{"as_of":"2026-08-07T10:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f43d6ea4e4a6a6cab391923f42ee5ac2dcaf0a1cdb50cfe0385a96c22d22e0ce","coverage":[{"denominator":22,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":22,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T05:26:07.371999Z","state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.16314/citation-record","integrity":"/paper/2607.16314/integrity","json":"/paper/2607.16314/citation-record.json","paper":"/paper/2607.16314"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2301.08243","last_updated":"2023-04-13T17:59:37Z","snapshot_observed_at":"2026-08-04T14:08:53.444823Z","submitted_at":"2023-01-19T18:59:01Z","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.08243","snapshot_observed_at":"2026-08-02T05:26:04.805429Z","title":"Self-supervised learning from images with a joint- embedding predictive architecture","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:04.805429Z"},"links":{"cited_paper":"/paper/2301.08243","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:d4b4d6ab7b5b2f75ebe150f69af21c380778b7c6f0e4ac96f32292437b239684","observation_id":"5a90c89e-bdce-4f79-b3f1-5414e33d70fe","resolution":{"observed_at":"2026-08-02T05:26:04.805429Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.09985","last_updated":"2025-06-11T17:57:09Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-06-11T17:57:09Z","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.09985","snapshot_observed_at":"2026-08-02T05:26:04.921748Z","title":"V-jepa 2: Self-supervised video models enable understanding, prediction and planning.arXiv preprint arXiv:2506.09985, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:04.921748Z"},"links":{"cited_paper":"/paper/2506.09985","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:4c9559eb9520acbfe09e48109d74620fa73fdf609dfee3659baf12d10317f322","observation_id":"c704d3c5-822b-4fcb-a443-da46daddbd7d","resolution":{"observed_at":"2026-08-02T05:26:04.921748Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.08471","last_updated":"2024-02-15T18:59:11Z","snapshot_observed_at":"2026-08-07T02:30:11.447693Z","submitted_at":"2024-02-15T18:59:11Z","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.08471","snapshot_observed_at":"2026-08-02T05:26:05.034435Z","title":"Revisiting feature prediction for learning visual repre- sentations from video.arXiv preprint arXiv:2404.08471, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:05.034435Z"},"links":{"cited_paper":"/paper/2404.08471","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:717f8dffbc6bb1f4e2fd9e13f1d3ae7aa29552a2f16380f7249e64167ae346a2","observation_id":"a8f65665-d5d1-480c-b65c-1f21ea0ec07b","resolution":{"observed_at":"2026-08-02T05:26:05.034435Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.03697","last_updated":"2021-03-29T13:02:36Z","snapshot_observed_at":"2026-07-06T10:31:24.691218Z","submitted_at":"2021-01-11T04:46:11Z","title":"RepVGG: Making VGG-style ConvNets Great Again","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.03697","snapshot_observed_at":"2026-08-02T05:26:05.111775Z","title":"Repvgg: Making vgg-style convnets great again","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:05.111775Z"},"links":{"cited_paper":"/paper/2101.03697","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:f64162c66fc64694fb3134b9ddaaf8b0e763c734e02fa258fbff87ba506137d2","observation_id":"112dbd3b-bb26-470a-a3c8-490844217460","resolution":{"observed_at":"2026-08-02T05:26:05.111775Z","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":"2026-08-02T05:26:05.275033Z","title":"seq-jepa: Autoregressive predictive learning of invariant-equivariant world models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:05.275033Z"},"links":{"citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:a92c0ecffef320702d57d2f04ce4bd0fab2b13dfd69864ae423ef7c7d65369c6","observation_id":"1259a05d-2f3a-4aa3-af2d-1a2bec789946","resolution":{"observed_at":"2026-08-02T05:26:05.275033Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.10122","last_updated":"2018-05-09T09:06:27Z","snapshot_observed_at":"2026-07-31T21:36:45.596575Z","submitted_at":"2018-03-27T15:08:55Z","title":"World Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.10122","snapshot_observed_at":"2026-08-02T05:26:05.369725Z","title":"World models.arXiv preprint arXiv:1803.10122, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:05.369725Z"},"links":{"cited_paper":"/paper/1803.10122","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:a01770048910ea90292971f9f8d57b923fdf4768bfed150981b6f39b798c2d10","observation_id":"09fd7272-cb8b-4187-8e12-ca4f6fea1828","resolution":{"observed_at":"2026-08-02T05:26:05.369725Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.01603","last_updated":"2020-03-17T17:10:58Z","snapshot_observed_at":"2026-08-03T15:20:23.515607Z","submitted_at":"2019-12-03T18:57:16Z","title":"Dream to Control: Learning Behaviors by Latent Imagination","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.01603","snapshot_observed_at":"2026-08-02T05:26:05.495721Z","title":"Dream to control: Learning behaviors by latent imagination.arXiv preprint arXiv:1912.01603, 