{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GWIW4SQLWFEYCXYPQ6KLBDKVCO","short_pith_number":"pith:GWIW4SQL","canonical_record":{"source":{"id":"2506.03569","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T04:32:54Z","cross_cats_sorted":[],"title_canon_sha256":"150696a54f0f3a061dc6f54d94f97b5425515d3b9116d6ec421aa31846d5284e","abstract_canon_sha256":"ccc66ff0127bf433fd200960d75917ac8c9fbac874f1ab81abcebcd876efc89a"},"schema_version":"1.0"},"canonical_sha256":"35916e4a0bb149815f0f8794b08d551396d8b0d459b3eb5229527201c41b28da","source":{"kind":"arxiv","id":"2506.03569","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03569","created_at":"2026-07-05T11:15:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03569v1","created_at":"2026-07-05T11:15:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03569","created_at":"2026-07-05T11:15:30Z"},{"alias_kind":"pith_short_12","alias_value":"GWIW4SQLWFEY","created_at":"2026-07-05T11:15:30Z"},{"alias_kind":"pith_short_16","alias_value":"GWIW4SQLWFEYCXYP","created_at":"2026-07-05T11:15:30Z"},{"alias_kind":"pith_short_8","alias_value":"GWIW4SQL","created_at":"2026-07-05T11:15:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GWIW4SQLWFEYCXYPQ6KLBDKVCO","target":"record","payload":{"canonical_record":{"source":{"id":"2506.03569","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T04:32:54Z","cross_cats_sorted":[],"title_canon_sha256":"150696a54f0f3a061dc6f54d94f97b5425515d3b9116d6ec421aa31846d5284e","abstract_canon_sha256":"ccc66ff0127bf433fd200960d75917ac8c9fbac874f1ab81abcebcd876efc89a"},"schema_version":"1.0"},"canonical_sha256":"35916e4a0bb149815f0f8794b08d551396d8b0d459b3eb5229527201c41b28da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:30.408230Z","signature_b64":"64gmn3gvN84ZLbdu1nX8Dq+URh2F1RXxL6did3M72xF+N6mgNrlq8vpQuWZ73xZo0Sl1sUKaLFVsJOIclwpkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35916e4a0bb149815f0f8794b08d551396d8b0d459b3eb5229527201c41b28da","last_reissued_at":"2026-07-05T11:15:30.407694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:30.407694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.03569","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+og4jCBtLZS8Ujr5Tpn2pDJUAEGEU0QSal54UnsThhPsCZSB1DVVRR14iZVudiDtlGxHBPSs9yMvt/QVfT5FCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:58:49.911103Z"},"content_sha256":"6704bbd0388467a8f7dedad675057874415a891a627ed4126bcc9d6e9f1cefad","schema_version":"1.0","event_id":"sha256:6704bbd0388467a8f7dedad675057874415a891a627ed4126bcc9d6e9f1cefad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GWIW4SQLWFEYCXYPQ6KLBDKVCO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MiMo-VL Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingquan Xia, Bowen Shen, Bowen Ye, Can Cai, Chang Liu, Chenhong He, Chong Ma, Cici, Dawei Zhu, Di Zhang, Dong Zhang, Duo Zhang, Gang Wang, Guoan Wang, Hailin Zhang, Hanglong Lv, Haochen Zhao, Hao Tian, Heng Qu, Hongshen Xu, Huaqiu Liu, Jiaming Xu, Jiebao Xiao, Jinhao Dong, Jun Shi, Kai Fang, Kainan Bao, Kangyang Zhou, Kang Zhou, Lei Li, Liang Zhao, Menghang Zhu, Nuo Chen, Peidian Li, Peng Wang, Qiantong Wang, Rui Ma, Shande Wang, Shaohui Liu, Shicheng Li, Shihua Yu, Shimao Chen, Shuhao Gu, Shuhuai Ren, Shuo Liu, Sirui Deng, Weiji Zhuang, Weikun Wang, Wei Liu, Weiwei Lv, Wenhan Ma, Wenyu