{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NGQGVISHEUGLHCFXJU4WYWMCX7","short_pith_number":"pith:NGQGVISH","canonical_record":{"source":{"id":"2508.11737","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-15T17:01:08Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"fc99a4c0a3021fc73f0bfa752295498c9fc389733691ba767bc28f3dddb295dc","abstract_canon_sha256":"a1d9b04e4e2d7624437f702c0157551661eccfa59b8bfbd4cd315543c7e0a673"},"schema_version":"1.0"},"canonical_sha256":"69a06aa247250cb388b74d396c5982bff1897a4b4e5fcd96726618264aa54fdd","source":{"kind":"arxiv","id":"2508.11737","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.11737","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.11737v1","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11737","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"NGQGVISHEUGL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NGQGVISHEUGLHCFX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NGQGVISH","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NGQGVISHEUGLHCFXJU4WYWMCX7","target":"record","payload":{"canonical_record":{"source":{"id":"2508.11737","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-15T17:01:08Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"fc99a4c0a3021fc73f0bfa752295498c9fc389733691ba767bc28f3dddb295dc","abstract_canon_sha256":"a1d9b04e4e2d7624437f702c0157551661eccfa59b8bfbd4cd315543c7e0a673"},"schema_version":"1.0"},"canonical_sha256":"69a06aa247250cb388b74d396c5982bff1897a4b4e5fcd96726618264aa54fdd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:50.261104Z","signature_b64":"BH44xFBRr8BJV1yY7M5Y5yUMAaJBeWip+JwTVEIUfN+AMmgD6D/xCtqMqvwqmOK6qxIExlWZrsQfHe+Unr9IBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69a06aa247250cb388b74d396c5982bff1897a4b4e5fcd96726618264aa54fdd","last_reissued_at":"2026-05-17T23:38:50.260604Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:50.260604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.11737","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":"2026-05-17T23:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ihRYF7WgAqsI7g+JsXUFLKHBWz27MxhVAEuNmFGZwpqTzhpCo4xPzVizLORUPbsDbstQAHqlaPWpFT9w/Y1/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:45:41.111138Z"},"content_sha256":"06998697d05b02e0203eef19e31904af03d995868b9edd2370d422e689a5bedb","schema_version":"1.0","event_id":"sha256:06998697d05b02e0203eef19e31904af03d995868b9edd2370d422e689a5bedb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NGQGVISHEUGLHCFXJU4WYWMCX7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ovis2.5 Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Ovis2.5 processes images at native resolutions and adds reflection to reach 78.3 on the OpenCompass multimodal leaderboard.","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chengkun Hou, Gui Hu, Guodong Zheng, Haijun Li, Hailong Sun, Hui Sun, Huping Ding, Jiahe Li, Jiamang Wang, Jianshan Zhao, Jinlong Huang, Junke Tang, Junpeng Jiang, Kaifu Zhang, Lunhao Duan, Qing-Guo Chen, Sensen Gao, Shanshan Zhao, Shengze Shi, Shiyin Lu, Sijia Chen, Siran Yang, Tianli Zhou, Wanying Chen, Weihong Zhang, Weihua Luo, Wenjie Zhang, Wen Li, Yang Li, Yanqing Ma, Yibo Wang, Yi-Feng Wu, Yiliang Gu, Yinglun Li, Yuhui Chen, Yuping He, Yuwei Hu, Yu Xia, Yuxuan Han, Zhao Xu, Zhichao Wei, Zhixing Du","submitted_at":"2025-08-15T17:01:08Z","abstract_excerpt":"We present Ovis2.5, a successor to Ovis2 designed for native-resolution visual perception and strong multimodal reasoning. Ovis2.5 integrates a native-resolution vision transformer that processes images at their native, variable resolutions, avoiding the degradation from fixed-resolution tiling and preserving both fine detail and global layout -- crucial for visually dense content like complex charts. To strengthen reasoning, we train the model to move beyond linear chain-of-thought and perform reflection -- including self-checking and revision. This advanced capability is exposed as an option"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Ovis2.5-9B averages 78.3 on the OpenCompass multimodal leaderboard, marking a substantial improvement over Ovis2-8B and achieving state-of-the-art results among open-source MLLMs in the sub-40B parameter range; Ovis2.5-2B scores 73.9 and establishes SOTA for its size.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the benchmark gains are primarily attributable to the native-resolution vision transformer and reflection mechanism rather than differences in training data volume, quality, or undisclosed hyperparameter tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Ovis2.5 introduces native-resolution visual processing and reflective chain-of-thought to reach SOTA open-source multimodal performance at 9B and 2B scales on benchmarks including STEM and chart analysis.