{"as_of":"2026-08-11T03:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4e103997862580e325fcb4b6612bc703e5cce9f129bce6d2e22d046f1695c5cf","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T00:49:02.463223Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2607.26056/citation-record","integrity":"/paper/2607.26056/integrity","json":"/paper/2607.26056/citation-record.json","paper":"/paper/2607.26056"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T00:48:58.578113Z","title":"Learning latent dynamics for planning from pixels.Inter- national Conference on Machine Learning, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:58.578113Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:28074a79c89e14d8e71caceaff76d09359a14fa149609b5d0d4a305850412c28","observation_id":"155429c4-b549-4051-bb16-0292a4cd523c","resolution":{"observed_at":"2026-08-01T00:48:58.578113Z","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":"2026-08-01T00:48:58.647099Z","title":"TD-MPC2: Scalable, robust world models for continuous control","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:58.647099Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:8b95f705d6ee3f8a9a52ccbf2d17532b8d7c54362c22cb4e4fcf4e47a689e124","observation_id":"a8ede6cc-6737-4168-ad47-8810c1485a5e","resolution":{"observed_at":"2026-08-01T00:48:58.647099Z","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":"2026-08-01T00:48:58.759504Z","title":"DINO-WM: World models on pre-trained visual features enable zero-shot planning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:58.759504Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:afa5176e7ced141ad95b4420c7c8c090d03d1bb2428f4dbb99d44707b56d6192","observation_id":"8b22ece9-b60c-4fd7-8cef-2e8b732ea87e","resolution":{"observed_at":"2026-08-01T00:48:58.759504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2603.19312","last_updated":"2026-06-03T18:50:40Z","snapshot_observed_at":"2026-08-06T05:42:53.129146Z","submitted_at":"2026-03-13T19:48:14Z","title":"LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2603.19312","snapshot_observed_at":"2026-08-01T00:48:58.851597Z","title":"Leworldmodel: Stable end-to-end joint-embedding predictive architecture from pixels.arXiv preprint arXiv:2603.19312, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:58.851597Z"},"links":{"cited_paper":"/paper/2603.19312","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:24608341092e4b9725bb2a5a97ed14647747be69d9b4057c01e7b77e971f020a","observation_id":"6c8e5026-dcfc-4458-ba0b-3f19ed9a5dc3","resolution":{"observed_at":"2026-08-01T00:48:58.851597Z","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":"2026-08-01T00:48:58.923758Z","title":"Kroese, Shie Mannor, and Reuven Y","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:58.923758Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:f07b740d09e2c652163fe16e81fef75be6136cea7680ee4a1e3c89503a16f0bc","observation_id":"a9d7753f-bcc9-47e5-811a-1ea534a89b68","resolution":{"observed_at":"2026-08-01T00:48:58.923758Z","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":"2026-08-01T00:48:59.006530Z","title":"Rehg, Byron Boots, and Evangelos A","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:59.006530Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:17d519344f6dc38cae7ad7a3a00e198d3d1c0c95e98e9fb889f77b0e486b521c","observation_id":"8b57f068-ee76-45da-9bab-7a527b3a5d25","resolution":{"observed_at":"2026-08-01T00:48:59.006530Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.04104","last_updated":"2024-04-17T17:41:20Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-01-10T18:12:16Z","title":"Mastering Diverse Domains through World Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.04104","snapshot_observed_at":"2026-08-01T00:48:59.096221Z","title":"Mastering diverse domains through world models.arXiv preprint