{"as_of":"2026-08-17T01:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:23a7f47c0204c906070a7286d57311397e3bbbf4650e74331fbf52b6d2a0dc47","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":31,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:10:25.500000Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":77,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":"2006.10742","doi":"10.48550/arxiv.2006.10742","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning invariant representations for reinforcement learning without reconstruction.arXiv preprint arXiv:2006.10742","venue":"arXiv (Cornell University)","work_id":"92ef126a-9005-43ad-9330-860508c864ca","year":2006},"citing_paper":{"arxiv_id":"2203.12601","last_updated":"2022-11-18T05:57:09Z","snapshot_observed_at":"2026-08-11T08:36:53.636356Z","submitted_at":"2022-03-23T17:55:09Z","title":"R3M: A Universal Visual Representation for Robot Manipulation","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-15T13:26:53.843613Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2203.12601"},"observation_digest":"sha256:cd6a17ec12d83b7cb0968efb7596a503f8c7c99b0a236f8960565aec0ef7151d","observation_id":"781a693a-7d47-4f67-96e8-0efad716c3c2","resolution":{"observed_at":"2026-05-15T13:26:53.911524Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":"2006.10742","doi":"10.48550/arxiv.2006.10742","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning invariant representations for reinforcement learning without reconstruction.arXiv preprint arXiv:2006.10742","venue":"arXiv (Cornell University)","work_id":"92ef126a-9005-43ad-9330-860508c864ca","year":2006},"citing_paper":{"arxiv_id":"2411.05174","last_updated":"2026-04-27T19:23:31Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-11-07T20:27:29Z","title":"Bayesian Inverse Transition Learning: Learning Dynamics From Near-Optimal Trajectories","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-05-23T17:10:04.386499Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2411.05174"},"observation_digest":"sha256:acf62550f142361005bcef7822d72c672af8740bd25200ee89efd9d5d0485317","observation_id":"ac87f509-a843-4003-8c9f-eca1b4d66716","resolution":{"observed_at":"2026-05-23T17:13:14.099190Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":"2006.10742","doi":"10.48550/arxiv.2006.10742","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning invariant representations for reinforcement learning without reconstruction.arXiv preprint arXiv:2006.10742","venue":"arXiv (Cornell University)","work_id":"92ef126a-9005-43ad-9330-860508c864ca","year":2006},"citing_paper":{"arxiv_id":"2412.08893","last_updated":"2026-05-05T23:38:18Z","snapshot_observed_at":"2026-07-06T20:05:36.919481Z","submitted_at":"2024-12-12T03:14:47Z","title":"Optimal Control with Natural Images: Efficient Reinforcement Learning using Overcomplete Sparse Codes","version":3},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-05-23T07:19:39.231145Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2412.08893"},"observation_digest":"sha256:09469c17a32aec2cac80fffbfad6b1ff427d8fe6c1ab8f38348bd69d15be978b","observation_id":"b9c1d488-5725-480b-9848-7bbad204caab","resolution":{"observed_at":"2026-05-23T07:22:42.504333Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-11T04:46:39.123950Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.18396","last_updated":"2025-06-14T15:20:18Z","snapshot_observed_at":"2026-08-14T07:59:58.376059Z","submitted_at":"2024-12-24T12:39:23Z","title":"Contrastive Representation for Interactive Recommendation","version":3},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-11T04:46:39.123950Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2412.18396"},"observation_digest":"sha256:dcc0e8924d9fc5441f1020682d623e6e5711cfdce8d10a50f32fb62b9f2914fa","observation_id":"9c139145-ea5c-41d5-ad42-0094979afa8b","resolution":{"observed_at":"2026-08-11T04:46:39.123950Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-09T19:18:45.167910Z","title":"Learning invariant representations for reinforcement learning without reconstruction","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2502.00379","last_updated":"2025-06-12T16:28:52Z","snapshot_observed_at":"2026-08-16T14:49:11.425556Z","submitted_at":"2025-02-01T09:35:51Z","title":"Latent Action Learning Requires Supervision in the Presence of