{"as_of":"2026-08-11T06:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:dd204da1e53c88f4d1d69e70eac53c1d9651d83a3c02cdd719b2478fcf08dee4","coverage":[{"denominator":23,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":23,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T17:56:17.032786Z","state":"measured"},{"denominator":23,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":23,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2502.00754/citation-record","integrity":"/paper/2502.00754/integrity","json":"/paper/2502.00754/citation-record.json","paper":"/paper/2502.00754"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.123094Z","title":"These values are intentionally larger than the theoretical minimum to enhance the model’s expressiveness","venue":null,"work_id":"845b0011-4276-426c-8f3c-2030ae9bd0da","year":2022},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:17.025296Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:b7b89a8fbb0585fbf99c9115ddc8a87fd04fd8c11e72076b6a6ddc27737a0cfc","observation_id":"861dd07b-5e44-46c7-b6f7-dc8d2c99d424","resolution":{"observed_at":"2026-08-09T17:56:17.126690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.294697Z","title":"Hamiltonian neural networks","venue":null,"work_id":"a8e27193-1e59-44b8-808a-7bcef6412c14","year":2019},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:16.954559Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:0ed788df06675f5bb94b97e2159399e85ded8d004ef9fabcd3d9d9b43f7b3a96","observation_id":"963cd602-7801-42a4-af8f-03c82efb2408","resolution":{"observed_at":"2026-08-09T17:56:17.297958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.275273Z","title":"Kingma and Max Welling","venue":null,"work_id":"801ee2db-66f0-41bb-8b4a-e41359218491","year":2014},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:16.964127Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:d2bea993a1a48cbc035b8a5c6e4dfb2f171792ff08190c9d0cec601a3f01677a","observation_id":"a9b6cd75-2f22-4ddc-a408-3084f26dfec4","resolution":{"observed_at":"2026-08-09T17:56:17.278392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.264524Z","title":"Deep lagrangian networks: Using physics as model prior for deep learning","venue":null,"work_id":"afbec07b-8227-4d64-9df0-5a5c1e562dd2","year":2019},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:16.967941Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:fe3f34c40232f22ad79e101f04842c7f630d446c8c7501f529fd8860ad089c44","observation_id":"401fb6e6-a16d-489c-8182-bb64eaade200","resolution":{"observed_at":"2026-08-09T17:56:17.268061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.252289Z","title":"Resnet after all: Neural ODEs and their numerical solution","venue":null,"work_id":"82d7ad9a-9e99-409d-bbb8-a087d20e1f07","year":2021},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:16.971498Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:c82d5ba43276f462ebae84f083bcc16fb2c480643c1e526cd49c32a312f71249","observation_id":"3dd95973-5374-43c3-9983-e33da04ddfde","resolution":{"observed_at":"2026-08-09T17:56:17.257014Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.101905Z","title":"We employ a very small VPNet for regularization","venue":null,"work_id":"def0e8fd-42f4-4de6-90c8-40944c04c760","year":2018},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:17.032786Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:fb7f7fd0609c7c30a8d2286b214356a52edc48eafddb5d0f36874af4cf49d9b8","observation_id":"7c982511-1b83-4048-8831-5755bd311920","resolution":{"observed_at":"2026-08-09T17:56:17.105506Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.195683Z","title":"Rezende, Andrew Jaegle, S ´ebastien Racani `ere, Aleksandar Botev, and Irina Higgins","venue":null,"work_id":"b717f287-a3b4-4bb6-9f0e-a7a5ee02fc3c","year":2020},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:16.997724Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:c7a43541c6b9753b945a172fd5e28eb1e34d2f102677506fb7acf9928d7080ae","observation_id":"66e2b460-879b-4919-aa10-822b058328c3","resolution":{"observed_at":"2026-08-09T17:56:17.199341Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.16756","last_updated":"2024-11-04T22:00:33Z","snapshot_observed_at":"2026-08-10T02:55:45.778049Z","submitted_at":"2024-05-27T01:58:23Z","title":"Symmetry-Informed Governing Equation Discovery","version":2},"cited_work":{"arxiv_id":"2405.16756","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.16756","snapshot_observed_at":"2026-08-09T17:56:17.061348Z","title":"Symmetry-Informed Governing Equation