arXiv:2301.04104, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:59.096221Z"},"links":{"cited_paper":"/paper/2301.04104","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:d47ca90b1b06a22cddc107bcdab447f72cc2321b753c4ea7e46b5d5893e38454","observation_id":"d2c2cc84-2f25-41e0-a941-18cb7a2b0b0d","resolution":{"observed_at":"2026-08-01T00:48:59.096221Z","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":"2026-08-01T00:48:59.188063Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:59.188063Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:a871007d11fe3b2608e849e09c4ef3abe95da9c745f93c5dce3e2b604c775c5f","observation_id":"b35769b5-6a06-4fbc-910c-7761b4be5273","resolution":{"observed_at":"2026-08-01T00:48:59.188063Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.08544","last_updated":"2025-11-14T08:38:32Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-11-11T18:21:55Z","title":"LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.08544","snapshot_observed_at":"2026-08-01T00:48:59.290462Z","title":"Lejepa: Provable and scalable self-supervised learning without the heuris- tics.arXiv preprint arXiv:2511.08544, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:59.290462Z"},"links":{"cited_paper":"/paper/2511.08544","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:04c3bb1bc3c52940a83ff1314a14d28814872db142bf8ee0589273774b142064","observation_id":"9aed2264-5c46-48f2-8109-1c8e101cbf4f","resolution":{"observed_at":"2026-08-01T00:48:59.290462Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2602.11389","last_updated":"2026-05-28T17:57:16Z","snapshot_observed_at":"2026-08-03T00:15:31.913366Z","submitted_at":"2026-02-11T21:47:26Z","title":"Causal-JEPA: Learning World Models through Object-Level Latent Masking","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.11389","snapshot_observed_at":"2026-08-01T00:48:59.378704Z","title":"Causal-JEPA: Learn- ing world models through object-level latent masking","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:59.378704Z"},"links":{"cited_paper":"/paper/2602.11389","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:d4fa3b4426b53488f030663c137d68d03386bd120e90142cc2c3f88f410dd9a6","observation_id":"4e8bd6d6-54c6-4185-8c1e-382afd8cd605","resolution":{"observed_at":"2026-08-01T00:48:59.378704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.26217","last_updated":"2026-06-24T17:59:59Z","snapshot_observed_at":"2026-08-09T10:56:24.381636Z","submitted_at":"2026-06-24T17:59:59Z","title":"Fast LeWorldModel","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.26217","snapshot_observed_at":"2026-08-01T00:48:59.436884Z","title":"Fast LeWorldModel.arXiv preprint arXiv:2606.26217, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:59.436884Z"},"links":{"cited_paper":"/paper/2606.26217","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:d5fa0939fbe778ec4f3bb7aa93786164090cb87170bd47596fdc4abc844db401","observation_id":"6c734855-366f-4d7e-bb48-e2216eef5450","resolution":{"observed_at":"2026-08-01T00:48:59.436884Z","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":"2026-08-01T00:48:59.519843Z","title":"Efros, and Trevor Darrell","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:59.519843Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:605c52a2145cd5d0b9003efca1702effce343c6d8965845184ea21d65fe0d7f9","observation_id":"19a763d9-9e0c-4c9a-889f-87fab0022afe","resolution":{"observed_at":"2026-08-01T00:48:59.519843Z","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":"2026-08-01T00:48:59.600305Z","title":"Provably filtering exogenous distractors using multistep inverse dynamics","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:59.600305Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:414a687c9d7a2a22bfc69cdfddaa73915ca4ceccce84451cad978f38580c320f","observation_id":"de0fc704-987f-4e08-9dd0-a07eec12e4a5","resolution":{"observed_at":"2026-08-01T00:48:59.600305Z","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":"2026-08-01T00:48:59.691046Z","title":"Inverse dynamics pretraining learns good representations for multitask imitation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:59.691046Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:4dd2f9fb991ee99e9eacf004ce3bd55340f602f994cb27727fba8ce63d06cbab","observation_id":"24a8ab2a-5374-42af-9290-9deea5acfc47","resolution":{"observed_at":"2026-08-01T00:48:59.691046Z","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":"2026-08-01T00:48:59.778080Z","title":"Nair, Pieter Abbeel, Jitendra Malik, and Sergey