{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XHL7HPSGADP7O4H2EE4EUI6QIB","short_pith_number":"pith:XHL7HPSG","schema_version":"1.0","canonical_sha256":"b9d7f3be4600dff770fa21384a23d04059e3366ccaeab3b09da23c964bfd7ccf","source":{"kind":"arxiv","id":"2311.14307","version":1},"attestation_state":"computed","paper":{"title":"Cosine Similarity Knowledge Distillation for Individual Class Information Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daeshik Kim, Gyeongdo Ham, Jae-Hyeok Lee, Seonghak Kim, Suin Lee","submitted_at":"2023-11-24T06:34:47Z","abstract_excerpt":"Previous logits-based Knowledge Distillation (KD) have utilized predictions about multiple categories within each sample (i.e., class predictions) and have employed Kullback-Leibler (KL) divergence to reduce the discrepancy between the student and teacher predictions. Despite the proliferation of KD techniques, the student model continues to fall short of achieving a similar level as teachers. In response, we introduce a novel and effective KD method capable of achieving results on par with or superior to the teacher models performance. We utilize teacher and student predictions about multiple"},"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":"2311.14307","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-24T06:34:47Z","cross_cats_sorted":[],"title_canon_sha256":"e3d2f87e34d4de874ea5e8bba77d5d023257ba1ed3e5e80672faff4311b99960","abstract_canon_sha256":"841118645a32a5091d12f2b5bec9a1178975d9c0ebdb29e1a9f5f85f1db166bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:16.164108Z","signature_b64":"eKxJk8UQfZ/GnQ9CLq91/Cw8R7yTTdlYJvJ7BzTZ47pDrM2VI5PrOpmjJsMRug2xRdy49P/JFxbEWKZgCHTbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9d7f3be4600dff770fa21384a23d04059e3366ccaeab3b09da23c964bfd7ccf","last_reissued_at":"2026-07-05T07:16:16.163719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:16.163719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cosine Similarity Knowledge Distillation for Individual Class Information Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daeshik Kim, Gyeongdo Ham, Jae-Hyeok Lee, Seonghak Kim, Suin Lee","submitted_at":"2023-11-24T06:34:47Z","abstract_excerpt":"Previous logits-based Knowledge Distillation (KD) have utilized predictions about multiple categories within each sample (i.e., class predictions) and have employed Kullback-Leibler (KL) divergence to reduce the discrepancy between the student and teacher predictions. Despite the proliferation of KD techniques, the student model continues to fall short of achieving a similar level as teachers. In response, we introduce a novel and effective KD method capable of achieving results on par with or superior to the teacher models performance. We utilize teacher and student predictions about multiple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14307","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/2311.14307/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":"2311.14307","created_at":"2026-07-05T07:16:16.163771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.14307v1","created_at":"2026-07-05T07:16:16.163771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14307","created_at":"2026-07-05T07:16:16.163771+00:00"},{"alias_kind":"pith_short_12","alias_value":"XHL7HPSGADP7","created_at":"2026-07-05T07:16:16.163771+00:00"},{"alias_kind":"pith_short_16","alias_value":"XHL7HPSGADP7O4H2","created_at":"2026-07-05T07:16:16.163771+00:00"},{"alias_kind":"pith_short_8","alias_value":"XHL7HPSG","created_at":"2026-07-05T07:16:16.163771+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07604","citing_title":"Contribution Weights: A Geometrical Analysis of Self-Attention Transformers","ref_index":115,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XHL7HPSGADP7O4H2EE4EUI6QIB","json":"https://pith.science/pith/XHL7HPSGADP7O4H2EE4EUI6QIB.json","graph_json":"https://pith.science/api/pith-number/XHL7HPSGADP7O4H2EE4EUI6QIB/graph.json","events_json":"https://pith.science/api/pith-number/XHL7HPSGADP7O4H2EE4EUI6QIB/events.json","paper":"https://pith.science/paper/XHL7HPSG"},"agent_actions":{"view_html":"https://pith.science/pith/XHL7HPSGADP7O4H2EE4EUI6QIB","download_json":"https://pith.science/pith/XHL7HPSGADP7O4H2EE4EUI6QIB.json","view_paper":"https://pith.science/paper/XHL7HPSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.14307&json=true","fetch_graph":"https://pith.science/api/pith-number/XHL7HPSGADP7O4H2EE4EUI6QIB/graph.json","fetch_events":"https://pith.science/api/pith-number/XHL7HPSGADP7O4H2EE4EUI6QIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XHL7HPSGADP7O4H2EE4EUI6QIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XHL7HPSGADP7O4H2EE4EUI6QIB/action/storage_attestation","attest_author":"https://pith.science/pith/XHL7HPSGADP7O4H2EE4EUI6QIB/action/author_attestation","sign_citation":"https://pith.science/pith/XHL7HPSGADP7O4H2EE4EUI6QIB/action/citation_signature","submit_replication":"https://pith.science/pith/XHL7HPSGADP7O4H2EE4EUI6QIB/action/replication_record"}},"created_at":"2026-07-05T07:16:16.163771+00:00","updated_at":"2026-07-05T07:16:16.163771+00:00"}