{"as_of":"2026-08-07T07:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:49b5c8cc8e8f236b3cf2b1539dc40e83bd9221f6c5b9ef3b46f60202b6cdfe63","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T15:03:56.706815Z","state":"measured"},{"denominator":29,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":29,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T18:02:12.278733Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-11T05:36:01.402377Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"cited_work":{"arxiv_id":"2507.17013","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.17013","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"laplax–laplace approximations with jax.arXiv preprint arXiv:2507.17013","venue":null,"work_id":"befcaf92-d450-4f2a-87c3-9aeb03c75a21","year":null},"citing_paper":{"arxiv_id":"2604.08639","last_updated":"2026-04-09T17:22:36Z","snapshot_observed_at":"2026-07-06T22:57:40.773778Z","submitted_at":"2026-04-09T17:22:36Z","title":"VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-10T18:02:12.278733Z"},"links":{"cited_paper":"/paper/2507.17013","citing_paper":"/paper/2604.08639"},"observation_digest":"sha256:bcd474d4ff9ef57953e0fbf1f74092ec680ddc26f0f816fd32620243d6e4e216","observation_id":"729b81d3-3109-4ad8-97db-2b6cd01647be","resolution":{"observed_at":"2026-05-11T05:36:01.407264Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2507.17013/citation-record","integrity":"/paper/2507.17013/integrity","json":"/paper/2507.17013/citation-record.json","paper":"/paper/2507.17013"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:03:57.027410Z","title":null,"venue":null,"work_id":"c437a8a0-8466-4abe-9e26-c11ee3c2ba7b","year":2024},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.706815Z"},"links":{"citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:c1fd44e0a40c7165107066bc55d1bbc8ad6c59308213295f9e103574a1e47552","observation_id":"9cd33654-9002-40d0-835c-b5eedd7be7ac","resolution":{"observed_at":"2026-08-06T15:03:57.029618Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.13711","last_updated":"2024-10-31T09:58:47Z","snapshot_observed_at":"2026-07-06T18:48:37.723242Z","submitted_at":"2024-07-18T17:08:58Z","title":"FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.13711","snapshot_observed_at":"2026-08-06T15:03:56.567195Z","title":"Dangel, F., Eschenhagen, R., Ormaniec, W., Fernandez, A., Tatzel, L., and Kristiadi, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.567195Z"},"links":{"cited_paper":"/paper/2407.13711","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:82cec308b849a591d8c4b211c726f9c4a2d6ff873db987af48ca02b7519bd269","observation_id":"e2a07eaf-3c36-450e-94d5-4c24e61a9c87","resolution":{"observed_at":"2026-08-06T15:03:56.567195Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15978","last_updated":"2024-11-04T20:36:15Z","snapshot_observed_at":"2026-07-06T17:35:01.907906Z","submitted_at":"2024-02-25T03:48:13Z","title":"Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood","version":2},"cited_work":{"arxiv_id":"2402.15978","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.15978","snapshot_observed_at":"2026-08-06T15:03:56.958438Z","title":"Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks Using the Marginal Likelihood","venue":"cs.LG","work_id":"6a6b6662-8360-4c5c-a349-1b11d59588e3","year":2024},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.639743Z"},"links":{"cited_paper":"/paper/2402.15978","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:c6415d48d99f12bbd13a71fe20883f1c7abcfabaebab062d0b4192c8ad674f24","observation_id":"d830f885-1a7b-47f9-a780-a1dca6c21137","resolution":{"observed_at":"2026-08-06T15:03:56.960700Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.01227","last_updated":"2022-05-31T06:50:20Z","snapshot_observed_at":"2026-08-07T06:14:48.105866Z","submitted_at":"2020-03-02T22:29:03Z","title":"Fast Predictive Uncertainty for Classification with Bayesian Deep Networks","version":4},"cited_work":{"arxiv_id":"2003.01227","doi":null,"metadata_source":"pith","pith_arxiv_id":"2003.01227","snapshot_observed_at":"2026-08-06T15:03:56.939331Z","title":"Fast Predictive Uncertainty for Classification with Bayesian Deep