Levine","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:59.778080Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:b53ef5cdf8a04b12230462534b86a257a8544fb9fa688fd6eedddbfb024c7daf","observation_id":"160cb57e-6cac-4910-9ff9-43080d80af76","resolution":{"observed_at":"2026-08-01T00:48:59.778080Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.20104","last_updated":"2026-06-18T11:25:16Z","snapshot_observed_at":"2026-08-02T12:07:11.942278Z","submitted_at":"2026-06-18T11:25:16Z","title":"Sensorimotor World Models: Perception for Action via Inverse Dynamics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.20104","snapshot_observed_at":"2026-08-01T00:48:59.861212Z","title":"Sensorimotor world models: Percep- tion for action via inverse dynamics.arXiv preprint arXiv:2606.20104, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:59.861212Z"},"links":{"cited_paper":"/paper/2606.20104","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:ddd7a5ad9e50fec7662e97e9ea607dba17aae99b6dfd5754dff91b09b6aaba6f","observation_id":"f735e831-436f-4c4a-bc3a-e59c0f3e0a81","resolution":{"observed_at":"2026-08-01T00:48:59.861212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.07687","last_updated":"2026-06-05T04:43:02Z","snapshot_observed_at":"2026-08-06T21:53:14.928140Z","submitted_at":"2026-06-05T04:43:02Z","title":"What Makes Video World Model Latents Action-Relevant: Prediction over Reconstruction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.07687","snapshot_observed_at":"2026-08-01T00:48:59.945946Z","title":"What makes video world model latents action-relevant: Prediction over reconstruc- tion.arXiv preprint arXiv:2606.07687, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T00:48:59.945946Z"},"links":{"cited_paper":"/paper/2606.07687","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:e4f37c39b23bfda2e3d28771dfd21eef945d6dc35b201dcfd4a6b5fe38cf7ca9","observation_id":"c845e808-c91a-4061-b0ca-26f448c2e37a","resolution":{"observed_at":"2026-08-01T00:48:59.945946Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.06088","last_updated":"2020-10-02T19:49:10Z","snapshot_observed_at":"2026-08-11T00:34:37.369946Z","submitted_at":"2019-12-12T17:26:47Z","title":"Learning to Reach Goals via Iterated Supervised Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.06088","snapshot_observed_at":"2026-08-01T00:49:00.033074Z","title":"Learning to reach goals via iterated supervised learning","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:00.033074Z"},"links":{"cited_paper":"/paper/1912.06088","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:ac29a8deadc7a034f4734e46566c2cc2ed0aa66c2c433b0cf137c3e8b62d5e12","observation_id":"c44246e3-72aa-4150-9137-819f79b53e22","resolution":{"observed_at":"2026-08-01T00:49:00.033074Z","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":"2026-08-01T00:49:00.123588Z","title":"C-Learning: Learning to achieve goals via recursive classification","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:00.123588Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:d4fa3e47b49629b501d0aee0eb8bc00f597e0c7d81ccd5f8fb632b37f519c0fc","observation_id":"8e9ad6cb-2ef5-401c-b0b8-9b9a38e6d281","resolution":{"observed_at":"2026-08-01T00:49:00.123588Z","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":"2026-08-01T00:49:00.264817Z","title":"Contrastive learning as goal- conditioned reinforcement learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:00.264817Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:553881bdb4eb6913de07ec0c81dfab91fa9e449b3213b3931e814ac8c2b25df6","observation_id":"64be9911-cac0-490e-b3d1-e0d8e29588a9","resolution":{"observed_at":"2026-08-01T00:49:00.264817Z","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":"2026-08-01T00:49:00.365796Z","title":"Sutton, Doina Precup, and Satinder Singh","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:00.365796Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:aed184a8c03dd0692c59a133a36bcb4e84cc4e8250477168de100f5b7f0013da","observation_id":"ba423836-26ca-497a-a17a-a172abf0d53c","resolution":{"observed_at":"2026-08-01T00:49:00.365796Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-01T00:49:00.467032Z","title":"Klyubin, Daniel Polani, and Chrystopher L","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:00.467032Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:53a6500e21f31ca0f1d74397f772e4bfc8581f7cc7c9f4816162d15e09d6cd6d","observation_id":"2307faed-f20d-46d1-b828-77f065bea4f8","resolution":{"observed_at":"2026-08-01T00:49:00.467032Z","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":"2026-08-01T00:49:00.563847Z","title":"Diversity