{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L35TTSYHKB5XDMBT6B6DTWQZFP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1f0b0573feb963ffca5fb9df6524f92e43065373bc101230dfd17063462a2f83","cross_cats_sorted":["cs.CV","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-18T22:06:58Z","title_canon_sha256":"271076f7bff7127ea066e33b2f91610943489f69dfae2f3f4b9424a2736cae51"},"schema_version":"1.0","source":{"id":"2503.15558","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.15558","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2503.15558v3","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15558","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"L35TTSYHKB5X","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"L35TTSYHKB5XDMBT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"L35TTSYH","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:213fc54b6601d1cd215af3567bcd60d32100e0469fe5ad93c735de830039bbb8","target":"graph","created_at":"2026-05-17T23:38:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Cosmos-Reason1 models can understand the physical world and generate appropriate embodied decisions (e.g., next step action) in natural language through long chain-of-thought reasoning processes."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The hierarchical ontology for physical common sense and the two-dimensional ontology for embodied reasoning sufficiently capture the knowledge needed to generalize across physical tasks and embodiments."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Cosmos-Reason1-7B and 56B models are trained with physical common sense and embodied reasoning ontologies via supervised fine-tuning and reinforcement learning to produce next-step physical actions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Cosmos-Reason1 models understand the physical world and generate embodied decisions through long chain-of-thought reasoning in natural language."}],"snapshot_sha256":"024d77bbcd9335b6bb5423d451418a5f6f6ffee30c36b5cfd54e643077b5241b"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"53f7af9ac5daa00f92b11232a6246454e2fe0b73fd940279e55de02190f80d77"},"paper":{"abstract_excerpt":"Physical AI systems need to perceive, understand, and perform complex actions in the physical world. In this paper, we present the Cosmos-Reason1 models that can understand the physical world and generate appropriate embodied decisions (e.g., next step action) in natural language through long chain-of-thought reasoning processes. We begin by defining key capabilities for Physical AI reasoning, with a focus on physical common sense and embodied reasoning. To represent physical common sense, we use a hierarchical ontology that captures fundamental knowledge about space, time, and physics. For em","authors_text":"Alice Luo, Andrew Mathau, Andrew Z. Wang, Boxin Wang, Brendan Johnson, David W. Romero, Dinghao Yang, Elena Lantz, Fangyin Wei, Francesco Ferroni, George Kurian, Hannah Brandon, Haoxiang Wang, Huayu Chen, Imad El Hanafi, Jacob Huffman, Jenna Diamond, Jiashu Xu, Jiaxin Cao, Jingxu Zhang, Jingyi Jin, Jinju Chu, Jinwei Gu, Junjie Bai, Liang Feng, Lindsey Pavao, Lyne Tchapmi, Maosheng Liao, Ming-Yu Liu, Misha Smelyanskiy, Nayeon Lee, NVIDIA: Alisson Azzolini, Prithvijit Chattopadhyay, Rama Govindaraju, Rizwan Khan, Shuran Song, Siddharth Gururani, Tsung-Yi Lin, Wei Ping, Xiangyu Lu, Xiaodong Yang, Xiaohui Zeng, Xuan Li, Yao Xu, Yen-Chen Lin, Yifan Ding, Yin Cui, Yun Ni, Zekun Hao, Zhaoshuo Li, Zhe Zhang, Zhuolin Yang","cross_cats":["cs.CV","cs.LG","cs.RO"],"headline":"Cosmos-Reason1 models understand the physical world and generate embodied decisions through long chain-of-thought reasoning in natural language.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-18T22:06:58Z","title":"Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning"},"references":{"count":60,"internal_anchors":20,"resolved_work":60,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Agibot world colosseum.https://github.com/OpenDriveLab/AgiBot-World, 2024","work_id":"b6e28cd0-4ca2-4a47-b4a5-fef58e17bdbe","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Do as i can, not as i say: Grounding language in robotic affordances","work_id":"a85fc3ea-bb91-47f3-b6a2-caa967931f52","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Flamingo: a visual language model for few-shot learning","work_id":"bcc10fec-5e16-45c2-8157-9a14a84708ac","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Covla: Comprehensive vision-language-action dataset for autonomous driving","work_id":"534db3f4-3bf9-47ee-b3b6-02f30b09e417","year":2024},{"cited_arxiv_id":"2502.13923","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Qwen2.5-VL Technical Report","work_id":"69dffacb-bfe8-442d-be86-48624c60426f","year":2025}],"snapshot_sha256":"59481525b03e77d420b38c4ff26892a4bbc90a552e2d100d01539931ade94e9f"},"source":{"id":"2503.15558","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T12:43:31.071002Z","id":"a2a69306-7128-4b3f-b9f3-744aad9489b3","model_set":{"reader":"grok-4.3"},"one_line_summary":"Cosmos-Reason1-7B and 56B models are trained with physical common sense and embodied reasoning ontologies via supervised fine-tuning and reinforcement learning to produce next-step physical actions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Cosmos-Reason1 models understand the physical world and generate embodied decisions through long chain-of-thought reasoning in natural language.","strongest_claim":"Cosmos-Reason1 models can understand the physical world and generate appropriate embodied decisions (e.g., next step action) in natural language through long chain-of-thought reasoning processes.","weakest_assumption":"The hierarchical ontology for physical common sense and the two-dimensional ontology for embodied reasoning sufficiently capture the knowledge needed to generalize across physical tasks and embodiments."}},"verdict_id":"a2a69306-7128-4b3f-b9f3-744aad9489b3"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a4df63f7b5e3db9242fccbd07585c278cd65d1b8bd896d4fdb5b190994fc2dde","target":"record","created_at":"2026-05-17T23:38:47Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1f0b0573feb963ffca5fb9df6524f92e43065373bc101230dfd17063462a2f83","cross_cats_sorted":["cs.CV","cs.LG","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-18T22:06:58Z","title_canon_sha256":"271076f7bff7127ea066e33b2f91610943489f69dfae2f3f4b9424a2736cae51"},"schema_version":"1.0","source":{"id":"2503.15558","kind":"arxiv","version":3}},"canonical_sha256":"5efb39cb07507b71b033f07c39da192bec8d1652a1d07700b132fffe02c2cbe5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5efb39cb07507b71b033f07c39da192bec8d1652a1d07700b132fffe02c2cbe5","first_computed_at":"2026-05-17T23:38:47.832540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:47.832540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qx5VCOpiVZCElbBUhqy1C60AwyAZPJnYHtyboBiiHaACfdR2l1vrghGUMBRgebHPVSranCE2tUDpnx/CBcRoAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:47.833334Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.15558","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4df63f7b5e3db9242fccbd07585c278cd65d1b8bd896d4fdb5b190994fc2dde","sha256:213fc54b6601d1cd215af3567bcd60d32100e0469fe5ad93c735de830039bbb8"],"state_sha256":"9fb440bbb13bac922a2f7088c272b4b27b3b7e8cfb3076da6d6f9d872508cf42"}