Networks","venue":"cs.LG","work_id":"fe25aedb-3949-4b5c-9a09-088afacd689a","year":2020},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.651723Z"},"links":{"cited_paper":"/paper/2003.01227","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:440d39520409ce5e680e869458002b0d7ad008cbb52bb8d8c0afa4b2088f335e","observation_id":"a66727d8-10d9-4f13-9ee3-a3e2c6af349a","resolution":{"observed_at":"2026-08-06T15:03:56.941670Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02720","last_updated":"2021-06-07T15:06:19Z","snapshot_observed_at":"2026-07-06T10:01:56.278150Z","submitted_at":"2020-10-06T13:43:33Z","title":"Learnable Uncertainty under Laplace Approximations","version":2},"cited_work":{"arxiv_id":"2010.02720","doi":null,"metadata_source":"pith","pith_arxiv_id":"2010.02720","snapshot_observed_at":"2026-08-06T15:03:56.925420Z","title":"Learnable Uncertainty under Laplace Approximations","venue":"cs.LG","work_id":"7c7c2eed-5ba1-4179-ae8c-f7a855eba301","year":2020},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.658633Z"},"links":{"cited_paper":"/paper/2010.02720","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:e8ed590a8f878d6cb8bc3842305d318e71cf5d57ca43af03d8a732089f011dcd","observation_id":"f4ff0cb7-fea7-4fc0-a808-6fc0cc15ae06","resolution":{"observed_at":"2026-08-06T15:03:56.927753Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.07584","last_updated":"2021-05-09T05:31:11Z","snapshot_observed_at":"2026-07-06T09:28:43.182396Z","submitted_at":"2020-06-13T07:32:38Z","title":"Mean-Field Approximation to Gaussian-Softmax Integral with Application to Uncertainty Estimation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.07584","snapshot_observed_at":"2026-08-06T15:03:56.663844Z","title":"MacKay, D","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.663844Z"},"links":{"cited_paper":"/paper/2006.07584","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:6c9c341dd2957d299e1c93692996675cc5c95d7cacca6e8bfdb26004f1f90a5d","observation_id":"c3e9d520-7691-4606-ae1b-7622ca0eeba0","resolution":{"observed_at":"2026-08-06T15:03:56.663844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.05072","last_updated":"2025-01-31T15:13:00Z","snapshot_observed_at":"2026-08-06T22:01:27.509263Z","submitted_at":"2024-06-07T16:43:54Z","title":"Linearization Turns Neural Operators into Function-Valued Gaussian Processes","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.05072","snapshot_observed_at":"2026-08-06T15:03:56.666336Z","title":"Mucs´anyi, B., Kirchhof, M., and Oh, S","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.666336Z"},"links":{"cited_paper":"/paper/2406.05072","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:e76cc76c587a87e8b68c601a5e51c5d6c813ad1a6c9af365c20974a9379a0b09","observation_id":"0ff90a16-4711-49bd-b389-1555c17406aa","resolution":{"observed_at":"2026-08-06T15:03:56.666336Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00809","last_updated":"2024-08-06T16:32:38Z","snapshot_observed_at":"2026-08-04T19:29:59.597640Z","submitted_at":"2024-02-01T17:45:26Z","title":"Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00809","snapshot_observed_at":"2026-08-06T15:03:56.668930Z","title":"Pinder, T","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.668930Z"},"links":{"cited_paper":"/paper/2402.00809","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:5723e011a00af1c7ce460f4640d372acfa50a2407cf36743ffa0aefbd148dbd0","observation_id":"f5530f4b-55f5-48b0-a426-e6833a6d97d1","resolution":{"observed_at":"2026-08-06T15:03:56.668930Z","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":"2026-08-06T15:03:56.671316Z","title":"URL https://doi.org/10.21105/joss.04455","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.671316Z"},"links":{"citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:76d4ede1f2487deb215ce0d9e68c3c68318c2ceab6a80e5bb3f0c3bae86b947e","observation_id":"61e6a39b-4964-4891-b5f1-6959b18771c7","resolution":{"observed_at":"2026-08-06T15:03:56.671316Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.03334","last_updated":"2025-02-10T11:12:37Z","snapshot_observed_at":"2026-08-04T19:27:33.554465Z","submitted_at":"2024-06-05T14:49:15Z","title":"Reparameterization invariance in approximate Bayesian inference","version":2},"cited_work":{"arxiv_id":"2406.03334","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.03334","snapshot_observed_at":"2026-08-06T15:03:56.881236Z","title":"Reparameterization invariance in approximate Bayesian