Distractors","version":5},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-09T19:18:45.167910Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2502.00379"},"observation_digest":"sha256:f67f56e2969918e5b25d6aa59616ee5c7115b2e11769c5032773095e24cc60e3","observation_id":"176cb31d-a95d-4667-a688-0828faf09e2f","resolution":{"observed_at":"2026-08-09T19:18:45.167910Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-09T11:22:28.984591Z","title":"Learning invariant representations for rein- forcement learning without reconstruction","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2502.02743","last_updated":"2025-02-04T22:09:43Z","snapshot_observed_at":"2026-08-14T11:59:50.011836Z","submitted_at":"2025-02-04T22:09:43Z","title":"LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T11:22:28.984591Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2502.02743"},"observation_digest":"sha256:51914ff6e14fcc10e08a5b98e1f58c450d7ca664fb9bffa9c27d410b82407d92","observation_id":"5c4ad380-aff4-4c88-8cf5-3c28898c07a3","resolution":{"observed_at":"2026-08-09T11:22:28.984591Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-07T19:33:22.105321Z","title":"Learning invariant representations for reinforcement learning without reconstruction","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2502.10077","last_updated":"2025-02-14T10:59:09Z","snapshot_observed_at":"2026-08-13T14:33:07.395379Z","submitted_at":"2025-02-14T10:59:09Z","title":"Towards Empowerment Gain through Causal Structure Learning in Model-Based RL","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T19:33:22.105321Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2502.10077"},"observation_digest":"sha256:6651d01745fb8d9eaa1004142bf97aef2bc02196998530e7431dbdf80c713746","observation_id":"38e5fc79-5ea7-4ffe-83ea-8a877a0d394d","resolution":{"observed_at":"2026-08-07T19:33:22.105321Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-15T23:10:25.500000Z","title":"Learning invariant representations for reinforcement learning without reconstruction","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2505.05691","last_updated":"2025-05-09T00:02:22Z","snapshot_observed_at":"2026-08-15T22:57:13.126027Z","submitted_at":"2025-05-09T00:02:22Z","title":"Physics-informed Temporal Difference Metric Learning for Robot Motion Planning","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-15T23:10:25.500000Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2505.05691"},"observation_digest":"sha256:fab478308b3a22819e8b012389f19c522cd22ff295dc0466adc6429300122204","observation_id":"9306d304-a8bb-4ec2-8753-2efd89d9e46c","resolution":{"observed_at":"2026-08-15T23:10:25.500000Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-15T21:24:27.477890Z","title":"Learn- ing invariant representations for reinforcement learning without reconstruction.CoRR, abs/2006.10742,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2505.09959","last_updated":"2025-05-15T04:41:21Z","snapshot_observed_at":"2026-08-16T10:58:23.415890Z","submitted_at":"2025-05-15T04:41:21Z","title":"Approximated Behavioral Metric-based State Projection for Federated Reinforcement Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T21:24:27.477890Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2505.09959"},"observation_digest":"sha256:dcf5777ed8205a8c24c36484976dced2639d0e65f318019b7ce34a3c2523668e","observation_id":"49aed078-ddc7-42b7-9de5-14a9594c55af","resolution":{"observed_at":"2026-08-15T21:24:27.477890Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-07T12:10:08.875246Z","title":"Learning invariant representations for reinforcement learning without reconstruction","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.00563","last_updated":"2025-09-08T18:56:14Z","snapshot_observed_at":"2026-08-15T02:41:01.519002Z","submitted_at":"2025-05-31T13:43:41Z","title":"Understanding Behavioral Metric Learning: A Large-Scale Study on Distracting Reinforcement Learning Environments","version":2},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-07T12:10:08.875246Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2506.00563"},"observation_digest":"sha256:5ec280a78027a06ba66c26585b2f7272b9eda87c3a62c67df3bbd9e54c3b215f","observation_id":"c31911ca-51a1-4fe3-9d1f-3e4581e9afdb","resolution":{"observed_at":"2026-08-07T12:10:08.875246Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-07T12:02:48.124549Z","title":"Learning invariant representations for reinforcement learning without reconstruc- tion,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.02050","last_updated":"2025-06-01T06:36:19Z","snapshot_observed_at":"2026-08-07T11:54:12.395783Z","submitted_at":"2025-06-01T06:36:19Z","title":"Decoupled Hierarchical Reinforcement Learning with State Abstraction for Discrete