is all you need: Learning skills without a reward function","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:00.563847Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:ec990ea0f8b91a3d3331b4f53e977e470a5d881d62a74171b793be5c8d0d67df","observation_id":"a5035503-8083-47e1-9459-39950fa32e2b","resolution":{"observed_at":"2026-08-01T00:49:00.563847Z","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":"2026-08-01T00:49:00.651386Z","title":"Dynamics-aware unsupervised discovery of skills","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:00.651386Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:18b216eddf5561b596fae4f1e3d7d85cd2fa6cbc8c3ed61494a1c47d7be6e94e","observation_id":"2b046f7c-fb47-415f-a5ea-fc1f1bde2c27","resolution":{"observed_at":"2026-08-01T00:49:00.651386Z","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":"2026-08-01T00:49:00.735528Z","title":"Unsupervised reinforcement learning with contrastive intrinsic control","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:00.735528Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:76646dfd05b94027a4fb5c1dc0c62f9f7d05df64b5dde6ae5829327d6403d20b","observation_id":"6e861261-ae47-4e13-80e5-2739c4b9bcb9","resolution":{"observed_at":"2026-08-01T00:49:00.735528Z","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":"2026-08-01T00:49:00.821355Z","title":"METRA: Scalable unsupervised RL with metric-aware abstraction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:00.821355Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:9d5a36415235767b6de7989b3347ef9d052f13a7058e6ae5cbe31b55644d1143","observation_id":"e4d5c61c-a666-45be-960f-6cc303b63cd3","resolution":{"observed_at":"2026-08-01T00:49:00.821355Z","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":"2026-08-01T00:49:00.948177Z","title":"Dimen- sionality reduction by learning an invariant mapping","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:00.948177Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:124bf1f445e170d3d6d8928224815384af3f9713f61eb70aa9b89a9b920dbb67","observation_id":"4d07b532-b440-4c85-98ef-a084201b5fba","resolution":{"observed_at":"2026-08-01T00:49:00.948177Z","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":"2026-08-01T00:49:01.009855Z","title":"FaceNet: A unified embedding for face recognition and clustering","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:01.009855Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:375e997a3894fed72a5b5055fa9a8b568787af76b074b70205ca8dd195f13e8c","observation_id":"a5c73204-2168-48c4-a970-75eb8d58df89","resolution":{"observed_at":"2026-08-01T00:49:01.009855Z","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":"2026-08-01T00:49:01.106259Z","title":"Learning invariant representations for reinforcement learning without recon- struction","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:01.106259Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:e000124bb38bf3f1050cf2450c8a6dac9346dfc65db83cc9a308c0847fe81dd6","observation_id":"ecdab1d1-6c69-40c6-a64e-772200120012","resolution":{"observed_at":"2026-08-01T00:49:01.106259Z","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":"2026-08-01T00:49:01.211920Z","title":"Bisimulation makes analogies in goal-conditioned reinforcement learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:01.211920Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:68218424ff57db11cf4c732800943e1a2b9374e99d4d9a2c60fdcbfd57c38e5c","observation_id":"86431b7e-f553-458a-ab4e-992ab7c82c35","resolution":{"observed_at":"2026-08-01T00:49:01.211920Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.02419","last_updated":"2020-12-04T06:07:36Z","snapshot_observed_at":"2026-07-06T10:20:40.500463Z","submitted_at":"2020-12-04T06:07:36Z","title":"Planning from Pixels using Inverse Dynamics Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.02419","snapshot_observed_at":"2026-08-01T00:49:01.435938Z","title":"McIlraith, and Jimmy Ba","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:01.435938Z"},"links":{"cited_paper":"/paper/2012.02419","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:e3d454e58f27793e12360aa44842a5dfa9357623ffdf2f9d2e222c687f8664fe","observation_id":"42a20284-376b-40c3-aefe-0f4df8c421db","resolution":{"observed_at":"2026-08-01T00:49:01.435938Z","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":"2026-08-01T00:49:01.569390Z","title":"Biased-MPPI: