{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GQXXCELSV6XQ3KKILVSG2QLED2","short_pith_number":"pith:GQXXCELS","schema_version":"1.0","canonical_sha256":"342f711172afaf0da9485d646d41641e81c8f0674220502c0839435b8ba0c040","source":{"kind":"arxiv","id":"2404.12711","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Temperature Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Yu Bai, Yukang Wei","submitted_at":"2024-04-19T08:40:52Z","abstract_excerpt":"Temperature plays a pivotal role in moderating label softness in the realm of knowledge distillation (KD). Traditional approaches often employ a static temperature throughout the KD process, which fails to address the nuanced complexities of samples with varying levels of difficulty and overlooks the distinct capabilities of different teacher-student pairings. This leads to a less-than-ideal transfer of knowledge. To improve the process of knowledge propagation, we proposed Dynamic Temperature Knowledge Distillation (DTKD) which introduces a dynamic, cooperative temperature control for both te"},"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":"2404.12711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-19T08:40:52Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"8c0ff3eabb4ac45c7b7ce3502a8b239127797afdcd4d078709d534ef0cc06f49","abstract_canon_sha256":"1f5ae79e39c51febaf398807b2b51b7240fc2bf1e458064104f9f1993bbe9c59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:09:58.002080Z","signature_b64":"T6GyXZsZnyso5RvmixbFwRV7u9HhKioQkXVsxTzDnlCn3ArMOS9TKEJHlyd74TDYQo8XwM3vxx81cEyiINDxBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"342f711172afaf0da9485d646d41641e81c8f0674220502c0839435b8ba0c040","last_reissued_at":"2026-07-05T08:09:58.001613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:09:58.001613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Temperature Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Yu Bai, Yukang Wei","submitted_at":"2024-04-19T08:40:52Z","abstract_excerpt":"Temperature plays a pivotal role in moderating label softness in the realm of knowledge distillation (KD). Traditional approaches often employ a static temperature throughout the KD process, which fails to address the nuanced complexities of samples with varying levels of difficulty and overlooks the distinct capabilities of different teacher-student pairings. This leads to a less-than-ideal transfer of knowledge. To improve the process of knowledge propagation, we proposed Dynamic Temperature Knowledge Distillation (DTKD) which introduces a dynamic, cooperative temperature control for both te"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.12711","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/2404.12711/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":"2404.12711","created_at":"2026-07-05T08:09:58.001673+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.12711v1","created_at":"2026-07-05T08:09:58.001673+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.12711","created_at":"2026-07-05T08:09:58.001673+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQXXCELSV6XQ","created_at":"2026-07-05T08:09:58.001673+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQXXCELSV6XQ3KKI","created_at":"2026-07-05T08:09:58.001673+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQXXCELS","created_at":"2026-07-05T08:09:58.001673+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07604","citing_title":"Contribution Weights: A Geometrical Analysis of Self-Attention Transformers","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00755","citing_title":"Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20357","citing_title":"Consistently Informative Soft-Label Temperature for Knowledge Distillation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQXXCELSV6XQ3KKILVSG2QLED2","json":"https://pith.science/pith/GQXXCELSV6XQ3KKILVSG2QLED2.json","graph_json":"https://pith.science/api/pith-number/GQXXCELSV6XQ3KKILVSG2QLED2/graph.json","events_json":"https://pith.science/api/pith-number/GQXXCELSV6XQ3KKILVSG2QLED2/events.json","paper":"https://pith.science/paper/GQXXCELS"},"agent_actions":{"view_html":"https://pith.science/pith/GQXXCELSV6XQ3KKILVSG2QLED2","download_json":"https://pith.science/pith/GQXXCELSV6XQ3KKILVSG2QLED2.json","view_paper":"https://pith.science/paper/GQXXCELS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.12711&json=true","fetch_graph":"https://pith.science/api/pith-number/GQXXCELSV6XQ3KKILVSG2QLED2/graph.json","fetch_events":"https://pith.science/api/pith-number/GQXXCELSV6XQ3KKILVSG2QLED2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQXXCELSV6XQ3KKILVSG2QLED2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQXXCELSV6XQ3KKILVSG2QLED2/action/storage_attestation","attest_author":"https://pith.science/pith/GQXXCELSV6XQ3KKILVSG2QLED2/action/author_attestation","sign_citation":"https://pith.science/pith/GQXXCELSV6XQ3KKILVSG2QLED2/action/citation_signature","submit_replication":"https://pith.science/pith/GQXXCELSV6XQ3KKILVSG2QLED2/action/replication_record"}},"created_at":"2026-07-05T08:09:58.001673+00:00","updated_at":"2026-07-05T08:09:58.001673+00:00"}