Grids","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T12:02:48.124549Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2506.02050"},"observation_digest":"sha256:e98ad8ec428a5e42586181993ce1e41aeefad0400d00843a6264a1d59f0d3d6c","observation_id":"745bc053-2879-47b3-a394-eea2e7e30507","resolution":{"observed_at":"2026-08-07T12:02:48.124549Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-07T10:47:32.924930Z","title":"Learn- ing invariant representations for reinforcement learning without reconstruction.arXiv preprint arXiv:2006.10742,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.05418","last_updated":"2025-06-05T00:36:54Z","snapshot_observed_at":"2026-08-15T18:45:00.919710Z","submitted_at":"2025-06-05T00:36:54Z","title":"Self-Predictive Dynamics for Generalization of Vision-based Reinforcement Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T10:47:32.924930Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2506.05418"},"observation_digest":"sha256:85189035406e51db1e9358760b9ddd36c38b7a6dcfc35d5d81dd35ba865ed853","observation_id":"4270a024-b1fc-4f57-bb03-5fc166d17ede","resolution":{"observed_at":"2026-08-07T10:47:32.924930Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-15T19:39:00.009760Z","title":"Learning invariant representations for reinforcement learning without reconstruction,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.15377","last_updated":"2025-06-18T11:47:02Z","snapshot_observed_at":"2026-08-15T19:33:02.138810Z","submitted_at":"2025-06-18T11:47:02Z","title":"Efficient and Generalizable Environmental Understanding for Visual Navigation","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T19:39:00.009760Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2506.15377"},"observation_digest":"sha256:e75df7acbd764699aab3e8bfc6f5dc8f71cbced11c72325af9f0360ba1c712bd","observation_id":"262d9d42-3a04-4d69-956b-7a8c212f3858","resolution":{"observed_at":"2026-08-15T19:39:00.009760Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-15T19:30:24.179126Z","title":"Learning invariant representa- tions for reinforcement learning without reconstruction","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.16565","last_updated":"2025-06-19T19:41:29Z","snapshot_observed_at":"2026-08-16T05:34:16.021768Z","submitted_at":"2025-06-19T19:41:29Z","title":"Reimagination with Test-time Observation Interventions: Distractor-Robust World Model Predictions for Visual Model Predictive Control","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T19:30:24.179126Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2506.16565"},"observation_digest":"sha256:1f1779218bb8c1d64da1fc7ff8f6fcf69709f183ba461fa07396a492e6f08fcb","observation_id":"1b84a277-27fa-4c80-9c63-5c2c2990b398","resolution":{"observed_at":"2026-08-15T19:30:24.179126Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-06T13:21:59.445779Z","title":"Learning invariant representations for reinforcement learning without reconstruction","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2507.20853","last_updated":"2025-07-28T14:06:44Z","snapshot_observed_at":"2026-08-13T02:46:13.000774Z","submitted_at":"2025-07-28T14:06:44Z","title":"Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces","version":1},"reference_index":138,"source":"arxiv_source","source_observed_at":"2026-08-06T13:21:59.445779Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2507.20853"},"observation_digest":"sha256:d23ca0c24fdfcb926cdb9d0821fb24edadb5f0e0f24eea2bd28f67d592343be3","observation_id":"932549f6-ac7a-4cf1-b8de-d70b042efbbd","resolution":{"observed_at":"2026-08-06T13:21:59.445779Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":"2006.10742","doi":"10.48550/arxiv.2006.10742","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning invariant representations for reinforcement learning without reconstruction.arXiv preprint arXiv:2006.10742","venue":"arXiv (Cornell University)","work_id":"92ef126a-9005-43ad-9330-860508c864ca","year":2006},"citing_paper":{"arxiv_id":"2511.05963","last_updated":"2026-05-25T15:53:24Z","snapshot_observed_at":"2026-08-08T22:18:33.888125Z","submitted_at":"2025-11-08T10:41:26Z","title":"Next-Latent Prediction Transformers Learn Compact World Models","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-25T07:21:04.684347Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2511.05963"},"observation_digest":"sha256:d1440411337eba59e995bd7ffd64646ba2c1be80b9c5810572ed36c069437d59","observation_id":"370db0ef-760c-4821-afd8-1d528ae46d08","resolution":{"observed_at":"2026-05-25T07:25:29.458245Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-03T23:27:57.468872Z","title":"Learning