{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FSZFQMEPVAUTKBNF6BPDUYRWNQ","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":"a9acd74e5356ca79596100b10ec9c534a8028947990184c562e94ff5d1197d98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:59:55Z","title_canon_sha256":"7fe742e818f7caffeb2df2cffd65c5d4b2cf3a6e5da982dfcaee8e99f836f917"},"schema_version":"1.0","source":{"id":"2411.14432","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14432","created_at":"2026-07-05T10:57:29Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14432v2","created_at":"2026-07-05T10:57:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14432","created_at":"2026-07-05T10:57:29Z"},{"alias_kind":"pith_short_12","alias_value":"FSZFQMEPVAUT","created_at":"2026-07-05T10:57:29Z"},{"alias_kind":"pith_short_16","alias_value":"FSZFQMEPVAUTKBNF","created_at":"2026-07-05T10:57:29Z"},{"alias_kind":"pith_short_8","alias_value":"FSZFQMEP","created_at":"2026-07-05T10:57:29Z"}],"graph_snapshots":[{"event_id":"sha256:9840b20f7c7d7b9022f27a7897d53adf6b0a26b6c7f11adec24374b8c066e5b3","target":"graph","created_at":"2026-07-05T10:57:29Z","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/2411.14432/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Hai-Long Sun, Jingkang Yang, Winston Hu, Yongming Rao, Yuhao Dong, Ziwei Liu, Zuyan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:59:55Z","title":"Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14432","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":"sha256:19f0f4f8cb250662a38049a8c1d09669885efed4b632d7225fe2ef26ac826f6a","target":"record","created_at":"2026-07-05T10:57:29Z","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":"a9acd74e5356ca79596100b10ec9c534a8028947990184c562e94ff5d1197d98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-21T18:59:55Z","title_canon_sha256":"7fe742e818f7caffeb2df2cffd65c5d4b2cf3a6e5da982dfcaee8e99f836f917"},"schema_version":"1.0","source":{"id":"2411.14432","kind":"arxiv","version":2}},"canonical_sha256":"2cb258308fa8293505a5f05e3a62366c1c4ec91a873395ba03fa0d455101c97f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cb258308fa8293505a5f05e3a62366c1c4ec91a873395ba03fa0d455101c97f","first_computed_at":"2026-07-05T10:57:29.946308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:29.946308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yg1vAod8XcsNzIl44a4WmRxchiXEZLUjc1W8XjU/OklvTN9FRqdrTeHpwM3d8+cIJBeyYBK8iPGB3pVuviCAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:29.946872Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14432","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19f0f4f8cb250662a38049a8c1d09669885efed4b632d7225fe2ef26ac826f6a","sha256:9840b20f7c7d7b9022f27a7897d53adf6b0a26b6c7f11adec24374b8c066e5b3"],"state_sha256":"03adc810eb7c95bffb0d618c3b879bd6b3cf4531b656ac67a51c02b250585b62"}