{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RN2WI3MQG6BJF34TZASITSCK2Z","short_pith_number":"pith:RN2WI3MQ","schema_version":"1.0","canonical_sha256":"8b75646d90378292ef93c82489c84ad64f5a79eb104995c29f1cd2e2d776ce52","source":{"kind":"arxiv","id":"2508.17298","version":2},"attestation_state":"computed","paper":{"title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fucai Ke, Gholamreza Haffari, Hamid Rezatofighi, Jiajun Wu, Joy Hsu, Pari Delir Haghighi, Ranjay Krishna, Sukai Huang, Weiqing Wang, Xindi Wu, Xin Zheng, Zhixi Cai, Zixian Ma","submitted_at":"2025-08-24T11:01:51Z","abstract_excerpt":"Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground intermediate concepts, and perform multi-step logical inference. While early surveys focus on monolithic vision-language models or general multimodal reasoning, a dedicated synthesis of the rapidly expanding compositional visual reasoning literature is still missing. We fill this gap with a comprehensive survey spanning 2023 to 2025 that systematically reviews 260+ papers from top venues (CVPR, ICCV, NeurIPS, ICML, ACL, "},"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":"2508.17298","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-24T11:01:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c6c5efce4c45b0ebe9cf41c8b98440353457581d69756c4b13acc054dda9b718","abstract_canon_sha256":"0ab206ad50e7ef5d045ac8a617f117caef9e07134ba2833878be7aea04db0f64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:09.488941Z","signature_b64":"wssUPSzHE+1k4hVu7oLk85ywcs0SijlPJ+nVe57Q2ilvE9MRzIl5Wv9mZ5iLhttF2qeFK5Z3Vz7KfJUcINBZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b75646d90378292ef93c82489c84ad64f5a79eb104995c29f1cd2e2d776ce52","last_reissued_at":"2026-07-05T12:00:09.488450Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:09.488450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fucai Ke, Gholamreza Haffari, Hamid Rezatofighi, Jiajun Wu, Joy Hsu, Pari Delir Haghighi, Ranjay Krishna, Sukai Huang, Weiqing Wang, Xindi Wu, Xin Zheng, Zhixi Cai, Zixian Ma","submitted_at":"2025-08-24T11:01:51Z","abstract_excerpt":"Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground intermediate concepts, and perform multi-step logical inference. While early surveys focus on monolithic vision-language models or general multimodal reasoning, a dedicated synthesis of the rapidly expanding compositional visual reasoning literature is still missing. We fill this gap with a comprehensive survey spanning 2023 to 2025 that systematically reviews 260+ papers from top venues (CVPR, ICCV, NeurIPS, ICML, ACL, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17298","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/2508.17298/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":"2508.17298","created_at":"2026-07-05T12:00:09.488510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.17298v2","created_at":"2026-07-05T12:00:09.488510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17298","created_at":"2026-07-05T12:00:09.488510+00:00"},{"alias_kind":"pith_short_12","alias_value":"RN2WI3MQG6BJ","created_at":"2026-07-05T12:00:09.488510+00:00"},{"alias_kind":"pith_short_16","alias_value":"RN2WI3MQG6BJF34T","created_at":"2026-07-05T12:00:09.488510+00:00"},{"alias_kind":"pith_short_8","alias_value":"RN2WI3MQ","created_at":"2026-07-05T12:00:09.488510+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":14,"sample":[{"citing_arxiv_id":"2606.27264","citing_title":"CORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMs","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2606.08035","citing_title":"DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11567","citing_title":"Dynamic Execution Commitment of Vision-Language-Action Models","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2606.27264","citing_title":"CORTEX: A Structured Reasoning Benchmark for Trustworthy 3D Chest CT MLLMs","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23602","citing_title":"GlowGS: Generative Semantic Feature Learning for 3D Gaussian Splatting in Nighttime Glow Scenes","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2504.21850","citing_title":"Visual Compositional Tuning","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20665","citing_title":"The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11567","citing_title":"Dynamic Execution Commitment of Vision-Language-Action Models","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2512.10941","citing_title":"Mull-Tokens: Modality-Agnostic Latent Thinking","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11567","citing_title":"Dynamic Execution Commitment of Vision-Language-Action Models","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00943","citing_title":"ARIS: Agentic and Relationship Intelligence System for Social Robots","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20665","citing_title":"The Expense of Seeing: Attaining Trustworthy Multimodal Reasoning Within the Monolithic Paradigm","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13313","citing_title":"Concrete Jungle: Towards Concreteness Paved Contrastive Negative Mining for Compositional Understanding","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16993","citing_title":"Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RN2WI3MQG6BJF34TZASITSCK2Z","json":"https://pith.science/pith/RN2WI3MQG6BJF34TZASITSCK2Z.json","graph_json":"https://pith.science/api/pith-number/RN2WI3MQG6BJF34TZASITSCK2Z/graph.json","events_json":"https://pith.science/api/pith-number/RN2WI3MQG6BJF34TZASITSCK2Z/events.json","paper":"https://pith.science/paper/RN2WI3MQ"},"agent_actions":{"view_html":"https://pith.science/pith/RN2WI3MQG6BJF34TZASITSCK2Z","download_json":"https://pith.science/pith/RN2WI3MQG6BJF34TZASITSCK2Z.json","view_paper":"https://pith.science/paper/RN2WI3MQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.17298&json=true","fetch_graph":"https://pith.science/api/pith-number/RN2WI3MQG6BJF34TZASITSCK2Z/graph.json","fetch_events":"https://pith.science/api/pith-number/RN2WI3MQG6BJF34TZASITSCK2Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RN2WI3MQG6BJF34TZASITSCK2Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RN2WI3MQG6BJF34TZASITSCK2Z/action/storage_attestation","attest_author":"https://pith.science/pith/RN2WI3MQG6BJF34TZASITSCK2Z/action/author_attestation","sign_citation":"https://pith.science/pith/RN2WI3MQG6BJF34TZASITSCK2Z/action/citation_signature","submit_replication":"https://pith.science/pith/RN2WI3MQG6BJF34TZASITSCK2Z/action/replication_record"}},"created_at":"2026-07-05T12:00:09.488510+00:00","updated_at":"2026-07-05T12:00:09.488510+00:00"}