","title":"Deformable convolutional networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.422479Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:bf15ad3526665ec94460aa6521bce18cdafefec50e6725b03083979f05a86a92","observation_id":"e3d50018-f2ec-4901-86c9-da0feb929a8a","resolution":{"observed_at":"2026-08-12T20:23:10.422479Z","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":"2026-08-12T20:23:10.426388Z","title":"Very deep convo- lutional neural networks for raw waveforms","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.426388Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:a356c2b934ec8e5cd3bfc9b945a137c55b195b865f378f5257a53d2e02e6f52d","observation_id":"ac1ba052-1ce1-4b6e-a720-3d2ebf6b18d1","resolution":{"observed_at":"2026-08-12T20:23:10.426388Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1901.02860","last_updated":"2019-06-02T21:21:48Z","snapshot_observed_at":"2026-07-06T07:25:48.468658Z","submitted_at":"2019-01-09T18:28:19Z","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.02860","snapshot_observed_at":"2026-08-12T20:23:10.430285Z","title":"Transformer-xl: Attentive language models beyond a fixed-length context","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.430285Z"},"links":{"cited_paper":"/paper/1901.02860","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:e6a21637071c92eebc9aeb1cfa2d0e8c351f7d91afa6188f8a76b9e3c1bc1be8","observation_id":"3abc047d-f911-48c6-897d-90126e95b2b9","resolution":{"observed_at":"2026-08-12T20:23:10.430285Z","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":"2026-08-12T20:23:10.434585Z","title":"Picture memory experiments","venue":null,"work_id":null,"year":1968},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.434585Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:f0e0ac82844a542eb3598e9bf8b949fb20de8efc800fca0550a03ab0f7c236fd","observation_id":"8052ce9f-2118-479d-8fb9-a1d908b3e129","resolution":{"observed_at":"2026-08-12T20:23:10.434585Z","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":"2026-08-12T20:23:10.438495Z","title":"Fundamental papers in wavelet theory","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.438495Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:073511d0a539e007d70ee777607b593d09183def04ccbfc04a48c1c86ad25ea7","observation_id":"eecd0cd1-8b8d-4901-818d-59902b077f26","resolution":{"observed_at":"2026-08-12T20:23:10.438495Z","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":"10.1109/29.1644","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T20:23:11.390841Z","title":null,"venue":null,"work_id":"be8d5217-a5d7-4fcf-8dde-1cf73759efce","year":1988},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.442254Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:a24a8f488bcd8510f923961d57406582a01d6eb4fe5f486301deff39ca833eb7","observation_id":"1e65b5b8-4688-4e91-878b-d614ce78de16","resolution":{"observed_at":"2026-08-12T20:23:11.394928Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T20:23:10.446550Z","title":"Language mod- eling with gated convolutional networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.446550Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:0eee4f24024e0b45121a653ad9ad59a115148c80b39b5e3363fe65d6f0652998","observation_id":"b51120c2-2955-4c92-8a4c-b7d616aeafe4","resolution":{"observed_at":"2026-08-12T20:23:10.446550Z","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":"2026-08-12T20:23:10.450150Z","title":"Gru-ode-bayes: Continuous modeling of sporadically-observed time series","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.450150Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:d6ff9e5d98d3f5d7a81381d4229b58530b3e237f4ef284de7268f6719162c33f","observation_id":"1b09c368-dff0-4a98-8133-098dfddf6a9b","resolution":{"observed_at":"2026-08-12T20:23:10.450150Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.15000","last_updated":"2020-12-30T01:35:27Z","snapshot_observed_at":"2026-08-04T07:49:32.632826Z","submitted_at":"2020-12-30T01:35:27Z","title":"DeepSphere: a graph-based spherical CNN","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.15000","snapshot_observed_at":"2026-08-12T20:23:10.453986Z","title":"Deepsphere: a graph-based spherical cnn","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.453986Z"},"links":{"cited_paper":"/paper/2012.15000","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:210fa55f0064c0830a574f02dead78ad615524aaac41d884761a8850861ca974","observation_id":"8da4abb2-dc82-4105-816c-922da1baf066","resolution":{"observed_at":"2026-08-12T20:23:10.453986Z","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":"2026-08-12T20:23:10.458143Z","title":"Au- tomatic symmetry discovery with lie algebra convolutional