{"_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_33039cc23eccab7c354d3f49cf59d2be59ea72312b598086c6c7716c1ae7ec7f","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_33039cc23eccab7c354d3f49cf59d2be59ea72312b598086c6c7716c1ae7ec7f","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"aa404bbfbcacbc07609fa9a3bd941e85172a6e8dc989163d5d42e7496a80fea8","published":"Mon, 01 Jun 2026 00:00:00 -0400","receipt_hash":"aa404bbfbcacbc07609fa9a3bd941e85172a6e8dc989163d5d42e7496a80fea8","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":"aa404bbfbcacbc07609fa9a3bd941e85172a6e8dc989163d5d42e7496a80fea8","observed_at":"2026-06-01T04:43:13.859018Z","parent_run_hash":"8993bbc535dae8c9669e099af3624cb39166b8d9bbfd66f26ae5c338cbb21be2","published":"Mon, 01 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:2509.12440v3 Announce Type: replace-cross \nAbstract: Deploying Large Language Models (LLMs) in medical applications requires fact-checking capabilities to ensure patient safety and regulatory compliance. We introduce MedFact, a challenging Chinese medical fact-checking benchmark with 2,116 expert-annotated instances from diverse real-world texts, spanning 13 specialties, 8 error types, 4 writing styles, and 5 difficulty levels. Construction uses a hybrid AI-human framework where iterative expert feedback refines AI-driven, multi-criteria filtering to ensure high quality and difficulty. We evaluate 20 leading LLMs on veracity classification and error localization, and results show models often determine if text contains errors but struggle to localize them precisely, with top performers falling short of human performance. Our analysis reveals the \"over-criticism\" phenomenon, a tendency for models to misidentify correct information as erroneous, which can be exacerbated by advanced","title":"MedFact: Benchmarking the Fact-Checking Capabilities of Large Language Models on Chinese Medical Texts","url":"https://arxiv.org/abs/2509.12440","vendor":"arxiv_cs_ai"},"summary":"arXiv:2509.12440v3 Announce Type: replace-cross \nAbstract: Deploying Large Language Models (LLMs) in medical applications requires fact-checking capabilities to ensure patient safety and regulatory compliance. We introduce MedFact, a challenging Chinese medical fact-checking benchmark with 2,116 expert-annotated instances from diverse real-world texts, spanning 13 specialties, 8 error types, 4 writing styles, and 5 difficulty levels. Construction uses a hybrid AI-human framework where iterative expert feedback refines AI-driven, multi-criteria filtering to ensure high quality and difficulty. We evaluate 20 leading LLMs on veracity classification and error localization, and results show models often determine if text contains errors but struggle to localize them precisely, with top performers falling short of human performance. Our analysis reveals the \"over-criticism\" phenomenon, a tendency for models to misidentify correct information as erroneous, which can be exacerbated by advanced","title":"MedFact: Benchmarking the Fact-Checking Capabilities of Large Language Models on Chinese Medical Texts","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-01T04:43:13Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2509.12440"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:ef5880a933126e428d61dbd686ef1d08ba6f76e3d371f660b957ceb9d203fd93053e5b0631950396b1e10349b589cb7ed414ee4f5b6e445ad57eda490d9add04","signer":"crovia.substrate","subject":{"observed_at":"2026-06-01T04:43:13Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2509.12440"},"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":"597248fb7daba69a2927dbfbf0007d3c97f4d5a4d68c016ad2b1e7c8d89aee63","leaf_index":164061,"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":"7c4116a00f7d695175999a378e9764d1b4206558a56bd1aa4da38e5750848f17","side":"left"},{"sibling":"4bf3fcbcc640906b02cafa9933fac017d3086246cd443ad8ba2be99610e58c2c","side":"right"},{"sibling":"acd20c1170bb8638105ba66b4f66cf82461795d2eef1c8135286515000e4ec45","side":"left"},{"sibling":"7540daa3359a500758df7cd3fdaa77293fc68d46652a2df2d62a354902b33b03","side":"left"},{"sibling":"b16a4bcc52aab207ead32190e85857efb7942983d3249d5b8971eea646e7588b","side":"left"},{"sibling":"64adb5bce7321511a79350afc07efd61fa36fccbb0acace802969f448bc3148b","side":"right"},{"sibling":"6b9f5e8f735af934c2b99502e36dfe0c82b536ef2c88dafbb196d5ab8771a38f","side":"left"},{"sibling":"c2ed258674acbec09c8c9dbf15c89e6fc50854c6eb5f8d42b378de7db248641a","side":"left"},{"sibling":"86fede29e507d01bfe35484a1579149e8e99b3527ff48559423f6056d11af46a","side":"right"},{"sibling":"fc601f0745c37fc5f7c249300e654db05d61bb9059885eeb0b0a5047b5d28408","side":"right"},{"sibling":"6ed9290cdae063f13bfeb71c4c5440595cabb61fd4b39225b9cc913ffb336dd7","side":"right"},{"sibling":"a0446b923d1ce90021e78edff07f6bfc7cc2a1326a565c5f0786b82a24dd0a2a","side":"right"},{"sibling":"e598fd53912c30e58ca8e58d7d8a338fe0f2ecb63fdd99225bc703c499c948ec","side":"right"},{"sibling":"fc4873333221ec8167697f75b6f6a8a08491a8cf18952defb65fb6d4958fa5e7","side":"right"},{"sibling":"05c8a827da2a05549ee3250310777009120c687885816bf6c7c74801bfaa346d","side":"right"},{"sibling":"5ea2f2dc9f046df723b6bd9932d61a9a3d80a76e79ce1b939b3d93ff79b5a91c","side":"left"},{"sibling":"ce41d9b82f34b16efd653dfb3552acc4e2512939e47903e5fc979fbed00c5764","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":164217,"merkle_root":"a1098816aea1b60b8fe37b62410469bc5024a2c335bbec4f6ef2add7875dbdf2","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260601T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-01T05:37:41Z","sig_algorithm":"ed25519","signature":"d7f91db1d54b9495c499440c2828f4bd53360555391ce6e25adea5183bc1fa0f697d80708a099d0b0429e6f8cb6c71e7fccf82acb3c84481149974fb26074708","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_33039cc23eccab7c354d3f49cf59d2be59ea72312b598086c6c7716c1ae7ec7f"}}