{"as_of":"2026-08-23T07:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:19731067334114df9e60da07d1f25f2d0bea8752987ddf837e596082ebdace70","coverage":[{"denominator":35,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T05:32:48.595901Z","state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+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/2608.09853/citation-record","integrity":"/paper/2608.09853/integrity","json":"/paper/2608.09853/citation-record.json","paper":"/paper/2608.09853"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2511.21631","last_updated":"2025-11-27T12:16:54Z","snapshot_observed_at":"2026-08-17T13:26:10.378579Z","submitted_at":"2025-11-26T17:59:08Z","title":"Qwen3-VL Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.21631","snapshot_observed_at":"2026-08-11T05:32:48.466505Z","title":"Qwen3-VL technical report.arXiv preprint arXiv:2511.21631, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.466505Z"},"links":{"cited_paper":"/paper/2511.21631","citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:0902a255acef9ca5eae120958572fa3ca4c086ddac21acfa5ff5c347de5551c2","observation_id":"c349d18c-dfb7-465e-8a73-9343cca2bf25","resolution":{"observed_at":"2026-08-11T05:32:48.466505Z","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":"2026-08-11T05:32:49.174125Z","title":"InProceedings of the Conference on Robot Learning, 2025","venue":null,"work_id":"98750bfe-cda6-405e-b3f9-b0b91ce3fd08","year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.471424Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:c45f4541311ed238c1715c77f1f5dea56c41114bb2cc196af58f684c32cddac1","observation_id":"a165dae4-3b6d-41df-9a56-847f0b49e8cd","resolution":{"observed_at":"2026-08-11T05:32:49.178305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:49.162466Z","title":"AgiBot World Colosseum: A large-scale manipulation platform for scalable and intelligent embodied systems","venue":null,"work_id":"524a5e80-c8f5-41eb-8df8-fc93ebe06703","year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.475117Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:847bc3956680e1a053d01031804dfcc991efdd27348748268f0126fecaf0ad01","observation_id":"c0dda3ab-8d52-4e4a-a976-39ccacb6bd50","resolution":{"observed_at":"2026-08-11T05:32:49.166567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:49.150401Z","title":"LeRobot: State-of-the-art machine learning for real-world robotics in PyTorch.https://github.com/huggingface/lerobot, 2024","venue":null,"work_id":"d3f8af72-53da-4723-9f80-bd6d64ea505c","year":2024},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.478790Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:803d84a0448a169b8cd96c53757857bbbfbc01d3327de8f3cbb7e08e7c11bd33","observation_id":"b799a5ea-064d-45b4-92c3-4123b836f69b","resolution":{"observed_at":"2026-08-11T05:32:49.154728Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:48.482927Z","title":"RynnBrain: Open embodied foundation models.arXiv preprint arXiv:2602.14979, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.482927Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:73dc1c6bf2cf06b1d574901913ec1017a1824914065266b9ce843bdf8ab0be54","observation_id":"7e8ab287-61fa-4750-864f-0216bfb4a877","resolution":{"observed_at":"2026-08-11T05:32:48.482927Z","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":"2026-08-11T05:32:49.138506Z","title":"Unified language model pre-training for natural language understanding and generation","venue":null,"work_id":"7b73564a-c9ea-458b-a692-d8e76856ded3","year":2019},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.487015Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:fe269056e338fe3b9f85472596608ace1d4bed87a084c5b625bab0c6c30737c9","observation_id":"19fbaae0-0730-4934-bedd-9cfe902fd8d1","resolution":{"observed_at":"2026-08-11T05:32:49.142533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:49.126360Z","title":"Stop regressing: Training value functions via classification for scalable deep RL","venue":null,"work_id":"df574ee9-36ee-41ab-922e-f24bde761011","year":2024},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.491350Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:24119d9bc93745eabaf831dd4b89477d8e872dc0762d2691329fd4b59090dd21","observation_id":"f8a4e68f-23c5-4767-aaa2-07c55c9d5afc","resolution":{"observed_at":"2026-08-11T05:32:49.130489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:48.494806Z","title":"Shortcut