{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_e5995c11c1defaea2de797546375170c89c1244654b6c4ae914e54016f1f70ee","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_e5995c11c1defaea2de797546375170c89c1244654b6c4ae914e54016f1f70ee","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"8fad31ca39c8823c74ae38a38b79e2da4c7c285585528f04cb88ffb4ce20e093","published":"Thu, 09 Jul 2026 00:00:00 -0400","receipt_hash":"8fad31ca39c8823c74ae38a38b79e2da4c7c285585528f04cb88ffb4ce20e093","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"8fad31ca39c8823c74ae38a38b79e2da4c7c285585528f04cb88ffb4ce20e093","observed_at":"2026-07-09T04:43:38.345231Z","parent_run_hash":"3e22c7c40abc4d94232acf1766a43492b8b8d51d10a58f1109535988a16554e6","published":"Thu, 09 Jul 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2508.17298v3 Announce Type: replace-cross \nAbstract: 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, etc.). We first formalize core definitions and describe why compositional approaches offer advantages in cognitive alignment, semantic fidelity, robustness, interpretability, and data efficiency. Next, we trace a five-stage paradigm shift: from prompt-enhanced language-centric pipelines, through tool-enhanced LLMs and tool-enhanced VLMs, t","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","url":"https://arxiv.org/abs/2508.17298","vendor":"arxiv_cs_ai"},"summary":"arXiv:2508.17298v3 Announce Type: replace-cross \nAbstract: 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, etc.). We first formalize core definitions and describe why compositional approaches offer advantages in cognitive alignment, semantic fidelity, robustness, interpretability, and data efficiency. Next, we trace a five-stage paradigm shift: from prompt-enhanced language-centric pipelines, through tool-enhanced LLMs and tool-enhanced VLMs, t","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-09T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2508.17298"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:e0521e26db84ed89df3ec36731cef937a388eb24007117fdb72c8d4eac4e22698249b04080d55d106c3d25353deaafbedbe165bf589dc9b233d00d82432b270a","signer":"crovia.substrate","subject":{"observed_at":"2026-07-09T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2508.17298"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"5b4c3355597111a94e5da20f4caaa628b86e24676b02e420adc70411e420a07f","leaf_index":296189,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"561dfd84624761777fae438b30482ac50395fcfc7b552c6d1881fa1fd1c0d90b","side":"left"},{"sibling":"d5d8ffce27e7064c23769cfda8c605c5e05ab7a3da1d8bfa63ccd8b19dd22c6b","side":"right"},{"sibling":"2d96155b7428196a3344a9c90124add345508f8acf667d943a3f84f6d03f50c7","side":"left"},{"sibling":"80592c03b01749cc128dfa6bee40cb24c6e9e72c2b4b483f1b953e6130bef7ff","side":"left"},{"sibling":"3d4f6ddfc02f6b588b8e7e47d928f6a9337230f2984b7bbc50b5608d7e7aa03b","side":"left"},{"sibling":"f95bff985aa7c669523e81a6b3e235ec2edadeeaf162721af802f1ea75a20888","side":"left"},{"sibling":"0c64b5ca40a519de00e7e467e1220b2def2b2b1f0826ffde72f1d615f3bcf094","side":"left"},{"sibling":"6e8f2e16cb75beb661e7f7b63be19804b6f6474dfbf899f8e417b19695f2fba4","side":"left"},{"sibling":"47a94dfb6e50a020e68582e6af2e6a8cf5a4c7efe9fed3deaedbc51f53d75367","side":"right"},{"sibling":"92bb57de69c78fd32ac7108b10d81676c184265a5a53de3c4b22d8cf3b54b499","side":"right"},{"sibling":"85a226efd14acc17835b04bc26706fa44595edbd531f194faf59f60ab72d4bb8","side":"left"},{"sibling":"da38b05536b12aee196b6ac988739211c257d32da790faccf5ac4b0cbc1bb15c","side":"right"},{"sibling":"d438dc3eddb0b14dc8b97cd021a4f44545ce5a8e827f3ea4044fd32b1877475e","side":"right"},{"sibling":"f73ad10346837ae47f59f0647f79b9416e1d499bf2b90af44448e7f09372200a","side":"right"},{"sibling":"bdc09902fcd434c0f7d3e680bf550e560777228c0b085ce80c637ce97fc4104c","side":"right"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"ba603dffe985ef518e3a72793a3eaca83a7f1a79e5491fd0f62f421339f2d137","side":"right"},{"sibling":"be20b90931f0a14e3558ea4387537200fcbd14e019b3c5ed07a2ae4c62fc7c42","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":296360,"merkle_root":"64af62f723a5bc02adfa98b77e2006fc634de4ebf68626694f052342a200bea2","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260709T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-09T05:38:18Z","sig_algorithm":"ed25519","signature":"92ece7411e0d82898aac164e7d6573a6d0f7a595aad0780d710d873e548a061d2a8678cef4d237d3bf0eabe0a5f766b41cbc0b4bada2801e7532026291b4a309","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_e5995c11c1defaea2de797546375170c89c1244654b6c4ae914e54016f1f70ee"}}