inference","venue":"cs.LG","work_id":"71709998-4a31-47e4-8c9d-bca9d51de314","year":2024},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.676200Z"},"links":{"cited_paper":"/paper/2406.03334","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:dba8b5542ad4e5eafe9163174d442b5f34218ec041e06155778da0c724e77753","observation_id":"78f6ad6e-8749-45f2-b9c6-5fbc76d43a3b","resolution":{"observed_at":"2026-08-06T15:03:56.883840Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2410.06800","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T15:03:56.871461Z","title":"6 laplax – Laplace Approximations with JAX Sun, S., Zhang, G., Shi, J., and Grosse, R","venue":null,"work_id":"59cae44f-dc63-40b9-877a-6aec432f8321","year":null},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.678734Z"},"links":{"citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:90a5788529fce4d39300473db81f5e569b2ce22dcb5ef861005b5cc2d6163245","observation_id":"39f49409-29a4-4b22-bdc9-d217a6fa7067","resolution":{"observed_at":"2026-08-06T15:03:56.874931Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06131","last_updated":"2023-10-09T20:22:43Z","snapshot_observed_at":"2026-07-06T16:30:08.320348Z","submitted_at":"2023-10-09T20:22:43Z","title":"Learning Layer-wise Equivariances Automatically using Gradients","version":1},"cited_work":{"arxiv_id":"2310.06131","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.06131","snapshot_observed_at":"2026-08-06T15:03:56.751856Z","title":"Learning Layer-wise Equivariances Automatically using Gradients","venue":"cs.LG","work_id":"f61a9b21-40fe-44ce-97cd-01070f9f39d5","year":2023},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.683793Z"},"links":{"cited_paper":"/paper/2310.06131","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:f8aa7fb4aaa659032370d030d867f89b1cdb88948807e417686e6783dc131482","observation_id":"fccc46f8-587f-44b7-9cf0-4d8b7a9385c8","resolution":{"observed_at":"2026-08-06T15:03:56.757274Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.17244","last_updated":"2024-03-20T20:21:58Z","snapshot_observed_at":"2026-08-04T16:58:03.675077Z","submitted_at":"2023-12-28T18:59:09Z","title":"The LLM Surgeon","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.17244","snapshot_observed_at":"2026-08-06T15:03:56.686638Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.686638Z"},"links":{"cited_paper":"/paper/2312.17244","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:e55d1aa05ae91ce03cc53ac843416b586bf0c20f839dbd32cf2950dc8fbeca6e","observation_id":"1c14f408-eaf5-488a-9681-6860f4707949","resolution":{"observed_at":"2026-08-06T15:03:56.686638Z","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":"2026-08-06T15:03:57.071572Z","title":"(8) • MEAN FIELD 0 PREDICTIVE","venue":null,"work_id":"599a9a02-1147-4f14-bdc2-62967b9cab9b","year":2021},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.689574Z"},"links":{"citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:e39f2d3fa423eb6bcace61e79235986efee1df8c701518ce0658d97a22c3cb49","observation_id":"24efffe4-41b1-457a-8829-d58659eebf35","resolution":{"observed_at":"2026-08-06T15:03:57.073503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T15:03:57.065782Z","title":"B Applications and extensions of the Laplace approximation Section 4 discusses Laplace approximation with the goal of calibrated predictive uncertainty","venue":null,"work_id":"d7d17028-1753-4ffe-9b0b-96075b8f7e6f","year":2021},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.691999Z"},"links":{"citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:69651d538dd4ec8ebe7c044e52642384eb4203fe9152a8230dfcdb840463e1d9","observation_id":"a6161ff6-e2a8-4fc1-b831-7db0a97d8da4","resolution":{"observed_at":"2026-08-06T15:03:57.067966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T15:03:57.059595Z","title":"(2025) lift the method to the setting of operator learning","venue":null,"work_id":"c688ea2d-6b1c-4900-8323-98218bf9b7d4","year":2025},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.694224Z"},"links":{"citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:a0644463766c4c5a33add6ddd85162ae349fc698b620a60ec87fd0ddc60ec1dc","observation_id":"7348ac9c-8a29-4dc8-bb45-93589fc6f924","resolution":{"observed_at":"2026-08-06T15:03:57.061895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T15:03:57.052891Z","title":"for