invariant representations for reinforcement learning without reconstruction.arXiv preprint arXiv:2006.10742,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2511.05963","last_updated":"2026-05-25T15:53:24Z","snapshot_observed_at":"2026-08-08T22:18:33.888125Z","submitted_at":"2025-11-08T10:41:26Z","title":"Next-Latent Prediction Transformers Learn Compact World Models","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T23:27:57.468872Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2511.05963"},"observation_digest":"sha256:df0005339ab958fd036b775cb128ff608ef9035ecfc70cee1dfb67fe6d1b5e59","observation_id":"dd6831bc-67aa-4601-aa33-37dc112c75d5","resolution":{"observed_at":"2026-08-03T23:27:57.468872Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-02T23:46:56.591823Z","title":"Learning invariant representations for rein- forcement learning without reconstruction.arXiv preprint arXiv:2006.10742,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2602.12753","last_updated":"2026-06-11T11:35:13Z","snapshot_observed_at":"2026-08-14T14:56:40.959040Z","submitted_at":"2026-02-13T09:32:26Z","title":"Hierarchical Successor Representation for Robust Transfer","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-02T23:46:56.591823Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2602.12753"},"observation_digest":"sha256:51d189186f1de00943f79dbdb4140fc8d1877a5eaf65876442e162e93168b0fe","observation_id":"8d209b51-f58e-41ea-93d7-7422cb413cbc","resolution":{"observed_at":"2026-08-02T23:46:56.591823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":"2006.10742","doi":"10.48550/arxiv.2006.10742","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning invariant representations for reinforcement learning without reconstruction.arXiv preprint arXiv:2006.10742","venue":"arXiv (Cornell University)","work_id":"92ef126a-9005-43ad-9330-860508c864ca","year":2006},"citing_paper":{"arxiv_id":"2605.07278","last_updated":"2026-05-08T05:43:33Z","snapshot_observed_at":"2026-08-01T00:55:28.214005Z","submitted_at":"2026-05-08T05:43:33Z","title":"Predictive but Not Plannable: RC-aux for Latent World Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-11T02:11:26.526418Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2605.07278"},"observation_digest":"sha256:2ba34610ecd240effa18463f356e6ef174a775f9cb5e421d07796c2b0f9f294b","observation_id":"fa3cfe61-a583-41ae-8dc9-612d19b1fabc","resolution":{"observed_at":"2026-05-11T03:50:57.323227Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":"2006.10742","doi":"10.48550/arxiv.2006.10742","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning invariant representations for reinforcement learning without reconstruction.arXiv preprint arXiv:2006.10742","venue":"arXiv (Cornell University)","work_id":"92ef126a-9005-43ad-9330-860508c864ca","year":2006},"citing_paper":{"arxiv_id":"2605.13105","last_updated":"2026-05-13T07:15:37Z","snapshot_observed_at":"2026-07-06T23:24:42.799888Z","submitted_at":"2026-05-13T07:15:37Z","title":"What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-14T18:46:34.102687Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2605.13105"},"observation_digest":"sha256:0b3acc1379b10f97bb2eda32e03ea72743671526f0828f517550bb223d38902c","observation_id":"01271e96-3075-4b09-83f2-64c1397f6db3","resolution":{"observed_at":"2026-05-14T18:47:36.094929Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":"2006.10742","doi":"10.48550/arxiv.2006.10742","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning invariant representations for reinforcement learning without reconstruction.arXiv preprint arXiv:2006.10742","venue":"arXiv (Cornell University)","work_id":"92ef126a-9005-43ad-9330-860508c864ca","year":2006},"citing_paper":{"arxiv_id":"2605.14304","last_updated":"2026-05-14T03:12:29Z","snapshot_observed_at":"2026-08-11T23:17:38.238283Z","submitted_at":"2026-05-14T03:12:29Z","title":"Matrix-Space Reinforcement Learning for Reusing Local Transition Geometry","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-15T02:03:11.540545Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2605.14304"},"observation_digest":"sha256:8172756b99f38e1b7d0303603cf23994d80a3dd010d5d0d218fe9b077a0f4922","observation_id":"9733eb41-d64c-4c30-b566-676eb4f0c864","resolution":{"observed_at":"2026-05-15T02:03:28.837266Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":"2006.10742","doi":"10.48550/arxiv.2006.10742","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning invariant representations for reinforcement learning