Informing sampling-based model predictive control by fus- ing ancillary controllers.IEEE Robotics and Automation Letters, 9(6):5871–5878, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:01.569390Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:71edfc705a544b5b0ca720fb36d8afdbdde5926ff9f37ac2845e1f756c4aa4af","observation_id":"2a667d91-5d9b-4d01-b2fe-b8b0cd154c98","resolution":{"observed_at":"2026-08-01T00:49:01.569390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.07974","last_updated":"2026-06-06T04:18:10Z","snapshot_observed_at":"2026-08-10T10:54:49.409389Z","submitted_at":"2026-06-06T04:18:10Z","title":"PRISM: PRior-guided Imagination Sampling in world Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.07974","snapshot_observed_at":"2026-08-01T00:49:01.635497Z","title":"PRISM: PRior- guided imagination sampling in world models, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:01.635497Z"},"links":{"cited_paper":"/paper/2606.07974","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:015b295d269bcf7e8e994e2304bc25f5bd80c554c25c353cc21a0d29b6a3e1b8","observation_id":"749ea159-346b-45b1-8341-e72a5d8bfc66","resolution":{"observed_at":"2026-08-01T00:49:01.635497Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.08732","last_updated":"2026-06-05T11:55:33Z","snapshot_observed_at":"2026-07-06T23:20:57.084438Z","submitted_at":"2026-05-09T06:36:23Z","title":"Latent Geometry Beyond Search: Amortizing Planning in World Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.08732","snapshot_observed_at":"2026-08-01T00:49:01.745908Z","title":"Latent geometry beyond search: Amortizing planning in world models.arXiv preprint arXiv:2605.08732, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:01.745908Z"},"links":{"cited_paper":"/paper/2605.08732","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:96d85298bd9b1c8132f4a3e5f8b35096dca8b722fe8ad60cfbc9551c13fbe7b6","observation_id":"fb381de0-e1da-4ec7-95e2-b83c53f99526","resolution":{"observed_at":"2026-08-01T00:49:01.745908Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.24890","last_updated":"2026-06-08T07:28:33Z","snapshot_observed_at":"2026-08-04T02:11:27.874111Z","submitted_at":"2026-05-24T06:28:53Z","title":"QuoVLA: Quotient Space for Vision-Language-Action Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.24890","snapshot_observed_at":"2026-08-01T00:49:01.863043Z","title":"QuoVLA: Quotient space for vision-language-action models.arXiv preprint arXiv:2605.24890, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:01.863043Z"},"links":{"cited_paper":"/paper/2605.24890","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:e29acceb1740a4fb5d3ead7e7d8319ff928bc4090c17426be7131c95ac504246","observation_id":"5b127739-2443-4ef9-8ea6-12243d128a15","resolution":{"observed_at":"2026-08-01T00:49:01.863043Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.08653","last_updated":"2026-06-07T14:41:22Z","snapshot_observed_at":"2026-08-08T02:07:04.461006Z","submitted_at":"2026-06-07T14:41:22Z","title":"FiberTune: Preserving Action-Fiber Visual Residuals in Vision-Language-Action Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.08653","snapshot_observed_at":"2026-08-01T00:49:01.978775Z","title":"FiberTune: Preserving action-fiber visual residuals in vision-language-action fine- tuning.arXiv preprint arXiv:2606.08653, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:01.978775Z"},"links":{"cited_paper":"/paper/2606.08653","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:076d0c1c09fd851fa5087503c2111352bad0ffcbb62e9ba6a6d503311a840a3c","observation_id":"3dc1766d-0e78-4ca2-934f-c615e924d758","resolution":{"observed_at":"2026-08-01T00:49:01.978775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.02792","last_updated":"2025-05-23T00:47:24Z","snapshot_observed_at":"2026-08-10T02:54:28.264405Z","submitted_at":"2025-04-03T17:38:59Z","title":"Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.02792","snapshot_observed_at":"2026-08-01T00:49:02.053139Z","title":"Unified world models: Coupling video and action diffusion for pretraining on large robotic datasets.arXiv preprint