{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U3E6Y3MTMFCRSEPLNLWUTVD3HR","short_pith_number":"pith:U3E6Y3MT","schema_version":"1.0","canonical_sha256":"a6c9ec6d9361451911eb6aed49d47b3c5ef3f6c0df5b1a0711cff4018c1b1596","source":{"kind":"arxiv","id":"2605.13143","version":1},"attestation_state":"computed","paper":{"title":"On the Generalization of Knowledge Distillation: An Information-Theoretic View","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Knowledge distillation generalization is bounded by the KL divergence between teacher and student training kernels.","cross_cats":["cs.LG","math.IT"],"primary_cat":"cs.IT","authors_text":"Bingying Li, Haiyun He","submitted_at":"2026-05-13T08:10:05Z","abstract_excerpt":"Knowledge distillation is widely used to improve generalization in practice, yet its theoretical understanding remains elusive. In the standard distillation setting, a teacher model provides soft predictions to guide the training of a student model. We model teacher and student training as coupled stochastic processes and introduce a distillation divergence, defined as the Kullback-Leibler divergence between these two stochastic kernels. Within this framework, we derive two generalization bounds for the student model relative to the teacher's generalization gap: an upper bound under a sub-Gaus"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13143","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2026-05-13T08:10:05Z","cross_cats_sorted":["cs.LG","math.IT"],"title_canon_sha256":"9e2d525555f8b45ca44c8252dce441cbd5e0ead050b8a393bfa1ec933bbe24fd","abstract_canon_sha256":"ec92b10b055b4c51f8bfeb8b5d713232228d3308586cc7838a46d764aef1b4e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:57.368619Z","signature_b64":"Y7+varc9ATZbatH6qNaJJPnd1bD0tTnGNtvx21rVl29sjBH/ZgD+c+PWHiqZk0jF5dWp47xjZ2iu83fJ0kYoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6c9ec6d9361451911eb6aed49d47b3c5ef3f6c0df5b1a0711cff4018c1b1596","last_reissued_at":"2026-05-18T03:08:57.367582Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:57.367582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Generalization of Knowledge Distillation: An Information-Theoretic View","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Knowledge distillation generalization is bounded by the KL divergence between teacher and student training kernels.","cross_cats":["cs.LG","math.IT"],"primary_cat":"cs.IT","authors_text":"Bingying Li, Haiyun He","submitted_at":"2026-05-13T08:10:05Z","abstract_excerpt":"Knowledge distillation is widely used to improve generalization in practice, yet its theoretical understanding remains elusive. In the standard distillation setting, a teacher model provides soft predictions to guide the training of a student model. We model teacher and student training as coupled stochastic processes and introduce a distillation divergence, defined as the Kullback-Leibler divergence between these two stochastic kernels. Within this framework, we derive two generalization bounds for the student model relative to the teacher's generalization gap: an upper bound under a sub-Gaus"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We derive two generalization bounds for the student model relative to the teacher's generalization gap: an upper bound under a sub-Gaussian assumption via algorithmic stability, and a lower bound under a central condition with sharper dependence on the distillation divergence. We further develop a loss-sharpness-aware bound with an explicit tightness regime, showing that the teacher's local flatness can strictly tighten the bound.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The modeling of teacher and student training as coupled stochastic processes whose kernels admit a well-defined KL divergence; the sub-Gaussian assumption required for the stability upper bound; and the central condition required for the lower bound.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Knowledge distillation generalization bounds are derived via a new distillation divergence measuring teacher-student kernel difference, with tighter bounds from teacher loss flatness.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Knowledge distillation generalization is bounded by the KL divergence between teacher and student training kernels.