{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TCZQENFJMSGHEDM5O4IFVN7V5I","short_pith_number":"pith:TCZQENFJ","canonical_record":{"source":{"id":"2502.01583","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-03T18:08:30Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.PR","math.ST","stat.TH"],"title_canon_sha256":"51d1f90b48246bdee77876b340645c4344dbd55f6e7ee2ccf3a094ba352a5af9","abstract_canon_sha256":"7c6a0d95d55ba5ebf203114aa9a3b58a44b1a89338bf30bde8743a9e43f7a251"},"schema_version":"1.0"},"canonical_sha256":"98b30234a9648c720d9d77105ab7f5ea1f6e8d275fde5529eb3f79f8c7e40156","source":{"kind":"arxiv","id":"2502.01583","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01583","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01583v2","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01583","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"pith_short_12","alias_value":"TCZQENFJMSGH","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"pith_short_16","alias_value":"TCZQENFJMSGHEDM5","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"pith_short_8","alias_value":"TCZQENFJ","created_at":"2026-07-05T11:19:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TCZQENFJMSGHEDM5O4IFVN7V5I","target":"record","payload":{"canonical_record":{"source":{"id":"2502.01583","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-03T18:08:30Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.PR","math.ST","stat.TH"],"title_canon_sha256":"51d1f90b48246bdee77876b340645c4344dbd55f6e7ee2ccf3a094ba352a5af9","abstract_canon_sha256":"7c6a0d95d55ba5ebf203114aa9a3b58a44b1a89338bf30bde8743a9e43f7a251"},"schema_version":"1.0"},"canonical_sha256":"98b30234a9648c720d9d77105ab7f5ea1f6e8d275fde5529eb3f79f8c7e40156","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:03.190027Z","signature_b64":"Bkf6vwwssGrauR/h+anquWc9fwFk7nh7AvrPppDPU1yQUoVwDTd/oHtmVPTewS190WHuPCNno2iS5E1sM8V6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"98b30234a9648c720d9d77105ab7f5ea1f6e8d275fde5529eb3f79f8c7e40156","last_reissued_at":"2026-07-05T11:19:03.189580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:03.189580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.01583","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":"2026-07-05T11:19:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xYi/P4nS/ItHG7D3lwursPUP6/BfXUDcda1jaJHvaJ4KJww40017LE+GZU4jOn1oBN0e+BdsWJ+qYKW7IY0pAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:51:48.046775Z"},"content_sha256":"6dc1b21b442b2e2c69a7e839bf36f903040a0ae22757b49ce48c0f0f4553d89b","schema_version":"1.0","event_id":"sha256:6dc1b21b442b2e2c69a7e839bf36f903040a0ae22757b49ce48c0f0f4553d89b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TCZQENFJMSGHEDM5O4IFVN7V5I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Spectral Estimators for Multi-Index Models: Precise Asymptotics and Optimal Weak Recovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","math.PR","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Filip Kova\\v{c}evi\\'c, Marco Mondelli, Yihan Zhang","submitted_at":"2025-02-03T18:08:30Z","abstract_excerpt":"Multi-index models provide a popular framework to investigate the learnability of functions with low-dimensional structure and, also due to their connections with neural networks, they have been object of recent intensive study. In this paper, we focus on recovering the subspace spanned by the signals via spectral estimators -- a family of methods routinely used in practice, often as a warm-start for iterative algorithms. Our main technical contribution is a precise asymptotic characterization of the performance of spectral methods, when sample size and input dimension grow proportionally and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01583","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/2502.01583/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":"2026-07-05T11:19:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0AvQ9nVs+3/r5WeuGbHfGtGShp2rOlRkkmY3vpTkJjQLOoBJqjTXK3RfjJU5iU8GVN9LZgoIGfejUV013DVeBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:51:48.047277Z"},"content_sha256":"59ca3c1d1d8e57fdad09b74d45942936bd25d3b6c37310384910c91429babae7","schema_version":"1.0","event_id":"sha256:59ca3c1d1d8e57fdad09b74d45942936bd25d3b6c37310384910c91429babae7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TCZQENFJMSGHEDM5O4IFVN7V5I/bundle.json","state_url":"https://pith.science/pith/TCZQENFJMSGHEDM5O4IFVN