{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FYBJD3J5YCMMKQXRCGXQGLAFB2","short_pith_number":"pith:FYBJD3J5","schema_version":"1.0","canonical_sha256":"2e0291ed3dc098c542f111af032c050e8cdb2275eb7026bf40eef21a0ae33278","source":{"kind":"arxiv","id":"2504.09130","version":1},"attestation_state":"computed","paper":{"title":"VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dacheng Tao, Liang Ding, Qinyuan Cheng, Qipeng Guo, Siyin Wang, Xipeng Qiu, Yikun Wang, Zhaoye Fei","submitted_at":"2025-04-12T08:37:30Z","abstract_excerpt":"Recent advancements in Large Vision-Language Models have showcased remarkable capabilities. However, they often falter when confronted with complex reasoning tasks that humans typically address through visual aids and deliberate, step-by-step thinking. While existing methods have explored text-based slow thinking or rudimentary visual assistance, they fall short of capturing the intricate, interleaved nature of human visual-verbal reasoning processes. To overcome these limitations and inspired by the mechanisms of slow thinking in human cognition, we introduce VisuoThink, a novel framework tha"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.09130","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-12T08:37:30Z","cross_cats_sorted":[],"title_canon_sha256":"b6c6bfe099d502756d5c1acc630a233960c62102f068c2dba67a1d24c54b589e","abstract_canon_sha256":"97587adf9487bbfc82aee3f3bfd43efee55c527de76ab853badafa9d77b7498e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:04.683556Z","signature_b64":"+pxQHIkAZiT1UmfkD7f01KQoG1UQ8q/vTsITpg7ue7k//0ABJ5Oe/kcdhbLAytT2jbGqegSAPrKO+f/5MZHtDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e0291ed3dc098c542f111af032c050e8cdb2275eb7026bf40eef21a0ae33278","last_reissued_at":"2026-07-05T10:48:04.683105Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:04.683105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dacheng Tao, Liang Ding, Qinyuan Cheng, Qipeng Guo, Siyin Wang, Xipeng Qiu, Yikun Wang, Zhaoye Fei","submitted_at":"2025-04-12T08:37:30Z","abstract_excerpt":"Recent advancements in Large Vision-Language Models have showcased remarkable capabilities. However, they often falter when confronted with complex reasoning tasks that humans typically address through visual aids and deliberate, step-by-step thinking. While existing methods have explored text-based slow thinking or rudimentary visual assistance, they fall short of capturing the intricate, interleaved nature of human visual-verbal reasoning processes. To overcome these limitations and inspired by the mechanisms of slow thinking in human cognition, we introduce VisuoThink, a novel framework tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09130","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/2504.09130/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.09130","created_at":"2026-07-05T10:48:04.683156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.09130v1","created_at":"2026-07-05T10:48:04.683156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09130","created_at":"2026-07-05T10:48:04.683156+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYBJD3J5YCMM","created_at":"2026-07-05T10:48:04.683156+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYBJD3J5YCMMKQXR","created_at":"2026-07-05T10:48:04.683156+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYBJD3J5","created_at":"2026-07-05T10:48:04.683156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25319","citing_title":"V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08231","citing_title":"Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10172","citing_title":"V-ABS: Action-Observer Driven Beam Search for Dynamic Visual Reasoning","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FYBJD3J5YCMMKQXRCGXQGLAFB2","json":"https://pith.science/pith/FYBJD3J5YCMMKQXRCGXQGLAFB2.json","graph_json":"https://pith.science/api/pith-number/FYBJD3J5YCMMKQXRCGXQGLAFB2/graph.json","events_json":"https://pith.science/api/pith-number/FYBJD3J5YCMMKQXRCGXQGLAFB2/events.json","paper":"https://pith.science/paper/FYBJD3J5"},"agent_actions":{"view_html":"https://pith.science/pith/FYBJD3J5YCMMKQXRCGXQGLAFB2","download_json":"https://pith.science/pith/FYBJD3J5YCMMKQXRCGXQGLAFB2.json","view_paper":"https://pith.science/paper/FYBJD3J5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.09130&json=true","fetch_graph":"https://pith.science/api/pith-number/FYBJD3J5YCMMKQXRCGXQGLAFB2/graph.json","fetch_events":"https://pith.science/api/pith-number/FYBJD3J5YCMMKQXRCGXQGLAFB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYBJD3J5YCMMKQXRCGXQGLAFB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYBJD3J5YCMMKQXRCGXQGLAFB2/action/storage_attestation","attest_author":"https://pith.science/pith/FYBJD3J5YCMMKQXRCGXQGLAFB2/action/author_attestation","sign_citation":"https://pith.science/pith/FYBJD3J5YCMMKQXRCGXQGLAFB2/action/citation_signature","submit_replication":"https://pith.science/pith/FYBJD3J5YCMMKQXRCGXQGLAFB2/action/replication_record"}},"created_at":"2026-07-05T10:48:04.683156+00:00","updated_at":"2026-07-05T10:48:04.683156+00:00"}