{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RN2WI3MQG6BJF34TZASITSCK2Z","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":"0ab206ad50e7ef5d045ac8a617f117caef9e07134ba2833878be7aea04db0f64","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-24T11:01:51Z","title_canon_sha256":"c6c5efce4c45b0ebe9cf41c8b98440353457581d69756c4b13acc054dda9b718"},"schema_version":"1.0","source":{"id":"2508.17298","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.17298","created_at":"2026-07-05T12:00:09Z"},{"alias_kind":"arxiv_version","alias_value":"2508.17298v2","created_at":"2026-07-05T12:00:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17298","created_at":"2026-07-05T12:00:09Z"},{"alias_kind":"pith_short_12","alias_value":"RN2WI3MQG6BJ","created_at":"2026-07-05T12:00:09Z"},{"alias_kind":"pith_short_16","alias_value":"RN2WI3MQG6BJF34T","created_at":"2026-07-05T12:00:09Z"},{"alias_kind":"pith_short_8","alias_value":"RN2WI3MQ","created_at":"2026-07-05T12:00:09Z"}],"graph_snapshots":[{"event_id":"sha256:734b825ddd9c0fe65cb1045656658513d69a3bac53daeaa7178d63f383405738","target":"graph","created_at":"2026-07-05T12:00:09Z","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/2508.17298/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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, ","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","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-24T11:01:51Z","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17298","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:d143c585a1de0fa19ba21a84c28017310dde166e69932057418d5355d51b8b9a","target":"record","created_at":"2026-07-05T12:00:09Z","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":"0ab206ad50e7ef5d045ac8a617f117caef9e07134ba2833878be7aea04db0f64","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-24T11:01:51Z","title_canon_sha256":"c6c5efce4c45b0ebe9cf41c8b98440353457581d69756c4b13acc054dda9b718"},"schema_version":"1.0","source":{"id":"2508.17298","kind":"arxiv","version":2}},"canonical_sha256":"8b75646d90378292ef93c82489c84ad64f5a79eb104995c29f1cd2e2d776ce52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b75646d90378292ef93c82489c84ad64f5a79eb104995c29f1cd2e2d776ce52","first_computed_at":"2026-07-05T12:00:09.488450Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:09.488450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wssUPSzHE+1k4hVu7oLk85ywcs0SijlPJ+nVe57Q2ilvE9MRzIl5Wv9mZ5iLhttF2qeFK5Z3Vz7KfJUcINBZCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:09.488941Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.17298","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d143c585a1de0fa19ba21a84c28017310dde166e69932057418d5355d51b8b9a","sha256:734b825ddd9c0fe65cb1045656658513d69a3bac53daeaa7178d63f383405738"],"state_sha256":"3c69de289d29be3a1452d126449ce88b904dceea2dc64ce6a7cdd115c793ca85"}