{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PIZHHPHORGFEETEGEWLLIMEVME","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":"98c000df40625c5b76bc9c702da9698c984cb30b0014dad8a942af0605ab5132","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-16T17:15:39Z","title_canon_sha256":"22cc2be6349b176ca112b92cdd8725cc56f6a5b76fe10a14d8b581cdc03f7b72"},"schema_version":"1.0","source":{"id":"2508.12109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12109","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12109v1","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12109","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"pith_short_12","alias_value":"PIZHHPHORGFE","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"pith_short_16","alias_value":"PIZHHPHORGFEETEG","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"pith_short_8","alias_value":"PIZHHPHO","created_at":"2026-07-05T11:55:00Z"}],"graph_snapshots":[{"event_id":"sha256:69fb12c4f3a346c2c9e84a503b8032adbbf7ac81bbbff548da9c9818e60f279d","target":"graph","created_at":"2026-07-05T11:55:00Z","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/2508.12109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have shown impressive performance on vision-language tasks, but their long Chain-of-Thought (CoT) capabilities in multimodal scenarios remain underexplored. Inspired by OpenAI's o3 model, which emulates human-like ''thinking with image'' through iterative visual transformations and linguistic reasoning, we propose Simple o3, an end-to-end framework that integrates dynamic tool interactions (e.g., cropping, zooming, and reusing) into interleaved vision-language reasoning via supervised fine-tuning (SFT). Our approach features a scalable data synthesis pi","authors_text":"Qianglong Chen, Shijie Guo, Siyuan Wang, Ye Wang, Zejun Li, Zhirui Zhang, Zhongyu Wei","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-16T17:15:39Z","title":"Simple o3: Towards Interleaved Vision-Language Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12109","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":"sha256:7009b9c987c4a46beb5c0a2bba5deeea2c1cf7e7fe32c0dba4e1e573de6e57d5","target":"record","created_at":"2026-07-05T11:55:00Z","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":"98c000df40625c5b76bc9c702da9698c984cb30b0014dad8a942af0605ab5132","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-16T17:15:39Z","title_canon_sha256":"22cc2be6349b176ca112b92cdd8725cc56f6a5b76fe10a14d8b581cdc03f7b72"},"schema_version":"1.0","source":{"id":"2508.12109","kind":"arxiv","version":1}},"canonical_sha256":"7a3273bcee898a424c862596b4309561249e72deb4c5565ffd228828802487ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a3273bcee898a424c862596b4309561249e72deb4c5565ffd228828802487ce","first_computed_at":"2026-07-05T11:55:00.245232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:00.245232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Og7Y89/YhkU6dCzJ+kNuTt8mohxqyFdfymrdd1BD7YwyPdlpWWOudv0Y/gyRkxiIEptX0gjnmC4a+9+RdrTdAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:00.245705Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.12109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7009b9c987c4a46beb5c0a2bba5deeea2c1cf7e7fe32c0dba4e1e573de6e57d5","sha256:69fb12c4f3a346c2c9e84a503b8032adbbf7ac81bbbff548da9c9818e60f279d"],"state_sha256":"cb161c367c71a972faf7c6eb068cb4737aaa9eef8160402432aa13ecc7477b9c"}