{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:A5JWW6FMXC54LM2AV6HM2QX2RO","short_pith_number":"pith:A5JWW6FM","canonical_record":{"source":{"id":"2504.18397","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T14:48:18Z","cross_cats_sorted":[],"title_canon_sha256":"a960bf62eeef491db75a061d5c1e7c77b1f47167d035db84307d99ea56dab309","abstract_canon_sha256":"39dc8e5531a6a398c1215ccc246f9236fe8a642e9f0f7cee39f1dcfa8945865a"},"schema_version":"1.0"},"canonical_sha256":"07536b78acb8bbc5b340af8ecd42fa8b8605ae8d7ab466166579cb34327169ce","source":{"kind":"arxiv","id":"2504.18397","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18397","created_at":"2026-07-05T11:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18397v2","created_at":"2026-07-05T11:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18397","created_at":"2026-07-05T11:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"A5JWW6FMXC54","created_at":"2026-07-05T11:37:18Z"},{"alias_kind":"pith_short_16","alias_value":"A5JWW6FMXC54LM2A","created_at":"2026-07-05T11:37:18Z"},{"alias_kind":"pith_short_8","alias_value":"A5JWW6FM","created_at":"2026-07-05T11:37:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:A5JWW6FMXC54LM2AV6HM2QX2RO","target":"record","payload":{"canonical_record":{"source":{"id":"2504.18397","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T14:48:18Z","cross_cats_sorted":[],"title_canon_sha256":"a960bf62eeef491db75a061d5c1e7c77b1f47167d035db84307d99ea56dab309","abstract_canon_sha256":"39dc8e5531a6a398c1215ccc246f9236fe8a642e9f0f7cee39f1dcfa8945865a"},"schema_version":"1.0"},"canonical_sha256":"07536b78acb8bbc5b340af8ecd42fa8b8605ae8d7ab466166579cb34327169ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:18.862187Z","signature_b64":"m+wLMAMcpycx9412Z9CWb/C3+p5/b3xqVTFVcieHPO4C2BqcqI+4UmqD4Ous90CI0tJMPKr5+7+KVKhY952XAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07536b78acb8bbc5b340af8ecd42fa8b8605ae8d7ab466166579cb34327169ce","last_reissued_at":"2026-07-05T11:37:18.861697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:18.861697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.18397","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":"2026-07-05T11:37:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hn3d/JqO2d9DNbJOZkNRPy9letUTWE8UX2ubVEc6qX1zTpaqPogcSgmcMUPb73WrS7rJvAtfIQA2n4OS/KWlDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:36:12.189797Z"},"content_sha256":"109259ff8c1fc4d0d92260e18aa5861ad0869243a1c935b20614d2fc799ab0bd","schema_version":"1.0","event_id":"sha256:109259ff8c1fc4d0d92260e18aa5861ad0869243a1c935b20614d2fc799ab0bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:A5JWW6FMXC54LM2AV6HM2QX2RO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beier Zhu, Hanwang Zhang, Kesen Zhao, Qianru Sun","submitted_at":"2025-04-25T14:48:18Z","abstract_excerpt":"Chain-of-thought (CoT) reasoning greatly improves the interpretability and problem-solving abilities of multimodal large language models (MLLMs). However, existing approaches are focused on text CoT, limiting their ability to leverage visual cues. Visual CoT remains underexplored, and the only work is based on supervised fine-tuning (SFT) that relies on extensive labeled bounding-box data and is hard to generalize to unseen cases. In this paper, we introduce Unsupervised Visual CoT (UV-CoT), a novel framework for image-level CoT reasoning via preference optimization. UV-CoT performs preference"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18397","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/2504.18397/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":"2026-07-05T11:37:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4S0PcNIgwZoauXcVJWoCZtVcWwUA2cwx53X9Ib61iYf5M8i1zsYaBE8J5SBgn8HiFjb6Xnd9eLxQWyZy0GvzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:36:12.190526Z"},"content_sha256":"854d4489e789dc3537fbbdb883aa8717789e6585453a9ba3e70c9ef3e45aad41","schema_version":"1.0","event_id":"sha256:854d4489e789dc3537fbbdb883aa8717789e6585453a9ba3e70c9ef3e45aad41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A5JWW6FMXC54LM2AV6HM2QX2RO/bundle.json","state_url":"https://pith.science/pith/A5JWW6FMXC54LM2AV6HM2QX2RO