{"_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_a59ac595d8da0e548ba042dc9bbcba2aa926ec136aabfc67f56db018f73591ed","bitcoin_anchor":{"bitcoin_attestations":["bitcoin_block_949451"],"calendar_attestations":["https://finney.calendar.eternitywall.com","https://btc.calendar.catallaxy.com","https://alice.btc.calendar.opentimestamps.org","https://bob.btc.calendar.opentimestamps.org"],"ots_url":"/registry/data/substrate/anchors/77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3.ots","stamped_at":"2026-05-15T03:00:03Z","status":"bitcoin"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_arxiv_retraction_v1","root_at_anchor":"spider_arxiv_retraction_v1"}],"axiom_id":"axm_a59ac595d8da0e548ba042dc9bbcba2aa926ec136aabfc67f56db018f73591ed","axiom_type":"AX.OBS","body":{"axiom_subtype":"research.arxiv_retraction.v1","category":"research","fingerprint":"c476dab6da16db9620b428ff09064eb959908078fbabcfd6179885b756b20e2e","published":"2025-09-27T15:10:54Z","receipt_hash":"c476dab6da16db9620b428ff09064eb959908078fbabcfd6179885b756b20e2e","schema":"spider.research.arxiv_retraction.v1","spider":"arxiv_retraction","spider_record":{"axiom_subtype":"research.arxiv_retraction.v1","category":"research","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"c476dab6da16db9620b428ff09064eb959908078fbabcfd6179885b756b20e2e","observed_at":"2026-05-03T16:20:10.417417Z","parent_run_hash":null,"published":"2025-09-27T15:10:54Z","runtime_version":"0.1.0","schema":"spider.research.arxiv_retraction.v1","source_status":200,"source_url":"http://export.arxiv.org/api/query?search_query=cat:cs.LG+AND+%28abs:withdrawn+OR+abs:retracted%29&max_results=20&sortBy=submittedDate&sortOrder=descending","spider":"arxiv_retraction","summary_excerpt":"Under the data manifold hypothesis, high-dimensional data are concentrated near a low-dimensional manifold. We study the problem of Riemannian optimization over such manifolds when they are given only implicitly through the data distribution, and the standard manifold operations required by classical algorithms are unavailable. This formulation captures a broad class of data-driven design problems that are central to modern generative AI. Our key idea is to introduce a link function that connects the data distribution to the geometric operations needed for optimization. We show that this function enables the recovery of essential manifold operations, such as retraction and Riemannian gradient computation. Moreover, we establish a direct connection between our construction and the score function in diffusion models of the data distribution. This connection allows us to leverage well-studied parameterizations, efficient training procedures, and even pretrained score networks from the dif","title":"Landing with the Score: Riemannian Optimization through Denoising","url":"https://arxiv.org/pdf/2509.23357v2","vendor":"arxiv"},"summary":"Under the data manifold hypothesis, high-dimensional data are concentrated near a low-dimensional manifold. We study the problem of Riemannian optimization over such manifolds when they are given only implicitly through the data distribution, and the standard manifold operations required by classical algorithms are unavailable. This formulation captures a broad class of data-driven design problems that are central to modern generative AI. Our key idea is to introduce a link function that connects the data distribution to the geometric operations needed for optimization. We show that this function enables the recovery of essential manifold operations, such as retraction and Riemannian gradient computation. Moreover, we establish a direct connection between our construction and the score function in diffusion models of the data distribution. This connection allows us to leverage well-studied parameterizations, efficient training procedures, and even pretrained score networks from the dif","title":"Landing with the Score: Riemannian Optimization through Denoising","vendor":"arxiv"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-03T16:20:10Z","notes":"Spider arxiv_retraction (research) research.arxiv_retraction.v1","object":{"captured_by":"crovia.spider.arxiv_retraction","primary_source_url":"https://arxiv.org/pdf/2509.23357v2"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:01aa5855a033c678c2238d4cd6917a503faa840fcbc63f266dad721dda9533d183baee7bc14abd2dd1b56297353a87392d5486a3d0ae39dc392e6f92c8480304","signer":"crovia.substrate","subject":{"observed_at":"2026-05-03T16:20:10Z","source_collector":"spider:arxiv_retraction","target_id":"https://arxiv.org/pdf/2509.23357v2"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/research/arxiv_retraction_v1.jsonl\",\"source_seal_merkle_root\":\"spider_arxiv_retraction_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"1eb0e224272d8df44d94446acc8d554259011b48c25ba07d025f1481a0f202d3","leaf_index":111942,"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":"00111b7ce9e0381bd99edbd2332765c77fce6e8a9139c34d0e0ff342c9168caf","side":"right"},{"sibling":"ce68e50c486d36889d077a4497034a54c7578f626e3536caa11d58dd19f2c0ba","side":"left"},{"sibling":"4ca75102ae0eaa75b89f156a3e6551f744fa4e3cf55f2c695f0cdbe150772482","side":"left"},{"sibling":"e34d335cae85ba6a34caa45f35a0cc16a495442d839437de3a1820d7491a905a","side":"right"},{"sibling":"753774e59ee1a795f876ec420e258ae77d369aa892917f6778e4fda7d080fe34","side":"right"},{"sibling":"04f08a05f60539e5d320a1d658ae9463ad3d1673f88287d19b483af959df3046","side":"right"},{"sibling":"7cc6ec0331a098790dc04ced8e8abc2b910e0fcce6830c8442fff364ca231498","side":"left"},{"sibling":"0994d51d2178913b0e3ac7346ceed16c5ea436d841a8e7f28a99362fa269bad0","side":"right"},{"sibling":"015d2ce3c58c7a790ad078159267c63cd54f9ae7e20530115a6a423419cefe22","side":"left"},{"sibling":"5bcdb02d4310fc8bfd791789d990714b0a10f44358ffa98c446f1755352c49b8","side":"right"},{"sibling":"cf8897e1feec248f5d05e2cafec4f8c2739e2005227d28b5ccc8cfa11ed66ee4","side":"left"},{"sibling":"a6d6e5bc888edc394757fbba02b675bac6ad0831e36a6f5ebbaa4e5548f25603","side":"right"},{"sibling":"76d7c4385d71ae8104107105be66eddb792e01ed6e493db5a9b4eec5441abb76","side":"left"},{"sibling":"b03f005860bf95148ea89c703a32ca19ab7a2ca71b58bb628ff94a9edb8703b0","side":"left"},{"sibling":"21d1e30b556f553dc939fddc23e6367f0a7755ebe3dd489dc0001cef017beb7f","side":"right"},{"sibling":"f2817ab288b5324fe49770372c7a10f33f7cd11005f8d4c0a730316f5229dc98","side":"left"},{"sibling":"725fac972e772ca0dc598810ea1abc70df472f72d2d6ab8a0baee2b80e5d2f4c","side":"left"},{"sibling":"98fc57dfef8873b512edc8340f7181df57302bb96777625e072235c62d7c5895","side":"right"}]},"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":134292,"merkle_root":"77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260515T023701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-15T02:37:25Z","sig_algorithm":"ed25519","signature":"68107a834b00b24f5d4501e5ec727445311f132a486567ecc4c72a4e6dff24c8c21f2de3105293353ba5fdbe370d032819af6aa70f694e2e39b6af6737507009","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_a59ac595d8da0e548ba042dc9bbcba2aa926ec136aabfc67f56db018f73591ed"}}