{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:C5LVORK7GZI24GYSPKIQRWENUW","short_pith_number":"pith:C5LVORK7","schema_version":"1.0","canonical_sha256":"175757455f3651ae1b127a9108d88da5bf8a1e1496514552d280953fd4ea3756","source":{"kind":"arxiv","id":"2307.08436","version":1},"attestation_state":"computed","paper":{"title":"DOT: A Distillation-Oriented Trainer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Borui Zhao, Jiajun Liang, Quan Cui, Renjie Song","submitted_at":"2023-07-17T12:31:13Z","abstract_excerpt":"Knowledge distillation transfers knowledge from a large model to a small one via task and distillation losses. In this paper, we observe a trade-off between task and distillation losses, i.e., introducing distillation loss limits the convergence of task loss. We believe that the trade-off results from the insufficient optimization of distillation loss. The reason is: The teacher has a lower task loss than the student, and a lower distillation loss drives the student more similar to the teacher, then a better-converged task loss could be obtained. To break the trade-off, we propose the Distilla"},"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":"2307.08436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-17T12:31:13Z","cross_cats_sorted":[],"title_canon_sha256":"4a95d717d2301491d7b693e91e0682b248a19d7c5e3487a350c43799118332e9","abstract_canon_sha256":"d37704cbb87be5f4dc07e82b66ec2740084fd4b0450ff0fdd6fd80a456a347e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:31:24.588340Z","signature_b64":"pRxhnvEky4aDmxHlreIkxii1Ewi4rY76QNRjEBsSJmVcYdCCaOcgGy1XGVKhH0GM7dXa/NzPkoR0sZ8KQaj2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"175757455f3651ae1b127a9108d88da5bf8a1e1496514552d280953fd4ea3756","last_reissued_at":"2026-07-05T06:31:24.587808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:31:24.587808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DOT: A Distillation-Oriented Trainer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Borui Zhao, Jiajun Liang, Quan Cui, Renjie Song","submitted_at":"2023-07-17T12:31:13Z","abstract_excerpt":"Knowledge distillation transfers knowledge from a large model to a small one via task and distillation losses. In this paper, we observe a trade-off between task and distillation losses, i.e., introducing distillation loss limits the convergence of task loss. We believe that the trade-off results from the insufficient optimization of distillation loss. The reason is: The teacher has a lower task loss than the student, and a lower distillation loss drives the student more similar to the teacher, then a better-converged task loss could be obtained. To break the trade-off, we propose the Distilla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.08436","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/2307.08436/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":"2307.08436","created_at":"2026-07-05T06:31:24.587886+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.08436v1","created_at":"2026-07-05T06:31:24.587886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.08436","created_at":"2026-07-05T06:31:24.587886+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5LVORK7GZI2","created_at":"2026-07-05T06:31:24.587886+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5LVORK7GZI24GYS","created_at":"2026-07-05T06:31:24.587886+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5LVORK7","created_at":"2026-07-05T06:31:24.587886+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10693","citing_title":"Multi-perspective Contrastive Logit Distillation","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5LVORK7GZI24GYSPKIQRWENUW","json":"https://pith.science/pith/C5LVORK7GZI24GYSPKIQRWENUW.json","graph_json":"https://pith.science/api/pith-number/C5LVORK7GZI24GYSPKIQRWENUW/graph.json","events_json":"https://pith.science/api/pith-number/C5LVORK7GZI24GYSPKIQRWENUW/events.json","paper":"https://pith.science/paper/C5LVORK7"},"agent_actions":{"view_html":"https://pith.science/pith/C5LVORK7GZI24GYSPKIQRWENUW","download_json":"https://pith.science/pith/C5LVORK7GZI24GYSPKIQRWENUW.json","view_paper":"https://pith.science/paper/C5LVORK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.08436&json=true","fetch_graph":"https://pith.science/api/pith-number/C5LVORK7GZI24GYSPKIQRWENUW/graph.json","fetch_events":"https://pith.science/api/pith-number/C5LVORK7GZI24GYSPKIQRWENUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5LVORK7GZI24GYSPKIQRWENUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5LVORK7GZI24GYSPKIQRWENUW/action/storage_attestation","attest_author":"https://pith.science/pith/C5LVORK7GZI24GYSPKIQRWENUW/action/author_attestation","sign_citation":"https://pith.science/pith/C5LVORK7GZI24GYSPKIQRWENUW/action/citation_signature","submit_replication":"https://pith.science/pith/C5LVORK7GZI24GYSPKIQRWENUW/action/replication_record"}},"created_at":"2026-07-05T06:31:24.587886+00:00","updated_at":"2026-07-05T06:31:24.587886+00:00"}