learning in deep neural networks.Nature Machine Intelligence, 2(11):665–673, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.494806Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:d1446b6196cb7d82d18190bbae704f2fe61dc9248a9c5d032c3af1f96c35123d","observation_id":"2a46edb3-503a-43c4-9187-a08d6b501b85","resolution":{"observed_at":"2026-08-11T05:32:48.494806Z","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":"2026-08-11T05:32:48.498440Z","title":"Mastering diverse control tasks through world models.Nature, pages 1–7, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.498440Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:d8df20c133ce3bdf26299bfefa446c86c8c485cde8a6623db7e1c44ce8ff1b46","observation_id":"de6652ff-49bc-42fe-b6e4-88f5c5f3417f","resolution":{"observed_at":"2026-08-11T05:32:48.498440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.11709","last_updated":"2026-03-09T06:44:42Z","snapshot_observed_at":"2026-08-12T03:35:51.024147Z","submitted_at":"2025-05-16T21:34:47Z","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.11709","snapshot_observed_at":"2026-08-11T05:32:48.502155Z","title":"EgoDex: Learning dexterous manipulation from large-scale egocentric video.arXiv preprint arXiv:2505.11709, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.502155Z"},"links":{"cited_paper":"/paper/2505.11709","citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:f4c748b0b87e1601cbf5bf4740061ad7ab5ea3ab2efa88b7e5018ad5203fb18e","observation_id":"aa50b288-3abc-48ea-b6b0-5f897cfba0a5","resolution":{"observed_at":"2026-08-11T05:32:48.502155Z","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":"2026-08-11T05:32:49.098242Z","title":"FiRE: En- hancing MLLMs with fine-grained context learning for complex image retrieval","venue":null,"work_id":"7890c87a-f565-42ca-b8b7-8af642781ac0","year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.506028Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:054f33f09a6ecec157a94ae5e5c3acdd84be8236c22b33aab8ff03a374b3e3b0","observation_id":"ad72e0b7-576f-4245-9a15-84d6cd9c8db4","resolution":{"observed_at":"2026-08-11T05:32:49.103143Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2511.14759","last_updated":"2025-11-19T04:34:49Z","snapshot_observed_at":"2026-08-20T22:25:56.255434Z","submitted_at":"2025-11-18T18:58:55Z","title":"$\\pi^{*}_{0.6}$: a VLA That Learns From Experience","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.14759","snapshot_observed_at":"2026-08-11T05:32:48.509349Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.509349Z"},"links":{"cited_paper":"/paper/2511.14759","citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:e6765839a4e26caa252ed18f008732479e0f9593cc9f6586493d6ccdff70871d","observation_id":"745b0c2d-1faa-40da-87ac-81c117d40981","resolution":{"observed_at":"2026-08-11T05:32:48.509349Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.00576","last_updated":"2025-08-30T18:04:19Z","snapshot_observed_at":"2026-08-14T02:52:34.768729Z","submitted_at":"2025-08-30T18:04:19Z","title":"Galaxea Open-World Dataset and G0 Dual-System VLA Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.00576","snapshot_observed_at":"2026-08-11T05:32:48.513096Z","title":"Galaxea open-world dataset and G0 dual-system VLA model.arXiv preprint arXiv:2509.00576, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.513096Z"},"links":{"cited_paper":"/paper/2509.00576","citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:20aa3f9bf23438ef55cc56e61094e09267e093143dfec2ac1debb9f974172c1b","observation_id":"bd3379af-6845-456e-b65e-1bc494e9ebef","resolution":{"observed_at":"2026-08-11T05:32:48.513096Z","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":"2026-08-11T05:32:49.087138Z","title":"Offline reinforcement learning with implicit Q-learning","venue":null,"work_id":"56339959-69ba-45db-b316-d98b4e4e69f1","year":2022},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.516957Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:d814bef9b80e39bd44ecb67d3b1fa680b76618b33338cece2dad03f91ab8f421","observation_id":"7dc2d07c-fa61-422c-af2d-18e7ea62a824","resolution":{"observed_at":"2026-08-11T05:32:49.090913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:48.520313Z","title":"RoboReward: