{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UN6BXNWPWW7BOFZGD6BGYQK2DR","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":"1f27c39d8c451fc7f2b8846dd4e2e5ed0a6e1ad9f8eddf2a8e32fc3547a9f1af","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T14:04:10Z","title_canon_sha256":"23a0a2a9aa2b46833c317c43de0f669ed242bb5cec6319a2290962c0dd725c29"},"schema_version":"1.0","source":{"id":"2406.19934","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.19934","created_at":"2026-07-05T09:19:10Z"},{"alias_kind":"arxiv_version","alias_value":"2406.19934v2","created_at":"2026-07-05T09:19:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.19934","created_at":"2026-07-05T09:19:10Z"},{"alias_kind":"pith_short_12","alias_value":"UN6BXNWPWW7B","created_at":"2026-07-05T09:19:10Z"},{"alias_kind":"pith_short_16","alias_value":"UN6BXNWPWW7BOFZG","created_at":"2026-07-05T09:19:10Z"},{"alias_kind":"pith_short_8","alias_value":"UN6BXNWP","created_at":"2026-07-05T09:19:10Z"}],"graph_snapshots":[{"event_id":"sha256:e07d4be72675b86e912fda6eaa57beb3de850c284070144f89fd8572275e546d","target":"graph","created_at":"2026-07-05T09:19:10Z","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/2406.19934/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore multi-step reasoning in vision-language models (VLMs). The problem is challenging, as reasoning data consisting of multiple steps of visual and language processing are barely available. To overcome the challenge, we first introduce a least-to-most visual reasoning paradigm, which interleaves steps of decomposing a question into sub-questions and invoking external tools for resolving sub-questions. Based on the paradigm, we further propose a novel data synthesis approach that can automatically create questions and multi-step reasoning paths for an image in a bottom-up manner. Our app","authors_text":"Chuanqi Cheng, Jian Guan, Rui Yan, Wei Wu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T14:04:10Z","title":"From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19934","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":"sha256:956d0781923cd54d7e74bca62cc7798a50bf756b9446510ecd1598630b539682","target":"record","created_at":"2026-07-05T09:19:10Z","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":"1f27c39d8c451fc7f2b8846dd4e2e5ed0a6e1ad9f8eddf2a8e32fc3547a9f1af","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T14:04:10Z","title_canon_sha256":"23a0a2a9aa2b46833c317c43de0f669ed242bb5cec6319a2290962c0dd725c29"},"schema_version":"1.0","source":{"id":"2406.19934","kind":"arxiv","version":2}},"canonical_sha256":"a37c1bb6cfb5be1717261f826c415a1c7a45bf4e9d7855e3ec1faba0511ee99e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a37c1bb6cfb5be1717261f826c415a1c7a45bf4e9d7855e3ec1faba0511ee99e","first_computed_at":"2026-07-05T09:19:10.962009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:10.962009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"F8Grry5q/O8RRKuP3VlBrA9+1hTtN0Wc064WV9QNXDl5omPPUA9MLQkuwU+Zv0y3BFTYBsIMCrdaX8HqarTQCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:10.962468Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.19934","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:956d0781923cd54d7e74bca62cc7798a50bf756b9446510ecd1598630b539682","sha256:e07d4be72675b86e912fda6eaa57beb3de850c284070144f89fd8572275e546d"],"state_sha256":"ee38c317c36753da967c6f509f86f99083f16375be2d36b56398a2b4fc14f2ed"}