{"as_of":"2026-08-20T19:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:07e8604ce33b03506fe141e12a3125921faa89e27e7fdf20f258aa9f22e1deb8","coverage":[{"denominator":86,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":86,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T23:43:25.912505Z","state":"measured"},{"denominator":86,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":86,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.15275/citation-record","integrity":"/paper/2607.15275/integrity","json":"/paper/2607.15275/citation-record.json","paper":"/paper/2607.15275"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2204.14198","last_updated":"2022-11-15T23:07:37Z","snapshot_observed_at":"2026-08-17T03:00:38.806206Z","submitted_at":"2022-04-29T16:29:01Z","title":"Flamingo: a Visual Language Model for Few-Shot Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.14198","snapshot_observed_at":"2026-08-01T23:43:15.852168Z","title":"Flamingo: a visual language model for few-shot learning.arXiv preprint arXiv: 2204.14198, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:15.852168Z"},"links":{"cited_paper":"/paper/2204.14198","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:410393d39758e9ef286dae67f905ed868e89cd0134f250797596241d26d5393f","observation_id":"671f71f6-7a6d-4ad5-8fe8-cd32eb40b0d2","resolution":{"observed_at":"2026-08-01T23:43:15.852168Z","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":"2026-08-01T23:43:15.916115Z","title":"Evolve-vla: Test-time training from environment feedback for vision-language-action models.arXiv preprint arXiv: 2512.14666, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:15.916115Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:e8f31171d597ed3fb25ba43d0af5c8abb71e0305e9454284e9cfd39a154347fd","observation_id":"87d0fd67-00cc-4ea4-b327-7e81e02c9d8a","resolution":{"observed_at":"2026-08-01T23:43:15.916115Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.00663","last_updated":"2024-12-31T22:32:03Z","snapshot_observed_at":"2026-08-16T10:45:05.594811Z","submitted_at":"2024-12-31T22:32:03Z","title":"Titans: Learning to Memorize at Test Time","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.00663","snapshot_observed_at":"2026-08-01T23:43:16.071652Z","title":"Titans: Learning to memorize at test time.arXiv preprint arXiv: 2501.00663, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:16.071652Z"},"links":{"cited_paper":"/paper/2501.00663","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:5399ac69d549d29a65cfd415638bce25eb724d48486a31cc8f86a78439615099","observation_id":"87295c2d-eee8-41da-afb4-1ff0acecf587","resolution":{"observed_at":"2026-08-01T23:43:16.071652Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.13173","last_updated":"2025-04-17T17:59:33Z","snapshot_observed_at":"2026-08-20T09:21:10.924293Z","submitted_at":"2025-04-17T17:59:33Z","title":"It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.13173","snapshot_observed_at":"2026-08-01T23:43:16.177997Z","title":"It’s all connected: A journey through test-time memorization, attentional bias, retention, and online optimization.arXiv preprint arXiv: 2504.13173, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:16.177997Z"},"links":{"cited_paper":"/paper/2504.13173","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:f7597b4bc0c4aa8a3f94b7a991ffa6d2543b0d4ffae3f2340c5c8ac8d54f5227","observation_id":"cae708cc-cd1d-47a8-ad70-5bfbc935b8bf","resolution":{"observed_at":"2026-08-01T23:43:16.177997Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.24164","last_updated":"2026-01-08T17:01:05Z","snapshot_observed_at":"2026-08-16T17:53:54.636855Z","submitted_at":"2024-10-31T17:22:30Z","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.24164","snapshot_observed_at":"2026-08-01T23:43:16.294135Z","title":"org/abs/2410.24164, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:16.294135Z"},"links":{"cited_paper":"/paper/2410.24164","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:7fcb0b5121b7a09d20acfcb640bc5fceec49d12f8ce5c0cd1b2515e8645f466e","observation_id":"ec4c9175-5ba2-4eaa-bd6b-1b5e11f3166d","resolution":{"observed_at":"2026-08-01T23:43:16.294135Z","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":"2026-08-01T23:43:16.399292Z","title":"Lee, Maria Bauzá Villalonga, Todor Davchev, Yuxiang Zhou, Agrim Gupta, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:16.399292Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:505735077dad1ce60cf254974a32db8aa1bd3d57dd4be8f8fb099a7507b23ca3","observation_id":"1dd3e937-17e2-4767-9b0a-44174ff6f27f","resolution":{"observed_at":"2026-08-01T23:43:16.399292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.06817","last_updated":"2023-08-11T17:45:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-12-13T18:55:15Z","title":"RT-1: Robotics Transformer for Real-World Control at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.06817","snapshot_observed_at":"2026-08-01T23:43:16.521454Z","title":"Irpan, Tomas Jackson, Sally Jesmonth, Nikhil J","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:16.521454Z"},"links":{"cited_paper":"/paper/2212.06817","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:90ec739ffb4c73420ca30ebc503c4524e7dcf11b5f349275caf60f689ec2ace3","observation_id":"43b50ebd-8ae5-4338-b6e0-70e44bd1e67f","resolution":{"observed_at":"2026-08-01T23:43:16.521454Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.15818","last_updated":"2023-07-28T21:18:02Z","snapshot_observed_at":"2026-08-02T16:17:50.621617Z","submitted_at":"2023-07-28T21:18:02Z","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.15818","snapshot_observed_at":"2026-08-01T23:43:16.588442Z","title":"Choromanski, Tianli Ding, Danny Driess, Kumar Avinava Dubey, Chelsea Finn, Peter R","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:16.588442Z"},"links":{"cited_paper":"/paper/2307.15818","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:3d4db50091a01265ea6859f21d91394b14b16a400040a3e403c56a5b2fe0c330","observation_id":"5170cf2e-5661-47c1-8aa0-baa5e3cdd8ab","resolution":{"observed_at":"2026-08-01T23:43:16.588442Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.14165","last_updated":"2020-07-22T19:47:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-05-28T17:29:03Z","title":"Language Models are Few-Shot