{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MGYOWXK3KQGT74MWRCLQOCEWJF","short_pith_number":"pith:MGYOWXK3","canonical_record":{"source":{"id":"2501.05452","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T18:59:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"444cb463d8d990ea2be44d53e18a88d96021922cc2af1ce484500e607fc0484e","abstract_canon_sha256":"a7667624c3aad63dd8dc710b428b7bde1306bed49dd19023c08fa0a269a92414"},"schema_version":"1.0"},"canonical_sha256":"61b0eb5d5b540d3ff19688970708964946ad17b80baf81924c41e63ca8cfc2e1","source":{"kind":"arxiv","id":"2501.05452","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05452","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05452v1","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05452","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"MGYOWXK3KQGT","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"MGYOWXK3KQGT74MW","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"MGYOWXK3","created_at":"2026-07-05T09:59:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MGYOWXK3KQGT74MWRCLQOCEWJF","target":"record","payload":{"canonical_record":{"source":{"id":"2501.05452","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T18:59:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"444cb463d8d990ea2be44d53e18a88d96021922cc2af1ce484500e607fc0484e","abstract_canon_sha256":"a7667624c3aad63dd8dc710b428b7bde1306bed49dd19023c08fa0a269a92414"},"schema_version":"1.0"},"canonical_sha256":"61b0eb5d5b540d3ff19688970708964946ad17b80baf81924c41e63ca8cfc2e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:10.081388Z","signature_b64":"6Q4BWO8zmEbnxowt5M9if5UxpLAE67J1iCj+NahNqUhZLbfMQFN6aTTRMpGtvhFXkmQACoo+7Ni/PB08SslcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61b0eb5d5b540d3ff19688970708964946ad17b80baf81924c41e63ca8cfc2e1","last_reissued_at":"2026-07-05T09:59:10.080889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:10.080889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.05452","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":"2026-07-05T09:59:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"snNI+OCqGsJo5AgXy1Ks4d+OCC2bt1bEy0piU33R2ngiAYfM1pDTK+wxTqJOhu9k4m9Sw76c4NMVqVNtUn5zCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:15:14.977481Z"},"content_sha256":"7e5218d20031b3c85039db35f463e983c0ccfb31762bd45c9902f6db1374600e","schema_version":"1.0","event_id":"sha256:7e5218d20031b3c85039db35f463e983c0ccfb31762bd45c9902f6db1374600e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MGYOWXK3KQGT74MWRCLQOCEWJF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Cha Zhang, Dan Roth, Dinei Florencio, Jianwei Yang, John Corring, Minqian Liu, Xingyu Fu, Yijuan Lu, Zhengyuan Yang","submitted_at":"2025-01-09T18:59:58Z","abstract_excerpt":"Structured image understanding, such as interpreting tables and charts, requires strategically refocusing across various structures and texts within an image, forming a reasoning sequence to arrive at the final answer. However, current multimodal large language models (LLMs) lack this multihop selective attention capability. In this work, we introduce ReFocus, a simple yet effective framework that equips multimodal LLMs with the ability to generate \"visual thoughts\" by performing visual editing on the input image through code, shifting and refining their visual focuses. Specifically, ReFocus e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05452","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/2501.05452/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":"2026-07-05T09:59:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j1kqKCabxh0L1ucqfHT8KQodWVkSjJzJhhXMZB9AXYvgrQwoiaphl4IB69JqjYcZfLGEsPBjVdTqAeNFNYpSDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T06:15:14.977821Z"},"content_sha256":"474b8726f2c64ce198e8f08692231cb0acbd70b8bc5590960059a2b1b0707a21","schema_version":"1.0","event_id":"sha256:474b8726f2c64ce198e8f08692231cb0acbd70b8bc5590960059a2b1b0707a21"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MGYOWXK3KQGT74MWRCLQOCEWJF/bundle.json","state_url":"https://pith.science/pith/MGYOWXK3KQGT74MWRCLQOCEWJF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MGYOWXK3KQGT74MWRCLQOCEWJF/