7V5I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TCZQENFJMSGHEDM5O4IFVN7V5I/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":"2026-08-09T19:51:48Z","links":{"resolver":"https://pith.science/pith/TCZQENFJMSGHEDM5O4IFVN7V5I","bundle":"https://pith.science/pith/TCZQENFJMSGHEDM5O4IFVN7V5I/bundle.json","state":"https://pith.science/pith/TCZQENFJMSGHEDM5O4IFVN7V5I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TCZQENFJMSGHEDM5O4IFVN7V5I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TCZQENFJMSGHEDM5O4IFVN7V5I","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":"7c6a0d95d55ba5ebf203114aa9a3b58a44b1a89338bf30bde8743a9e43f7a251","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.PR","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-03T18:08:30Z","title_canon_sha256":"51d1f90b48246bdee77876b340645c4344dbd55f6e7ee2ccf3a094ba352a5af9"},"schema_version":"1.0","source":{"id":"2502.01583","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.01583","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"arxiv_version","alias_value":"2502.01583v2","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.01583","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"pith_short_12","alias_value":"TCZQENFJMSGH","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"pith_short_16","alias_value":"TCZQENFJMSGHEDM5","created_at":"2026-07-05T11:19:03Z"},{"alias_kind":"pith_short_8","alias_value":"TCZQENFJ","created_at":"2026-07-05T11:19:03Z"}],"graph_snapshots":[{"event_id":"sha256:59ca3c1d1d8e57fdad09b74d45942936bd25d3b6c37310384910c91429babae7","target":"graph","created_at":"2026-07-05T11:19:03Z","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/2502.01583/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-index models provide a popular framework to investigate the learnability of functions with low-dimensional structure and, also due to their connections with neural networks, they have been object of recent intensive study. In this paper, we focus on recovering the subspace spanned by the signals via spectral estimators -- a family of methods routinely used in practice, often as a warm-start for iterative algorithms. Our main technical contribution is a precise asymptotic characterization of the performance of spectral methods, when sample size and input dimension grow proportionally and ","authors_text":"Filip Kova\\v{c}evi\\'c, Marco Mondelli, Yihan Zhang","cross_cats":["cs.IT","cs.LG","math.IT","math.PR","math.ST","stat.TH"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-03T18:08:30Z","title":"Spectral Estimators for Multi-Index Models: Precise Asymptotics and Optimal Weak Recovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.01583","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":"sha256:6dc1b21b442b2e2c69a7e839bf36f903040a0ae22757b49ce48c0f0f4553d89b","target":"record","created_at":"2026-07-05T11:19:03Z","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":"7c6a0d95d55ba5ebf203114aa9a3b58a44b1a89338bf30bde8743a9e43f7a251","cross_cats_sorted":["cs.IT","cs.LG","math.IT","math.PR","math.ST","stat.TH"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-03T18:08:30Z","title_canon_sha256":"51d1f90b48246bdee77876b340645c4344dbd55f6e7ee2ccf3a094ba352a5af9"},"schema_version":"1.0","source":{"id":"2502.01583","kind":"arxiv","version":2}},"canonical_sha256":"98b30234a9648c720d9d77105ab7f5ea1f6e8d275fde5529eb3f79f8c7e40156","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"98b30234a9648c720d9d77105ab7f5ea1f6e8d275fde5529eb3f79f8c7e40156","first_computed_at":"2026-07-05T11:19:03.189580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:03.189580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bkf6vwwssGrauR/h+anquWc9fwFk7nh7AvrPppDPU1yQUoVwDTd/oHtmVPTewS190WHuPCNno2iS5E1sM8V6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:03.190027Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.01583","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6dc1b21b442b2e2c69a7e839bf36f903040a0ae22757b49ce48c0f0f4553d89b","sha256:59ca3c1d1d8e57fdad09b74d45942936bd25d3b6c37310384910c91429babae7"],"state_sha256":"cf53f4b28260fc2ae7d65c6b04dce2fb442bf39ba49dbcb14b564e3249df58f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oXKdTpgPNnnsIPOufR3KZaVlrsUAeYvqNTo2vHcA3qXNUDZ+o9QxD0fAWGV4h1PECROMjZPhQHC/EuKtRaIyBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:51:48.051611Z","bundle_sha256":"62b25f5a54af564022b153f0d0e655203d44a1a474797b94b1c69f56d15fa7f3"}}