learning layerwise equivariance (van der Ouderaa et al., 2023)","venue":null,"work_id":"b5ff519c-292b-4f56-8bd5-927d119103d8","year":2023},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.696847Z"},"links":{"citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:a5ec012dc448fc23ec1a35af21f7536cbb510247cff4392d1f13d57362ba583a","observation_id":"23c0c778-3215-4776-8671-ef91c0997497","resolution":{"observed_at":"2026-08-06T15:03:57.055092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T15:03:57.046543Z","title":"Various other applications exist and this non-extensive list aimed only at provided some pointers for potential use cases","venue":null,"work_id":"426964b8-1251-445a-b9ba-b02a2ac22815","year":2023},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.699604Z"},"links":{"citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:f284264ba042a1ff2b1cd7e4f2089315540782494d20f3d05c74ad89e9250da3","observation_id":"d7724316-f62a-4656-b594-5f9294c0de07","resolution":{"observed_at":"2026-08-06T15:03:57.048789Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T15:03:57.040377Z","title":"This yields a more refined MAP estimate and well-calibrated epistemic uncertainties when prior knowledge is available","venue":null,"work_id":"32615949-a0b5-43f6-b7fa-c80d9897fb30","year":2024},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.701894Z"},"links":{"citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:807d0c34054e8a590a8fa8bba9a2c430e253ca1079744163d05fce6b3103d701","observation_id":"fddf0f05-025a-4b45-af82-6071a5797fc7","resolution":{"observed_at":"2026-08-06T15:03:57.042556Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T15:03:57.033726Z","title":"This regulariser (eq","venue":null,"work_id":"9a78d7c7-2fde-48de-955a-dfa884f4ce08","year":2024},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":1992,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.704342Z"},"links":{"citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:3f38b0f5d6e0e3bcc7a9a779d2dbee99654de79ccf139bbf3d52a5f5a8b174c4","observation_id":"af524252-e39c-45c0-bb8c-18d35ec9f3ae","resolution":{"observed_at":"2026-08-06T15:03:57.035804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.07810","last_updated":"2018-05-20T18:26:23Z","snapshot_observed_at":"2026-07-06T06:40:12.419240Z","submitted_at":"2018-05-20T18:26:23Z","title":"Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting","version":1},"cited_work":{"arxiv_id":"1805.07810","doi":null,"metadata_source":"pith","pith_arxiv_id":"1805.07810","snapshot_observed_at":"2026-08-06T15:03:56.890602Z","title":"Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting","venue":"stat.ML","work_id":"8902a338-1b13-456c-9230-2316dac5f997","year":2018},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.673724Z"},"links":{"cited_paper":"/paper/1805.07810","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:cd6a839be1f427259e1a399d5dc03e2fd433fd707eefd2c4816bb4bf2629bb89","observation_id":"28b1ec2d-3c97-4227-b455-c774706ab874","resolution":{"observed_at":"2026-08-06T15:03:56.893235Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.05779","last_updated":"2019-03-14T01:05:24Z","snapshot_observed_at":"2026-07-06T07:39:11.191289Z","submitted_at":"2019-03-14T01:05:24Z","title":"Functional Variational Bayesian Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.05779","snapshot_observed_at":"2026-08-06T15:03:56.680959Z","title":"Tran, B.-H., Rossi, S., Milios, D., and Filippone, M","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.680959Z"},"links":{"cited_paper":"/paper/1903.05779","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:aa257abb0c4835a639fbe14df575523e7f9919e1211b90f59c9a58d5b65b7b69","observation_id":"55936bab-aa83-475c-b62f-497b5bf6feee","resolution":{"observed_at":"2026-08-06T15:03:56.680959Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.10118","last_updated":"2020-07-17T15:04:19Z","snapshot_observed_at":"2026-08-05T15:59:29.633801Z","submitted_at":"2020-02-24T08:52:06Z","title":"Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.10118","snapshot_observed_at":"2026-08-06T15:03:56.655983Z","title":"Kristiadi, A., Hein, M., and