{"_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_df47bff8f889b2791dd4854f9b30f0be3b5654fcd090e34fbe17cb9a5d15c312","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_df47bff8f889b2791dd4854f9b30f0be3b5654fcd090e34fbe17cb9a5d15c312","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"7a98a9c2064439826eb906cd89451f6633de0eda3b0c7a9c5d6887ffbeb0c66b","published":"Thu, 23 Jul 2026 00:00:00 -0400","receipt_hash":"7a98a9c2064439826eb906cd89451f6633de0eda3b0c7a9c5d6887ffbeb0c66b","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":"7a98a9c2064439826eb906cd89451f6633de0eda3b0c7a9c5d6887ffbeb0c66b","observed_at":"2026-07-23T04:43:18.446221Z","parent_run_hash":"b3f5e4095688e31d15c25de2607bca42111343bdfdac967d48e47905415ddea0","published":"Thu, 23 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:2602.00462v5 Announce Type: replace-cross \nAbstract: Transforming a large language model (LLM) into a vision-language model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM. Intriguingly, this mapping can be as simple as a shallow MLP transformation. To understand why LLMs can so readily process visual tokens, we need interpretability methods that reveal what is encoded in the visual token representations at every layer of LLM processing. In this work, we introduce LatentLens, a novel approach for mapping latent representations to descriptions in natural language. LatentLens encodes a large text corpus and stores contextualized token representations for each token in that corpus. Visual token representations are then compared to these contextualized representations and the top-nearest neighbor representations serve as descriptions of the visual token. We evaluate this method on 15 different VLMs, showing that commonly use","title":"LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs","url":"https://arxiv.org/abs/2602.00462","vendor":"arxiv_cs_ai"},"summary":"arXiv:2602.00462v5 Announce Type: replace-cross \nAbstract: Transforming a large language model (LLM) into a vision-language model (VLM) can be achieved by mapping the visual tokens from a vision encoder into the embedding space of an LLM. Intriguingly, this mapping can be as simple as a shallow MLP transformation. To understand why LLMs can so readily process visual tokens, we need interpretability methods that reveal what is encoded in the visual token representations at every layer of LLM processing. In this work, we introduce LatentLens, a novel approach for mapping latent representations to descriptions in natural language. LatentLens encodes a large text corpus and stores contextualized token representations for each token in that corpus. Visual token representations are then compared to these contextualized representations and the top-nearest neighbor representations serve as descriptions of the visual token. We evaluate this method on 15 different VLMs, showing that commonly use","title":"LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-23T04:43:18Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2602.00462"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:934e35e1172bcb6b7648c73bdb5864ba553501a400a05a3a24f89e89a8ad7434e3bab9ddc9517ffb1dddc3b2649540912d71313b46b88dfa1af99954b8b29101","signer":"crovia.substrate","subject":{"observed_at":"2026-07-23T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2602.00462"},"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":"28e4eb893f1ad1daf08661e856e47f23574b1a882a6b0cde0bfbbea307c70ddd","leaf_index":343790,"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":"13efcd0503f359ebc42d965c3c2ca0e02925ba6c576ee6ff5d7d3c9d616e9c1f","side":"right"},{"sibling":"0eabf73c34a5a4628c25055708be3cca75b4da3a6c93d069998b8b48bd933674","side":"left"},{"sibling":"bd610be2c51eb6dbf75742b4589ff059c0bc78601c28bc2590b7af1b044d47f8","side":"left"},{"sibling":"40ed9da47a33a9570c66a7723be3829f7b725c922f9c46ad59079f04f9b7ed54","side":"left"},{"sibling":"c423429d1a8c3090b58f8897f311a3b03f9f60ac7fb988ff530039a6c6e7c129","side":"right"},{"sibling":"8c4abba7f73d017263c7cfa7cf00e7dad2248eccd24b930d64f9284ce5a8897d","side":"left"},{"sibling":"84e2bd69f70ff0e814f453c01a295fde8d94bdb3824a1424ab4fd97be4fa4cba","side":"left"},{"sibling":"fbe8bc0f33cd1a297ce2f845b101ed1107ebb67f2c2577c28ed032c1046d3b97","side":"left"},{"sibling":"6ecdcc1e2fb6ab44777fffbb7c8297d723018c63aac9d90c7a1bbebe728d84cf","side":"right"},{"sibling":"93d7d8e0e882d05b2a15bb707a824979a0427907eb47e687c712906674a0d345","side":"left"},{"sibling":"92219a3ef58cd145d94f071b0b9396cec3707812b02a8c7c63f2d0e22340552b","side":"left"},{"sibling":"4eb402d67bd4bf583b0434363061166fe259c34cc6c42adb32dcfbff0a9f5767","side":"left"},{"sibling":"2dd9cb2521044ee7c6b74f2315e0a0253b8df0d04a7b810bbbbe7da5a9788769","side":"left"},{"sibling":"21d66dd41003813f710b7617944f1bfba3258658a5d3370c21cad8f9e945bc99","side":"left"},{"sibling":"941f71d7ce3990a507b8f485de3f872a51d0e9a8c59405d76c2ae6f4a6af494a","side":"right"},{"sibling":"6281b6f7a93c44e3c4895bc65cfcb6f2be24dd725f4f46540ec022a6e215f4e8","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"6baede22892163664bb2e4d92cf75e6b290761533a6c39491c3afd89bb3a0252","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":343944,"merkle_root":"afab58f71597d393a7a61b857dac2eacb72fd1c04cd1432c2622d7b19309dffd","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260723T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-23T05:38:39Z","sig_algorithm":"ed25519","signature":"1a58fdc6367d0c86f83d2385be748e0800a64bcf9987c92fadca53deda009cd390d2070302c2b6e44841febfd864637c323ba12c7a1e9ae58fdf2a0cf546ac01","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_df47bff8f889b2791dd4854f9b30f0be3b5654fcd090e34fbe17cb9a5d15c312"}}