{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AQBO3LKXPYJ4HF4XCGR7JCQP5A","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":"010c66bb82a91a4ee1faf38aba3b8cdea1738f3a9a7ae98e80a0956c88f7c1f3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T11:40:17Z","title_canon_sha256":"f1adabe0fafa3eb6cb0fb6f249f95fbdd733638f1b122ae775eb8677a11728a7"},"schema_version":"1.0","source":{"id":"2404.02657","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.02657","created_at":"2026-07-05T09:45:45Z"},{"alias_kind":"arxiv_version","alias_value":"2404.02657v4","created_at":"2026-07-05T09:45:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02657","created_at":"2026-07-05T09:45:45Z"},{"alias_kind":"pith_short_12","alias_value":"AQBO3LKXPYJ4","created_at":"2026-07-05T09:45:45Z"},{"alias_kind":"pith_short_16","alias_value":"AQBO3LKXPYJ4HF4X","created_at":"2026-07-05T09:45:45Z"},{"alias_kind":"pith_short_8","alias_value":"AQBO3LKX","created_at":"2026-07-05T09:45:45Z"}],"graph_snapshots":[{"event_id":"sha256:043fe02c7870beb36635e649c467af16c35d6290ec63f58a6e05fcac7f5e7845","target":"graph","created_at":"2026-07-05T09:45:45Z","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/2404.02657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Kullback-Leiber divergence has been widely used in Knowledge Distillation (KD) to compress Large Language Models (LLMs). Contrary to prior assertions that reverse Kullback-Leibler (RKL) divergence is mode-seeking and thus preferable over the mean-seeking forward Kullback-Leibler (FKL) divergence, this study empirically and theoretically demonstrates that neither mode-seeking nor mean-seeking properties manifest in KD for LLMs. Instead, RKL and FKL are found to share the same optimization objective and both converge after a sufficient number of epochs. However, due to practical constraints, LLM","authors_text":"Chaofan Tao, Jiahao Wang, Ngai Wong, Runming Yang, Taiqiang Wu, Zhe Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T11:40:17Z","title":"Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02657","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":"sha256:110822f936e5af0c59d22d1ae4e113f47e3bf0e93218f05450bf3cdc0d44f09f","target":"record","created_at":"2026-07-05T09:45:45Z","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":"010c66bb82a91a4ee1faf38aba3b8cdea1738f3a9a7ae98e80a0956c88f7c1f3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T11:40:17Z","title_canon_sha256":"f1adabe0fafa3eb6cb0fb6f249f95fbdd733638f1b122ae775eb8677a11728a7"},"schema_version":"1.0","source":{"id":"2404.02657","kind":"arxiv","version":4}},"canonical_sha256":"0402edad577e13c3979711a3f48a0fe80dcd3a00797dd7bbb0b17e5e98467d9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0402edad577e13c3979711a3f48a0fe80dcd3a00797dd7bbb0b17e5e98467d9d","first_computed_at":"2026-07-05T09:45:45.991228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:45.991228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E02ZBFpb/F1nuYQKD43lnLC3SxkGF+BHvqJ2ziogarEdUlAVVsv+EkoP9Ny6J55K634zCckeKBCs2FgYEK2RBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:45.991694Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.02657","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:110822f936e5af0c59d22d1ae4e113f47e3bf0e93218f05450bf3cdc0d44f09f","sha256:043fe02c7870beb36635e649c467af16c35d6290ec63f58a6e05fcac7f5e7845"],"state_sha256":"ae4937116721e672784c9a63fbc9268fb952dd95637fcfeff65d18ff5f07a806"}