2019","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:05.495721Z"},"links":{"cited_paper":"/paper/1912.01603","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:1ad25e9a562413e1f9b1e9277bcc647564570ee2d750a0b7845f5b801b22cfca","observation_id":"a3473f55-b651-4e6d-80cf-9afb3a961a2d","resolution":{"observed_at":"2026-08-02T05:26:05.495721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.04551","last_updated":"2019-06-04T18:13:09Z","snapshot_observed_at":"2026-07-06T07:14:03.735574Z","submitted_at":"2018-11-12T04:30:10Z","title":"Learning Latent Dynamics for Planning from Pixels","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.04551","snapshot_observed_at":"2026-08-02T05:26:05.620687Z","title":"Learning latent dynamics for planning from pixels","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:05.620687Z"},"links":{"cited_paper":"/paper/1811.04551","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:74d7953a1dfd35aeccd21837831154470a3c50405a7c1eb93810ca65f28340f5","observation_id":"1f44cb60-8d53-47f5-b3ee-daf048f5b506","resolution":{"observed_at":"2026-08-02T05:26:05.620687Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-02T05:26:05.750791Z","title":"Distilling the knowledge in a neural network","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:05.750791Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:93ddf14acbe7205050495be90a093810b2fff3499b47746a1d761ecf40a71452","observation_id":"842e11a1-32f3-486b-995d-fb8ce60e9c32","resolution":{"observed_at":"2026-08-02T05:26:05.750791Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.24181","last_updated":"2026-06-05T18:04:44Z","snapshot_observed_at":"2026-08-02T20:08:29.492757Z","submitted_at":"2026-02-27T17:03:45Z","title":"A Mixed Diet Makes DINO An Omnivorous Vision Encoder","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.24181","snapshot_observed_at":"2026-08-02T05:26:05.863088Z","title":"Hudson, Ye Xia, Skanda Koppula, Andre Araujo, Joao Carreira, and Niloy J","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:05.863088Z"},"links":{"cited_paper":"/paper/2602.24181","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:52479b4e59aca8b97c4a4cd5c6c0260ab643de9e537475e0aaf96c20d74bd0c0","observation_id":"bfd85a2f-f3b8-4892-abda-a9fe302d48cb","resolution":{"observed_at":"2026-08-02T05:26:05.863088Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.08481","last_updated":"2025-02-28T07:43:38Z","snapshot_observed_at":"2026-07-06T18:29:49.284504Z","submitted_at":"2024-06-12T17:59:21Z","title":"Enhancing End-to-End Autonomous Driving with Latent World Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.08481","snapshot_observed_at":"2026-08-02T05:26:05.968550Z","title":"Enhancing end-to-end autonomous driving with latent world model.arXiv preprint arXiv:2406.08481, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:05.968550Z"},"links":{"cited_paper":"/paper/2406.08481","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:b398671e6a8ea45c042f7a5ebf026ba4795d9523517ef32959c9534c7825a35c","observation_id":"9ccf1645-04d4-4e00-9c8f-bb712c95ffb7","resolution":{"observed_at":"2026-08-02T05:26:05.968550Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2603.19312","last_updated":"2026-06-03T18:50:40Z","snapshot_observed_at":"2026-08-06T05:42:53.129146Z","submitted_at":"2026-03-13T19:48:14Z","title":"LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.19312","snapshot_observed_at":"2026-08-02T05:26:06.151401Z","title":"Leworld- model: Stable end-to-end joint-embedding predictive architecture from pixels.arXiv preprint arXiv:2603.19312, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:06.151401Z"},"links":{"cited_paper":"/paper/2603.19312","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:6f478d3cec6614aad3948096a06757445777bcd04ff1b22f1f1449cc6848dfe0","observation_id":"0b83fd7e-78c0-4522-82a0-eb030e4941e0","resolution":{"observed_at":"2026-08-02T05:26:06.151401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-06T05:58:29.182448Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-02T05:26:06.280601Z","title":"Dinov2: Learning robust visual features without supervision.arXiv preprint arXiv:2304.07193, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:06.280601Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:05d26c26d5c725e62626a1a02c295d3590d22859d72794935494b1028ab7ee57","observation_id":"843d1e97-eb7b-44d2-a6f4-14d5a2b99948","resolution":{"observed_at":"2026-08-02T05:26:06.280601Z","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":"2026-08-02T05:26:06.430491Z","title":"Tartanground: A large-scale dataset for ground robot perception and navigation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:06.430491Z"},"links":{"citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:d44b029f44b4d3bac6a2313d16f4ceb6d838c0da00fe57202a15cacab15a6038","observation_id":"42960ff1-e226-4347-88de-e1545849c598","resolution":{"observed_at":"2026-08-02T05:26:06.430491Z","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":"2026-08-02T05:26:06.630169Z","title":"Learning from reward-free offline data: A case for planning with latent dynamics models.arXiv preprint arXiv:2502.14819, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:06.630169Z"},"links":{"citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:755e00f989dafccb6b8273a65217376a358537fe2a0199501bdbf18dc54b1f72","observation_id":"8cd4fe41-00a2-4f4f-a707-11ac168a0b2a","resolution":{"observed_at":"2026-08-02T05:26:06.630169Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.06810","last_updated":"2021-10-08T02:41:50Z","snapshot_observed_at":"2026-08-05T23:30:19.398803Z","submitted_at":"2021-02-12T22:57:28Z","title":"Understanding