General-purpose vision-language reward models for robotics.arXiv preprint arXiv:2601.00675, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.520313Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:60acf43d6fb430c0741a5f58263aade22a0da2de057de79ad9816d500f2d999d","observation_id":"1dbf5659-3f55-40b9-acd4-6ab1829be227","resolution":{"observed_at":"2026-08-11T05:32:48.520313Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2603.02115","last_updated":"2026-05-13T21:07:49Z","snapshot_observed_at":"2026-08-12T16:18:51.295325Z","submitted_at":"2026-03-02T17:38:58Z","title":"Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.02115","snapshot_observed_at":"2026-08-11T05:32:48.523516Z","title":"Robometer: Scaling general-purpose robotic reward models via trajectory comparisons.arXiv preprint arXiv:2603.02115, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.523516Z"},"links":{"cited_paper":"/paper/2603.02115","citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:f7fd48d5a214dd6269d6f4b6de1ad5058319930d84b4e72220391f150684a4d8","observation_id":"5d2bf1e1-856a-4b59-a0af-a7cebd03f51c","resolution":{"observed_at":"2026-08-11T05:32:48.523516Z","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":"2026-08-11T05:32:49.075508Z","title":"RDT-1B: a diffusion foundation model for bimanual manipulation","venue":null,"work_id":"20d3bd12-1c91-4039-b53d-6e2c37820d76","year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.527505Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:2ebd9767342c95e927a4dfc66de3a24ccee0dd9c82829aabfd62ba05c39c95cf","observation_id":"ed2d972c-5ef6-4251-9a2b-198ee893ba93","resolution":{"observed_at":"2026-08-11T05:32:49.079424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.26627","last_updated":"2026-05-20T11:23:00Z","snapshot_observed_at":"2026-08-15T09:06:21.337959Z","submitted_at":"2025-09-30T17:58:20Z","title":"TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.26627","snapshot_observed_at":"2026-08-11T05:32:48.531404Z","title":"TimeRewarder: Learning dense reward from passive videos via frame-wise temporal distance.arXiv preprint arXiv:2509.26627, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.531404Z"},"links":{"cited_paper":"/paper/2509.26627","citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:e0fdd34b92c25e7452561363b6d284cb294fc8884846768066fe9a996ca83c82","observation_id":"0e5e173b-0dee-4c70-ab77-98cba3480e39","resolution":{"observed_at":"2026-08-11T05:32:48.531404Z","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":"2026-08-11T05:32:49.062710Z","title":"Vision language models are in-context value learners","venue":null,"work_id":"46ba504e-1dcf-49c9-86e7-9ba7af1ca12e","year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.535408Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:b7d744445f470c23f3f728953eb644ae390d50c8f726af65967c779bda4a8d07","observation_id":"b42df604-629c-450a-9164-e1904295e3f3","resolution":{"observed_at":"2026-08-11T05:32:49.066740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:49.050811Z","title":"RoboTwin: Dual-arm robot benchmark with generative digital twins","venue":null,"work_id":"73f666a4-ef37-47ed-b4cb-6170578ee45c","year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.539127Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:dd5db2a76b7e0313de4a847b23d7f54da18a0bd8dc89d6ecb45b16df00b28782","observation_id":"22c029c0-64f5-40b1-b666-522eca1ada82","resolution":{"observed_at":"2026-08-11T05:32:49.055115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:49.037690Z","title":"Bigger, Regularized, Optimistic: scaling for compute and sample efficient continuous control","venue":null,"work_id":"dba4bde7-d752-4415-b911-382eda6f07f9","year":2024},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.543114Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:5741617298f89b082d67bdb9d532f04efc6030e3f09c5f758ae60d304f52682f","observation_id":"429b123f-dce8-4f35-b199-24c4e74a02f2","resolution":{"observed_at":"2026-08-11T05:32:49.042485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:49.025193Z","title":"Policy invariance under reward transformations: Theory and application to reward