Discovery","venue":"cs.LG","work_id":"ed376ac6-c88b-4aa5-9d11-5ee03dbc0ed2","year":2024},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:17.001054Z"},"links":{"cited_paper":"/paper/2405.16756","citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:7a68330ca3b4172ba8c5cdd7b5580ad625537ea70d5c0a6b1333e7aa9111cf54","observation_id":"8597b081-386c-4163-a888-b1b0fc8ae959","resolution":{"observed_at":"2026-08-09T17:56:17.067494Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.182846Z","title":"Symplectic ode-net: Learning hamiltonian dynamics with control","venue":null,"work_id":"33087516-5fcf-4010-86d4-733bae6fc1d3","year":2020},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:17.005070Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:23ce12f40d84abd0a3f327e4c12d3b28958ff55b4c67ddf2d9fe94f70586f1e2","observation_id":"2fbaa909-779b-4f2a-b07f-8c3a7382cc7b","resolution":{"observed_at":"2026-08-09T17:56:17.187647Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.170627Z","title":null,"venue":null,"work_id":"90eca521-c044-4b48-b6d6-212913dff09a","year":2025},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:17.008358Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:44ba4396a5f796fe78222621db7ea186695cf9211b6959f6fb40b594c94d3fb9","observation_id":"3e4b5681-7f62-4ff0-bac3-d5938dd6d3fe","resolution":{"observed_at":"2026-08-09T17:56:17.174679Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.156545Z","title":"15 Published as a conference paper at ICLR 2025 Given that maxl maxj1,j2 |ϕl(yl−1 1 , yl)|/(⌈Jl/2⌉δ) ≤ cϕ, we must choose Jl = O(1/δ)","venue":null,"work_id":"3f48d31e-1ed2-42c5-abfe-413257e5c950","year":2025},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:17.012468Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:7595656bf9a7b43656a261846a536bacab2c625b8b4d93a06a6c3ee385ffa2c2","observation_id":"3c1df8c0-926c-4c49-9428-48b7a3b0af99","resolution":{"observed_at":"2026-08-09T17:56:17.161300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.145307Z","title":"Due to weight sharing, the convolution operation exhibits translational invariance","venue":null,"work_id":"6294f9fb-ab3a-4f52-9bd8-643380ecec5c","year":2025},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:17.017138Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:9a3f2ebe499e6c216a0796c282117194934a3882f3f47f20bc0a567038d90079","observation_id":"464416e6-456a-48d0-844c-d48bfe9330b0","resolution":{"observed_at":"2026-08-09T17:56:17.149161Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.133392Z","title":"Finally, applying Lemma A.3, we have aL(∆) ≤ L−1X i=0 M i ϕMI KX k=1 cϕ 2l∗ k,1−1 |∆k,1| + cϕ 2l∗ k,2−1 |∆k,2|","venue":null,"work_id":"55cad649-45a8-4005-8632-f214c763f97c","year":2025},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:17.020811Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:4f3c46ada63423d61cc62facefcb5358e3f44d5a1541ea91dc509fc8f0788bc0","observation_id":"64f56fda-e176-4438-8df6-26f7001f40d7","resolution":{"observed_at":"2026-08-09T17:56:17.137315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.112397Z","title":"All convolutional layers are ac- companied by a batch normalization layer and a ReLU activation function","venue":null,"work_id":"96cad6d6-37b2-42e3-94d3-13f736c62bd3","year":2025},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:17.029049Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:df79cddfce6f4a19ab37ae045fce18ff0add4899e2dafc2b07ab40e99cfa75bd","observation_id":"7c4a2cd5-a688-4b71-a963-63fad35071f1","resolution":{"observed_at":"2026-08-09T17:56:17.116263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.220137Z","title":"Distilling free-form natural laws from experimental data.Science, 324(5923):81–85,","venue":null,"work_id":"c90b5dda-182c-4de8-97fc-0049f0e67489","year":2025},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":1985,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:16.989717Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:4cbc5077648f3e366220c55bde8c76d85d7012e0907729c57339ea05059d9eb4","observation_id":"c2a92ef0-901c-4cd5-a3f2-77ff8c981cdf","resolution":{"observed_at":"2026-08-09T17:56:17.223791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.207683Z","title":"Auto-encoder based data clustering","venue":null,"work_id":"00f5a132-6224-4b1f-a6e6-fb8754ce434f","year":2013},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:16.994030Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:91016e17e3e9893e8e052f98bd05e586f3ea80e01e81df9b0394728cdc9594f9","observation_id":"cc6ed1c8-f9ae-4d7a-84fd-f7d2ded7e66e","resolution":{"observed_at":"2026-08-09T17:56:17.212586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.06955","last_updated":"2024-07-13T16:54:28Z","snapshot_observed_at":"2026-07-06T15:41:28.693657Z","submitted_at":"2023-06-12T08:37:38Z","title":"A Brief Review of