{"_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_83ea27c36b0ffb28f7716d4776adbc8249e011267e5389ba0e2f76edc4dd99ec","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_83ea27c36b0ffb28f7716d4776adbc8249e011267e5389ba0e2f76edc4dd99ec","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"af0586d82b1b69576e5ed6becd1bec248979019303dbab2a122237e744fea9fb","published":"Fri, 24 Jul 2026 00:00:00 -0400","receipt_hash":"af0586d82b1b69576e5ed6becd1bec248979019303dbab2a122237e744fea9fb","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":"af0586d82b1b69576e5ed6becd1bec248979019303dbab2a122237e744fea9fb","observed_at":"2026-07-24T04:43:08.456021Z","parent_run_hash":"b018378f86139a28e6209ec008b31c1282cd1b5c1632dbd43b054c17aa88ab96","published":"Fri, 24 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:2607.21155v1 Announce Type: cross \nAbstract: Knowledge-Intensive Visual Question Answering (KI-VQA) benchmarks evaluate Vision-Language Models (VLMs) as multimodal knowledge assistants by requiring external information beyond a provided image to answer questions. KI-VQA involves multiple sub-problems -referring expression understanding, visual grounding, object recognition, knowledge retrieval, and reasoning-yet existing benchmarks typically report only end-task accuracy, obscuring where failures arise. To analyze the full KI-VQA pipeline, we introduce CRAG-MM-Diagnostics, a diagnostic benchmark with stage-wise data annotations that isolate 1) language-based visual grounding, 2) object identification, and 3) knowledge retrieval and reasoning. We evaluate fully parametric and retrieval-augmented VLMs, providing fine-grained analyses using newly collected metadata, such as target ROIs, entity names, and visual complexity scores. Our results point to knowledge retrieval and reasonin","title":"CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQA","url":"https://arxiv.org/abs/2607.21155","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.21155v1 Announce Type: cross \nAbstract: Knowledge-Intensive Visual Question Answering (KI-VQA) benchmarks evaluate Vision-Language Models (VLMs) as multimodal knowledge assistants by requiring external information beyond a provided image to answer questions. KI-VQA involves multiple sub-problems -referring expression understanding, visual grounding, object recognition, knowledge retrieval, and reasoning-yet existing benchmarks typically report only end-task accuracy, obscuring where failures arise. To analyze the full KI-VQA pipeline, we introduce CRAG-MM-Diagnostics, a diagnostic benchmark with stage-wise data annotations that isolate 1) language-based visual grounding, 2) object identification, and 3) knowledge retrieval and reasoning. We evaluate fully parametric and retrieval-augmented VLMs, providing fine-grained analyses using newly collected metadata, such as target ROIs, entity names, and visual complexity scores. Our results point to knowledge retrieval and reasonin","title":"CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQA","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-24T04:43:08Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.21155"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:e626ec6b7ee19195f86ae88207289388a66cd50a2b75c4cc0b5244e5ba5fb63ff55279df58b7615ccfa83f2d61c715104b11b13d26c282c97583244763e50908","signer":"crovia.substrate","subject":{"observed_at":"2026-07-24T04:43:08Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.21155"},"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":"8ca6786936b65e95c7e38718276a18458a8e885b1931af3d8203b93e33dbba0e","leaf_index":347157,"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":"e069fab170411b27e754e009ff6a724e056652b4e4b25c6c95a8b1d6c206ee9e","side":"left"},{"sibling":"f538c9472a7dde88cd2e046d30e544b9b2c1a70031d7ef8186d03a4ad2e75b80","side":"right"},{"sibling":"3abceaf662b6b7184f192ad71401d238821f35469501071226f24ed128d9b1e0","side":"left"},{"sibling":"2e725062525df613b0c18d205a974bd10f2992115fa921769b286ae3f6378121","side":"right"},{"sibling":"851159c4e1693c285e7d457ed28a12bf32ffb9fd5b340aaacb668afc7e106416","side":"left"},{"sibling":"b6debb6f2e4bf22e2169ef83d8bddaa57a78351013d058637030f185562dd879","side":"right"},{"sibling":"174e185d067a50aecc913edd90ba49fd072a31a09e0b3a18c0687f362c61e57b","side":"right"},{"sibling":"aa4b293ba10895bb7f8b28f0f04360b53a8fc5a7523d9a560dbb7b29d003643e","side":"right"},{"sibling":"759f431c97765cb7fb12d38ee64fd6a87076abf1b63c87d7c8c172d57b29084d","side":"right"},{"sibling":"b9cb83ecb59812b3b9270c365951fa79dead288c3923b6cf1f83ffb911b27405","side":"right"},{"sibling":"e6c9083cd0939b38f691f619de2054068654e9c77f7c7ab051e0d48b77339e5d","side":"left"},{"sibling":"d3139af8c5ce235438e1c69e4b7afa44ba09129fd86674968434f23e546f423e","side":"left"},{"sibling":"cb89775a838ee16d10fc8da3213420c2012b4d96e8d55cd49939b0887a4b92d3","side":"right"},{"sibling":"252d30ea8052c3bb6b40bc5cc29fc9b9725343d212f84c08fbbae4215a125b00","side":"right"},{"sibling":"f3e45bceed774d2402fa45d41ff5190f295823bd2f216eb90157884150034693","side":"left"},{"sibling":"3cfa2102c0224815c6f3bf73e6710e24103f43f7bf5da1ca2abad1416d9c0890","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"e871fd7edf9b2ad89bce1609a028f5225eea4d14372169bac242420830f86530","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":347413,"merkle_root":"9efe042c5dd6583dfd3b6a58fbfc289807f60bcf2bd2927f10488a54a8ba11fc","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260724T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-24T05:38:42Z","sig_algorithm":"ed25519","signature":"8633c55f558d42994850505218b2862c6134bad2b1c80d4b80736c2fd3ea7a19690ca3498727a8adbdc47791176128a8d64bef0883b888db809f0477355bd00c","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_83ea27c36b0ffb28f7716d4776adbc8249e011267e5389ba0e2f76edc4dd99ec"}}