shaping","venue":null,"work_id":"f571e6d8-c42c-4c83-863b-e5883dd3050c","year":1999},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.546786Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:161004020549dff3b69221fd558cf67ed0906864de3f62a08d50d8cdb19572c0","observation_id":"c03cdd45-37ca-480c-8f42-353d81d8aec2","resolution":{"observed_at":"2026-08-11T05:32:49.029426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:49.012806Z","title":"Open X-Embodiment: Robotic learning datasets and RT-X models","venue":null,"work_id":"1f6824b6-9b5a-4f4b-adf8-036a6c4eb476","year":2023},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.550369Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:9e77dead69d76416d80d814e33628d8fe3dc59140543f4d974ecdcc9b4fb4112","observation_id":"79937961-2ee2-47c2-ad8b-c6a635302651","resolution":{"observed_at":"2026-08-11T05:32:49.017158Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:48.554182Z","title":"John Wiley & Sons, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.554182Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:453652f37b885bf06209d6abecf8074cb13363e2a3806c8e5b00cc89f2c5f66a","observation_id":"1eaa496b-71d8-4200-8775-21f1bb96b99e","resolution":{"observed_at":"2026-08-11T05:32:48.554182Z","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":"2026-08-11T05:32:48.992576Z","title":"Universal value function approximators","venue":null,"work_id":"44cf235f-318c-4576-9f4b-d91934139efb","year":2015},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.557670Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:5bdef5068115f03c0248016a4afbdf7812ee4c6d5ae380ef7eefa35c8efeaa41","observation_id":"00dd8569-ffb3-42e3-a161-732f1e7c0f34","resolution":{"observed_at":"2026-08-11T05:32:48.996869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:48.561306Z","title":"Robo-Dopamine: General process reward modeling for high-precision robotic manipulation.arXiv preprint arXiv:2512.23703, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.561306Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:3a95e253e299b3f2e6e1db1bd1a2e508596c34f9101d491a9e43d20d255a3186","observation_id":"28b13ea7-eef2-4ee2-857f-41579df08142","resolution":{"observed_at":"2026-08-11T05:32:48.561306Z","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":"2026-08-11T05:32:48.979127Z","title":"InternData-A1: Pioneering high-fidelity synthetic data for pre-training generalist policy","venue":null,"work_id":"cdf5625f-d5fa-455d-beb9-3f133763d9dc","year":2026},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.564797Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:0e822c27af743727d0e78444c7741bc290dda5987c5405883656510fde0461ea","observation_id":"351c74ec-0a12-41bf-af5b-3d3551480249","resolution":{"observed_at":"2026-08-11T05:32:48.983520Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:48.967239Z","title":"Steering your diffusion policy with latent space reinforcement learning","venue":null,"work_id":"603f195e-9dbf-4dc1-8bf7-ab8bb0d9bf11","year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.568288Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:4b8f1b28a1069d182729f9be0aa9463f7d921c86d073b5af0f0b4d3de8e04961","observation_id":"a5fcf16e-2549-4d75-aa90-c4fffd07e0dd","resolution":{"observed_at":"2026-08-11T05:32:48.971221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.13877","last_updated":"2025-05-27T01:46:53Z","snapshot_observed_at":"2026-08-15T09:21:12.808847Z","submitted_at":"2024-12-18T14:17:16Z","title":"RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.13877","snapshot_observed_at":"2026-08-11T05:32:48.572467Z","title":"RoboMIND: Benchmark on multi-embodiment intelligence normative data for robot manipulation.arXiv preprint arXiv:2412.13877, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.572467Z"},"links":{"cited_paper":"/paper/2412.13877","citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:15d9c46aee2fb224c5871c7e53fed66d782c8b8af4b90648e50c41f81e94ba7b","observation_id":"2e79d696-80aa-40b4-895c-54c0156463e8","resolution":{"observed_at":"2026-08-11T05:32:48.572467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.17441","last_updated":"2026-04-13T12:31:35Z","snapshot_observed_at":"2026-08-14T08:08:04.254754Z","submitted_at":"2025-11-21T17:39:22Z","title":"RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.17441","snapshot_observed_at":"2026-08-11T05:32:48.576131Z","title":"RoboCOIN: