{"as_of":"2026-08-09T21:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b98ab29fc700faafa7699bde2cee512fe2676fba980a0fc1a44cf60dd9391c33","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-11T20:32:22.412216Z","state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T03:16:53.099063Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2607.04265","snapshot_observed_at":"2026-08-02T03:16:53.099063Z","title":"Halo-wa: Hybrid-attention latent-guided online reinforcement learning for world-action models.arXiv preprint arXiv:2607.04265, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.13960","last_updated":"2026-07-17T13:39:37Z","snapshot_observed_at":"2026-08-03T18:30:12.569959Z","submitted_at":"2026-07-15T15:46:42Z","title":"GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-02T03:16:53.099063Z"},"links":{"cited_paper":"/paper/2607.04265","citing_paper":"/paper/2607.13960"},"observation_digest":"sha256:e8eaaef2a3220204ba29567a576e1e109da61883aa4163ddfdb6854b2e24a21e","observation_id":"0e2be43d-316a-4b64-bad9-c41302c51ee2","resolution":{"observed_at":"2026-08-02T03:16:53.099063Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2607.04265/citation-record","integrity":"/paper/2607.04265/integrity","json":"/paper/2607.04265/citation-record.json","paper":"/paper/2607.04265"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2605.12090","last_updated":"2026-05-12T13:10:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-05-12T13:10:52Z","title":"World Action Models: The Next Frontier in Embodied AI","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.12090","snapshot_observed_at":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2605.12090","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:3c5f0a6afb715ab413ddc4a4e0cfb01ba3d79928d1fc025ede7585017ef9f836","observation_id":"1899715e-cec5-4a35-9f81-d73a61e7bb05","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.00080","last_updated":"2026-04-30T14:35:31Z","snapshot_observed_at":"2026-08-04T20:02:32.182599Z","submitted_at":"2026-04-30T14:35:31Z","title":"World Model for Robot Learning: A Comprehensive Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.00080","snapshot_observed_at":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2605.00080","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:4515b76e39e8a24be698ec20e6e0916bfcbe840be691bc5e0c43b77469dd5204","observation_id":"81d42cae-d0f2-4494-ad45-182d1c3b2ffa","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:9afd1188c96784fd3eb89a4e601f9cdd44e99af2fc68e573ea4b8048f4109391","observation_id":"6c31730c-8af4-47af-ae35-aa0d4e4f1800","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-08-06T02:05:52.408905Z","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":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2601.16163","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:1b91af17b2f4c88855a51fedf7a7044a8e2d36725536a4fd1c1408c630bbe4a2","observation_id":"d58553d9-9a38-4c8e-a8fa-ed17c9063c44","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2512.13030","last_updated":"2025-12-25T08:16:05Z","snapshot_observed_at":"2026-07-06T22:38:59.725645Z","submitted_at":"2025-12-15T06:58:40Z","title":"Motus: A Unified Latent Action World Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2512.13030","snapshot_observed_at":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2512.13030","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:fdaa3e20ef4e54ef2e5fd19307b8fca741a27cf2bce9bd26b9ee2b23bb8dbb32","observation_id":"4f738922-05ae-4de2-8c4a-f7bb8580e10b","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":"Luo et al","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:6239ac19e9162c3d565801c1a1dc32d932a8eca2b666661075d271c1bbf52d07","observation_id":"e9c74d38-0384-4f3e-81cb-9d4407d7b549","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:5120675904c9e71fa4e33a12f6ed2c9ba3f39d468cb843ef53347f44cafb1422","observation_id":"b158d5b2-c619-420a-b93f-0b8ba880d0a7","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.15815","last_updated":"2024-10-23T05:32:34Z","snapshot_observed_at":"2026-07-06T18:50:13.559866Z","submitted_at":"2024-07-22T17:29:02Z","title":"Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.15815","snapshot_observed_at":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2407.15815","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:420fbc95955a45914a4fb32952242525e60e6345a6ef55246bf4500f748f6a95","observation_id":"ce9bad05-4d09-4e77-8520-05ba9bc6ce06","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:7c09c68f751e6199a7bb8d2446f31a36461c3f34e47ada031a5b4d247f583627","observation_id":"f224192d-bdef-4397-b03f-4d26efaa45dd","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.23073","last_updated":"2026-04-30T20:04:38Z","snapshot_observed_at":"2026-07-31T07:02:53.376869Z","submitted_at":"2026-04-24T23:57:45Z","title":"RL Token: Bootstrapping Online RL with Vision-Language-Action Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2604.23073","snapshot_observed_at":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2604.23073","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:58014cd0a749354fe7a64516691ef6f4df34e6cfc42b21bc5554387216c3e32f","observation_id":"fc806294-a3d2-4ef1-83aa-3414aeecc8fb","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:b8145adf64698a9cb66499054024b1b370f02007f1e47f4742e01dc0322080a2","observation_id":"3479754b-4242-43bd-9761-7a426a7f8741","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.18719","last_updated":"2025-05-24T14:42:51Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-24T14:42:51Z","title":"VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.18719","snapshot_observed_at":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2505.18719","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:46aba7c1b79fe798017a814b1348467eecae169af89dec1f1433964c802e26d6","observation_id":"4fab7b81-c372-41c5-bab5-ab5298d2d764","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-06T02:11:23.670680Z","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":"2026-07-11T20:32:22.412216Z","title":"Black, N","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2410.24164","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:ea25037d0dba90fa7826240bffb071f7f877871b53db03423e48e9d9470a4e6d","observation_id":"51dfefa8-1fc1-49ea-ac24-163302a5214a","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:bf4a887da94494b384d3aaefdb37d3d1c04f3b2a28737be446ad23054c7f2538","observation_id":"cab190fd-afbd-4385-9062-5b5152ae614a","