{"_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_2f4392b76cc9967c2013c319f46888b38f1b93aaa57a98d67ded7dec01b10553","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_2f4392b76cc9967c2013c319f46888b38f1b93aaa57a98d67ded7dec01b10553","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"2f0cdd414eeb1532a245efa128a852f5295115331de32c958f0d15a1109bf36b","published":"Wed, 22 Jul 2026 00:00:00 -0400","receipt_hash":"2f0cdd414eeb1532a245efa128a852f5295115331de32c958f0d15a1109bf36b","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":"2f0cdd414eeb1532a245efa128a852f5295115331de32c958f0d15a1109bf36b","observed_at":"2026-07-22T04:43:18.261256Z","parent_run_hash":"4765c85b8b4b27ff9a690c1ae11c3b009baa2c60297295f395ad422f5afed68c","published":"Wed, 22 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:2606.16952v2 Announce Type: replace-cross \nAbstract: The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets. However, generating high-utility synthetic data often carries the risk of memorizing and regurgitating private information from the training corpus. In this work, we present a customizable empirical auditing framework designed to detect and explain such data disclosures. Our framework introduces a mechanism to distinguish between \"true disclosures\"-where the system directly reproduces a user's information-and \"phantom disclosures''-where the system incidentally generates a user's data. By partitioning input data into training and holdout sets and applying rigorous statistical hypothesis testing, we determine if observed disclosures are consistent with strict privacy baselines, such as zero-learning or specific Differential Privacy (DP) bounds. Crucially","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","url":"https://arxiv.org/abs/2606.16952","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.16952v2 Announce Type: replace-cross \nAbstract: The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets. However, generating high-utility synthetic data often carries the risk of memorizing and regurgitating private information from the training corpus. In this work, we present a customizable empirical auditing framework designed to detect and explain such data disclosures. Our framework introduces a mechanism to distinguish between \"true disclosures\"-where the system directly reproduces a user's information-and \"phantom disclosures''-where the system incidentally generates a user's data. By partitioning input data into training and holdout sets and applying rigorous statistical hypothesis testing, we determine if observed disclosures are consistent with strict privacy baselines, such as zero-learning or specific Differential Privacy (DP) bounds. Crucially","title":"Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-22T04:43:18Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.16952"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:a397a8fecb68faa092085b2f078ceb1ba8173cbf704577761d5fad0016c839ef3fe5b655ea2fd1216366d1cc37283ab8fdcf5fa5638de13e9db8dd0deba60505","signer":"crovia.substrate","subject":{"observed_at":"2026-07-22T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.16952"},"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":"176c76f73a16e73528e312bdd3ae29fefc4732fca80182dae7aaaf0bb8edf4bf","leaf_index":340416,"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":"8272a2ac5d8a0e64449689fc39d3a93912193c4214c3198570fe6877f1cba320","side":"right"},{"sibling":"e7596aced0e0036ec26678577fdd47ee0b406b4af560ac6a52b70ae6d40ef08a","side":"right"},{"sibling":"4e9573dbcd535e0e000962bbe79ba60ac3bfb93195663cf0851b30677834fe5b","side":"right"},{"sibling":"e29de7a76e04358204ceb5d975e0dd12ca378fe371a6e12df2f32aa3253d4ef0","side":"right"},{"sibling":"19b2ed8d087fedaee101559083db0b80d75c923d902b218d89860e6af335aae4","side":"right"},{"sibling":"a57e92d63b010c5b62c98864bb8cae1dcb58e4fc847798938d37f421f42b19d2","side":"right"},{"sibling":"59ec0f16698aa66a7cbc22ab77872ce579117827bc4c3ee9e52b0edfef8840fc","side":"left"},{"sibling":"5666268df88c3cf54274085bda986b69261da088d4bea21e6975025aadd566d3","side":"left"},{"sibling":"99d4b7aea5e7c917c580af0f1a9556bbd4d44f3f36cf9391892e7ef0340a8258","side":"left"},{"sibling":"c7fc9d4187cdc36f4c03b4b13daf4b880ea65536b051f71a5cc2543839d02697","side":"right"},{"sibling":"1758ec6ac206ce40e8368cb702195322fe3737d0fb03d8bd9e3b30acc4fa7d81","side":"right"},{"sibling":"0c407f0d553cf3fab8f9bd79205b8180e090cbf29fa0490ebb55155041ad5c86","side":"right"},{"sibling":"2dd9cb2521044ee7c6b74f2315e0a0253b8df0d04a7b810bbbbe7da5a9788769","side":"left"},{"sibling":"21d66dd41003813f710b7617944f1bfba3258658a5d3370c21cad8f9e945bc99","side":"left"},{"sibling":"787ee3744642ff909d610b0514cb100784f0ef1ba0ef4c70a0dc91f0ab2bb192","side":"right"},{"sibling":"9fc8a8ebbc1bff7e62b9f1e1c681c91e7196092ce9551573df6e23096df13e4d","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"ee6f33920899d9bdef2eb706dfff29e26eea61e29ea9824c6c8e6bcd48275d76","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":340557,"merkle_root":"7d45d94f20b5bf82263df45b87749e19e06161972f25141dd573cc138d566338","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260722T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-22T05:38:39Z","sig_algorithm":"ed25519","signature":"812cb61e90d3582ba508db8515c4168bbf8ee1c6762885609049d012f680f8068f15c98b9accf2042047dcfc6a6fc3885820ee34b0be350846386f64f2591309","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_2f4392b76cc9967c2013c319f46888b38f1b93aaa57a98d67ded7dec01b10553"}}