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":"2026-08-05T06:15:14Z","links":{"resolver":"https://pith.science/pith/MGYOWXK3KQGT74MWRCLQOCEWJF","bundle":"https://pith.science/pith/MGYOWXK3KQGT74MWRCLQOCEWJF/bundle.json","state":"https://pith.science/pith/MGYOWXK3KQGT74MWRCLQOCEWJF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MGYOWXK3KQGT74MWRCLQOCEWJF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MGYOWXK3KQGT74MWRCLQOCEWJF","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":"a7667624c3aad63dd8dc710b428b7bde1306bed49dd19023c08fa0a269a92414","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T18:59:58Z","title_canon_sha256":"444cb463d8d990ea2be44d53e18a88d96021922cc2af1ce484500e607fc0484e"},"schema_version":"1.0","source":{"id":"2501.05452","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.05452","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"arxiv_version","alias_value":"2501.05452v1","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05452","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"pith_short_12","alias_value":"MGYOWXK3KQGT","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"pith_short_16","alias_value":"MGYOWXK3KQGT74MW","created_at":"2026-07-05T09:59:10Z"},{"alias_kind":"pith_short_8","alias_value":"MGYOWXK3","created_at":"2026-07-05T09:59:10Z"}],"graph_snapshots":[{"event_id":"sha256:474b8726f2c64ce198e8f08692231cb0acbd70b8bc5590960059a2b1b0707a21","target":"graph","created_at":"2026-07-05T09:59:10Z","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/2501.05452/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Structured image understanding, such as interpreting tables and charts, requires strategically refocusing across various structures and texts within an image, forming a reasoning sequence to arrive at the final answer. However, current multimodal large language models (LLMs) lack this multihop selective attention capability. In this work, we introduce ReFocus, a simple yet effective framework that equips multimodal LLMs with the ability to generate \"visual thoughts\" by performing visual editing on the input image through code, shifting and refining their visual focuses. Specifically, ReFocus e","authors_text":"Cha Zhang, Dan Roth, Dinei Florencio, Jianwei Yang, John Corring, Minqian Liu, Xingyu Fu, Yijuan Lu, Zhengyuan Yang","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T18:59:58Z","title":"ReFocus: Visual Editing as a Chain of Thought for Structured Image Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05452","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":"sha256:7e5218d20031b3c85039db35f463e983c0ccfb31762bd45c9902f6db1374600e","target":"record","created_at":"2026-07-05T09:59:10Z","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":"a7667624c3aad63dd8dc710b428b7bde1306bed49dd19023c08fa0a269a92414","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-09T18:59:58Z","title_canon_sha256":"444cb463d8d990ea2be44d53e18a88d96021922cc2af1ce484500e607fc0484e"},"schema_version":"1.0","source":{"id":"2501.05452","kind":"arxiv","version":1}},"canonical_sha256":"61b0eb5d5b540d3ff19688970708964946ad17b80baf81924c41e63ca8cfc2e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61b0eb5d5b540d3ff19688970708964946ad17b80baf81924c41e63ca8cfc2e1","first_computed_at":"2026-07-05T09:59:10.080889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:10.080889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6Q4BWO8zmEbnxowt5M9if5UxpLAE67J1iCj+NahNqUhZLbfMQFN6aTTRMpGtvhFXkmQACoo+7Ni/PB08SslcCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:10.081388Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.05452","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e5218d20031b3c85039db35f463e983c0ccfb31762bd45c9902f6db1374600e","sha256:474b8726f2c64ce198e8f08692231cb0acbd70b8bc5590960059a2b1b0707a21"],"state_sha256":"349db6653ae675877ae7f548651cd9870f55119df129155359fb1587f56ede0e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"me83zpR21wMHW9sgXY4F7vBmCBK81M4OoMMqQM93fkB/GMvx9rPA/tR+n58CPkfRMYfnRvQYb4roDErw/syVAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T06:15:14.981390Z","bundle_sha256":"b0709eeb467c521ab8880ba62916115a593802eb14c4550c4ae8e6895f1cd360"}}