{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YNSFSVJZCMG2FC6L7EAJ7424NZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4a3d24248edebeaa03086d94d0a5b1aa650759de8e09e8ab82dcf02ca24dc2b7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T03:36:18Z","title_canon_sha256":"6a076276c2aa5932ba3ad3f9c7d544e7bddb2b449b7ff79126e09411281fc643"},"schema_version":"1.0","source":{"id":"2311.07052","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.07052","created_at":"2026-07-05T11:45:27Z"},{"alias_kind":"arxiv_version","alias_value":"2311.07052v4","created_at":"2026-07-05T11:45:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.07052","created_at":"2026-07-05T11:45:27Z"},{"alias_kind":"pith_short_12","alias_value":"YNSFSVJZCMG2","created_at":"2026-07-05T11:45:27Z"},{"alias_kind":"pith_short_16","alias_value":"YNSFSVJZCMG2FC6L","created_at":"2026-07-05T11:45:27Z"},{"alias_kind":"pith_short_8","alias_value":"YNSFSVJZ","created_at":"2026-07-05T11:45:27Z"}],"graph_snapshots":[{"event_id":"sha256:5e28eb793f0a97478a29854a571ab64db35266e05d9c370c49828ad19cbdf361","target":"graph","created_at":"2026-07-05T11:45:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.07052/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chen Zhang, Dawei Song, Qiuchi Li, Yan Gao, Yan Hu, Zheyu Ye","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T03:36:18Z","title":"Towards the Law of Capacity Gap in Distilling Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.07052","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d4de71d5a77a041da8dca023bd87f0175082e9ee2b483b9ce5a50c066029f65c","target":"record","created_at":"2026-07-05T11:45:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4a3d24248edebeaa03086d94d0a5b1aa650759de8e09e8ab82dcf02ca24dc2b7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-13T03:36:18Z","title_canon_sha256":"6a076276c2aa5932ba3ad3f9c7d544e7bddb2b449b7ff79126e09411281fc643"},"schema_version":"1.0","source":{"id":"2311.07052","kind":"arxiv","version":4}},"canonical_sha256":"c364595539130da28bcbf9009ff35c6e70ebbc61061a9be7ff6b65d786ca5c9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c364595539130da28bcbf9009ff35c6e70ebbc61061a9be7ff6b65d786ca5c9f","first_computed_at":"2026-07-05T11:45:27.189647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:45:27.189647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0sbo4+RD/cXBu48fzQYU9B8OQL+dsWytjNIoOk62XNo+lsRXTv7bySbKecyI+FHByxqUuJnenK+GzxytZX5iBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:45:27.190142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.07052","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4de71d5a77a041da8dca023bd87f0175082e9ee2b483b9ce5a50c066029f65c","sha256:5e28eb793f0a97478a29854a571ab64db35266e05d9c370c49828ad19cbdf361"],"state_sha256":"ec50de56d57f72278311665b5de4c9167b1b7c72f41ad5de6e897e1513666fd7"}