{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UN6BXNWPWW7BOFZGD6BGYQK2DR","short_pith_number":"pith:UN6BXNWP","canonical_record":{"source":{"id":"2406.19934","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T14:04:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"23a0a2a9aa2b46833c317c43de0f669ed242bb5cec6319a2290962c0dd725c29","abstract_canon_sha256":"1f27c39d8c451fc7f2b8846dd4e2e5ed0a6e1ad9f8eddf2a8e32fc3547a9f1af"},"schema_version":"1.0"},"canonical_sha256":"a37c1bb6cfb5be1717261f826c415a1c7a45bf4e9d7855e3ec1faba0511ee99e","source":{"kind":"arxiv","id":"2406.19934","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UN6BXNWPWW7BOFZGD6BGYQK2DR","target":"record","payload":{"canonical_record":{"source":{"id":"2406.19934","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-28T14:04:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"23a0a2a9aa2b46833c317c43de0f669ed242bb5cec6319a2290962c0dd725c29","abstract_canon_sha256":"1f27c39d8c451fc7f2b8846dd4e2e5ed0a6e1ad9f8eddf2a8e32fc3547a9f1af"},"schema_version":"1.0"},"canonical_sha256":"a37c1bb6cfb5be1717261f826c415a1c7a45bf4e9d7855e3ec1faba0511ee99e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:10.962468Z","signature_b64":"F8Grry5q/O8RRKuP3VlBrA9+1hTtN0Wc064WV9QNXDl5omPPUA9MLQkuwU+Zv0y3BFTYBsIMCrdaX8HqarTQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a37c1bb6cfb5be1717261f826c415a1c7a45bf4e9d7855e3ec1faba0511ee99e","last_reissued_at":"2026-07-05T09:19:10.962009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:10.962009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.19934","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":"2026-07-05T09:19:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"joRUSzUl5X4Ug9CyaRDoDnIZAu8TVKF2bHg3LuYURDYKuE/WENMtldr2NZQgfqtfLRTIP+vOrpSIj/MXWNbkCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:59:53.435483Z"},"content_sha256":"956d0781923cd54d7e74bca62cc7798a50bf756b9446510ecd1598630b539682","schema_version":"1.0","event_id":"sha256:956d0781923cd54d7e74bca62cc7798a50bf756b9446510ecd1598630b539682"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UN6BXNWPWW7BOFZGD6BGYQK2DR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From the Least to the Most: Building a Plug-and-Play Visual Reasoner via Data Synthesis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chuanqi Cheng, Jian Guan, Rui Yan, Wei Wu","submitted_at":"2024-06-28T14:04:10Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.19934","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/2406.19934/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":"2026-07-05T09:19:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UQXzvm3lazgJQCA42V7yWKbdMSGfX7Xjfk/VG4bMeni/tY9Wm7AyZaX1/hYvVMBVenSszS5srs573gIIQVdZCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T22:59:53.436120Z"},"content_sha256":"e07d4be72675b86e912fda6eaa57beb3de850c284070144f89fd8572275e546d","schema_version":"1.0","event_id":"sha256:e07d4be72675b86e912fda6eaa57beb3de850c284070144f89fd8572275e546d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UN6BXNWPWW7BOFZGD6BGYQK2DR/bundle.json","state_url":"https://pith.science/pith/UN6BXNWPWW7BOFZGD6BGYQK2DR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UN6BXNWPWW7BOFZGD6BGYQK2DR/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":"2026-08-20T22:59:53Z","links":{"resolver":"https://pith.science/pith/UN6BXNWPWW7BOFZGD6BGYQK2DR","bundle":"https://pith.science/pith/UN6BXNWPWW7BOFZGD6BGYQK2DR/bundle.json","state":"https://pith.science/pith/UN6BXNWPWW7BOFZGD6BGYQK2DR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UN6BXNWPWW7BOFZGD6BGYQK2DR/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gj1orTpOLWEczv3lh/sKFiZPHO/4jscNuqRT0BbLGYGjFaJzxnrvw+NNHI9nHgmanZMi/xVbkSKyDCV/x62BDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T22:59:53.440127Z","bundle_sha256":"1810f44f3d24080456415210c5e086fb3f2a758309eb0b5c70278e6a5bce387f"}}