Learners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.14165","snapshot_observed_at":"2026-08-01T23:43:16.661783Z","title":null,"venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:16.661783Z"},"links":{"cited_paper":"/paper/2005.14165","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:76b0df913de3d70e185db7a251ca5c6f3afb5c00098abb6d68eb2e6c3456d353","observation_id":"1ce2541c-c102-420a-9336-fdad6ebe6408","resolution":{"observed_at":"2026-08-01T23:43:16.661783Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.01392","last_updated":"2024-12-10T01:32:23Z","snapshot_observed_at":"2026-08-16T13:38:04.174848Z","submitted_at":"2024-07-01T15:43:25Z","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.01392","snapshot_observed_at":"2026-08-01T23:43:16.885697Z","title":"Diffusion forcing: Next-token prediction meets full-sequence diffusion.arXiv preprint arXiv: 2407.01392,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:16.885697Z"},"links":{"cited_paper":"/paper/2407.01392","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:bfe9791b2eedbfd0f656901a396257f77daedd0e16a66252960c308eb984777a","observation_id":"ba99f4cc-faef-4fc4-a770-985fb8768e4c","resolution":{"observed_at":"2026-08-01T23:43:16.885697Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.26645","last_updated":"2026-03-03T12:58:09Z","snapshot_observed_at":"2026-08-08T05:03:09.924311Z","submitted_at":"2025-09-30T17:59:51Z","title":"TTT3R: 3D Reconstruction as Test-Time Training","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.26645","snapshot_observed_at":"2026-08-01T23:43:17.014614Z","title":"Ttt3r: 3d reconstruction as test-time training, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:17.014614Z"},"links":{"cited_paper":"/paper/2509.26645","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:a9bf28352e9457a71ef6f108cc3fbd822223e4a78c4c15d9038f736fe7e2f6bd","observation_id":"ffd473b7-1a65-4935-8b6f-613148047e70","resolution":{"observed_at":"2026-08-01T23:43:17.014614Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2603.04639","last_updated":"2026-05-26T02:02:04Z","snapshot_observed_at":"2026-08-15T17:59:09.916273Z","submitted_at":"2026-03-04T21:59:32Z","title":"RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.04639","snapshot_observed_at":"2026-08-01T23:43:17.148290Z","title":"Robomme: Benchmarking and understanding memory for robotic generalist policies","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:17.148290Z"},"links":{"cited_paper":"/paper/2603.04639","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:db1bffd3f3459f5e8a52ddca8cd81cb57526d87a98803e6ec393e4a9aec19506","observation_id":"f24fac04-fb31-4f2e-b5e9-3f8aa9c44a6d","resolution":{"observed_at":"2026-08-01T23:43:17.148290Z","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":"2026-08-01T23:43:17.227957Z","title":"One-minute video generation with test-time training","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:17.227957Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:746d0a98cdea148ba720cbdfab0f6bc5903daf1bb58494866c02807b9ce866f5","observation_id":"86ba3f13-1d1f-4d36-8783-7c0627f4972e","resolution":{"observed_at":"2026-08-01T23:43:17.227957Z","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":"2026-08-01T23:43:17.313447Z","title":"Vision transformers need registers","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:17.313447Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:92f1cd22f6e29a4401eeb2d5d42565808d677b24d4f28f818376c10c2ab95925","observation_id":"6a7de362-72df-47b0-b697-2286cf9eb70d","resolution":{"observed_at":"2026-08-01T23:43:17.313447Z","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":"2026-08-01T23:43:17.500771Z","title":"Causal confusion in imitation learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:17.500771Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:cc5e5828f983c582fe8d7775b89ec7796b1576a43ca9973bdc798473d1dfb8be","observation_id":"75aabaec-bae6-446b-9c3f-6b52c9fa259b","resolution":{"observed_at":"2026-08-01T23:43:17.500771Z","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":"2026-08-01T23:43:17.554338Z","title":"Longrope: Extending LLM context window beyond 2 million tokens","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:17.554338Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:ef52cedd8bf0bf31eb51dc31d10a9630221b654a4c1f55de7899a78ba4c95a68","observation_id":"64a89432-6cef-4f8d-8c0f-a90073924f07","resolution":{"observed_at":"2026-08-01T23:43:17.554338Z","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":"2026-08-01T23:43:17.621297Z","title":"Knowledge insulating vision-language-action models: Train fast, run fast, generalize better.Advances in Neural Information Processing Systems, 38:102867–102888,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:17.621297Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:aca778fa19cbd0849ba29b5372964447dfa1c8f048220300af229b32041d8df9","observation_id":"0e767ef8-3bf3-4dfa-ad51-c4b56f495fe0","resolution":{"observed_at":"2026-08-01T23:43:17.621297Z","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":"2026-08-01T23:43:17.701330Z","title":"One-shot imitation learning.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:17.701330Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:c7b8839c728f1b21a59ba0c7a78f5cdb4671a05b592aec423cd7b2ce9dd5513e","observation_id":"45908b95-8882-4a25-8430-4e8aa0feedaf","resolution":{"observed_at":"2026-08-01T23:43:17.701330Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.02881","last_updated":"2026-05-08T04:21:51Z","snapshot_observed_at":"2026-08-16T22:33:00.868689Z","submitted_at":"2026-05-04T17:51:21Z","title":"MolmoAct2: Action Reasoning Models for Real-world Deployment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.02881","snapshot_observed_at":"2026-08-01T23:43:17.812765Z","title":"Molmoact2: Action reasoning models for real-world deployment, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:17.812765Z"},"links":{"cited_paper":"/paper/2605.02881","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:97f88140d6dde8351043b19dad3c5e7f5312e315744c35189450f501c81fcc1c","observation_id":"3ce97011-8962-433a-b591-c49bd1ccf417","resolution":{"observed_at":"2026-08-01T23:43:17.812765Z","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":"2026-08-01T23:43:17.935850Z","title":"In-place test-time training","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:17.935850Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:6c9a4086a744470e6c26491a50d1c36f58b1792d4a113035d3a357536ad2c42e","observation_id":"df012763-9c9e-4d9e-b527-d19ad5d2d84b","resolution":{"observed_at":"2026-08-01T23:43:17.935850Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.03400","last_updated":"2017-07-18T16:45:29Z","snapshot_observed_at":"2026-08-15T14:31:49.004808Z","submitted_at":"2017-03-09T18:58:03Z","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.03400","snapshot_observed_at":"2026-08-01T23:43:18.143170Z","title":"Model-agnostic meta-learning for fast adaptation of deep networks.arXiv preprint arXiv: 