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Ovis2.5 processes images at native resolutions and adds reflection to reach 78.3 on the OpenCompass multimodal leaderboard.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"029ca85268d2631dd753927534197d93120c6c21e5a65dbd302549e645fd12b6"},"source":{"id":"2508.11737","kind":"arxiv","version":1},"verdict":{"id":"1e22e58d-8d9e-4e92-adf4-b846d1e2e62f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T20:26:58.365351Z","strongest_claim":"Ovis2.5-9B averages 78.3 on the OpenCompass multimodal leaderboard, marking a substantial improvement over Ovis2-8B and achieving state-of-the-art results among open-source MLLMs in the sub-40B parameter range; Ovis2.5-2B scores 73.9 and establishes SOTA for its size.","one_line_summary":"Ovis2.5 introduces native-resolution visual processing and reflective chain-of-thought to reach SOTA open-source multimodal performance at 9B and 2B scales on benchmarks including STEM and chart analysis.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the benchmark gains are primarily attributable to the native-resolution vision transformer and reflection mechanism rather than differences in training data volume, quality, or undisclosed hyperparameter tuning.","pith_extraction_headline":"Ovis2.5 processes images at native resolutions and adds reflection to reach 78.3 on the OpenCompass multimodal leaderboard."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":3,"snapshot_sha256":"45b54bf26d5059f82d62f62629fcdcc84b42ec1e97721d442abfd3fa458cc41b"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"1e22e58d-8d9e-4e92-adf4-b846d1e2e62f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kg0JO1eLiJKSJPG6BjT7OkOkZCFk3ulptnEGT9gJ0upIYGWFvY7BsvAwE9xSaEemndedf97fsvztJGVR0hOaBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:45:41.111608Z"},"content_sha256":"2714fb3cc1d71c2c0f3b7c3168599147af7090cb6f0a38fcaa718a5632fc798f","schema_version":"1.0","event_id":"sha256:2714fb3cc1d71c2c0f3b7c3168599147af7090cb6f0a38fcaa718a5632fc798f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NGQGVISHEUGLHCFXJU4WYWMCX7/bundle.json","state_url":"https://pith.science/pith/NGQGVISHEUGLHCFXJU4WYWMCX7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NGQGVISHEUGLHCFXJU4WYWMCX7/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":"2026-05-30T13:45:41Z","links":{"resolver":"https://pith.science/pith/NGQGVISHEUGLHCFXJU4WYWMCX7","bundle":"https://pith.science/pith/NGQGVISHEUGLHCFXJU4WYWMCX7/bundle.json","state":"https://pith.science/pith/NGQGVISHEUGLHCFXJU4WYWMCX7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NGQGVISHEUGLHCFXJU4WYWMCX7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NGQGVISHEUGLHCFXJU4WYWMCX7","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":"a1d9b04e4e2d7624437f702c0157551661eccfa59b8bfbd4cd315543c7e0a673","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-15T17:01:08Z","title_canon_sha256":"fc99a4c0a3021fc73f0bfa752295498c9fc389733691ba767bc28f3dddb295dc"},"schema_version":"1.0","source":{"id":"2508.11737","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.11737","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"arxiv_version","alias_value":"2508.11737v1","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11737","created_at":"2026-05-17T23:38:50Z"},{"alias_kind":"pith_short_12","alias_value":"NGQGVISHEUGL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"NGQGVISHEUGLHCFX","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"NGQGVISH","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:2714fb3cc1d71c2c0f3b7c3168599147af7090cb6f0a38fcaa718a5632fc798f","target":"graph","created_at":"2026-05-17T23:38:50Z","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":"Ovis2.5-9B averages 78.3 on the OpenCompass multimodal leaderboard, marking a substantial improvement over Ovis2-8B and achieving state-of-the-art results among open-source MLLMs in the sub-40B parameter range; Ovis2.5-2B scores 73.9 and establishes SOTA for its size."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the benchmark gains are primarily attributable to the native-resolution vision transformer and reflection mechanism rather than differences in training data volume, quality, or undisclosed hyperparameter tuning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Ovis2.5 introduces native-resolution visual processing and reflective chain-of-thought to reach SOTA open-source multimodal performance at 9B and 2B scales on benchmarks including STEM and chart analysis."