without reconstruction.arXiv preprint arXiv:2006.10742","venue":"arXiv (Cornell University)","work_id":"92ef126a-9005-43ad-9330-860508c864ca","year":2006},"citing_paper":{"arxiv_id":"2606.00427","last_updated":"2026-05-29T23:29:49Z","snapshot_observed_at":"2026-08-09T12:00:27.086758Z","submitted_at":"2026-05-29T23:29:49Z","title":"Topology-Aware State Abstraction with Tangle Cores for Markov Decision Processes","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-28T22:51:27.142004Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2606.00427"},"observation_digest":"sha256:dbb15401dd6eab664fb50102b902443ebd8a5275b73d37ed466ea55874f6fee1","observation_id":"a27e217f-c1e2-4ebf-839a-9fe2c1b87dc1","resolution":{"observed_at":"2026-06-28T22:52:44.937214Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":"2006.10742","doi":"10.48550/arxiv.2006.10742","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning invariant representations for reinforcement learning without reconstruction.arXiv preprint arXiv:2006.10742","venue":"arXiv (Cornell University)","work_id":"92ef126a-9005-43ad-9330-860508c864ca","year":2006},"citing_paper":{"arxiv_id":"2606.11525","last_updated":"2026-06-10T00:06:24Z","snapshot_observed_at":"2026-07-06T23:50:35.052764Z","submitted_at":"2026-06-10T00:06:24Z","title":"Learning Object Manipulation from Scratch via Contrastive Interaction","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-06-27T10:10:21.427118Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2606.11525"},"observation_digest":"sha256:a096e2681453cb0c779ac93dbd28e9a2e4ca3e581d636a024441356e409d54f0","observation_id":"d592bc2d-b457-41a2-ab71-ef168aad790a","resolution":{"observed_at":"2026-07-03T10:17:57.422451Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":"2006.10742","doi":"10.48550/arxiv.2006.10742","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning invariant representations for reinforcement learning without reconstruction.arXiv preprint arXiv:2006.10742","venue":"arXiv (Cornell University)","work_id":"92ef126a-9005-43ad-9330-860508c864ca","year":2006},"citing_paper":{"arxiv_id":"2606.20411","last_updated":"2026-06-18T15:58:48Z","snapshot_observed_at":"2026-08-08T10:53:09.850580Z","submitted_at":"2026-06-18T15:58:48Z","title":"Direct Advantage Estimation for Scalable and Sample-efficient Deep Reinforcement Learning","version":1},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-06-26T18:12:00.111067Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2606.20411"},"observation_digest":"sha256:9ad457dd741c036047470fa7496247c83096d9e95ec9c5cdf0510054446114ff","observation_id":"ba372a39-d7ac-4f7f-ad95-731e4701af78","resolution":{"observed_at":"2026-07-04T03:19:31.172548Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":"2006.10742","doi":"10.48550/arxiv.2006.10742","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning invariant representations for reinforcement learning without reconstruction.arXiv preprint arXiv:2006.10742","venue":"arXiv (Cornell University)","work_id":"92ef126a-9005-43ad-9330-860508c864ca","year":2006},"citing_paper":{"arxiv_id":"2606.25421","last_updated":"2026-06-24T05:31:00Z","snapshot_observed_at":"2026-08-13T01:41:53.860669Z","submitted_at":"2026-06-24T05:31:00Z","title":"Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-06-25T21:11:50.874696Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2606.25421"},"observation_digest":"sha256:ba616c0302c47a228e7a3cebba79a86c809b4281ea3bf726ef5a3c6f41e54577","observation_id":"85f26f7b-d96a-4380-9974-ef2e081cd7cd","resolution":{"observed_at":"2026-07-04T19:40:06.155010Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":"2006.10742","doi":"10.48550/arxiv.2006.10742","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning invariant representations for reinforcement learning without reconstruction.arXiv preprint arXiv:2006.10742","venue":"arXiv (Cornell University)","work_id":"92ef126a-9005-43ad-9330-860508c864ca","year":2006},"citing_paper":{"arxiv_id":"2606.25556","last_updated":"2026-06-24T08:32:42Z","snapshot_observed_at":"2026-07-07T00:00:02.505448Z","submitted_at":"2026-06-24T08:32:42Z","title":"BiPACE: Bisimulation-Guided Policy Optimization with Action Counterfactual Estimation for LLM Agents","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-25T21:04:09.237686Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2606.25556"},"observation_digest":"sha256:c63d2ccd1af6d83771f2eea7834f7e9d8b57ed7f3e179346c021b06f7bc46af9","observation_id":"352d998d-fff4-42ed-a36d-3956d1af82a9","resolution":{"observed_at":"2026-07-04T19:40:07.693168Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":"2006.10742","doi":"10.48550/arxiv.2006.10742","metadata_source":"arxiv_reference","pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Learning