1703.03400, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:18.143170Z"},"links":{"cited_paper":"/paper/1703.03400","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:ac274d27d806360e4be4cbe90e5ebd69aa0dff41fda59942adf9d07c8dedaba7","observation_id":"21ae6f51-285f-4fbf-b66d-ad128b44c05c","resolution":{"observed_at":"2026-08-01T23:43:18.143170Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.15980","last_updated":"2024-09-27T20:10:08Z","snapshot_observed_at":"2026-08-16T13:23:07.878277Z","submitted_at":"2024-08-28T17:50:19Z","title":"In-Context Imitation Learning via Next-Token Prediction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.15980","snapshot_observed_at":"2026-08-01T23:43:18.315751Z","title":"In-context imitation learning via next-token prediction.arXiv preprint arXiv:2408.15980, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:18.315751Z"},"links":{"cited_paper":"/paper/2408.15980","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:f62e8b7df4eb7a7e9edaedc6c6b3500efd59cb4a723d55a40946839262f985d3","observation_id":"7c56c801-f669-475d-bbf6-15a1ece47b77","resolution":{"observed_at":"2026-08-01T23:43:18.315751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.18933","last_updated":"2026-08-03T20:19:45Z","snapshot_observed_at":"2026-08-16T00:57:45.111946Z","submitted_at":"2026-04-21T00:14:50Z","title":"Gated Memory Policy: In-Context Memorization and Adaptation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.18933","snapshot_observed_at":"2026-08-01T23:43:18.434497Z","title":"Gated memory policy.arXiv preprint arXiv: 2604.18933, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:18.434497Z"},"links":{"cited_paper":"/paper/2604.18933","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:899f8ebffdc970edd093c2d264c65935a74a6b977945881dc3aa93d7aae87f16","observation_id":"ab592c32-4aee-464e-adb5-8488050eb4c8","resolution":{"observed_at":"2026-08-01T23:43:18.434497Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.01643","last_updated":"2026-04-20T11:19:37Z","snapshot_observed_at":"2026-07-06T22:37:26.652349Z","submitted_at":"2025-12-01T13:14:48Z","title":"ViT$^3$: Unlocking Test-Time Training in Vision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2512.01643","snapshot_observed_at":"2026-08-01T23:43:18.499311Z","title":"Vit3: Unlocking test-time training in vision.arXiv preprint arXiv: 2512.01643, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:18.499311Z"},"links":{"cited_paper":"/paper/2512.01643","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:9264915c7755cf53cbe63043652e00659c5dbdebb4c6da321e9181a51b3a1029","observation_id":"bbdbafdb-7351-4a15-b427-df3b4c3af5c5","resolution":{"observed_at":"2026-08-01T23:43:18.499311Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.08415","last_updated":"2023-06-06T01:53:32Z","snapshot_observed_at":"2026-08-13T19:48:28.322536Z","submitted_at":"2016-06-27T19:20:40Z","title":"Gaussian Error Linear Units (GELUs)","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.08415","snapshot_observed_at":"2026-08-01T23:43:18.605850Z","title":"Gaussian error linear units (gelus).arXiv preprint arXiv: 1606.08415,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:18.605850Z"},"links":{"cited_paper":"/paper/1606.08415","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:a85c69decd8723203d9faff6edf87ad1cbb939d6199d14fc3db81b1a47cd342a","observation_id":"32f5db61-5831-4dd5-b454-5197ca70c90f","resolution":{"observed_at":"2026-08-01T23:43:18.605850Z","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":"2026-08-01T23:43:18.660931Z","title":"Long short-term memory.Neural Comput., 9(8):1735–1780, November 1997","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:18.660931Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:f121ee54ec60c2069bc8c62e473767ff1d9c658d8569569b98eea8bfa60bd51c","observation_id":"246a5cf8-fc7f-4118-8de1-dc5f914c3587","resolution":{"observed_at":"2026-08-01T23:43:18.660931Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.06654","last_updated":"2024-08-06T21:48:58Z","snapshot_observed_at":"2026-08-18T14:33:16.365411Z","submitted_at":"2024-04-09T23:41:27Z","title":"RULER: What's the Real Context Size of Your Long-Context Language Models?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.06654","snapshot_observed_at":"2026-08-01T23:43:18.771836Z","title":"Ruler: What’s the real context size of your long-context language models?arXiv preprint arXiv: 2404.06654, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:18.771836Z"},"links":{"cited_paper":"/paper/2404.06654","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:48e5a7ae652a1b1a4e9427f0a3263a58185d306477fbe4d2e070ab7e1f188f9e","observation_id":"cb44f0c5-655b-44cb-bc94-7ab8f1a0fd00","resolution":{"observed_at":"2026-08-01T23:43:18.771836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.06395","last_updated":"2024-06-03T08:54:38Z","snapshot_observed_at":"2026-08-12T13:10:06.472493Z","submitted_at":"2024-04-09T15:36:50Z","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.06395","snapshot_observed_at":"2026-08-01T23:43:18.895438Z","title":"Minicpm: Unveiling the potential of small language models with scalable training strategies.arXiv preprint arXiv: 2404.06395, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:18.895438Z"},"links":{"cited_paper":"/paper/2404.06395","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:a0f2c2574cd369eb84396afd7f799ae95e1d519fe4ecb53150f4b74f7cc7f3de","observation_id":"f17fabd4-e606-4f7e-a0f6-2d0dab8c9170","resolution":{"observed_at":"2026-08-01T23:43:18.895438Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.16054","last_updated":"2025-04-22T17:31:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-04-22T17:31:29Z","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.16054","snapshot_observed_at":"2026-08-01T23:43:18.982220Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:18.982220Z"},"links":{"cited_paper":"/paper/2504.16054","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:705e494203073a2105855879d6cd772788877256e4dcbf86f7584930abd4cbae","observation_id":"2f34aee2-6ed3-479c-8b72-6d7c3d813a3a","resolution":{"observed_at":"2026-08-01T23:43:18.982220Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.03206","last_updated":"2021-06-23T00:25:31Z","snapshot_observed_at":"2026-08-16T18:41:11.947734Z","submitted_at":"2021-03-04T18:20:50Z","title":"Perceiver: General Perception with Iterative Attention","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.03206","snapshot_observed_at":"2026-08-01T23:43:19.069877Z","title":"Perceiver: General perception with iterative attention.arXiv preprint arXiv: 