{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:I7FL4N5TTYUMZPZDQBD2ATZ2YU","short_pith_number":"pith:I7FL4N5T","schema_version":"1.0","canonical_sha256":"47cabe37b39e28ccbf238047a04f3ac534045429ce0d4d4d39ad824623c7a813","source":{"kind":"arxiv","id":"2102.13088","version":2},"attestation_state":"computed","paper":{"title":"Even your Teacher Needs Guidance: Ground-Truth Targets Dampen Regularization Imposed by Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kenneth Borup, Lars N. Andersen","submitted_at":"2021-02-25T18:56:09Z","abstract_excerpt":"Knowledge distillation is classically a procedure where a neural network is trained on the output of another network along with the original targets in order to transfer knowledge between the architectures. The special case of self-distillation, where the network architectures are identical, has been observed to improve generalization accuracy. In this paper, we consider an iterative variant of self-distillation in a kernel regression setting, in which successive steps incorporate both model outputs and the ground-truth targets. This allows us to provide the first theoretical results on the im"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2102.13088","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-25T18:56:09Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f0182aa083a92377901d5cae49f58d7171100c3f688c62a355c39f5b123fee9e","abstract_canon_sha256":"3d1ff76205116c4c0eb60600756e9ec7df65cb6e5e87370e978c07b378d4cc4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:45.316158Z","signature_b64":"f7ttesxpSm80cHRpEykTpbJnIi4ysxwSDNyxo+Htiw0sOwZ801I/lG081fbV/cCiUoh1yGerrCzPkkqpok90Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47cabe37b39e28ccbf238047a04f3ac534045429ce0d4d4d39ad824623c7a813","last_reissued_at":"2026-07-05T03:22:45.315648Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:45.315648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Even your Teacher Needs Guidance: Ground-Truth Targets Dampen Regularization Imposed by Self-Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kenneth Borup, Lars N. Andersen","submitted_at":"2021-02-25T18:56:09Z","abstract_excerpt":"Knowledge distillation is classically a procedure where a neural network is trained on the output of another network along with the original targets in order to transfer knowledge between the architectures. The special case of self-distillation, where the network architectures are identical, has been observed to improve generalization accuracy. In this paper, we consider an iterative variant of self-distillation in a kernel regression setting, in which successive steps incorporate both model outputs and the ground-truth targets. This allows us to provide the first theoretical results on the im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.13088","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/2102.13088/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2102.13088","created_at":"2026-07-05T03:22:45.315706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.13088v2","created_at":"2026-07-05T03:22:45.315706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.13088","created_at":"2026-07-05T03:22:45.315706+00:00"},{"alias_kind":"pith_short_12","alias_value":"I7FL4N5TTYUM","created_at":"2026-07-05T03:22:45.315706+00:00"},{"alias_kind":"pith_short_16","alias_value":"I7FL4N5TTYUMZPZD","created_at":"2026-07-05T03:22:45.315706+00:00"},{"alias_kind":"pith_short_8","alias_value":"I7FL4N5T","created_at":"2026-07-05T03:22:45.315706+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I7FL4N5TTYUMZPZDQBD2ATZ2YU","json":"https://pith.science/pith/I7FL4N5TTYUMZPZDQBD2ATZ2YU.json","graph_json":"https://pith.science/api/pith-number/I7FL4N5TTYUMZPZDQBD2ATZ2YU/graph.json","events_json":"https://pith.science/api/pith-number/I7FL4N5TTYUMZPZDQBD2ATZ2YU/events.json","paper":"https://pith.science/paper/I7FL4N5T"},"agent_actions":{"view_html":"https://pith.science/pith/I7FL4N5TTYUMZPZDQBD2ATZ2YU","download_json":"https://pith.science/pith/I7FL4N5TTYUMZPZDQBD2ATZ2YU.json","view_paper":"https://pith.science/paper/I7FL4N5T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.13088&json=true","fetch_graph":"https://pith.science/api/pith-number/I7FL4N5TTYUMZPZDQBD2ATZ2YU/graph.json","fetch_events":"https://pith.science/api/pith-number/I7FL4N5TTYUMZPZDQBD2ATZ2YU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I7FL4N5TTYUMZPZDQBD2ATZ2YU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I7FL4N5TTYUMZPZDQBD2ATZ2YU/action/storage_attestation","attest_author":"https://pith.science/pith/I7FL4N5TTYUMZPZDQBD2ATZ2YU/action/author_attestation","sign_citation":"https://pith.science/pith/I7FL4N5TTYUMZPZDQBD2ATZ2YU/action/citation_signature","submit_replication":"https://pith.science/pith/I7FL4N5TTYUMZPZDQBD2ATZ2YU/action/replication_record"}},"created_at":"2026-07-05T03:22:45.315706+00:00","updated_at":"2026-07-05T03:22:45.315706+00:00"}