network","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.458143Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:f9b6c898f322166e9e4a4783ce17a2a5177cc12fa55b1a5ed91c3fcae4707b4e","observation_id":"48e77e55-3963-4cb4-a99d-5ba90d4e4443","resolution":{"observed_at":"2026-08-12T20:23:10.458143Z","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":"2026-08-12T20:23:10.462430Z","title":"Insect cyborgs: Bio-mimetic feature gen- erators improve ml accuracy on limited data","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.462430Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:d5abfc5f1742b070489ee1215c24e1bc102f9afdb3faac84af9d67af2416b8f3","observation_id":"14a10926-b3e3-4551-ae14-91bff9c331e3","resolution":{"observed_at":"2026-08-12T20:23:10.462430Z","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":"2026-08-12T20:23:10.467002Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.467002Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:a940b740bbcebe6dad748e0ff53ea203c6a86e8066f8ba876a9b515fb3d662da","observation_id":"e6569776-14c3-48e0-bc54-dbbaff121105","resolution":{"observed_at":"2026-08-12T20:23:10.467002Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.07704","last_updated":"2019-11-18T15:33:00Z","snapshot_observed_at":"2026-07-06T08:37:51.370343Z","submitted_at":"2019-11-18T15:33:00Z","title":"Affine Self Convolution","version":1},"cited_work":{"arxiv_id":"1911.07704","doi":null,"metadata_source":"pith","pith_arxiv_id":"1911.07704","snapshot_observed_at":"2026-08-12T20:23:12.263001Z","title":"Affine Self Convolution","venue":"cs.CV","work_id":"2ece0236-bdba-409f-93fb-63fa0b29aa4c","year":2019},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.470560Z"},"links":{"cited_paper":"/paper/1911.07704","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:42b384493870e7a61ab49e3b10ec2e7e3764037d90d6082b929d3d2ec99ba9d3","observation_id":"d68eaf9b-05ec-4ad8-b4a8-13c5b2f612fe","resolution":{"observed_at":"2026-08-12T20:23:12.267244Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T20:23:10.474656Z","title":"Learning to convolve: A generalized weight-tying approach","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.474656Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:0d3659f370471b9d4c50e3644e78be96c96858093a0e96931888bd2e0cd4ddc6","observation_id":"e8c43759-48a2-48d4-a344-b34d9ab1b502","resolution":{"observed_at":"2026-08-12T20:23:10.474656Z","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":"2026-08-12T20:23:10.478921Z","title":"End-to-end learning for music au- dio","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.478921Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:e8384fc2e7d9709ad839c7f724704c7696b91fe02d6f07cf7a6489d40a3e4b93","observation_id":"213dffc3-c41e-49e8-abd8-5e41119f7960","resolution":{"observed_at":"2026-08-12T20:23:10.478921Z","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":"2026-08-12T20:23:10.482634Z","title":"Exploiting cyclic symmetry in convolutional neural networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.482634Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:12ab579603c01c13259d88b1e3e1c240f925dcd810dfc8e987a13e4cf54af137","observation_id":"e2c16019-9f7b-4a13-a348-12b92eee74da","resolution":{"observed_at":"2026-08-12T20:23:10.482634Z","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":"2026-08-12T20:23:10.486568Z","title":"Searching for a robust neural architecture in four gpu hours","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.486568Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:2de8dd13e361862ec5cd5a83e59c8e0be0cc0fa42ebab78544976e45167506dc","observation_id":"173f7923-1171-4c64-af87-d0aaed02c686","resolution":{"observed_at":"2026-08-12T20:23:10.486568Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-13T14:19:26.598265Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-12T20:23:10.490141Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.490141Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:a9836caa0826539f5e4a9f9a5adde852388ad59e66cf9bc976f7ba7f09a8a8ef","observation_id":"177d66cb-6bb7-4d43-9320-534440d96506","resolution":{"observed_at":"2026-08-12T20:23:10.490141Z","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":"2026-08-12T20:23:10.493990Z","title":"Brp-nas: Prediction-based nas using gcns","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.493990Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:f080335e47e396d9f3fc8bb3234d0b021d1d097ac5668e97f97cf4a14fc97665","observation_id":"8d03f604-bdce-4680-92e4-0a16c3f6d6a4","resolution":{"observed_at":"2026-08-12T20:23:10.493990Z","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":"2026-08-12T20:23:10.497714Z","title":"Abstract algebra, volume 