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Ovis2.5 processes images at native resolutions and adds reflection to reach 78.3 on the OpenCompass multimodal leaderboard."}],"snapshot_sha256":"029ca85268d2631dd753927534197d93120c6c21e5a65dbd302549e645fd12b6"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"45b54bf26d5059f82d62f62629fcdcc84b42ec1e97721d442abfd3fa458cc41b"},"paper":{"abstract_excerpt":"We present Ovis2.5, a successor to Ovis2 designed for native-resolution visual perception and strong multimodal reasoning. Ovis2.5 integrates a native-resolution vision transformer that processes images at their native, variable resolutions, avoiding the degradation from fixed-resolution tiling and preserving both fine detail and global layout -- crucial for visually dense content like complex charts. To strengthen reasoning, we train the model to move beyond linear chain-of-thought and perform reflection -- including self-checking and revision. This advanced capability is exposed as an option","authors_text":"Chengkun Hou, Gui Hu, Guodong Zheng, Haijun Li, Hailong Sun, Hui Sun, Huping Ding, Jiahe Li, Jiamang Wang, Jianshan Zhao, Jinlong Huang, Junke Tang, Junpeng Jiang, Kaifu Zhang, Lunhao Duan, Qing-Guo Chen, Sensen Gao, Shanshan Zhao, Shengze Shi, Shiyin Lu, Sijia Chen, Siran Yang, Tianli Zhou, Wanying Chen, Weihong Zhang, Weihua Luo, Wenjie Zhang, Wen Li, Yang Li, Yanqing Ma, Yibo Wang, Yi-Feng Wu, Yiliang Gu, Yinglun Li, Yuhui Chen, Yuping He, Yuwei Hu, Yu Xia, Yuxuan Han, Zhao Xu, Zhichao Wei, Zhixing Du","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"Ovis2.5 processes images at native resolutions and adds reflection to reach 78.3 on the OpenCompass multimodal leaderboard.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-15T17:01:08Z","title":"Ovis2.5 Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11737","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T20:26:58.365351Z","id":"1e22e58d-8d9e-4e92-adf4-b846d1e2e62f","model_set":{"reader":"grok-4.3"},"one_line_summary":"Ovis2.5 introduces native-resolution visual processing and reflective chain-of-thought to reach SOTA open-source multimodal performance at 9B and 2B scales on benchmarks including STEM and chart analysis.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Ovis2.5 processes images at native resolutions and adds reflection to reach 78.3 on the OpenCompass multimodal leaderboard.","strongest_claim":"Ovis2.5-9B averages 78.3 on the OpenCompass multimodal leaderboard, marking a substantial improvement over Ovis2-8B and achieving state-of-the-art results among open-source MLLMs in the sub-40B parameter range; Ovis2.5-2B scores 73.9 and establishes SOTA for its size.","weakest_assumption":"That the benchmark gains are primarily attributable to the native-resolution vision transformer and reflection mechanism rather than differences in training data volume, quality, or undisclosed hyperparameter tuning."}},"verdict_id":"1e22e58d-8d9e-4e92-adf4-b846d1e2e62f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:06998697d05b02e0203eef19e31904af03d995868b9edd2370d422e689a5bedb","target":"record","created_at":"2026-05-17T23:38:50Z","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":"a1d9b04e4e2d7624437f702c0157551661eccfa59b8bfbd4cd315543c7e0a673","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-15T17:01:08Z","title_canon_sha256":"fc99a4c0a3021fc73f0bfa752295498c9fc389733691ba767bc28f3dddb295dc"},"schema_version":"1.0","source":{"id":"2508.11737","kind":"arxiv","version":1}},"canonical_sha256":"69a06aa247250cb388b74d396c5982bff1897a4b4e5fcd96726618264aa54fdd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69a06aa247250cb388b74d396c5982bff1897a4b4e5fcd96726618264aa54fdd","first_computed_at":"2026-05-17T23:38:50.260604Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:50.260604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BH44xFBRr8BJV1yY7M5Y5yUMAaJBeWip+JwTVEIUfN+AMmgD6D/xCtqMqvwqmOK6qxIExlWZrsQfHe+Unr9IBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:50.261104Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.11737","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06998697d05b02e0203eef19e31904af03d995868b9edd2370d422e689a5bedb","sha256:2714fb3cc1d71c2c0f3b7c3168599147af7090cb6f0a38fcaa718a5632fc798f"],"state_sha256":"776e8b1aafa4ff786d0eb5f8e2eac5d396a33643f1dd0cd5e6d4cb9164ebccc3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fW/nTcK7zW416TSS1VuCcz+vOgOlXkZYXRvuaEbOCTKRoFe4lRoZGzbvDFy64LaJ5HTDIa0527bjXH39nkUqDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T13:45:41.113961Z","bundle_sha256":"5716bf0edda72dd75f1be5bcc26946531f723b9af7873dfc7195f26ee319c7d6"}}