2103.03206, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:19.069877Z"},"links":{"cited_paper":"/paper/2103.03206","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:c1ccaf1dec8130db6cb818722bd23f3dc7f2c845860e52ecc76159d9cf2d8bcd","observation_id":"8dc905b8-b698-4345-b55c-684e686e9301","resolution":{"observed_at":"2026-08-01T23:43:19.069877Z","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":"2026-08-01T23:43:19.171172Z","title":"Contextvla: Vision-language-action model with amortized multi-frame context.arXiv preprint arXiv: 2510.04246,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:19.171172Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:a0e4de27a7d0539231bd83ce25fc8ab37c0dac0224ec01c67061cfc75622ab36","observation_id":"f797f881-d5c3-487b-a9b2-cb05b3d30b68","resolution":{"observed_at":"2026-08-01T23:43:19.171172Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.03094","last_updated":"2023-05-28T07:32:38Z","snapshot_observed_at":"2026-08-16T16:26:20.587132Z","submitted_at":"2022-10-06T17:50:11Z","title":"VIMA: General Robot Manipulation with Multimodal Prompts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.03094","snapshot_observed_at":"2026-08-01T23:43:19.452926Z","title":"Vima: General robot manipulation with multimodal prompts.arXiv preprint arXiv: 2210.03094, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:19.452926Z"},"links":{"cited_paper":"/paper/2210.03094","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:f4253bc5a0fc84d19502785890670b45a58a0f84544a55ad2b319cfbdcddb08f","observation_id":"96156111-14c3-4546-9035-d4717af3cdce","resolution":{"observed_at":"2026-08-01T23:43:19.452926Z","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":"2026-08-01T23:43:19.568390Z","title":"Muon: An optimizer for hidden layers in neural networks, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:19.568390Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:35748bfbe1803731d2ac839d2a2d99d52f42d3d72a208b3547b3da7f4e291777","observation_id":"4c22e418-8a6e-4445-bbff-1ffa2a8be276","resolution":{"observed_at":"2026-08-01T23:43:19.568390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-08-13T17:41:53.092611Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-01T23:43:19.641902Z","title":"Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:19.641902Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:9d94925af883fca7760f1c5a38d63f4ab72713a7aa849d92bd4729921150387a","observation_id":"c3431f6d-aad9-47d3-a82e-05a67bb29b1f","resolution":{"observed_at":"2026-08-01T23:43:19.641902Z","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":"2026-08-01T23:43:19.751404Z","title":"Lattice: Learning to efficiently compress the memory.arXiv preprint arXiv: 2504.05646, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:19.751404Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:6c45082bbc6fcc3169e1fb0a5e6d8b9d8d14828791e0c8e2c274dc4f8b3ad70a","observation_id":"1063c27c-5bae-46b2-aa5a-f8dc9d8d6bf5","resolution":{"observed_at":"2026-08-01T23:43:19.751404Z","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":"2026-08-01T23:43:19.849746Z","title":"OpenVLA: An open-source vision-language- action model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:19.849746Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:663828272062a076ffedfba651a79ac648ef829f39ef439469d7f93b9b5fde2e","observation_id":"401bba7f-0bd1-4c22-971f-075677c5e615","resolution":{"observed_at":"2026-08-01T23:43:19.849746Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.16163","last_updated":"2026-01-22T18:09:30Z","snapshot_observed_at":"2026-08-20T07:20:19.015572Z","submitted_at":"2026-01-22T18:09:30Z","title":"Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.16163","snapshot_observed_at":"2026-08-01T23:43:19.940511Z","title":"Cosmos policy: Fine-tuning video models for visuomotor control and planning.arXiv preprint arXiv: 2601.16163, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:19.940511Z"},"links":{"cited_paper":"/paper/2601.16163","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:f382a49dbfcc6be3b35fe3250a4296b023f331aaa393fd3320338290699ae255","observation_id":"94557673-8d31-41ed-ad4e-7e5f89972af1","resolution":{"observed_at":"2026-08-01T23:43:19.940511Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.04034","last_updated":"2021-07-08T17:59:59Z","snapshot_observed_at":"2026-08-18T15:06:14.253218Z","submitted_at":"2021-07-08T17:59:59Z","title":"RMA: Rapid Motor Adaptation for Legged Robots","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.04034","snapshot_observed_at":"2026-08-01T23:43:20.059531Z","title":"Rma: Rapid motor adaptation for legged robots.arXiv preprint arXiv:2107.04034, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:20.059531Z"},"links":{"cited_paper":"/paper/2107.04034","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:e6dfba78b90141ba5563a1adfecd5322fcc573ef5d46c911fc32d143bdd692c5","observation_id":"1c405f48-a7c0-4971-926a-952c256c786e","resolution":{"observed_at":"2026-08-01T23:43:20.059531Z","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":"2026-08-01T23:43:20.145535Z","title":"In-context reinforcement learning with algorithm distillation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:20.145535Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:b5f1a8e87d3377fc0719e60acc523834f790aa533cac4ccca86314edb33800f2","observation_id":"ac733d51-5719-42ca-865a-df219808172f","resolution":{"observed_at":"2026-08-01T23:43:20.145535Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.21998","last_updated":"2026-03-22T15:37:40Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-01-29T17:07:43Z","title":"Causal World Modeling for Robot Control","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.21998","snapshot_observed_at":"2026-08-01T23:43:20.476805Z","title":"Causal world modeling for robot control.arXiv preprint arXiv: 2601.21998, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:20.476805Z"},"links":{"cited_paper":"/paper/2601.21998","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:3331acedc213e960095440d746cfb46befca47500fa1addf2f8bf1200186e3ba","observation_id":"ab1bf8e4-3a6a-463b-9724-9859ef227146","resolution":{"observed_at":"2026-08-01T23:43:20.476805Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.00200","last_updated":"2025-04-24T20:02:43Z","snapshot_observed_at":"2026-08-14T06:14:38.487820Z","submitted_at":"2025-02-28T21:38:17Z","title":"Unified Video Action Model","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.00200","snapshot_observed_at":"2026-08-01T23:43:20.625021Z","title":"Unified video action model.arXiv preprint arXiv: 