self-supervised Learning Dynamics without Contrastive Pairs","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.06810","snapshot_observed_at":"2026-08-02T05:26:06.743589Z","title":"Understanding self-supervised learning dynamics without contrastive pairs","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:06.743589Z"},"links":{"cited_paper":"/paper/2102.06810","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:e1c1ac47b5bd7d1a2dab57d6036dba3b336d98c15285666e0837dc5d94c60761","observation_id":"99a6e6b6-09ee-4aa3-bb0a-308daa6455b5","resolution":{"observed_at":"2026-08-02T05:26:06.743589Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.16908","last_updated":"2021-01-20T09:35:03Z","snapshot_observed_at":"2026-08-04T05:18:19.603942Z","submitted_at":"2020-06-30T15:38:37Z","title":"MDP Homomorphic Networks: Group Symmetries in Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.16908","snapshot_observed_at":"2026-08-02T05:26:06.835803Z","title":"Oliehoek, and Max Welling","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:06.835803Z"},"links":{"cited_paper":"/paper/2006.16908","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:d67a7eca43d43b2e5c9e4a7a4dafb45548625012387a770a9d6b251936771d4b","observation_id":"5b63f2e0-60fc-4aa9-9334-b9acf01812e5","resolution":{"observed_at":"2026-08-02T05:26:06.835803Z","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":"2026-08-02T05:26:06.988946Z","title":"A new learning paradigm: Learning using privileged information.Neural Networks, 22(5–6):544–557, 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:06.988946Z"},"links":{"citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:8d61948dac1430a3337c536f367659526e12b403289c27e2faca5523b684d3a4","observation_id":"44855899-f39d-4a36-818b-54708130812c","resolution":{"observed_at":"2026-08-02T05:26:06.988946Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04040","last_updated":"2023-03-28T18:38:47Z","snapshot_observed_at":"2026-07-06T13:18:44.773914Z","submitted_at":"2022-06-08T17:55:11Z","title":"MobileOne: An Improved One millisecond Mobile Backbone","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04040","snapshot_observed_at":"2026-08-02T05:26:07.067135Z","title":"Mobileone: An improved one millisecond mobile backbone","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:07.067135Z"},"links":{"cited_paper":"/paper/2206.04040","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:e5b14a8cd53e1f93bbbed2ccd7a55448a117df0a359d394569f77d34e2c84abe","observation_id":"e16df18f-8b4d-49b5-ac20-40de3b5d5419","resolution":{"observed_at":"2026-08-02T05:26:07.067135Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.00603","last_updated":"2025-07-01T09:36:38Z","snapshot_observed_at":"2026-08-07T02:31:44.510306Z","submitted_at":"2025-07-01T09:36:38Z","title":"World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.00603","snapshot_observed_at":"2026-08-02T05:26:07.155612Z","title":"World4drive: End-to-endautonomousdrivingviaintention-awarephysical latent world model.arXiv preprint arXiv:2507.00603, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:07.155612Z"},"links":{"cited_paper":"/paper/2507.00603","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:e818dfe156e763365008290907f64efa6324fd4cd2191ff0399d4e85dcac7eb8","observation_id":"494a20fd-e69d-45db-9f83-7cc66dacf5fa","resolution":{"observed_at":"2026-08-02T05:26:07.155612Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2411.04983","last_updated":"2025-02-01T02:40:49Z","snapshot_observed_at":"2026-07-06T19:46:54.707852Z","submitted_at":"2024-11-07T18:54:37Z","title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.04983","snapshot_observed_at":"2026-08-02T05:26:07.242925Z","title":"Dino-wm: World models on pre-trained visual features enable zero-shot planning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:07.242925Z"},"links":{"cited_paper":"/paper/2411.04983","citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:a2bd9cb6aafa31bac53ea6545f0febe5ad942a10eb69cf511083853fa480d368","observation_id":"2d818f8c-4859-49b3-999f-7b0c8e6c9d9d","resolution":{"observed_at":"2026-08-02T05:26:07.242925Z","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":"2026-08-02T05:26:07.371999Z","title":"Ad-l-jepa: Self- supervised spatial world models with joint embedding predictive architecture for autonomous driving with lidar data","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T05:26:07.371999Z"},"links":{"citing_paper":"/paper/2607.16314"},"observation_digest":"sha256:6bc14deac546456c4152332ad5507136077978526869c028ea7ca569d682f186","observation_id":"e9803679-2181-4994-b24b-a8c2c8e3db6a","resolution":{"observed_at":"2026-08-02T05:26:07.371999Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.16314","last_updated":"2026-07-15T00:58:45Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T02:32:13.619549Z","submitted_at":"2026-07-15T00:58:45Z","title":"Depth-Regularized JEPA World Models Learn More Transferable Representations from Real Outdoor Robot Data"},"reference_resolution":{"displayed":22,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":22,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":22},"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 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2607.16314."}