Hypernetworks in Deep Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.06955","snapshot_observed_at":"2026-08-09T17:56:16.942260Z","title":"A brief review of hypernetworks in deep learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:16.942260Z"},"links":{"cited_paper":"/paper/2306.06955","citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:798bd810a03e7036003d721ca5f43ca4ac534f5df920879bec10441854b7c039","observation_id":"bf3d1978-16df-4e65-a6ef-d896820340ee","resolution":{"observed_at":"2026-08-09T17:56:16.942260Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.231637Z","title":"Unsupervised learning of invariant feature hierarchies with applications to object recognition","venue":null,"work_id":"9b4be291-604e-40dd-a38c-7a75e159268f","year":2007},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:16.986250Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:aa0e70ca125b5656c1165a1edc4ced08fe4b114d4e0a20aaea678918d6ba8715","observation_id":"4449f12f-46dd-4843-878c-db682f777c19","resolution":{"observed_at":"2026-08-09T17:56:17.235696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.303977Z","title":"Identification of dis- tributed parameter systems: A neural net based approach","venue":null,"work_id":"fe4be34c-03bf-44c1-8849-dbbc4524f883","year":2025},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:16.950107Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:2b30aa0006a56e663afdf3085d8835e95cb7814cffb4ecd8fde40dcf360622de","observation_id":"c0672f97-2769-42f1-b66b-34b9ec51bac5","resolution":{"observed_at":"2026-08-09T17:56:17.307597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.242390Z","title":"Variational autoencoder for deep learning of images, labels and captions","venue":null,"work_id":"3b9efd54-6a61-4809-9b1f-761e0afff845","year":2016},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:16.978408Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:fd306081fe1198622f99948a37fc14d73df84c6c6ed603521c075d32c66ea3fc","observation_id":"be673a56-633c-40d5-9465-ff07f77a8b21","resolution":{"observed_at":"2026-08-09T17:56:17.245939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1801.01236","last_updated":"2018-01-04T03:27:07Z","snapshot_observed_at":"2026-07-06T06:17:06.222443Z","submitted_at":"2018-01-04T03:27:07Z","title":"Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.01236","snapshot_observed_at":"2026-08-09T17:56:16.982074Z","title":"Multistep neural networks for data- driven discovery of nonlinear dynamical systems","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:16.982074Z"},"links":{"cited_paper":"/paper/1801.01236","citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:9aa3f8ecf87b4c2174d71c687efc2e65ffb5344e77dd64b0112fba6fbd2e0c30","observation_id":"5d2cba73-7a07-4f46-bc97-bfd8ec2ca828","resolution":{"observed_at":"2026-08-09T17:56:16.982074Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:56:17.284449Z","title":"Deep clustering with convolutional au- toencoders","venue":null,"work_id":"be229929-eb8c-482a-99e7-6951bec9df91","year":2017},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:16.960165Z"},"links":{"citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:926416da30c94f8d17f55895799b27576e31aecc32b7956996aff46129dd24c7","observation_id":"75106585-8f81-478b-99b8-9bff15e63828","resolution":{"observed_at":"2026-08-09T17:56:17.287923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.04630","last_updated":"2020-07-30T05:22:58Z","snapshot_observed_at":"2026-08-04T10:05:44.957260Z","submitted_at":"2020-03-10T10:55:25Z","title":"Lagrangian Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.04630","snapshot_observed_at":"2026-08-09T17:56:16.946521Z","title":"Lagrangian neural networks","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-09T17:56:16.946521Z"},"links":{"cited_paper":"/paper/2003.04630","citing_paper":"/paper/2502.00754"},"observation_digest":"sha256:c24d76843659dbe290efac3a5f2206f2e10b25db56bec4e8ae9c378755b7a667","observation_id":"0f3e2f47-d0b7-4f44-aa96-a0a7ae82bd6d","resolution":{"observed_at":"2026-08-09T17:56:16.946521Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.00754","last_updated":"2025-02-02T11:31:58Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T02:55:44.741726Z","submitted_at":"2025-02-02T11:31:58Z","title":"Continuity-Preserving Convolutional Autoencoders for Learning Continuous Latent Dynamical Models from Images"},"reference_resolution":{"displayed":23,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":1,"verified_fuzzy":17},"total_outbound_references":23},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 23 of 23 outbound references and 0 inbound Pith citation observations for arXiv:2502.00754."}