2503.00200, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:20.625021Z"},"links":{"cited_paper":"/paper/2503.00200","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:a91f769191cca35faa66d3938b7b50e3dba1d04d8b689c44117a83b016a94d04","observation_id":"f16f371a-f3fe-45b3-aa73-c8c688eee140","resolution":{"observed_at":"2026-08-01T23:43:20.625021Z","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":"2026-08-01T23:43:20.753194Z","title":"Tnt: Improving chunkwise training for test-time memorization.arXiv preprint arXiv:2511.07343, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:20.753194Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:226af4492c1e91a38eae8f1e3e71ad6e64f13dba0f54c3561e67a694dac9be3a","observation_id":"093fd230-a580-4b3e-81ae-e6d38fd91f8d","resolution":{"observed_at":"2026-08-01T23:43:20.753194Z","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":"2026-08-01T23:43:20.853254Z","title":"Parallelizing non-linear sequential models over the sequence length","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:20.853254Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:83554c46ca7864d6bf99e6b47a71e5d6186277920d75216d4b6cd8956aec3f9a","observation_id":"12caec7c-83d3-4426-b2aa-63680cdd518a","resolution":{"observed_at":"2026-08-01T23:43:20.853254Z","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":"2026-08-01T23:43:20.961154Z","title":"Onetwovla: A unified vision-language-action model with adaptive reasoning.arXiv preprint arXiv:2505.11917, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:20.961154Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:c81472f9cd86e87527caa533df687afb7b240491e9a52da4cd063f4e51633de2","observation_id":"7c7c90f2-7598-44a3-b5a1-9e85496a7252","resolution":{"observed_at":"2026-08-01T23:43:20.961154Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.06748","last_updated":"2026-04-07T03:39:20Z","snapshot_observed_at":"2026-08-16T10:45:52.781857Z","submitted_at":"2026-01-11T01:51:30Z","title":"On-the-Fly VLA Adaptation via Test-Time Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.06748","snapshot_observed_at":"2026-08-01T23:43:21.089034Z","title":"On-the-fly vla adaptation via test-time reinforcement learning.arXiv preprint arXiv:2601.06748, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:21.089034Z"},"links":{"cited_paper":"/paper/2601.06748","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:ed77deb7a195b28e3621a965b29002623e24055632f40177c116bf41f8165fb4","observation_id":"82486657-606f-4bfe-ba84-a0eeefb1a8fa","resolution":{"observed_at":"2026-08-01T23:43:21.089034Z","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":"2026-08-01T23:43:21.243324Z","title":"Lost in the middle: How language models use long contexts.Transactions of the association for computational linguistics, 12:157–173, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:21.243324Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:faf641ef816208dabd0c8a9945dce42cfb275c3841564e6e8ee8f03d35eb3ba2","observation_id":"52691eba-b89c-48b3-84db-2ecbc6d25aa4","resolution":{"observed_at":"2026-08-01T23:43:21.243324Z","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":"2026-08-01T23:43:21.388466Z","title":"RDT-1B:a diffusionfoundationmodelforbimanual manipulation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:21.388466Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:8a6f3b2046bb4442b3a6b9887d9c73c52a81f26100ef1bcf1aab0ce7cfec67c1","observation_id":"b5d65760-c1b0-4697-b8f9-96d99ec09698","resolution":{"observed_at":"2026-08-01T23:43:21.388466Z","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":"2026-08-01T23:43:21.500150Z","title":"Loshchilov and F","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:21.500150Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:b48900252deb1e7d649ab45eff65369876899e2994fe30bd210afc1a43d214d0","observation_id":"540f2c13-b83f-4193-b1f6-702aacb3ce6f","resolution":{"observed_at":"2026-08-01T23:43:21.500150Z","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":"2026-08-01T23:43:21.701526Z","title":"Savarese, Yuke Zhu, and Roberto Mart’in-Mart’in","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:21.701526Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:cc673b7f17449a37d757926101d176a4277431a4ac805f9a7427444c63ba4602","observation_id":"8a09a967-5b70-4d1c-bbb3-dad3b3669094","resolution":{"observed_at":"2026-08-01T23:43:21.701526Z","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":"2026-08-01T23:43:21.860647Z","title":"Bpp: Long-context robot imitation learning by focusing on key history frames.arXiv preprint arXiv: 2602.15010, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:21.860647Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:235a79183f889af9d585b8a0773f24f70fdc55d2f58bf8cb2fe795bcb57ac290","observation_id":"d4504d80-b22a-4cbf-b028-bc209c9a4f8d","resolution":{"observed_at":"2026-08-01T23:43:21.860647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.14734","last_updated":"2025-03-27T02:52:43Z","snapshot_observed_at":"2026-08-02T04:15:31.100670Z","submitted_at":"2025-03-18T21:06:21Z","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.14734","snapshot_observed_at":"2026-08-01T23:43:22.041546Z","title":"Gr00t n1: An open foundation model for generalist humanoid robots.arXiv preprint arXiv: 2503.14734, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:22.041546Z"},"links":{"cited_paper":"/paper/2503.14734","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:d713023bd22132548ff663fe010e2a37c34ce683b6fe3f176be175b02855d0bd","observation_id":"ccfa2e99-5d96-4274-bc32-8cd3b2d3c3ab","resolution":{"observed_at":"2026-08-01T23:43:22.041546Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09748","last_updated":"2023-03-02T09:06:55Z","snapshot_observed_at":"2026-08-17T19:22:44.145403Z","submitted_at":"2022-12-19T18:59:58Z","title":"Scalable Diffusion Models with Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09748","snapshot_observed_at":"2026-08-01T23:43:22.166559Z","title":"Scalable diffusion models with transformers.arXiv preprint arXiv: 2212.09748, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:22.166559Z"},"links":{"cited_paper":"/paper/2212.09748","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:a1368f8115d13083786d33d638db4583e3f9bbf1eb5df88bce576ce9c148f0ce","observation_id":"5801f085-fe96-4c43-847b-ef08b6073d5f","resolution":{"observed_at":"2026-08-01T23:43:22.166559Z","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":"2026-08-01T23:43:22.282663Z","title":"Yarn: Efficient context window extension of