{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D36ARPQ3C5XZRJWXWMXGXNC5NU","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":"feedada2a755afc85cb1596d457f4ea7fa83fcbb44c35b0c106448e2afd5b557","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-24T15:22:53Z","title_canon_sha256":"bf7d0b264b6225a0244af71802ee0d45e30e77dd8d81493f09827f101a06e616"},"schema_version":"1.0","source":{"id":"2410.18837","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18837","created_at":"2026-07-05T10:21:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18837v2","created_at":"2026-07-05T10:21:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18837","created_at":"2026-07-05T10:21:05Z"},{"alias_kind":"pith_short_12","alias_value":"D36ARPQ3C5XZ","created_at":"2026-07-05T10:21:05Z"},{"alias_kind":"pith_short_16","alias_value":"D36ARPQ3C5XZRJWX","created_at":"2026-07-05T10:21:05Z"},{"alias_kind":"pith_short_8","alias_value":"D36ARPQ3","created_at":"2026-07-05T10:21:05Z"}],"graph_snapshots":[{"event_id":"sha256:9b84dab0bb74880481e59a61828dda516afd01e21a93339d81ade8c37c71c87f","target":"graph","created_at":"2026-07-05T10:21:05Z","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/2410.18837/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A growing number of machine learning scenarios rely on knowledge distillation where one uses the output of a surrogate model as labels to supervise the training of a target model. In this work, we provide a sharp characterization of this process for ridgeless, high-dimensional regression, under two settings: (i) model shift, where the surrogate model is arbitrary, and (ii) distribution shift, where the surrogate model is the solution of empirical risk minimization with out-of-distribution data. In both cases, we characterize the precise risk of the target model through non-asymptotic bounds in","authors_text":"Ege Onur Taga, Halil Alperen Gozeten, Marco Mondelli, M. Emrullah Ildiz, Samet Oymak","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-24T15:22:53Z","title":"High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18837","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":"sha256:7e74c7242dd2ede463859a5f3f5920a3d05a9dc24d50f24eb8c542ebe5193754","target":"record","created_at":"2026-07-05T10:21:05Z","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":"feedada2a755afc85cb1596d457f4ea7fa83fcbb44c35b0c106448e2afd5b557","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-24T15:22:53Z","title_canon_sha256":"bf7d0b264b6225a0244af71802ee0d45e30e77dd8d81493f09827f101a06e616"},"schema_version":"1.0","source":{"id":"2410.18837","kind":"arxiv","version":2}},"canonical_sha256":"1efc08be1b176f98a6d7b32e6bb45d6d00b2028a7c8153291a4e80dfcdc90e3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1efc08be1b176f98a6d7b32e6bb45d6d00b2028a7c8153291a4e80dfcdc90e3c","first_computed_at":"2026-07-05T10:21:05.159728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:05.159728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hSOpR6/1XQL+ujJhe+VFD5qK9cJJMVksj2xThxzxE7LyI5/eq3G7ZKOIYy4jjzNqLuCbS48G539U3WIWbRLiDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:05.160228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18837","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e74c7242dd2ede463859a5f3f5920a3d05a9dc24d50f24eb8c542ebe5193754","sha256:9b84dab0bb74880481e59a61828dda516afd01e21a93339d81ade8c37c71c87f"],"state_sha256":"949f683fa30434d25c96e6f06cc49963be9d8c5f0d6f71693d86e00ca3c5574b"}