{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XPGVLTNRJXK6R6CP6E47RE46I5","short_pith_number":"pith:XPGVLTNR","canonical_record":{"source":{"id":"2502.09525","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T17:37:42Z","cross_cats_sorted":["cs.DS","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"0ecbc3f77b6a01469947987441ba2e80593c7d2251d7fda01e379d14ca1d17e6","abstract_canon_sha256":"1a957edec0644bbb8e6dbd8c154be668f2da06c5851194cd461d4868acff0855"},"schema_version":"1.0"},"canonical_sha256":"bbcd55cdb14dd5e8f84ff139f8939e4759a75ccce170e007a4e3a6d30ad82a47","source":{"kind":"arxiv","id":"2502.09525","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09525","created_at":"2026-07-05T10:48:57Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09525v2","created_at":"2026-07-05T10:48:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09525","created_at":"2026-07-05T10:48:57Z"},{"alias_kind":"pith_short_12","alias_value":"XPGVLTNRJXK6","created_at":"2026-07-05T10:48:57Z"},{"alias_kind":"pith_short_16","alias_value":"XPGVLTNRJXK6R6CP","created_at":"2026-07-05T10:48:57Z"},{"alias_kind":"pith_short_8","alias_value":"XPGVLTNR","created_at":"2026-07-05T10:48:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XPGVLTNRJXK6R6CP6E47RE46I5","target":"record","payload":{"canonical_record":{"source":{"id":"2502.09525","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T17:37:42Z","cross_cats_sorted":["cs.DS","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"0ecbc3f77b6a01469947987441ba2e80593c7d2251d7fda01e379d14ca1d17e6","abstract_canon_sha256":"1a957edec0644bbb8e6dbd8c154be668f2da06c5851194cd461d4868acff0855"},"schema_version":"1.0"},"canonical_sha256":"bbcd55cdb14dd5e8f84ff139f8939e4759a75ccce170e007a4e3a6d30ad82a47","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:48:57.780331Z","signature_b64":"6yUjPdZgigrNL+vLrm0n9/x0GtNpHWpVEpMNhJJs2HQg35k/HT/TP9jVQ2O5QmyMsCWyOtD4nK1qjA99vGTwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbcd55cdb14dd5e8f84ff139f8939e4759a75ccce170e007a4e3a6d30ad82a47","last_reissued_at":"2026-07-05T10:48:57.779859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:48:57.779859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.09525","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:48:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nlLmQoAxnOn8GUeI3dNiSCuohur3EEZ1Mf37PGQKlHhfRtLf/z/fQZPYx+yr26y4KgqQ6MepUmNKG+AJc51VAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:53:43.362779Z"},"content_sha256":"9c2d37073984a89efde751714b1f524e070d7fcbcda3a9990b2cb8758c45cff0","schema_version":"1.0","event_id":"sha256:9c2d37073984a89efde751714b1f524e070d7fcbcda3a9990b2cb8758c45cff0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XPGVLTNRJXK6R6CP6E47RE46I5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Learning of Multi-index Models via Iterative Subspace Approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Daniel M. Kane, Giannis Iakovidis, Ilias Diakonikolas, Nikos Zarifis","submitted_at":"2025-02-13T17:37:42Z","abstract_excerpt":"We study the task of learning Multi-Index Models (MIMs) with label noise under the Gaussian distribution. A $K$-MIM is any function $f$ that only depends on a $K$-dimensional subspace. We focus on well-behaved MIMs with finite ranges that satisfy certain regularity properties. Our main contribution is a general robust learner that is qualitatively optimal in the Statistical Query (SQ) model. Our algorithm iteratively constructs better approximations to the defining subspace by computing low-degree moments conditional on the projection to the subspace computed thus far, and adding directions wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09525","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.09525/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:48:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JbrV1PYSGG0xub23E6y95LoWsBPzawQ4KjgCtTSBxrzDNbyPszlWeZb1A5F2dG9+rLhRsRke9veS3vRGx2A5Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:53:43.363316Z"},"content_sha256":"a3eefdd3744acecf79b29d7e1cb01f071882356d4e6e6982b2bb21078a728145","schema_version":"1.0","event_id":"sha256:a3eefdd3744acecf79b29d7e1cb01f071882356d4e6e6982b2bb21078a728145"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XPGVLTNRJXK6R6CP6E47RE46I5/bundle.json","state_url":"https://