{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:D4NJBCF6UC6JGRPL6GQ6TPPZVW","short_pith_number":"pith:D4NJBCF6","schema_version":"1.0","canonical_sha256":"1f1a9088bea0bc9345ebf1a1e9bdf9adae00ec2c275de540cda1546a3d26eb9a","source":{"kind":"arxiv","id":"2310.19444","version":1},"attestation_state":"computed","paper":{"title":"One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Xu, Han Hu, Jianyuan Guo, Kai Han, Yehui Tang, Yunhe Wang, Zhiwei Hao","submitted_at":"2023-10-30T11:13:02Z","abstract_excerpt":"Knowledge distillation~(KD) has proven to be a highly effective approach for enhancing model performance through a teacher-student training scheme. However, most existing distillation methods are designed under the assumption that the teacher and student models belong to the same model family, particularly the hint-based approaches. By using centered kernel alignment (CKA) to compare the learned features between heterogeneous teacher and student models, we observe significant feature divergence. This divergence illustrates the ineffectiveness of previous hint-based methods in cross-architectur"},"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":"2310.19444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T11:13:02Z","cross_cats_sorted":[],"title_canon_sha256":"3df68f8ed0212e7c1ba4043c40e1b95b78b05818ef3aef8f83b2007158d4b19f","abstract_canon_sha256":"76c9c7260dbc0b454668fe4f1d611ba0a97a4e166a5da7f1aff70ea8198a749d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:51.079194Z","signature_b64":"an9nEz+aagvMw/tMHMywZ0hFf0q9qLhQJWIiIjYrR/CXCyty1Z+q549Z0XRYAnHGgxCXZtz0zsUW3YYhZ/IABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f1a9088bea0bc9345ebf1a1e9bdf9adae00ec2c275de540cda1546a3d26eb9a","last_reissued_at":"2026-07-05T07:06:51.078794Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:51.078794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chang Xu, Han Hu, Jianyuan Guo, Kai Han, Yehui Tang, Yunhe Wang, Zhiwei Hao","submitted_at":"2023-10-30T11:13:02Z","abstract_excerpt":"Knowledge distillation~(KD) has proven to be a highly effective approach for enhancing model performance through a teacher-student training scheme. However, most existing distillation methods are designed under the assumption that the teacher and student models belong to the same model family, particularly the hint-based approaches. By using centered kernel alignment (CKA) to compare the learned features between heterogeneous teacher and student models, we observe significant feature divergence. This divergence illustrates the ineffectiveness of previous hint-based methods in cross-architectur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19444","kind":"arxiv","version":1},"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/2310.19444/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":"2310.19444","created_at":"2026-07-05T07:06:51.078851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.19444v1","created_at":"2026-07-05T07:06:51.078851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19444","created_at":"2026-07-05T07:06:51.078851+00:00"},{"alias_kind":"pith_short_12","alias_value":"D4NJBCF6UC6J","created_at":"2026-07-05T07:06:51.078851+00:00"},{"alias_kind":"pith_short_16","alias_value":"D4NJBCF6UC6JGRPL","created_at":"2026-07-05T07:06:51.078851+00:00"},{"alias_kind":"pith_short_8","alias_value":"D4NJBCF6","created_at":"2026-07-05T07:06:51.078851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01048","citing_title":"Compared to What? Baselines and Metrics for Counterfactual Prompting","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D4NJBCF6UC6JGRPL6GQ6TPPZVW","json":"https://pith.science/pith/D4NJBCF6UC6JGRPL6GQ6TPPZVW.json","graph_json":"https://pith.science/api/pith-number/D4NJBCF6UC6JGRPL6GQ6TPPZVW/graph.json","events_json":"https://pith.science/api/pith-number/D4NJBCF6UC6JGRPL6GQ6TPPZVW/events.json","paper":"https://pith.science/paper/D4NJBCF6"},"agent_actions":{"view_html":"https://pith.science/pith/D4NJBCF6UC6JGRPL6GQ6TPPZVW","download_json":"https://pith.science/pith/D4NJBCF6UC6JGRPL6GQ6TPPZVW.json","view_paper":"https://pith.science/paper/D4NJBCF6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.19444&json=true","fetch_graph":"https://pith.science/api/pith-number/D4NJBCF6UC6JGRPL6GQ6TPPZVW/graph.json","fetch_events":"https://pith.science/api/pith-number/D4NJBCF6UC6JGRPL6GQ6TPPZVW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D4NJBCF6UC6JGRPL6GQ6TPPZVW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D4NJBCF6UC6JGRPL6GQ6TPPZVW/action/storage_attestation","attest_author":"https://pith.science/pith/D4NJBCF6UC6JGRPL6GQ6TPPZVW/action/author_attestation","sign_citation":"https://pith.science/pith/D4NJBCF6UC6JGRPL6GQ6TPPZVW/action/citation_signature","submit_replication":"https://pith.science/pith/D4NJBCF6UC6JGRPL6GQ6TPPZVW/action/replication_record"}},"created_at":"2026-07-05T07:06:51.078851+00:00","updated_at":"2026-07-05T07:06:51.078851+00:00"}