{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:H37IGTXUQIDDXXTF3M4QC43S4F","short_pith_number":"pith:H37IGTXU","canonical_record":{"source":{"id":"2505.07608","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T14:30:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4e3320ae491ed6c4a6540aef866bd8cc583bb0b7a6a5e673b9e2a3e0bc20ac1f","abstract_canon_sha256":"4c41f96e17f9aaf831445ae95eefabd4ae6e75dc8d9490e11a5e8ed56157b6d6"},"schema_version":"1.0"},"canonical_sha256":"3efe834ef482063bde65db39017372e15aa7cc3e2e58cc62f1ca71f1e1629ced","source":{"kind":"arxiv","id":"2505.07608","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07608","created_at":"2026-07-05T11:16:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07608v2","created_at":"2026-07-05T11:16:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07608","created_at":"2026-07-05T11:16:34Z"},{"alias_kind":"pith_short_12","alias_value":"H37IGTXUQIDD","created_at":"2026-07-05T11:16:34Z"},{"alias_kind":"pith_short_16","alias_value":"H37IGTXUQIDDXXTF","created_at":"2026-07-05T11:16:34Z"},{"alias_kind":"pith_short_8","alias_value":"H37IGTXU","created_at":"2026-07-05T11:16:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:H37IGTXUQIDDXXTF3M4QC43S4F","target":"record","payload":{"canonical_record":{"source":{"id":"2505.07608","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T14:30:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4e3320ae491ed6c4a6540aef866bd8cc583bb0b7a6a5e673b9e2a3e0bc20ac1f","abstract_canon_sha256":"4c41f96e17f9aaf831445ae95eefabd4ae6e75dc8d9490e11a5e8ed56157b6d6"},"schema_version":"1.0"},"canonical_sha256":"3efe834ef482063bde65db39017372e15aa7cc3e2e58cc62f1ca71f1e1629ced","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:34.142342Z","signature_b64":"AuVF5lvE8BzaNIB5LATvoQiPDbg+DPSeNhxiafCfZLLcHpQtohfb5F3YgZKCJbdeKFVJoLIYW4jJE3Q7ezXVBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3efe834ef482063bde65db39017372e15aa7cc3e2e58cc62f1ca71f1e1629ced","last_reissued_at":"2026-07-05T11:16:34.141762Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:34.141762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.07608","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:16:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QPz9g/ap+WV2izcEIHzWD13P4mN5xsVIDjWN1MMhJS4eNIjS3RsqJZMENpYkowGXtOIlX7oUDxbo1mt4fsXjBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:41:49.128988Z"},"content_sha256":"99945616fde33c4e332c1924e0ec171c23ef05c2bc3d4f1403ff64aae7861cde","schema_version":"1.0","event_id":"sha256:99945616fde33c4e332c1924e0ec171c23ef05c2bc3d4f1403ff64aae7861cde"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:H37IGTXUQIDDXXTF3M4QC43S4F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Shen, Bowen Ye, Can Cai, Chenhong He, Cici, Dawei Zhu, Di Zhang, Dong Zhang, Duo Zhang, Gang Wang, Guoan Wang, Hailin Zhang, Haochen Zhao, Hao Tian, Heng Qu, Hongshen Xu, Huaqiu Liu, Jiebao Xiao, Jinhao Dong, Jun Shi, Kai Fang, Kainan Bao, Kangyang Zhou, Kang Zhou, Lei Li, Liang Zhao, LLM-Core Xiaomi: Bingquan Xia, Menghang Zhu, Nuo Chen, Peidian Li, Peng Wang, Qiantong Wang, Shaohui Liu, Shicheng Li, Shihua Yu, Shimao Chen, Shuhao Gu, Shuhuai Ren, Shuo Liu, Sirui Deng, Weiji Zhuang, Weikun Wang, Weiwei Lv, Wenhan Ma, Wenyu Yang, Xiangwei Deng, 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, Zhenru Lin, Zhichao Song, Zihan Jiang, Zihao Yue","submitted_at":"2025-05-12T14:30:11Z","abstract_excerpt":"We present MiMo-7B, a large language model born for reasoning tasks, with optimization across both pre-training and post-training stages. During pre-training, we enhance the data preprocessing pipeline and employ a three-stage data mixing strategy to strengthen the base model's reasoning potential. MiMo-7B-Base is pre-trained on 25 trillion tokens, with additional Multi-Token Prediction objective for enhanced performance and accelerated inference speed. During post-training, we curate a dataset of 130K verifiable mathematics and programming problems for reinforcement learning, integrating a te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07608","kind":"arxiv","version":2},"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/2505.07608/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":"2026-07-05T11:16:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B6x1mqzV3BQjDQa8AALUJDEF7FuihZFnOAJmHJNimAmBABA+NRL+FS3uUpbFBfMYlEFVDuVhVMTAc08gyq4IDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:41:49.129675Z"},"content_sha256":"51cec69dcbb14cc454e3ea8a13162eca75b5b70bd9aee6601cb62cf78f74cd49","schema_version":"1.0","event_id":"sha256:51cec69dcbb14cc454e3ea8a13162eca75b5b70bd9aee6601cb62cf78f74cd49"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H37IGTXUQIDDXXTF3M4QC43S4F/bundle.json","state_url":"https://pith.science/pith/H37IGTXUQIDDXXTF3M4QC43S4F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H37IGTXUQIDDXXTF3M4QC43S4F/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":"2026-08-04T20:41:49Z","links":{"resolver":"https://pith.science/pith/H37IGTXUQIDDXXTF3M4QC43S4F","bundle":"https://pith.science/pith/H37IGTXUQIDDXXTF3M4QC43S4F/bundle.json","state":"https://pith.science/pith/H37IGTXUQIDDXXTF3M4QC43S4F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H37IGTXUQIDDXXTF3M4QC43S4F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H37IGTXUQIDDXXTF3M4QC43S4F","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":"4c41f96e17f9aaf831445ae95eefabd4ae6e75dc8d9490e11a5e8ed56157b6d6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T14:30:11Z","title_canon_sha256":"4e3320ae491ed6c4a6540aef866bd8cc583bb0b7a6a5e673b9e2a3e0bc20ac1f"},"schema_version":"1.0","source":{"id":"2505.07608","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07608","created_at":"2026-07-05T11:16:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07608v2","created_at":"2026-07-05T11:16:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07608","created_at":"2026-07-05T11:16:34Z"},{"alias_kind":"pith_short_12","alias_value":"H37IGTXUQIDD","created_at":"2026-07-05T11:16:34Z"},{"alias_kind":"pith_short_16","alias_value":"H37IGTXUQIDDXXTF","created_at":"2026-07-05T11:16:34Z"},{"alias_kind":"pith_short_8","alias_value":"H37IGTXU","created_at":"2026-07-05T11:16:34Z"}],"graph_snapshots":[{"event_id":"sha256:51cec69dcbb14cc454e3ea8a13162eca75b5b70bd9aee6601cb62cf78f74cd49","target":"graph","created_at":"2026-07-05T11:16:34Z","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/2505.07608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present MiMo-7B, a large language model born for reasoning tasks, with optimization across both pre-training and post-training stages. During pre-training, we enhance the data preprocessing pipeline and employ a three-stage data mixing strategy to strengthen the base model's reasoning potential. MiMo-7B-Base is pre-trained on 25 trillion tokens, with additional Multi-Token Prediction objective for enhanced performance and accelerated inference speed. During post-training, we curate a dataset of 130K verifiable mathematics and programming problems for reinforcement learning, integrating a te","authors_text":"Bowen Shen, Bowen Ye, Can Cai, Chenhong He, Cici, Dawei Zhu, Di Zhang, Dong Zhang, Duo Zhang, Gang Wang, Guoan Wang, Hailin Zhang, Haochen Zhao, Hao Tian, Heng Qu, Hongshen Xu, Huaqiu Liu, Jiebao Xiao, Jinhao Dong, Jun Shi, Kai Fang, Kainan Bao, Kangyang Zhou, Kang Zhou, Lei Li, Liang Zhao, LLM-Core Xiaomi: Bingquan Xia, Menghang Zhu, Nuo Chen, Peidian Li, Peng Wang, Qiantong Wang, Shaohui Liu, Shicheng Li, Shihua Yu, Shimao Chen, Shuhao Gu, Shuhuai Ren, Shuo Liu, Sirui Deng, Weiji Zhuang, Weikun Wang, Weiwei Lv, Wenhan Ma, Wenyu Yang, Xiangwei Deng, 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, Zhenru Lin, Zhichao Song, Zihan Jiang, Zihao Yue","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T14:30:11Z","title":"MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07608","kind":"arxiv","version":2},"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":"sha256:99945616fde33c4e332c1924e0ec171c23ef05c2bc3d4f1403ff64aae7861cde","target":"record","created_at":"2026-07-05T11:16:34Z","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":"4c41f96e17f9aaf831445ae95eefabd4ae6e75dc8d9490e11a5e8ed56157b6d6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-12T14:30:11Z","title_canon_sha256":"4e3320ae491ed6c4a6540aef866bd8cc583bb0b7a6a5e673b9e2a3e0bc20ac1f"},"schema_version":"1.0","source":{"id":"2505.07608","kind":"arxiv","version":2}},"canonical_sha256":"3efe834ef482063bde65db39017372e15aa7cc3e2e58cc62f1ca71f1e1629ced","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3efe834ef482063bde65db39017372e15aa7cc3e2e58cc62f1ca71f1e1629ced","first_computed_at":"2026-07-05T11:16:34.141762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:34.141762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AuVF5lvE8BzaNIB5LATvoQiPDbg+DPSeNhxiafCfZLLcHpQtohfb5F3YgZKCJbdeKFVJoLIYW4jJE3Q7ezXVBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:34.142342Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07608","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99945616fde33c4e332c1924e0ec171c23ef05c2bc3d4f1403ff64aae7861cde","sha256:51cec69dcbb14cc454e3ea8a13162eca75b5b70bd9aee6601cb62cf78f74cd49"],"state_sha256":"49b945abae53e461d361ab3c8fe8a5fd69227a075c772d1516238b8b4385a74e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bQCX3FzGpA3UQ0JlKhKIyh/s/Tljki03e7/YGDF4IpQA6gT0bN7xaRhYajxc1e+W6Fup/HGacH82wMAxdaGICg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:41:49.135148Z","bundle_sha256":"d7c01f2b6ca6c9867411c5a0324858ab5aa23fadeae50fd106cb324bb2175666"}}