{"_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_a076b6b274b52d07fdc76e395d9c5384eac75dc16ce79565ca553acb20c01a8a","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_a076b6b274b52d07fdc76e395d9c5384eac75dc16ce79565ca553acb20c01a8a","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"0ff08f87ccf781a440a0ab70101cd9d965fbb8d8be6f80465defef4e5c0a731f","published":"Fri, 26 Jun 2026 00:00:00 -0400","receipt_hash":"0ff08f87ccf781a440a0ab70101cd9d965fbb8d8be6f80465defef4e5c0a731f","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":"0ff08f87ccf781a440a0ab70101cd9d965fbb8d8be6f80465defef4e5c0a731f","observed_at":"2026-06-26T04:43:58.168958Z","parent_run_hash":"9459505a803125e4b968df08c74ed0054a2aafd44e4e1a036e3b0709a8a65cb4","published":"Fri, 26 Jun 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:2606.26535v1 Announce Type: cross \nAbstract: Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we introduce CRISP, a novel structural-diagnostic evaluation paradigm that assesses visual spatial intelligence through consistency, the alignment between implicit perception and explicit reasoning. Unlike traditional black-box QA, CRISP utilizes metric 3D Scene Graphs and an oracle intervention protocol to decouple latent reasoning capabilities from perceptual bottlenecks. This granular diagnosis uncovers a systematic perception-reasoning disconnect. Crucially, we reveal that while proprietary models possess robust latent reasoning engines, they suffer from inaccurate metric estimation and a critical failure to leverage their implicit structural representations. Conversely, open-source models remain fundamentally bottlenecked by their lack of multi-hop compositional reasoning. By shifting the focus from merely ``guessing correctly''","title":"From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP","url":"https://arxiv.org/abs/2606.26535","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.26535v1 Announce Type: cross \nAbstract: Current VLM evaluations often conflate language priors with genuine spatial reasoning. To address this, we introduce CRISP, a novel structural-diagnostic evaluation paradigm that assesses visual spatial intelligence through consistency, the alignment between implicit perception and explicit reasoning. Unlike traditional black-box QA, CRISP utilizes metric 3D Scene Graphs and an oracle intervention protocol to decouple latent reasoning capabilities from perceptual bottlenecks. This granular diagnosis uncovers a systematic perception-reasoning disconnect. Crucially, we reveal that while proprietary models possess robust latent reasoning engines, they suffer from inaccurate metric estimation and a critical failure to leverage their implicit structural representations. Conversely, open-source models remain fundamentally bottlenecked by their lack of multi-hop compositional reasoning. By shifting the focus from merely ``guessing correctly''","title":"From Hallucination to Grounding: Diagnosing Visual Spatial Intelligence via CRISP","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-26T04:43:58Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.26535"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:48b8ede0a8c66d6eec32eaf393e4f9f7b9bc74da99376a696fd3fca63b53cb96ef8c621c375c0438c053ef662ce8b46b8ed08cbc7545c7e01c5f9b408ac27307","signer":"crovia.substrate","subject":{"observed_at":"2026-06-26T04:43:58Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.26535"},"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":"9df969a4c954b1e39c349f6034a80657b9faee394d8cadc853d7519d9005f0d5","leaf_index":251125,"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":"16a44e52c8948a7f11a3fff7f3a12a78378d47cb60b1e4d736792fd38355aec1","side":"left"},{"sibling":"51f1b205835abdfaaa4ed7200452d92031f9a26e2d201bc08da673da5b6ebf75","side":"right"},{"sibling":"232937ece0f1837b7f3c59f3d5ee4c3c4972ab8356e216ba53f9f5c39e41e41d","side":"left"},{"sibling":"04c9b2449c31a5fc0a66c5e6ede02500e507c5ad225e5bc220edaec09b9e36fb","side":"right"},{"sibling":"043a8dd64f80957814930e09a29dbc6ddf3a82b09e07c34e3ccd1573dea3af79","side":"left"},{"sibling":"92cd327d65300d9092d295875064bd3bc7c40618e92d136fc9e99599d4ed2feb","side":"left"},{"sibling":"f9190af89759db1d872794d338826ddd18310851f89900539ca641d4cae8ad95","side":"left"},{"sibling":"762a50202e5bb846bfb5afec2f3cc80d9313546598c6c53f53acc51c6325b763","side":"left"},{"sibling":"e276c2896e885a069398e8350a2d9aae49ed0ab34771e352045341312283b40a","side":"right"},{"sibling":"b6709caadc8510310ee2ec0b66d1058fcad31c91c65cc2bad6f46a693d553580","side":"right"},{"sibling":"a72c3b8804a37d1a9d18e02e6fdb048bc8ea6b0746909cd2de10bdbabc793737","side":"left"},{"sibling":"803703dc2c50a646fa77b57c0056e9a5126611ba4bcde0d6013ccd6b2d44bdbf","side":"right"},{"sibling":"e78f244b1b8df6d5e3fdc6dd76b5c27d4e6fe3b93b8cd61355497b63d7e4cfe8","side":"left"},{"sibling":"6167cb552ed6871fbf0afcf3db01d1017af7d472b136fcbe5404d1df09f41cc1","side":"right"},{"sibling":"f29798d8bb6aa9900eab878992d9ff0c53266debd87472f31ab26a6a3fb55880","side":"left"},{"sibling":"a04392fb9f2a3a620840e3b3fecd93d12e6d224e481c162389d8ae64e7194599","side":"left"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","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":251380,"merkle_root":"e042805d07cd8dc777d49695ad78b8d4ec9721df271ff0245d7706773c30b4a5","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260626T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-26T05:37:59Z","sig_algorithm":"ed25519","signature":"c68a6e827804771acd244208495c5e35c6f417307db3c76192f038dedaa5b5f86e019074a3bea353357ff7457924c4f7907832638bb9a4d3d18e7a7f50c6a10b","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_a076b6b274b52d07fdc76e395d9c5384eac75dc16ce79565ca553acb20c01a8a"}}