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2602.15922","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:069a23df675bd713411f2762ba741123d91da9f3914b83f6389cab956dc8eebc","observation_id":"a94b7b6e-f7f2-412a-b3ee-a6489b037587","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-06T22:49:23.750692Z","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":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2603.16666","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:4bb244ad83689ad6f43ea31e30dfe79c487fb599bd689e18444ea72bd6d5e06a","observation_id":"9355e1ff-691d-49a1-8409-6c92dfffe13f","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.10942","last_updated":"2026-05-11T17:59:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-05-11T17:59:56Z","title":"HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.10942","snapshot_observed_at":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2605.10942","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:afdea9ad2aef86d0b62ca0294e61071beb7df7273284ccf46cc0c1a9021f619d","observation_id":"984341a5-1e83-49d5-a77c-e7c2f02d8c17","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.06481","last_updated":"2026-05-07T16:06:08Z","snapshot_observed_at":"2026-08-03T04:45:05.402667Z","submitted_at":"2026-05-07T16:06:08Z","title":"OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.06481","snapshot_observed_at":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2605.06481","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:58663ebed34e3098875dd51ad2a3123709c2388bc822cfcfb29be75223600de3","observation_id":"f51892a0-944f-4767-a64e-ef3f7ba1865c","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.06388","last_updated":"2026-05-07T15:05:26Z","snapshot_observed_at":"2026-08-02T19:03:40.916172Z","submitted_at":"2026-05-07T15:05:26Z","title":"Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.06388","snapshot_observed_at":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2605.06388","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:251ae766bead407b4069d36be8055d0bd58b58ed36ad234392c4f057ad7ea263","observation_id":"7c758a15-df9a-46c7-b0b1-b63d0bef67ca","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":"Vaswani, N","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:59913231c9b681db4e8b64bda3737c4b6d80bed5f4fcf2e2066adc2c6d77e88e","observation_id":"10917a8c-ea85-4f46-a47a-d62809ba1595","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.0473","last_updated":"2016-05-19T21:53:22Z","snapshot_observed_at":"2026-07-06T03:53:10.336430Z","submitted_at":"2014-09-01T16:33:02Z","title":"Neural Machine Translation by Jointly Learning to Align and Translate","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.0473","snapshot_observed_at":"2026-07-11T20:32:22.412216Z","title":"Bahdanau, K","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/1409.0473","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:c26cfe7f088bcad8cab5ca1c0b9b2f956d2ee1e278e5d0db5805e7594d11414a","observation_id":"eed135af-6194-4c53-99c2-12536b916edf","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.18088","last_updated":"2025-08-27T17:52:42Z","snapshot_observed_at":"2026-08-01T01:17:47.017808Z","submitted_at":"2025-06-22T16:26:53Z","title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.18088","snapshot_observed_at":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2506.18088","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:189ec3b0b6eb4b0d4f98348346f7a162a846d9f6213d633a4b1fcd50404e66c5","observation_id":"0c73e39b-554c-45a7-a4dc-8022156560e0","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:a041f6ccac68c762d9fc96d5654a9fd9152bb7ef0d2253d2b9a32cd163c2268f","observation_id":"69c4fadd-2c07-4f82-9eef-4e60645b0168","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2601.21998","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:68d8570c6cd2321ba01917689a92f6458dfafb9355f7cad5143c34ddeb64fd6b","observation_id":"532d333b-68a5-44b2-9f6e-6c0818d3547d","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.05198","last_updated":"2025-07-07T16:58:17Z","snapshot_observed_at":"2026-08-07T04:00:02.770729Z","submitted_at":"2025-07-07T16:58:17Z","title":"EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modeling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.05198","snapshot_observed_at":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"cited_paper":"/paper/2507.05198","citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:193562e7d6c1b51116b5e2531a4d2e489618243577c7bc2e94784b80f9f9ae5e","observation_id":"c32bebfd-18a8-4124-8c1b-754ef66c6037","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:cb2dfee45cb197758f8e6067c769647249a2aff275bd0f5c0634f8203253a5ab","observation_id":"f91ebc77-185f-475c-b610-e039a1ac3ff8","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":"Kelly, C","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:5a7b27bfb99175005a4db5c316c75121164939f625eb8b182aecb6dae33cef02","observation_id":"10c85fb8-9224-4b42-aa29-b04638a1793e","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:429248c3cd111a80af2701a7c8fa307c46a508cf674a34e3bf9183e0e768487a","observation_id":"deca2004-37d6-4e14-a962-e0d6bdd19844","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":"Fujimoto, H","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:a10f6ae222aadb4f7b7b655bc79d2b212fcf2ff93a1626c02d22ee65b516bddf","observation_id":"6c8d7aaa-0ba8-4022-a04d-d468bb0413bf","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:4de4277b9c732f7739d3c2736fd6376dfc7b8c0538c3824ec8e746d5946632cf","observation_id":"1219f6d1-20b0-4594-a9bc-7a30e6ed42c2","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","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":"2026-07-11T20:32:22.412216Z","title":"LeCun, L","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-11T20:32:22.412216Z"},"links":{"citing_paper":"/paper/2607.04265"},"observation_digest":"sha256:d2325b95866d104a2fac0b87825a26daead76228bc03bee9f485ff9441446946","observation_id":"262433fc-54d1-4a77-a407-e10cb37100ee","resolution":{"observed_at":"2026-07-11T20:32:22.412216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.04265","last_updated":"2026-07-05T12:24:14Z","latest_version":1,"primary_category":"cs.RO","snapshot_observed_at":"2026-08-03T14:46:31.336834Z","submitted_at":"2026-07-05T12:24:14Z","title":"HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":31,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":31},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 1 inbound Pith citation observation for arXiv:2607.04265."}