{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YNSFSVJZCMG2FC6L7EAJ7424NZ","short_pith_number":"pith:YNSFSVJZ","schema_version":"1.0","canonical_sha256":"c364595539130da28bcbf9009ff35c6e70ebbc61061a9be7ff6b65d786ca5c9f","source":{"kind":"arxiv","id":"2311.07052","version":4},"attestation_state":"computed","paper":{"title":"Towards the Law of Capacity Gap in Distilling Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Zhang, Dawei Song, Qiuchi Li, Yan Gao, Yan Hu, Zheyu Ye","submitted_at":"2023-11-13T03:36:18Z","abstract_excerpt":"Language model (LM) distillation aims at distilling the knowledge in a large teacher LM to a small student one. As a critical issue facing LM distillation, a superior student often arises from a teacher of a relatively small scale instead of a larger one, especially in the presence of substantial capacity gap between the teacher and student. This issue, often referred to as the \\textit{curse of capacity gap}, suggests that there is likely an optimal teacher yielding the best-performing student along the scaling course of the teacher. Consequently, distillation trials on teachers of a wide rang"},"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":"2311.07052","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T03:36:18Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6a076276c2aa5932ba3ad3f9c7d544e7bddb2b449b7ff79126e09411281fc643","abstract_canon_sha256":"4a3d24248edebeaa03086d94d0a5b1aa650759de8e09e8ab82dcf02ca24dc2b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:27.190142Z","signature_b64":"0sbo4+RD/cXBu48fzQYU9B8OQL+dsWytjNIoOk62XNo+lsRXTv7bySbKecyI+FHByxqUuJnenK+GzxytZX5iBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c364595539130da28bcbf9009ff35c6e70ebbc61061a9be7ff6b65d786ca5c9f","last_reissued_at":"2026-07-05T11:45:27.189647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:27.189647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards the Law of Capacity Gap in Distilling Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Zhang, Dawei Song, Qiuchi Li, Yan Gao, Yan Hu, Zheyu Ye","submitted_at":"2023-11-13T03:36:18Z","abstract_excerpt":"Language model (LM) distillation aims at distilling the knowledge in a large teacher LM to a small student one. As a critical issue facing LM distillation, a superior student often arises from a teacher of a relatively small scale instead of a larger one, especially in the presence of substantial capacity gap between the teacher and student. This issue, often referred to as the \\textit{curse of capacity gap}, suggests that there is likely an optimal teacher yielding the best-performing student along the scaling course of the teacher. Consequently, distillation trials on teachers of a wide rang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07052","kind":"arxiv","version":4},"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/2311.07052/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":"2311.07052","created_at":"2026-07-05T11:45:27.189706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.07052v4","created_at":"2026-07-05T11:45:27.189706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07052","created_at":"2026-07-05T11:45:27.189706+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNSFSVJZCMG2","created_at":"2026-07-05T11:45:27.189706+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNSFSVJZCMG2FC6L","created_at":"2026-07-05T11:45:27.189706+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNSFSVJZ","created_at":"2026-07-05T11:45:27.189706+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07783","citing_title":"Chain-based Distillation for Effective Initialization of Variable-Sized Small Language Models","ref_index":110,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YNSFSVJZCMG2FC6L7EAJ7424NZ","json":"https://pith.science/pith/YNSFSVJZCMG2FC6L7EAJ7424NZ.json","graph_json":"https://pith.science/api/pith-number/YNSFSVJZCMG2FC6L7EAJ7424NZ/graph.json","events_json":"https://pith.science/api/pith-number/YNSFSVJZCMG2FC6L7EAJ7424NZ/events.json","paper":"https://pith.science/paper/YNSFSVJZ"},"agent_actions":{"view_html":"https://pith.science/pith/YNSFSVJZCMG2FC6L7EAJ7424NZ","download_json":"https://pith.science/pith/YNSFSVJZCMG2FC6L7EAJ7424NZ.json","view_paper":"https://pith.science/paper/YNSFSVJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.07052&json=true","fetch_graph":"https://pith.science/api/pith-number/YNSFSVJZCMG2FC6L7EAJ7424NZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YNSFSVJZCMG2FC6L7EAJ7424NZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNSFSVJZCMG2FC6L7EAJ7424NZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNSFSVJZCMG2FC6L7EAJ7424NZ/action/storage_attestation","attest_author":"https://pith.science/pith/YNSFSVJZCMG2FC6L7EAJ7424NZ/action/author_attestation","sign_citation":"https://pith.science/pith/YNSFSVJZCMG2FC6L7EAJ7424NZ/action/citation_signature","submit_replication":"https://pith.science/pith/YNSFSVJZCMG2FC6L7EAJ7424NZ/action/replication_record"}},"created_at":"2026-07-05T11:45:27.189706+00:00","updated_at":"2026-07-05T11:45:27.189706+00:00"}