{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FSZFQMEPVAUTKBNF6BPDUYRWNQ","short_pith_number":"pith:FSZFQMEP","schema_version":"1.0","canonical_sha256":"2cb258308fa8293505a5f05e3a62366c1c4ec91a873395ba03fa0d455101c97f","source":{"kind":"arxiv","id":"2411.14432","version":2},"attestation_state":"computed","paper":{"title":"Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hai-Long Sun, Jingkang Yang, Winston Hu, Yongming Rao, Yuhao Dong, Ziwei Liu, Zuyan Liu","submitted_at":"2024-11-21T18:59:55Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate enhanced capabilities and reliability by reasoning more, evolving from Chain-of-Thought prompting to product-level solutions like OpenAI o1. Despite various efforts to improve LLM reasoning, high-quality long-chain reasoning data and optimized training pipelines still remain inadequately explored in vision-language tasks. In this paper, we present Insight-V, an early effort to 1) scalably produce long and robust reasoning data for complex multi-modal tasks, and 2) an effective training pipeline to enhance the reasoning capabilities of multi-modal large "},"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":"2411.14432","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"7fe742e818f7caffeb2df2cffd65c5d4b2cf3a6e5da982dfcaee8e99f836f917","abstract_canon_sha256":"a9acd74e5356ca79596100b10ec9c534a8028947990184c562e94ff5d1197d98"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:29.946872Z","signature_b64":"yg1vAod8XcsNzIl44a4WmRxchiXEZLUjc1W8XjU/OklvTN9FRqdrTeHpwM3d8+cIJBeyYBK8iPGB3pVuviCAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cb258308fa8293505a5f05e3a62366c1c4ec91a873395ba03fa0d455101c97f","last_reissued_at":"2026-07-05T10:57:29.946308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:29.946308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hai-Long Sun, Jingkang Yang, Winston Hu, Yongming Rao, Yuhao Dong, Ziwei Liu, Zuyan Liu","submitted_at":"2024-11-21T18:59:55Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate enhanced capabilities and reliability by reasoning more, evolving from Chain-of-Thought prompting to product-level solutions like OpenAI o1. Despite various efforts to improve LLM reasoning, high-quality long-chain reasoning data and optimized training pipelines still remain inadequately explored in vision-language tasks. In this paper, we present Insight-V, an early effort to 1) scalably produce long and robust reasoning data for complex multi-modal tasks, and 2) an effective training pipeline to enhance the reasoning capabilities of multi-modal large "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14432","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/2411.14432/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":"2411.14432","created_at":"2026-07-05T10:57:29.946381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14432v2","created_at":"2026-07-05T10:57:29.946381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14432","created_at":"2026-07-05T10:57:29.946381+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSZFQMEPVAUT","created_at":"2026-07-05T10:57:29.946381+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSZFQMEPVAUTKBNF","created_at":"2026-07-05T10:57:29.946381+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSZFQMEP","created_at":"2026-07-05T10:57:29.946381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17888","citing_title":"MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23678","citing_title":"Grounded Reinforcement Learning for Visual Reasoning","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2506.06856","citing_title":"Vision-EKIPL: External Knowledge-Infused Policy Learning for Visual Reasoning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05920","citing_title":"High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12937","citing_title":"R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27507","citing_title":"Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2503.09567","citing_title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","ref_index":162,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FSZFQMEPVAUTKBNF6BPDUYRWNQ","json":"https://pith.science/pith/FSZFQMEPVAUTKBNF6BPDUYRWNQ.json","graph_json":"https://pith.science/api/pith-number/FSZFQMEPVAUTKBNF6BPDUYRWNQ/graph.json","events_json":"https://pith.science/api/pith-number/FSZFQMEPVAUTKBNF6BPDUYRWNQ/events.json","paper":"https://pith.science/paper/FSZFQMEP"},"agent_actions":{"view_html":"https://pith.science/pith/FSZFQMEPVAUTKBNF6BPDUYRWNQ","download_json":"https://pith.science/pith/FSZFQMEPVAUTKBNF6BPDUYRWNQ.json","view_paper":"https://pith.science/paper/FSZFQMEP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14432&json=true","fetch_graph":"https://pith.science/api/pith-number/FSZFQMEPVAUTKBNF6BPDUYRWNQ/graph.json","fetch_events":"https://pith.science/api/pith-number/FSZFQMEPVAUTKBNF6BPDUYRWNQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSZFQMEPVAUTKBNF6BPDUYRWNQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSZFQMEPVAUTKBNF6BPDUYRWNQ/action/storage_attestation","attest_author":"https://pith.science/pith/FSZFQMEPVAUTKBNF6BPDUYRWNQ/action/author_attestation","sign_citation":"https://pith.science/pith/FSZFQMEPVAUTKBNF6BPDUYRWNQ/action/citation_signature","submit_replication":"https://pith.science/pith/FSZFQMEPVAUTKBNF6BPDUYRWNQ/action/replication_record"}},"created_at":"2026-07-05T10:57:29.946381+00:00","updated_at":"2026-07-05T10:57:29.946381+00:00"}