3","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.497714Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:e6f05c00ca84d9800a67a723bd20399d4040de79c0fa6f2a761a6dad91b85e13","observation_id":"463314c0-6771-4624-848b-e026f4c00473","resolution":{"observed_at":"2026-08-12T20:23:10.497714Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.04776","last_updated":"2022-02-17T16:18:12Z","snapshot_observed_at":"2026-08-12T15:20:38.835244Z","submitted_at":"2021-02-09T11:47:55Z","title":"Generative Models as Distributions of Functions","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.04776","snapshot_observed_at":"2026-08-12T20:23:10.501398Z","title":"Generative models as dis- tributions of functions","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.501398Z"},"links":{"cited_paper":"/paper/2102.04776","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:63b7ef4e1efb10754a5c28863b5507b10dd0a8d2582c3897b144b7cfc02ac8ed","observation_id":"566d1921-0867-49ab-85c3-1cc0cec04da0","resolution":{"observed_at":"2026-08-12T20:23:10.501398Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.09081","last_updated":"2019-02-26T16:06:36Z","snapshot_observed_at":"2026-08-02T03:09:12.462232Z","submitted_at":"2018-04-24T15:01:07Z","title":"Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.09081","snapshot_observed_at":"2026-08-12T20:23:10.505815Z","title":"Efficient multi- objective neural architecture search via lamarckian evolution","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.505815Z"},"links":{"cited_paper":"/paper/1804.09081","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:dc56a007b38c7a3894219f9da68a4511fc3df5c4c8d0e215e376c9a96500f325","observation_id":"da51decc-f16c-4b1e-9dc2-8288ef4dd2e0","resolution":{"observed_at":"2026-08-12T20:23:10.505815Z","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":"2026-08-12T20:23:10.509892Z","title":"Neural architecture search: A survey","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.509892Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:9a3d43fb706c082496e78b9b2aa1f437f75efbb491d9668f6e9364e0de01a3ee","observation_id":"97399485-0ec5-41ff-956d-8b4179cc6aed","resolution":{"observed_at":"2026-08-12T20:23:10.509892Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.12070","last_updated":"2021-04-24T03:31:59Z","snapshot_observed_at":"2026-07-06T09:31:19.187163Z","submitted_at":"2020-06-22T08:44:52Z","title":"Lipschitz Recurrent Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.12070","snapshot_observed_at":"2026-08-12T20:23:10.513484Z","title":"Lipschitz recurrent neural networks","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.513484Z"},"links":{"cited_paper":"/paper/2006.12070","citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:9f39451b344e2f24e5173f66b2e911f8782a2f0e99c10f62b783380dc213a1cf","observation_id":"bbd51b07-25c0-43b9-b285-cf99fe083ef7","resolution":{"observed_at":"2026-08-12T20:23:10.513484Z","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":"2026-08-12T20:23:10.517407Z","title":"Cross-domain 3d equivariant image embeddings","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.517407Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:b83b617402376dbf7db4567a20ac179582500ad65489ad63bc7f890fa12ed718","observation_id":"e5fb6591-b3fe-4634-b3ea-b936ad20b8d7","resolution":{"observed_at":"2026-08-12T20:23:10.517407Z","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":"2026-08-12T20:23:10.521244Z","title":"Equivariant multi-view networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.521244Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:40068d9209f92257019609988d8eb3f322b34107b54e2dde4f0c258d941145a8","observation_id":"f01c220b-ad08-466c-bc09-4e9cc622f375","resolution":{"observed_at":"2026-08-12T20:23:10.521244Z","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":"2026-08-12T20:23:10.525489Z","title":"Spin-weighted spherical cnns","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-12T20:23:10.525489Z"},"links":{"citing_paper":"/paper/2411.09827"},"observation_digest":"sha256:d1f37cf9bc7ddfbd11bef8ba51aabde3794652d7570750836cce768aa678f116","observation_id":"dd9c69d1-9696-4ce9-af49-7d65ef1535aa","resolution":{"observed_at":"2026-08-12T20:23:10.525489Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2411.09827","last_updated":"2024-11-14T22:24:59Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T18:35:39.109965Z","submitted_at":"2024-11-14T22:24:59Z","title":"The Good, The Efficient and the Inductive Biases: Exploring Efficiency in Deep Learning Through the Use of Inductive Biases"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":96,"verified_exact":4,"verified_fuzzy":0},"total_outbound_references":300},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 100 of 300 outbound references and 0 inbound Pith citation observations for arXiv:2411.09827."}