An open-sourced bimanual robotic data collection for integrated manipulation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.576131Z"},"links":{"cited_paper":"/paper/2511.17441","citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:66e326db7c440c0b5589431a100ddb8915e0de590ab75d14a270aac1623a197d","observation_id":"0c7a8e4e-0052-43df-9882-be2c793ad717","resolution":{"observed_at":"2026-08-11T05:32:48.576131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.22027","last_updated":"2026-06-24T05:16:35Z","snapshot_observed_at":"2026-07-06T23:56:54.959593Z","submitted_at":"2026-06-20T13:03:21Z","title":"RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation","version":2},"cited_work":{"arxiv_id":"2606.22027","doi":null,"metadata_source":"pith","pith_arxiv_id":"2606.22027","snapshot_observed_at":"2026-08-11T05:32:48.641034Z","title":"RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation","venue":"cs.RO","work_id":"b4836dc1-d061-47ca-ac24-4429876d4fd1","year":2026},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.580065Z"},"links":{"cited_paper":"/paper/2606.22027","citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:955cd9982d238523a994b6f1a1662eca272535db0b351aed06440ae1674b326f","observation_id":"3522ce36-9afb-4e4e-93c4-af104b06265a","resolution":{"observed_at":"2026-08-11T05:32:48.647549Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:48.955885Z","title":null,"venue":null,"work_id":"f4d81359-0b3b-4207-b71d-67f171c553f1","year":2019},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.583960Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:c611c701f016ddb6a21b6c11a837b493c5915ccfc2bf67ade4c3e1c254784835","observation_id":"2bce8115-83ad-4522-93cf-d1bc173ff88f","resolution":{"observed_at":"2026-08-11T05:32:48.959879Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:48.943101Z","title":"ReWiND: Language-guided rewards teach robot policies without new demonstrations","venue":null,"work_id":"ef9047c6-f51c-4de8-9a36-84daa8a377dc","year":2025},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.587977Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:51df5418c4b90c36f767e292dc2fe6f9ddbd1c2aeb89470db56fd6c561e28823","observation_id":"8afe2dda-66af-4c8e-8901-f071bac1b9b5","resolution":{"observed_at":"2026-08-11T05:32:48.947428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+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":"2026-08-11T05:32:48.931187Z","title":"A generalist pair-wise progress critic model for vision-language-action robots","venue":null,"work_id":"730f8403-9135-45e3-930e-a4926c3e57c3","year":2026},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.591813Z"},"links":{"citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:4d593602b34119e7c86b96d3d45df2d0011305e478dc7a921fd283562aa91e6d","observation_id":"a9204c97-86ea-404b-927b-afec7cd48479","resolution":{"observed_at":"2026-08-11T05:32:48.934880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2510.10274","last_updated":"2025-10-11T16:20:17Z","snapshot_observed_at":"2026-08-18T08:46:36.907284Z","submitted_at":"2025-10-11T16:20:17Z","title":"X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.10274","snapshot_observed_at":"2026-08-11T05:32:48.595901Z","title":"Put the two pieces of bread in the basket","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T05:32:48.595901Z"},"links":{"cited_paper":"/paper/2510.10274","citing_paper":"/paper/2608.09853"},"observation_digest":"sha256:1853ee87d3387a1269897cb6c34e41ca2020212247b437bb6b5d980be4882243","observation_id":"a66f0281-1e28-43ff-b182-15ed73fbc7d5","resolution":{"observed_at":"2026-08-11T05:32:48.595901Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.09853","last_updated":"2026-08-10T17:09:37Z","latest_version":1,"primary_category":"cs.RO","snapshot_observed_at":"2026-08-16T12:14:37.854568Z","submitted_at":"2026-08-10T17:09:37Z","title":"RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance"},"reference_resolution":{"displayed":35,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":1,"verified_fuzzy":18},"total_outbound_references":35},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2608.09853."}