large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:22.282663Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:c337189a5d6b8f53343877ee330d073695b2ba7d6594f4e1fed672180801f670","observation_id":"d8959a2c-822e-4bc9-8aff-15794a67d0e3","resolution":{"observed_at":"2026-08-01T23:43:22.282663Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.09747","last_updated":"2025-01-16T18:57:04Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-16T18:57:04Z","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.09747","snapshot_observed_at":"2026-08-01T23:43:22.434898Z","title":"Fast: Efficient action tokenization for vision-language-action models, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:22.434898Z"},"links":{"cited_paper":"/paper/2501.09747","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:3441913c9ea4b38949ad5ace234aab0d32a1f168cbf3be401b6ba092bb76d27b","observation_id":"a70971ab-1cc4-4288-9f12-9d103f668b30","resolution":{"observed_at":"2026-08-01T23:43:22.434898Z","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":"2026-08-01T23:43:22.579096Z","title":"In-hand object rotation via rapid motor adaptation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:22.579096Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:b4909daadc146921c63559f72d0f2d85356e0e892a76536d094fb783d2784544","observation_id":"0d5f071e-d6cb-4c66-8427-19b06453fef4","resolution":{"observed_at":"2026-08-01T23:43:22.579096Z","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":"2026-08-01T23:43:22.735442Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:22.735442Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:802eaca6edd57b2c3cb9831844a323aa0424fefc89226a139801b9320043e706","observation_id":"891e13c8-ca28-45ac-b20e-a2c8ed408713","resolution":{"observed_at":"2026-08-01T23:43:22.735442Z","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":"2026-08-01T23:43:22.864898Z","title":"A reduction of imitation learning and structured prediction to no-regret online learning","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:22.864898Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:fb411c2bfdf79d1638272e974f89fe645c9b1b017136a840298a4a5d6aad4ba6","observation_id":"b1020e68-589a-410f-89ae-082605916bfe","resolution":{"observed_at":"2026-08-01T23:43:22.864898Z","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":"2026-08-01T23:43:22.987980Z","title":"Linear transformers are secretly fast weight programmers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:22.987980Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:d62bf523e9d4817db68c9b15c565e54008d5eb8435b4606bb612b44bbdaa6b7d","observation_id":"fae23fa3-a051-474e-b2df-864b44533411","resolution":{"observed_at":"2026-08-01T23:43:22.987980Z","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":"2026-08-01T23:43:23.154909Z","title":"Eagle: Exploring the design space for multimodal llms with mixture of encoders","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:23.154909Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:5969afae73992efe5af9a8ca473f5778899912d68236cd5eb77ced522c3c2122","observation_id":"64578de8-8e8d-49a0-b2e5-6c9c8ec74eaf","resolution":{"observed_at":"2026-08-01T23:43:23.154909Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.01844","last_updated":"2025-06-02T16:30:19Z","snapshot_observed_at":"2026-08-18T04:25:30.115862Z","submitted_at":"2025-06-02T16:30:19Z","title":"SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.01844","snapshot_observed_at":"2026-08-01T23:43:23.313663Z","title":"Smolvla: A vision-language-action model for affordable and efficient robotics","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:23.313663Z"},"links":{"cited_paper":"/paper/2506.01844","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:85b093d07bbfdef700d70d29c7f2cabea8a52ef071cdfae8459a7df41b67b0a2","observation_id":"38c3137a-f89f-4ebc-972b-08378acbe12b","resolution":{"observed_at":"2026-08-01T23:43:23.313663Z","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":"2026-08-01T23:43:23.447664Z","title":"Memer: Scaling up memory for robot control via experience retrieval.arXiv preprint arXiv: 2510.20328, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:23.447664Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:b34cc39222d212d6ec6c04cc19ef4186d9565ead3411eb7da0b9b45a0f792110","observation_id":"a0d925c1-36b6-47a0-b14e-dda8d3251f56","resolution":{"observed_at":"2026-08-01T23:43:23.447664Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.09864","last_updated":"2023-11-08T13:36:32Z","snapshot_observed_at":"2026-08-17T06:56:20.644738Z","submitted_at":"2021-04-20T09:54:06Z","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.09864","snapshot_observed_at":"2026-08-01T23:43:23.575896Z","title":"Roformer: Enhanced transformer with rotary position embedding.arXiv preprint arXiv: 2104.09864, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:23.575896Z"},"links":{"cited_paper":"/paper/2104.09864","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:b41601f47285f79680a4b700bee0365d255ba621475c23f92be0b1acdc03fa96","observation_id":"9a9b1450-4036-4991-b2bf-e4ff38ff5fb2","resolution":{"observed_at":"2026-08-01T23:43:23.575896Z","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":"2026-08-01T23:43:23.667612Z","title":"Efros, and Moritz Hardt","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:23.667612Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:30709134c6bc648439229caf01653542688eca12856e9e33b32fa7a91c67a971","observation_id":"413bb12a-8ad4-4bdc-ac38-0680d192f275","resolution":{"observed_at":"2026-08-01T23:43:23.667612Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.04620","last_updated":"2025-08-31T18:32:59Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-07-05T16:23:20Z","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.04620","snapshot_observed_at":"2026-08-01T23:43:23.808805Z","title":"Learning to (learn at test time): Rnns with expressive hidden states.arXiv preprint arXiv: 2407.04620, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:23.808805Z"},"links":{"cited_paper":"/paper/2407.04620","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:17d6f9e4df4de3ae058e0c678f8f881a0e3f7688bbb81075b49e13d2b8586fd6","observation_id":"7b605e73-4aa8-472f-8145-f110b76246a0","resolution":{"observed_at":"2026-08-01T23:43:23.808805Z","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":"2026-08-01T23:43:23.953687Z","title":"End-to-end test-time training for long context.arXiv preprint arXiv: 2512.23675, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:23.953687Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:482f2fa800b73844dd9220555b4228da9350c776445c3723d1e6f61d4fc03762","observation_id":"0340e60d-b7e9-4757-852e-1e738abeaee5","resolution":{"observed_at":"2026-08-01T23:43:23.953687Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.07608","last_updated":"2023-01-18T15:39:21Z","snapshot_observed_at":"2026-08-16T16:01:39.145118Z","submitted_at":"2023-01-18T15:39:21Z","title":"Human-Timescale