{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:A4GWVO2CGHUAEA6XHH447CFUNJ","short_pith_number":"pith:A4GWVO2C","schema_version":"1.0","canonical_sha256":"070d6abb4231e80203d739f9cf88b46a40d943b3f6ba28af1da36fb39362321f","source":{"kind":"arxiv","id":"2607.21722","version":1},"attestation_state":"computed","paper":{"title":"Be Consistent! Enhancing Robust Visual Reasoning in LVLMs with Consistency Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liqiang Jing, Neha Anna John, Siddharth Varia, Vassilis N. Ioannidis, Xinya Du, Xiong Zhou","submitted_at":"2026-07-23T18:04:51Z","abstract_excerpt":"While Large Vision-Language Models (LVLMs) exhibit strong perceptual capabilities, they remain vulnerable in visual reasoning tasks. Existing benchmarks largely focus on symbolic mathematical or scientific problems and simple vision-centric tasks, offering limited assessment of complex visual reasoning and logical consistency, a critical requirement for reliable reasoning systems. We introduce ConVBench, a complex vision-centric reasoning benchmark in which each image is paired with two logically equivalent questions across six categories: action and state, complex counting, spatial reasoning,"},"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":"2607.21722","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T18:04:51Z","cross_cats_sorted":[],"title_canon_sha256":"99cba99f76a55211ff291970e633e422a3974155e30872b26f3f59424bb458e2","abstract_canon_sha256":"6d0f91954c36499e476da363df5a5bb4d2bb0e2dfff73ace60862c16a9a800ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T00:20:17.503197Z","signature_b64":"p1qahW48A8B8Z6rVqX5PqTnO1vu+5u74zegQmCSrSRNqw0haxiK0Kiw4qG4dXqz5O6nJBtwh2sga9kLB13r1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"070d6abb4231e80203d739f9cf88b46a40d943b3f6ba28af1da36fb39362321f","last_reissued_at":"2026-07-27T00:20:17.502344Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T00:20:17.502344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Be Consistent! Enhancing Robust Visual Reasoning in LVLMs with Consistency Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liqiang Jing, Neha Anna John, Siddharth Varia, Vassilis N. Ioannidis, Xinya Du, Xiong Zhou","submitted_at":"2026-07-23T18:04:51Z","abstract_excerpt":"While Large Vision-Language Models (LVLMs) exhibit strong perceptual capabilities, they remain vulnerable in visual reasoning tasks. Existing benchmarks largely focus on symbolic mathematical or scientific problems and simple vision-centric tasks, offering limited assessment of complex visual reasoning and logical consistency, a critical requirement for reliable reasoning systems. We introduce ConVBench, a complex vision-centric reasoning benchmark in which each image is paired with two logically equivalent questions across six categories: action and state, complex counting, spatial reasoning,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21722","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/2607.21722/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":"2607.21722","created_at":"2026-07-27T00:20:17.502789+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21722v1","created_at":"2026-07-27T00:20:17.502789+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21722","created_at":"2026-07-27T00:20:17.502789+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4GWVO2CGHUA","created_at":"2026-07-27T00:20:17.502789+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4GWVO2CGHUAEA6X","created_at":"2026-07-27T00:20:17.502789+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4GWVO2C","created_at":"2026-07-27T00:20:17.502789+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A4GWVO2CGHUAEA6XHH447CFUNJ","json":"https://pith.science/pith/A4GWVO2CGHUAEA6XHH447CFUNJ.json","graph_json":"https://pith.science/api/pith-number/A4GWVO2CGHUAEA6XHH447CFUNJ/graph.json","events_json":"https://pith.science/api/pith-number/A4GWVO2CGHUAEA6XHH447CFUNJ/events.json","paper":"https://pith.science/paper/A4GWVO2C"},"agent_actions":{"view_html":"https://pith.science/pith/A4GWVO2CGHUAEA6XHH447CFUNJ","download_json":"https://pith.science/pith/A4GWVO2CGHUAEA6XHH447CFUNJ.json","view_paper":"https://pith.science/paper/A4GWVO2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21722&json=true","fetch_graph":"https://pith.science/api/pith-number/A4GWVO2CGHUAEA6XHH447CFUNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/A4GWVO2CGHUAEA6XHH447CFUNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4GWVO2CGHUAEA6XHH447CFUNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4GWVO2CGHUAEA6XHH447CFUNJ/action/storage_attestation","attest_author":"https://pith.science/pith/A4GWVO2CGHUAEA6XHH447CFUNJ/action/author_attestation","sign_citation":"https://pith.science/pith/A4GWVO2CGHUAEA6XHH447CFUNJ/action/citation_signature","submit_replication":"https://pith.science/pith/A4GWVO2CGHUAEA6XHH447CFUNJ/action/replication_record"}},"created_at":"2026-07-27T00:20:17.502789+00:00","updated_at":"2026-07-27T00:20:17.502789+00:00"}