Yang, Xiangwei Deng, Xiaomi LLM-Core Team: Zihao Yue, Xingchen Song, Xing Yong, Xing Zhang, Xin Zhang, Xinzhe Xu, Xu Wang, Yifan Song, Yihan Yan, Yi Huang, Yuanyuan Tian, Yudong Wang, Yue Yu, Yu Tu, Zhenbo Luo, Zhenru Lin, Zhichao Song, Zhixian Zheng, Zihan Jiang, Zihan Zhang","submitted_at":"2025-06-04T04:32:54Z","abstract_excerpt":"We open-source MiMo-VL-7B-SFT and MiMo-VL-7B-RL, two powerful vision-language models delivering state-of-the-art performance in both general visual understanding and multimodal reasoning. MiMo-VL-7B-RL outperforms Qwen2.5-VL-7B on 35 out of 40 evaluated tasks, and scores 59.4 on OlympiadBench, surpassing models with up to 78B parameters. For GUI grounding applications, it sets a new standard with 56.1 on OSWorld-G, even outperforming specialized models such as UI-TARS. Our training combines four-stage pre-training (2.4 trillion tokens) with Mixed On-policy Reinforcement Learning (MORL) integra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03569","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.03569/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:15:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+onZnVFEq4vWNi3x9DSEL4TAjxByq3llm2pVB74ftELHO/NCIqIynBW2HJBOniDvZhBAuqQdC3zp6GCnbls5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:58:49.911629Z"},"content_sha256":"6aa5cc8678b4e301aa90334af4b7dee4169c02abf3c63a5e9ced536c4211826c","schema_version":"1.0","event_id":"sha256:6aa5cc8678b4e301aa90334af4b7dee4169c02abf3c63a5e9ced536c4211826c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GWIW4SQLWFEYCXYPQ6KLBDKVCO/bundle.json","state_url":"https://pith.science/pith/GWIW4SQLWFEYCXYPQ6KLBDKVCO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GWIW4SQLWFEYCXYPQ6KLBDKVCO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T15:58:49Z","links":{"resolver":"https://pith.science/pith/GWIW4SQLWFEYCXYPQ6KLBDKVCO","bundle":"https://pith.science/pith/GWIW4SQLWFEYCXYPQ6KLBDKVCO/bundle.json","state":"https://pith.science/pith/GWIW4SQLWFEYCXYPQ6KLBDKVCO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GWIW4SQLWFEYCXYPQ6KLBDKVCO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GWIW4SQLWFEYCXYPQ6KLBDKVCO","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":"ccc66ff0127bf433fd200960d75917ac8c9fbac874f1ab81abcebcd876efc89a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T04:32:54Z","title_canon_sha256":"150696a54f0f3a061dc6f54d94f97b5425515d3b9116d6ec421aa31846d5284e"},"schema_version":"1.0","source":{"id":"2506.03569","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.03569","created_at":"2026-07-05T11:15:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.03569v1","created_at":"2026-07-05T11:15:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03569","created_at":"2026-07-05T11:15:30Z"},{"alias_kind":"pith_short_12","alias_value":"GWIW4SQLWFEY","created_at":"2026-07-05T11:15:30Z"},{"alias_kind":"pith_short_16","alias_value":"GWIW4SQLWFEYCXYP","created_at":"2026-07-05T11:15:30Z"},{"alias_kind":"pith_short_8","alias_value":"GWIW4SQL","created_at":"2026-07-05T11:15:30Z"}],"graph_snapshots":[{"event_id":"sha256:6aa5cc8678b4e301aa90334af4b7dee4169c02abf3c63a5e9ced536c4211826c","target":"graph","created_at":"2026-07-05T11:15:30Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.03569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We