invariant representations for reinforcement learning without reconstruction.arXiv preprint arXiv:2006.10742","venue":"arXiv (Cornell University)","work_id":"92ef126a-9005-43ad-9330-860508c864ca","year":2006},"citing_paper":{"arxiv_id":"2606.27681","last_updated":"2026-06-26T03:26:02Z","snapshot_observed_at":"2026-08-07T08:14:08.958302Z","submitted_at":"2026-06-26T03:26:02Z","title":"Textual Belief States for World Models: Identifiable Representation Learning Under Strict Mediation","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-06-29T04:51:28.634376Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2606.27681"},"observation_digest":"sha256:a3e6b5c52b02ac8c0fb3f942ed639bec3543a11f65f6981c321b30a7d559d5b7","observation_id":"c1497871-8c96-4503-b634-4a8afdf2633d","resolution":{"observed_at":"2026-06-29T19:13:53.227287Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-07-11T21:18:56.362614Z","title":"arXiv preprint arXiv:2006.10742 , year=","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.04153","last_updated":"2026-07-05T07:42:00Z","snapshot_observed_at":"2026-08-13T19:02:37.501843Z","submitted_at":"2026-07-05T07:42:00Z","title":"Mask-based Predictive Representations for Reinforcement Learning","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-07-11T21:18:56.362614Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2607.04153"},"observation_digest":"sha256:cfbaf64864b9e89d6e86fe0142edb7dd0e6cfa2dc68eedc1b580b069156f5c3a","observation_id":"1df26121-5b5d-4d3a-9fa9-f6e9efdcaee8","resolution":{"observed_at":"2026-07-11T21:18:56.362614Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-02T07:20:40.531548Z","title":"Zhang, R","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.11953","last_updated":"2026-08-06T23:25:08Z","snapshot_observed_at":"2026-08-16T20:40:09.789038Z","submitted_at":"2026-07-11T21:33:32Z","title":"When Does Reward Teach State? A Hidden-Automaton Instrument and a Group-Language Warning Signal","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-02T07:20:40.531548Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2607.11953"},"observation_digest":"sha256:9fffc62421d0d738ec895f4f5023bf1aea463b389fa01a64487ee15a230e2ad2","observation_id":"666940ed-ca11-4316-b663-587cfa4c0341","resolution":{"observed_at":"2026-08-02T07:20:40.531548Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-10T04:21:20.349823Z","title":"arXiv preprint arXiv:2006.10742 , year=","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2608.06544","last_updated":"2026-08-06T19:49:31Z","snapshot_observed_at":"2026-08-16T13:33:18.412567Z","submitted_at":"2026-08-06T19:49:31Z","title":"TaskSense: Focusing on What Matters in World Models","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-10T04:21:20.349823Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2608.06544"},"observation_digest":"sha256:77c6d9cfe7ec2960c43ec9d77bd167eabefca548381902a42bf9106fcff09a0e","observation_id":"598dd703-9069-434e-a509-d80dca1144a7","resolution":{"observed_at":"2026-08-10T04:21:20.349823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10742","snapshot_observed_at":"2026-08-10T17:33:56.347350Z","title":"& Levine, S","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.06968","last_updated":"2026-08-07T08:44:20Z","snapshot_observed_at":"2026-08-15T09:23:06.357601Z","submitted_at":"2026-08-07T08:44:20Z","title":"Same physical state, different collective dynamics: state encodings select synchronization outcomes in language-model agents","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T17:33:56.347350Z"},"links":{"cited_paper":"/paper/2006.10742","citing_paper":"/paper/2608.06968"},"observation_digest":"sha256:6b4abcb4391aca71a34aa6d98d8db71720b48a2b1edbdda4e95bff5da2e57b09","observation_id":"fd9920c3-ef01-4b67-a935-1db39ff9b084","resolution":{"observed_at":"2026-08-10T17:33:56.347350Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2006.10742/citation-record","integrity":"/paper/2006.10742/integrity","json":"/paper/2006.10742/citation-record.json","paper":"/paper/2006.10742"},"outbound":[],"paper":{"arxiv_id":"2006.10742","last_updated":"2021-04-07T01:57:14Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T08:19:24.097653Z","submitted_at":"2020-06-18T17:59:35Z","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 31 inbound Pith citation observations for arXiv:2006.10742."}