Hennig, P","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.655983Z"},"links":{"cited_paper":"/paper/2002.10118","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:081565d78e173240760404cb089a450bb8cc36aba4581745ed86841c1d6d2725","observation_id":"becc4ad5-acb9-4d7e-b259-e3fd3a94c632","resolution":{"observed_at":"2026-08-06T15:03:56.655983Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.03577","last_updated":"2021-11-05T15:52:48Z","snapshot_observed_at":"2026-07-06T12:05:52.781976Z","submitted_at":"2021-11-05T15:52:48Z","title":"Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.03577","snapshot_observed_at":"2026-08-06T15:03:56.642670Z","title":"Fortuin, V","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.642670Z"},"links":{"cited_paper":"/paper/2111.03577","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:28fcd8bfd36939e10d85777b66e7104784d492765ec813a31c91167e4f4b8ef5","observation_id":"c918087a-a84a-4c77-89c1-b0c4124651e1","resolution":{"observed_at":"2026-08-06T15:03:56.642670Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.06868","last_updated":"2022-03-18T15:17:30Z","snapshot_observed_at":"2026-08-05T19:40:17.824746Z","submitted_at":"2021-05-14T14:53:30Z","title":"Priors in Bayesian Deep Learning: A Review","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.06868","snapshot_observed_at":"2026-08-06T15:03:56.644997Z","title":"Hobbhahn, M., Kristiadi, A., and Hennig, P","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.644997Z"},"links":{"cited_paper":"/paper/2105.06868","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:1f2267c58cf1a056f1871573ee94a1e5a241cfdfea30ac5f6ad2455786559f56","observation_id":"65b48e54-33f9-43ee-b701-81165ecda8a8","resolution":{"observed_at":"2026-08-06T15:03:56.644997Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.08309","last_updated":"2023-07-10T16:35:03Z","snapshot_observed_at":"2026-08-05T00:35:37.158347Z","submitted_at":"2023-04-17T14:23:43Z","title":"Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization","version":2},"cited_work":{"arxiv_id":"2304.08309","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.08309","snapshot_observed_at":"2026-08-06T15:03:56.916028Z","title":"Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization","venue":"cs.LG","work_id":"e24f5466-4025-4a2d-af11-1efb33f2e08c","year":2023},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.661220Z"},"links":{"cited_paper":"/paper/2304.08309","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:bb9f17510d6ac0d9e9121508cb52f737110e3c6836bc8be12dc6f609500abe35","observation_id":"4554d02b-2305-436b-bbc5-de3d53046028","resolution":{"observed_at":"2026-08-06T15:03:56.918963Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T15:03:56.564720Z","title":"URL https://docs","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.564720Z"},"links":{"citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:1bf4296ee87d76b8d077eff0d94273f33c72e470f49d2dfedf01182d6f6e0240","observation_id":"43a26124-beda-4f7d-b387-ce7ca212c31d","resolution":{"observed_at":"2026-08-06T15:03:56.564720Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.19183","last_updated":"2025-01-31T14:46:30Z","snapshot_observed_at":"2026-07-06T20:29:02.246836Z","submitted_at":"2025-01-31T14:46:30Z","title":"Position: Curvature Matrices Should Be Democratized via Linear Operators","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.19183","snapshot_observed_at":"2026-08-06T15:03:56.569578Z","title":"Daxberger, E., Kristiadi, A., Immer, A., Eschenhagen, R., Bauer, M., and Hennig, P","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-06T15:03:56.569578Z"},"links":{"cited_paper":"/paper/2501.19183","citing_paper":"/paper/2507.17013"},"observation_digest":"sha256:dd31ebc46ce80b0e09fd992e6e26c24e1e0de5ab54aac2ce7ede37b61e65d9d0","observation_id":"1d293932-d2ee-44c1-a119-01f3db328bc0","resolution":{"observed_at":"2026-08-06T15:03:56.569578Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.17013","last_updated":"2025-07-22T20:49:30Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T14:56:09.144793Z","submitted_at":"2025-07-22T20:49:30Z","title":"laplax -- Laplace Approximations with JAX"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":0,"metadata_mismatch":6,"parse_uncertain":0,"unresolved":13,"verified_exact":2,"verified_fuzzy":7},"total_outbound_references":28},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 1 inbound Pith citation observation for arXiv:2507.17013."}