Adaptation in an Open-Ended Task Space","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.07608","snapshot_observed_at":"2026-08-01T23:43:24.092787Z","title":"Human-timescale adaptation in an open-ended task space.arXiv preprint arXiv:2301.07608, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:24.092787Z"},"links":{"cited_paper":"/paper/2301.07608","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:500c4da32ae452aac0b2cd1ad2a52d604bb84d071d82ba0569a4f5bfa61f2bfe","observation_id":"46e329bf-da5f-4283-bab2-3740d621764c","resolution":{"observed_at":"2026-08-01T23:43:24.092787Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.12213","last_updated":"2024-05-26T19:55:26Z","snapshot_observed_at":"2026-08-14T08:22:11.295012Z","submitted_at":"2024-05-20T17:57:01Z","title":"Octo: An Open-Source Generalist Robot Policy","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.12213","snapshot_observed_at":"2026-08-01T23:43:24.217680Z","title":"Sanketi, Quan Vuong, Ted Xiao, Dorsa Sadigh, Chelsea Finn, and Sergey Levine","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:24.217680Z"},"links":{"cited_paper":"/paper/2405.12213","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:1f977dad974fcfce6627c62d172f3cc4680d914443a5e05a8012e256af31537d","observation_id":"8364f1c7-de09-47db-ae52-87245e16f758","resolution":{"observed_at":"2026-08-01T23:43:24.217680Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.09561","last_updated":"2025-05-19T20:37:41Z","snapshot_observed_at":"2026-08-19T14:31:49.212833Z","submitted_at":"2025-05-14T17:00:47Z","title":"Learning Long-Context Diffusion Policies via Past-Token Prediction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.09561","snapshot_observed_at":"2026-08-01T23:43:24.325693Z","title":"Learning long-context diffusion policies via past-token prediction.arXiv preprint arXiv: 2505.09561, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:24.325693Z"},"links":{"cited_paper":"/paper/2505.09561","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:3923fc3f39b6264353bd86feda5c9c500f02367a9c96a796a1e339a34b6e2d25","observation_id":"f9bbfd80-e5c7-45fa-a24c-bb465117d700","resolution":{"observed_at":"2026-08-01T23:43:24.325693Z","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":"2026-08-01T23:43:24.424837Z","title":"Ren, Haohuan Wang, Jiaming Tang, Kyle Stachowicz, Karan Dhabalia, Michael Equi, Quan Vuong, Jost Tobias Springen- berg, Sergey Levine, Chelsea Finn, and Danny Driess","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:24.424837Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:01c793655ae6902adcc18923d3cff8fde65889bc8f9c3a4b567a842d4e3cb157","observation_id":"ead81c8c-1ab1-4049-abb4-9fd29beeb56c","resolution":{"observed_at":"2026-08-01T23:43:24.424837Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.14876","last_updated":"2020-10-28T10:52:10Z","snapshot_observed_at":"2026-08-17T18:40:07.626452Z","submitted_at":"2020-10-28T10:52:10Z","title":"Fighting Copycat Agents in Behavioral Cloning from Observation Histories","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.14876","snapshot_observed_at":"2026-08-01T23:43:24.534250Z","title":"Fighting copycat agents in behavioral cloning from observation histories.arXiv preprint arXiv: 2010.14876, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:24.534250Z"},"links":{"cited_paper":"/paper/2010.14876","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:f2943aad190c774fd94869ff131324efee8d3a91e26a3426e4eed08cd510c4dc","observation_id":"bd438cd3-dc70-4862-ba26-62d73d10ad53","resolution":{"observed_at":"2026-08-01T23:43:24.534250Z","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":"2026-08-01T23:43:24.619347Z","title":"Efficient streaming language models with attention sinks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:24.619347Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:5e3ab18fea4329606ec6ef7d588b2b4f216aeadf1705b4fb8b2cdb845417e06f","observation_id":"ba4c103c-6603-43ad-b217-23528caa1e82","resolution":{"observed_at":"2026-08-01T23:43:24.619347Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13130","last_updated":"2025-02-18T18:55:21Z","snapshot_observed_at":"2026-08-16T12:57:13.112901Z","submitted_at":"2025-02-18T18:55:21Z","title":"Magma: A Foundation Model for Multimodal AI Agents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13130","snapshot_observed_at":"2026-08-01T23:43:24.735638Z","title":"Magma: A foundation model for multimodal ai agents, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:24.735638Z"},"links":{"cited_paper":"/paper/2502.13130","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:e260b1840536881755be2f8d008098632665e33c3f0b1e92081c40b59897a327","observation_id":"288b4dad-98b3-488b-b329-3d80118200b4","resolution":{"observed_at":"2026-08-01T23:43:24.735638Z","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":"2026-08-01T23:43:24.824823Z","title":"Fla: A triton-based library for hardware-efficient implementations of linear attention mechanism, January 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:24.824823Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:d67fbb2c2fbe16b47dd9e6134b255ac3c1bdbeac67f0451b1ae042f3dea1585c","observation_id":"13d7e682-ecc2-4b03-b4af-f7de2875f4b7","resolution":{"observed_at":"2026-08-01T23:43:24.824823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.06464","last_updated":"2025-03-06T06:57:34Z","snapshot_observed_at":"2026-08-14T21:08:22.323819Z","submitted_at":"2024-12-09T13:09:04Z","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.06464","snapshot_observed_at":"2026-08-01T23:43:24.934146Z","title":"Gated delta networks: Improving mamba2 with delta rule.International Conference on Learning Representations, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:24.934146Z"},"links":{"cited_paper":"/paper/2412.06464","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:8ce7259d4235914e95305e12ec6458e90e7883c8d47d4f4174c8a5405323590e","observation_id":"ba062ce4-2292-4fa6-8e6d-b262b94d2869","resolution":{"observed_at":"2026-08-01T23:43:24.934146Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.15922","last_updated":"2026-02-17T15:04:02Z","snapshot_observed_at":"2026-08-09T12:54:21.149243Z","submitted_at":"2026-02-17T15:04:02Z","title":"World Action Models are Zero-shot Policies","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.15922","snapshot_observed_at":"2026-08-01T23:43:25.044994Z","title":"World action models are zero-shot policies.arXiv preprint arXiv:2602.15922, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:25.044994Z"},"links":{"cited_paper":"/paper/2602.15922","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:7ff54e08e585efd86350a459a36336f1a3c6294733f2f43d910528e6d9f815f5","observation_id":"1406adec-9535-4996-a609-bb4c1d099445","resolution":{"observed_at":"2026-08-01T23:43:25.044994Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2603.16666","last_updated":"2026-03-23T05:41:14Z","snapshot_observed_at":"2026-08-20T03:53:25.888886Z","submitted_at":"2026-03-17T15:33:43Z","title":"Fast-WAM: Do World Action Models Need Test-time Future Imagination?