open-source MiMo-VL-7B-SFT and MiMo-VL-7B-RL, two powerful vision-language models delivering state-of-the-art performance in both general visual understanding and multimodal reasoning. MiMo-VL-7B-RL outperforms Qwen2.5-VL-7B on 35 out of 40 evaluated tasks, and scores 59.4 on OlympiadBench, surpassing models with up to 78B parameters. For GUI grounding applications, it sets a new standard with 56.1 on OSWorld-G, even outperforming specialized models such as UI-TARS. Our training combines four-stage pre-training (2.4 trillion tokens) with Mixed On-policy Reinforcement Learning (MORL) integra","authors_text":"Bingquan Xia, Bowen Shen, Bowen Ye, Can Cai, Chang Liu, Chenhong He, Chong Ma, Cici, Dawei Zhu, Di Zhang, Dong Zhang, Duo Zhang, Gang Wang, Guoan Wang, Hailin Zhang, Hanglong Lv, Haochen Zhao, Hao Tian, Heng Qu, Hongshen Xu, Huaqiu Liu, Jiaming Xu, Jiebao Xiao, Jinhao Dong, Jun Shi, Kai Fang, Kainan Bao, Kangyang Zhou, Kang Zhou, Lei Li, Liang Zhao, Menghang Zhu, Nuo Chen, Peidian Li, Peng Wang, Qiantong Wang, Rui Ma, Shande Wang, Shaohui Liu, Shicheng Li, Shihua Yu, Shimao Chen, Shuhao Gu, Shuhuai Ren, Shuo Liu, Sirui Deng, Weiji Zhuang, Weikun Wang, Wei Liu, Weiwei Lv, Wenhan Ma, Wenyu Yang, Xiangwei Deng, Xiaomi LLM-Core Team: Zihao Yue, Xingchen Song, Xing Yong, Xing Zhang, Xin Zhang, Xinzhe Xu, Xu Wang, Yifan Song, Yihan Yan, Yi Huang, Yuanyuan Tian, Yudong Wang, Yue Yu, Yu Tu, Zhenbo Luo, Zhenru Lin, Zhichao Song, Zhixian Zheng, Zihan Jiang, Zihan Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T04:32:54Z","title":"MiMo-VL Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03569","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6704bbd0388467a8f7dedad675057874415a891a627ed4126bcc9d6e9f1cefad","target":"record","created_at":"2026-07-05T11:15:30Z","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":"ccc66ff0127bf433fd200960d75917ac8c9fbac874f1ab81abcebcd876efc89a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T04:32:54Z","title_canon_sha256":"150696a54f0f3a061dc6f54d94f97b5425515d3b9116d6ec421aa31846d5284e"},"schema_version":"1.0","source":{"id":"2506.03569","kind":"arxiv","version":1}},"canonical_sha256":"35916e4a0bb149815f0f8794b08d551396d8b0d459b3eb5229527201c41b28da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35916e4a0bb149815f0f8794b08d551396d8b0d459b3eb5229527201c41b28da","first_computed_at":"2026-07-05T11:15:30.407694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:30.407694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"64gmn3gvN84ZLbdu1nX8Dq+URh2F1RXxL6did3M72xF+N6mgNrlq8vpQuWZ73xZo0Sl1sUKaLFVsJOIclwpkBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:30.408230Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.03569","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6704bbd0388467a8f7dedad675057874415a891a627ed4126bcc9d6e9f1cefad","sha256:6aa5cc8678b4e301aa90334af4b7dee4169c02abf3c63a5e9ced536c4211826c"],"state_sha256":"049895decf283650b9d1a5ef75275eb680604269b9de77be7c7126701c537281"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+1oMuIc2BuT3uyof6gb+fFbQ3WhuvON5fxmRu2QfB7uVANK8SHUsK/O+FB2sJgQElTVJ81fGU8Zfw9HRci1xDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:58:49.915347Z","bundle_sha256":"f625494f03e543c60438e075070f21af604e091630a250510f8c8b024b1f0260"}}