arXiv:2504.02792, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:02.053139Z"},"links":{"cited_paper":"/paper/2504.02792","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:5fffe132f550f76de4b4c41557f8700aa9c103a5db1526499c48bacf86c5a56d","observation_id":"ac9dc69b-9213-404e-b205-7953cc6800b1","resolution":{"observed_at":"2026-08-01T00:49:02.053139Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.12705","last_updated":"2025-06-17T22:33:35Z","snapshot_observed_at":"2026-07-06T21:26:01.534136Z","submitted_at":"2025-05-19T04:55:39Z","title":"DreamGen: Unlocking Generalization in Robot Learning through Video World Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.12705","snapshot_observed_at":"2026-08-01T00:49:02.167489Z","title":"Dreamgen: Un- locking generalization in robot learning through video world models.arXiv preprint arXiv:2505.12705, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:02.167489Z"},"links":{"cited_paper":"/paper/2505.12705","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:8a1023c19c2738952df43ed0f5de5ee551561865ce237b81e32e83e61d19539b","observation_id":"1fdeceee-41cd-48c1-bac2-6c9539e8293a","resolution":{"observed_at":"2026-08-01T00:49:02.167489Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2607.04978","last_updated":"2026-07-06T12:12:50Z","snapshot_observed_at":"2026-08-07T22:37:57.928894Z","submitted_at":"2026-07-06T12:12:50Z","title":"Qantara: Bridge-Flow Training for Multi-Paradigm JEPA Control","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2607.04978","snapshot_observed_at":"2026-08-01T00:49:02.265256Z","title":"Qantara: Bridge-flow training for multi- paradigm JEPA control.arXiv preprint arXiv:2607.04978, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:02.265256Z"},"links":{"cited_paper":"/paper/2607.04978","citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:b806761f8966ce5cc44247c130e678f4ce60ecf01540637062912c6cf234f6ad","observation_id":"27225d81-287e-4dc0-b9ec-f5a9e3974b62","resolution":{"observed_at":"2026-08-01T00:49:02.265256Z","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":"2026-08-01T00:49:02.291947Z","title":"OGBench: Benchmarking offline goal- conditioned reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:02.291947Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:6ad2b7b5d6e4c5c7a9145ccf12615e0010ccf499a3eb68268daee840b4eb5442","observation_id":"94b20b3c-3143-4259-8869-5fadcf52af6b","resolution":{"observed_at":"2026-08-01T00:49:02.291947Z","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":"2026-08-01T00:49:02.353138Z","title":"CLEAR- LeWM: Calibrated, legality-aware evaluation for LeWM control","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:02.353138Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:cccc1533d2fde8445a5905877fbff5fc02d6340f7eb1d8a316712344e9088a32","observation_id":"241b7daa-3e61-400f-b387-8dfd1a9dc1a0","resolution":{"observed_at":"2026-08-01T00:49:02.353138Z","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":"2026-08-01T00:49:01.304828Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:01.304828Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:c7800313fdf922ddd959834d72f027ff05419ba80a5a6714c715d71fb2053277","observation_id":"46bcf3aa-b8b7-455e-810e-90ee4991918e","resolution":{"observed_at":"2026-08-01T00:49:01.304828Z","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":"2026-08-01T00:49:02.463223Z","title":"Shared fraction","venue":null,"work_id":null,"year":2064},"citing_paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models","version":1},"reference_index":2026,"source":"pdf_text","source_observed_at":"2026-08-01T00:49:02.463223Z"},"links":{"citing_paper":"/paper/2607.26056"},"observation_digest":"sha256:ee487b75fef1730872e2596b962ee0582f86e7cc93b087780a81097d0a66848f","observation_id":"9f7e484d-df51-4b16-a7a2-b1f3a49ce892","resolution":{"observed_at":"2026-08-01T00:49:02.463223Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.26056","last_updated":"2026-07-28T17:59:40Z","latest_version":1,"primary_category":"cs.RO","snapshot_observed_at":"2026-08-10T17:39:46.431436Z","submitted_at":"2026-07-28T17:59:40Z","title":"INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":41,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":43},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2607.26056."}