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A5JWW6FMXC54LM2AV6HM2QX2RO/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":"2026-08-05T08:36:12Z","links":{"resolver":"https://pith.science/pith/A5JWW6FMXC54LM2AV6HM2QX2RO","bundle":"https://pith.science/pith/A5JWW6FMXC54LM2AV6HM2QX2RO/bundle.json","state":"https://pith.science/pith/A5JWW6FMXC54LM2AV6HM2QX2RO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A5JWW6FMXC54LM2AV6HM2QX2RO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:A5JWW6FMXC54LM2AV6HM2QX2RO","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":"39dc8e5531a6a398c1215ccc246f9236fe8a642e9f0f7cee39f1dcfa8945865a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T14:48:18Z","title_canon_sha256":"a960bf62eeef491db75a061d5c1e7c77b1f47167d035db84307d99ea56dab309"},"schema_version":"1.0","source":{"id":"2504.18397","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18397","created_at":"2026-07-05T11:37:18Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18397v2","created_at":"2026-07-05T11:37:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18397","created_at":"2026-07-05T11:37:18Z"},{"alias_kind":"pith_short_12","alias_value":"A5JWW6FMXC54","created_at":"2026-07-05T11:37:18Z"},{"alias_kind":"pith_short_16","alias_value":"A5JWW6FMXC54LM2A","created_at":"2026-07-05T11:37:18Z"},{"alias_kind":"pith_short_8","alias_value":"A5JWW6FM","created_at":"2026-07-05T11:37:18Z"}],"graph_snapshots":[{"event_id":"sha256:854d4489e789dc3537fbbdb883aa8717789e6585453a9ba3e70c9ef3e45aad41","target":"graph","created_at":"2026-07-05T11:37:18Z","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/2504.18397/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Chain-of-thought (CoT) reasoning greatly improves the interpretability and problem-solving abilities of multimodal large language models (MLLMs). However, existing approaches are focused on text CoT, limiting their ability to leverage visual cues. Visual CoT remains underexplored, and the only work is based on supervised fine-tuning (SFT) that relies on extensive labeled bounding-box data and is hard to generalize to unseen cases. In this paper, we introduce Unsupervised Visual CoT (UV-CoT), a novel framework for image-level CoT reasoning via preference optimization. UV-CoT performs preference","authors_text":"Beier Zhu, Hanwang Zhang, Kesen Zhao, Qianru Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T14:48:18Z","title":"Unsupervised Visual Chain-of-Thought Reasoning via Preference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18397","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":"sha256:109259ff8c1fc4d0d92260e18aa5861ad0869243a1c935b20614d2fc799ab0bd","target":"record","created_at":"2026-07-05T11:37:18Z","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":"39dc8e5531a6a398c1215ccc246f9236fe8a642e9f0f7cee39f1dcfa8945865a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T14:48:18Z","title_canon_sha256":"a960bf62eeef491db75a061d5c1e7c77b1f47167d035db84307d99ea56dab309"},"schema_version":"1.0","source":{"id":"2504.18397","kind":"arxiv","version":2}},"canonical_sha256":"07536b78acb8bbc5b340af8ecd42fa8b8605ae8d7ab466166579cb34327169ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07536b78acb8bbc5b340af8ecd42fa8b8605ae8d7ab466166579cb34327169ce","first_computed_at":"2026-07-05T11:37:18.861697Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:37:18.861697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m+wLMAMcpycx9412Z9CWb/C3+p5/b3xqVTFVcieHPO4C2BqcqI+4UmqD4Ous90CI0tJMPKr5+7+KVKhY952XAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:37:18.862187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.18397","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:109259ff8c1fc4d0d92260e18aa5861ad0869243a1c935b20614d2fc799ab0bd","sha256:854d4489e789dc3537fbbdb883aa8717789e6585453a9ba3e70c9ef3e45aad41"],"state_sha256":"f9f9ff090dfb7e90a02cafd7d919aeecd430254ebf6ff5c52f3634cab8f76b2c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7qoyyvcw+zGvjIzOK+l986Zih5ze6JUp88EP2HUh2CF9lDQYkBiLJp6iJMclKR1gFkiPeeOPAQ4jmGD3J/snDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:36:12.201091Z","bundle_sha256":"35df4ec7f79a847f0250491f64725cc6d220433681541865f20e41b2fbab8bdf"}}