{"_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_1bf33a664c930568ac801229e33b60f2a37fa6ba9733ab08d6b610b1059b4800","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_1bf33a664c930568ac801229e33b60f2a37fa6ba9733ab08d6b610b1059b4800","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"e32af13419d5c1c2c79a5ade6a053f6d0cee26568c7050c02d28c9bed9a53fad","published":"Fri, 22 May 2026 00:00:00 -0400","receipt_hash":"e32af13419d5c1c2c79a5ade6a053f6d0cee26568c7050c02d28c9bed9a53fad","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":"e32af13419d5c1c2c79a5ade6a053f6d0cee26568c7050c02d28c9bed9a53fad","observed_at":"2026-05-22T04:43:12.593252Z","parent_run_hash":"dd4d56660d55b2d65dc84dc5e7c8f83487d90da2dd343b5707d6948a3bb0d917","published":"Fri, 22 May 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:2605.19846v2 Announce Type: replace-cross \nAbstract: Vision-Language Models (VLMs) have demonstrated remarkable capabilities in general video understanding, yet they often struggle with the fine-grained comprehension crucial for real-world applications requiring nuanced interpretation of human actions and interactions. While some recent human-centric benchmarks evaluate aspects of model behaviour such as fairness/ethics, emotion perception, and broader human-centric metrics, they do not combine long-form videos, very dense QA coverage, and frame-level spatial/temporal grounding at scale. To bridge this gap, we introduce FineBench, a human-centric video question answering (VQA) benchmark specifically designed to assess fine-grained understanding. FineBench comprises 199,420 multiple-choice QA pairs densely annotated across 64 long-form videos (15 minutes each), focusing on detailed person movement, person interaction, and object manipulation, including compositional actions. Our e","title":"FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding","url":"https://arxiv.org/abs/2605.19846","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.19846v2 Announce Type: replace-cross \nAbstract: Vision-Language Models (VLMs) have demonstrated remarkable capabilities in general video understanding, yet they often struggle with the fine-grained comprehension crucial for real-world applications requiring nuanced interpretation of human actions and interactions. While some recent human-centric benchmarks evaluate aspects of model behaviour such as fairness/ethics, emotion perception, and broader human-centric metrics, they do not combine long-form videos, very dense QA coverage, and frame-level spatial/temporal grounding at scale. To bridge this gap, we introduce FineBench, a human-centric video question answering (VQA) benchmark specifically designed to assess fine-grained understanding. FineBench comprises 199,420 multiple-choice QA pairs densely annotated across 64 long-form videos (15 minutes each), focusing on detailed person movement, person interaction, and object manipulation, including compositional actions. Our e","title":"FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-22T04:43:12Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.19846"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:4e3c5b7c6927eba0e76e10f3caed0d71e74f33e37b10ac3a0b63f02512afe972fd604705d8fe5d2ee3eca8b26fb4a09ab57317a849b31dd1cd589ded320eb802","signer":"crovia.substrate","subject":{"observed_at":"2026-05-22T04:43:12Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.19846"},"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":"e767509f3c86d96650b8c906c00ef22fdb6e5339e2b05d4f2f2459d6afdd3b92","leaf_index":148504,"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":"06f267b42195d3cb6114ae9c3e5bce91ddaf033dae776990efcd953ecafb03d7","side":"right"},{"sibling":"da80d54b04a704ffb142e59f1ae6a837bb03c6badac227ce7290acdb0963c9c0","side":"right"},{"sibling":"44926275de6875cde64316448ab6ad576c441c8db23aed26162aee6d1864ecf7","side":"right"},{"sibling":"417c954e3645c4395c66a6714447fcca59e7a22fd541292442d1a6e88df5b973","side":"left"},{"sibling":"2de629520ae84b446abd8907ed7134eb0bc7ce31ca25e4de1d77f904b6dd4fb3","side":"left"},{"sibling":"29c83f92eefcf37fd5647bf9965bae343542cc3cafabe85a14c353be2579820c","side":"right"},{"sibling":"b2b3e1dd273a89fa858097a49ad18f7a787e5f5108ffd3d34e2db914ff0f8893","side":"right"},{"sibling":"c2464e6156ff209e78b1366fb55bf2f9d9ab654edb687e533a50f92f1ec063fe","side":"right"},{"sibling":"45d7b77845fd951e51c069dff3d17eaf26d1981d61660baa90643a8a3e33efac","side":"right"},{"sibling":"46ba1960714c5ca099e764bc8d2a0242369a84e0255d7a9e3bb6ab00ffa50417","side":"right"},{"sibling":"5c4ff01819c3dfe5105c2c31139b878c525a66d2ed2f835e2d6579c68da04611","side":"left"},{"sibling":"79a713e1e345ccb99c5fe994a11708c8e9bcfa2e91f940d70421cb7d8d77ecc6","side":"right"},{"sibling":"249870fb494bef050c409081e5de45f9042938d7b2823524ee496f296aa63667","side":"right"},{"sibling":"96c48ee8328f1b7925a4cc4421df5cb0bd81c92a5d8354c93126fa5f0166d225","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"4e13b4a3e69bb83d13913477a782913ce03937edd65046853c1964d3cbb6564b","side":"right"},{"sibling":"0f7b2df1c4580bf7bb7c24b9158ba20593a06af18a5f18d0973e5eff20c35cd8","side":"right"},{"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":148601,"merkle_root":"44900cffd986f40535c83f46a250e86fbf1019d41f27080a00fbf9b8d77ec33a","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260524T133701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-24T13:37:32Z","sig_algorithm":"ed25519","signature":"059e428c3c5241de303721ad6ac7b748758372180f3f0a717810312aecd6fab073abb3ea264157666de581a2b361c4c6e2aa8ca081b08ce9be090721f0e3400e","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_1bf33a664c930568ac801229e33b60f2a37fa6ba9733ab08d6b610b1059b4800"}}