{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KNAXNP4DATVWOBVCIWLLFHLQXY","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":"f51fe2f7f9702e80715630f79c52acb10cf134ec8350fbcef938712de7aa4639","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T05:50:25Z","title_canon_sha256":"ba0f60f9e2942fdcf87709c72ed8ce9f5e8ccdae9a0d10b335fef9a317b5ba07"},"schema_version":"1.0","source":{"id":"2505.20753","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20753","created_at":"2026-07-05T11:10:18Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20753v1","created_at":"2026-07-05T11:10:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20753","created_at":"2026-07-05T11:10:18Z"},{"alias_kind":"pith_short_12","alias_value":"KNAXNP4DATVW","created_at":"2026-07-05T11:10:18Z"},{"alias_kind":"pith_short_16","alias_value":"KNAXNP4DATVWOBVC","created_at":"2026-07-05T11:10:18Z"},{"alias_kind":"pith_short_8","alias_value":"KNAXNP4D","created_at":"2026-07-05T11:10:18Z"}],"graph_snapshots":[{"event_id":"sha256:5d855f558bc2ff4d95b39e93b9956fbd533285253d1b105398f98b861cd2aa4a","target":"graph","created_at":"2026-07-05T11:10:18Z","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/2505.20753/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Multimodal Models (LMMs) have recently demonstrated remarkable visual understanding performance on both vision-language and vision-centric tasks. However, they often fall short in integrating advanced, task-specific capabilities for compositional reasoning, which hinders their progress toward truly competent general vision models. To address this, we present a unified visual reasoning mechanism that enables LMMs to solve complicated compositional problems by leveraging their intrinsic capabilities (e.g. grounding and visual understanding capabilities). Different from the previous shortcu","authors_text":"Fan Yang, Hongyin Zhao, Jinqiao Wang, Ming Tang, Shurong Zheng, Yousong Zhu, Yufei Zhan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T05:50:25Z","title":"Understand, Think, and Answer: Advancing Visual Reasoning with Large Multimodal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20753","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":"sha256:5e904c07f52b901b2df1aa56d764600eaa866f07bb977efee56e9dcfbc1fc9b6","target":"record","created_at":"2026-07-05T11:10:18Z","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":"f51fe2f7f9702e80715630f79c52acb10cf134ec8350fbcef938712de7aa4639","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T05:50:25Z","title_canon_sha256":"ba0f60f9e2942fdcf87709c72ed8ce9f5e8ccdae9a0d10b335fef9a317b5ba07"},"schema_version":"1.0","source":{"id":"2505.20753","kind":"arxiv","version":1}},"canonical_sha256":"534176bf8304eb6706a24596b29d70be16483ef5a07a5b3f3d59a17785d163b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"534176bf8304eb6706a24596b29d70be16483ef5a07a5b3f3d59a17785d163b7","first_computed_at":"2026-07-05T11:10:18.009303Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:18.009303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yUTG++LQOA7edkv0t1gKmXz+b7kE/Q+7jaxa+IagtbZcBzr67ZcRxzAgN1M43SP0KMV8PXu8dKYfaFGydNxqDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:18.009744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20753","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e904c07f52b901b2df1aa56d764600eaa866f07bb977efee56e9dcfbc1fc9b6","sha256:5d855f558bc2ff4d95b39e93b9956fbd533285253d1b105398f98b861cd2aa4a"],"state_sha256":"97cc6361a58bab60a989f336a2d9c756a90f633ea78ad8e47bbc706d6955b095"}