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.16666","snapshot_observed_at":"2026-08-01T23:43:25.154593Z","title":"Fast-wam: Do world action models need test-time future imagination?arXiv preprint arXiv: 2603.16666, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:25.154593Z"},"links":{"cited_paper":"/paper/2603.16666","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:4c04c64741856adb83b2b64097917318c04d57c4690482d1d8779a8a1a74941f","observation_id":"b699bc61-a853-48c1-b0b8-29722b0c2715","resolution":{"observed_at":"2026-08-01T23:43:25.154593Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.16175","last_updated":"2026-02-05T18:03:03Z","snapshot_observed_at":"2026-08-01T10:41:29.420510Z","submitted_at":"2026-01-22T18:24:00Z","title":"Learning to Discover at Test Time","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.16175","snapshot_observed_at":"2026-08-01T23:43:25.247468Z","title":"Learning to discover at test time, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:25.247468Z"},"links":{"cited_paper":"/paper/2601.16175","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:4d3bd55fcc7ddf79700e7849ac9397d9a4600851baf4d318132d2a233cc22c8d","observation_id":"46c6a371-52b0-468b-ad5e-a2f6f9c866f0","resolution":{"observed_at":"2026-08-01T23:43:25.247468Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.23884","last_updated":"2025-05-29T17:50:34Z","snapshot_observed_at":"2026-08-08T17:47:51.120243Z","submitted_at":"2025-05-29T17:50:34Z","title":"Test-Time Training Done Right","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.23884","snapshot_observed_at":"2026-08-01T23:43:25.364420Z","title":"Freeman, and Hao Tan","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:25.364420Z"},"links":{"cited_paper":"/paper/2505.23884","citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:4b3051e2704d5c2a7caaa1831f017553c2a98114e13ee2a3727ae0687033ee8f","observation_id":"e6ff4bbe-9653-450f-a74b-dba3b8ab30c3","resolution":{"observed_at":"2026-08-01T23:43:25.364420Z","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":"2026-08-01T23:43:25.476872Z","title":"Fast-weight product key memory.arXiv preprint arXiv: 2601.00671, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:25.476872Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:d90c732060712705adc0ce5d625e6ae4167b4f5bb4a9153e5e0807342bb27b6e","observation_id":"163994e5-5d4d-4c82-a6b8-ecd5b181612d","resolution":{"observed_at":"2026-08-01T23:43:25.476872Z","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":"2026-08-01T23:43:25.589301Z","title":"TraceVLA: Visual trace prompting enhances spatial-temporal awareness for generalist robotic policies","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:25.589301Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:ab5b8d4bca30040e406870e2fa1264a98f6cd2eece5325a13eb85ac3619f3115","observation_id":"48010602-8a08-4728-8576-64ddd5699ae3","resolution":{"observed_at":"2026-08-01T23:43:25.589301Z","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":"2026-08-01T23:43:25.694733Z","title":"Egoscale: Scaling dexterous manipulation with diverse egocentric human data.arXiv preprint arXiv: 2602.16710, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:25.694733Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:7ac533a8a9d63d5bf31452e47666ca35433f97a5c9dc160610a31698d93d4ce0","observation_id":"0b2b2155-4bf6-479a-bc5b-69fdfe1ab351","resolution":{"observed_at":"2026-08-01T23:43:25.694733Z","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":"2026-08-01T23:43:25.797883Z","title":"Ttt-parkour: Rapid test-time training for perceptive robot parkour.arXiv preprint arXiv:2602.02331, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:25.797883Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:3f88a88e3f8713fcc7f82ba0797f21b6a820c6a9f90652766ecfb9775af1195a","observation_id":"17e5b6a8-7bb5-4e4f-9b51-960e3ae87ff1","resolution":{"observed_at":"2026-08-01T23:43:25.797883Z","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":"2026-08-01T23:43:25.912505Z","title":"Pup Go Car","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:25.912505Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:890cca3a0f19125ee0fd113ca67ef67ab30904422a5c64dd7ec4cefe435b7ef8","observation_id":"b17d375b-cfa8-4fce-b228-2402c456cf02","resolution":{"observed_at":"2026-08-01T23:43:25.912505Z","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":"2026-08-01T23:43:20.312710Z","title":"URLhttps://openreview.net/forum?id=hy0a5MMPUv","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:20.312710Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:9b8335b9c3c204f2d4fed79053b2578a47bfba1f51862cec7b7e5ec2ab9b5f13","observation_id":"a48f8ce1-3742-4e94-8690-a0157bcb9aec","resolution":{"observed_at":"2026-08-01T23:43:20.312710Z","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":"2026-08-01T23:43:17.415629Z","title":"URLhttps://openreview.net/forum?id=2dnO3LLiJ1","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:17.415629Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:7183cbcd19d71ffae4a075fd261a8df73a4779301b1b67fb6225cd133e6afcfc","observation_id":"7f80de5a-26ac-47d6-903b-74fe1cdaf01a","resolution":{"observed_at":"2026-08-01T23:43:17.415629Z","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":"2026-08-01T23:43:19.275272Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-01T23:43:19.275272Z"},"links":{"citing_paper":"/paper/2607.15275"},"observation_digest":"sha256:bc3ec51e40708c340dc7eeefc3d120256dfb4f526dd45f01c37724cb89bb806a","observation_id":"c190bd0d-7235-4835-8d49-daeca4bb0222","resolution":{"observed_at":"2026-08-01T23:43:19.275272Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.15275","last_updated":"2026-07-16T17:59:06Z","latest_version":1,"primary_category":"cs.RO","snapshot_observed_at":"2026-08-18T20:54:19.864423Z","submitted_at":"2026-07-16T17:59:06Z","title":"RoboTTT: Context Scaling for Robot Policies"},"reference_resolution":{"displayed":86,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":86,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":86},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 86 of 86 outbound references and 0 inbound Pith citation observations for arXiv:2607.15275."}