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"465d037b85ef728b0b3a698cc4a1fa9bcc54f8866c8876828c6bcf47afab11ed"},"source":{"id":"2605.13143","kind":"arxiv","version":1},"verdict":{"id":"9a1a90dd-91fd-4198-ab52-778d0780dd9a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T20:17:32.574187Z","strongest_claim":"We derive two generalization bounds for the student model relative to the teacher's generalization gap: an upper bound under a sub-Gaussian assumption via algorithmic stability, and a lower bound under a central condition with sharper dependence on the distillation divergence. We further develop a loss-sharpness-aware bound with an explicit tightness regime, showing that the teacher's local flatness can strictly tighten the bound.","one_line_summary":"Knowledge distillation generalization bounds are derived via a new distillation divergence measuring teacher-student kernel difference, with tighter bounds from teacher loss flatness.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The modeling of teacher and student training as coupled stochastic processes whose kernels admit a well-defined KL divergence; the sub-Gaussian assumption required for the stability upper bound; and the central condition required for the lower bound.","pith_extraction_headline":"Knowledge distillation generalization is bounded by the KL divergence between teacher and student training kernels."},"references":{"count":27,"sample":[{"doi":"","year":2015,"title":"Distilling the Knowledge in a Neural Network","work_id":"d927ab1f-17b8-4002-9d09-c3d55764fbad","ref_index":1,"cited_arxiv_id":"1503.02531","is_internal_anchor":true},{"doi":"","year":2018,"title":"Y . Zhang, T. Xiang, T. M. Hospedales, and H. Lu, “Deep mutual learning,” inProceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2018","work_id":"dc2acf6a-0b71-49b1-afcb-66e6af5f3cfa","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1145/3097983","year":2017,"title":"In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","work_id":"549e2be2-2a91-45cb-975d-7e91ebca64c1","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"Towards understanding knowledge distillation,","work_id":"4b8048df-7596-42b7-bbf8-ca6b43789c73","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"Do deep nets really need to be deep?","work_id":"e6d1e85f-e2c2-4839-ae24-a62aa2c387d0","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":27,"snapshot_sha256":"eb41b6dfbea3ce4f0030c1ba790fd7c6768ce31f429689eb196e394bb2c26912","internal_anchors":2},"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":"2605.13143","created_at":"2026-05-18T03:08:57.367760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13143v1","created_at":"2026-05-18T03:08:57.367760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13143","created_at":"2026-05-18T03:08:57.367760+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3E6Y3MTMFCR","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3E6Y3MTMFCRSEPL","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3E6Y3MT","created_at":"2026-05-18T12:33:37.589309+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/U3E6Y3MTMFCRSEPLNLWUTVD3HR","json":"https://pith.science/pith/U3E6Y3MTMFCRSEPLNLWUTVD3HR.json","graph_json":"https://pith.science/api/pith-number/U3E6Y3MTMFCRSEPLNLWUTVD3HR/graph.json","events_json":"https://pith.science/api/pith-number/U3E6Y3MTMFCRSEPLNLWUTVD3HR/events.json","paper":"https://pith.science/paper/U3E6Y3MT"},"agent_actions":{"view_html":"https://pith.science/pith/U3E6Y3MTMFCRSEPLNLWUTVD3HR","download_json":"https://pith.science/pith/U3E6Y3MTMFCRSEPLNLWUTVD3HR.json","view_paper":"https://pith.science/paper/U3E6Y3MT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13143&json=true","fetch_graph":"https://pith.science/api/pith-number/U3E6Y3MTMFCRSEPLNLWUTVD3HR/graph.json","fetch_events":"https://pith.science/api/pith-number/U3E6Y3MTMFCRSEPLNLWUTVD3HR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3E6Y3MTMFCRSEPLNLWUTVD3HR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3E6Y3MTMFCRSEPLNLWUTVD3HR/action/storage_attestation","attest_author":"https://pith.science/pith/U3E6Y3MTMFCRSEPLNLWUTVD3HR/action/author_attestation","sign_citation":"https://pith.science/pith/U3E6Y3MTMFCRSEPLNLWUTVD3HR/action/citation_signature","submit_replication":"https://pith.science/pith/U3E6Y3MTMFCRSEPLNLWUTVD3HR/action/replication_record"}},"created_at":"2026-05-18T03:08:57.367760+00:00","updated_at":"2026-05-18T03:08:57.367760+00:00"}