pith.science/pith/XPGVLTNRJXK6R6CP6E47RE46I5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XPGVLTNRJXK6R6CP6E47RE46I5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T15:53:43Z","links":{"resolver":"https://pith.science/pith/XPGVLTNRJXK6R6CP6E47RE46I5","bundle":"https://pith.science/pith/XPGVLTNRJXK6R6CP6E47RE46I5/bundle.json","state":"https://pith.science/pith/XPGVLTNRJXK6R6CP6E47RE46I5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XPGVLTNRJXK6R6CP6E47RE46I5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XPGVLTNRJXK6R6CP6E47RE46I5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1a957edec0644bbb8e6dbd8c154be668f2da06c5851194cd461d4868acff0855","cross_cats_sorted":["cs.DS","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T17:37:42Z","title_canon_sha256":"0ecbc3f77b6a01469947987441ba2e80593c7d2251d7fda01e379d14ca1d17e6"},"schema_version":"1.0","source":{"id":"2502.09525","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.09525","created_at":"2026-07-05T10:48:57Z"},{"alias_kind":"arxiv_version","alias_value":"2502.09525v2","created_at":"2026-07-05T10:48:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09525","created_at":"2026-07-05T10:48:57Z"},{"alias_kind":"pith_short_12","alias_value":"XPGVLTNRJXK6","created_at":"2026-07-05T10:48:57Z"},{"alias_kind":"pith_short_16","alias_value":"XPGVLTNRJXK6R6CP","created_at":"2026-07-05T10:48:57Z"},{"alias_kind":"pith_short_8","alias_value":"XPGVLTNR","created_at":"2026-07-05T10:48:57Z"}],"graph_snapshots":[{"event_id":"sha256:a3eefdd3744acecf79b29d7e1cb01f071882356d4e6e6982b2bb21078a728145","target":"graph","created_at":"2026-07-05T10:48:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.09525/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the task of learning Multi-Index Models (MIMs) with label noise under the Gaussian distribution. A $K$-MIM is any function $f$ that only depends on a $K$-dimensional subspace. We focus on well-behaved MIMs with finite ranges that satisfy certain regularity properties. Our main contribution is a general robust learner that is qualitatively optimal in the Statistical Query (SQ) model. Our algorithm iteratively constructs better approximations to the defining subspace by computing low-degree moments conditional on the projection to the subspace computed thus far, and adding directions wi","authors_text":"Daniel M. Kane, Giannis Iakovidis, Ilias Diakonikolas, Nikos Zarifis","cross_cats":["cs.DS","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T17:37:42Z","title":"Robust Learning of Multi-index Models via Iterative Subspace Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09525","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9c2d37073984a89efde751714b1f524e070d7fcbcda3a9990b2cb8758c45cff0","target":"record","created_at":"2026-07-05T10:48:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1a957edec0644bbb8e6dbd8c154be668f2da06c5851194cd461d4868acff0855","cross_cats_sorted":["cs.DS","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-13T17:37:42Z","title_canon_sha256":"0ecbc3f77b6a01469947987441ba2e80593c7d2251d7fda01e379d14ca1d17e6"},"schema_version":"1.0","source":{"id":"2502.09525","kind":"arxiv","version":2}},"canonical_sha256":"bbcd55cdb14dd5e8f84ff139f8939e4759a75ccce170e007a4e3a6d30ad82a47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbcd55cdb14dd5e8f84ff139f8939e4759a75ccce170e007a4e3a6d30ad82a47","first_computed_at":"2026-07-05T10:48:57.779859Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:57.779859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6yUjPdZgigrNL+vLrm0n9/x0GtNpHWpVEpMNhJJs2HQg35k/HT/TP9jVQ2O5QmyMsCWyOtD4nK1qjA99vGTwDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:57.780331Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.09525","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9c2d37073984a89efde751714b1f524e070d7fcbcda3a9990b2cb8758c45cff0","sha256:a3eefdd3744acecf79b29d7e1cb01f071882356d4e6e6982b2bb21078a728145"],"state_sha256":"a5ebe650901a7308f157f98b323d33c0819ac3a30ee89e80e4f63eb5bd7ea396"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ywroBNf3E6ySoQbgUu3UbT4Ptp/yZxEvasVvl+C0va0QmUR5g7aDJfVvPNf4niovd8XeXzm5zpB3gae6OklUDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T15:53:43.368735Z","bundle_sha256":"ac2a36f30383bb919f4a062e17640846f30c01063642f688cbbc4aa913f06189"}}