{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ODXWRQYNXKOR3ZX6FVYSFXZLUC","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":"d3883b76b02e2cc11bb101e4b4b99096c4653e9dddd62c8cc77bd4da17007bbb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T16:17:37Z","title_canon_sha256":"12f954505e87a6800491342b9b9738cfea9318a753e579e6b7d8f80c95b99e9c"},"schema_version":"1.0","source":{"id":"2402.13116","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13116","created_at":"2026-05-17T23:37:42Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13116v4","created_at":"2026-05-17T23:37:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13116","created_at":"2026-05-17T23:37:42Z"},{"alias_kind":"pith_short_12","alias_value":"ODXWRQYNXKOR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ODXWRQYNXKOR3ZX6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ODXWRQYN","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:605c635a09d7178390da94bbbd10f557a4c3c350f0219f2bb616964123d4dbd5","target":"graph","created_at":"2026-05-17T23:37:42Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"KD emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and Mistral, while also enabling model compression and self-improvement."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That data augmentation within the KD framework can reliably enable open-source models to approximate the contextual adeptness, ethical alignment, and deep semantic insights of proprietary models."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A comprehensive survey of knowledge distillation for LLMs structured around algorithms, skill enhancement, and vertical applications, highlighting data augmentation as a key enabler."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Knowledge distillation transfers advanced capabilities from proprietary LLMs like GPT-4 to open-source models such as LLaMA and Mistral."}],"snapshot_sha256":"e3b88ff0303c0d4d2e95c70c9ed3150d2102ed0863b08d9400bc05dadafabdf4"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"daf0e6e47c588826aa57be3413278158443d5742bee93599f2d5c63c4dc5478e"},"paper":{"abstract_excerpt":"In the era of Large Language Models (LLMs), Knowledge Distillation (KD) emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and Mistral. Additionally, as open-source LLMs flourish, KD plays a crucial role in both compressing these models, and facilitating their self-improvement by employing themselves as teachers. This paper presents a comprehensive survey of KD's role within the realm of LLM, highlighting its critical function in imparting advanced knowledge to smaller models and its","authors_text":"Can Xu, Chongyang Tao, Dacheng Tao, Jinyang Li, Ming Li, Reynold Cheng, Tao Shen, Tianyi Zhou, Xiaohan Xu","cross_cats":[],"headline":"Knowledge distillation transfers advanced capabilities from proprietary LLMs like GPT-4 to open-source models such as LLaMA and Mistral.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T16:17:37Z","title":"A Survey on Knowledge Distillation of Large Language Models"},"references":{"count":300,"internal_anchors":25,"resolved_work":300,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Advances in Neural Information Processing Systems , volume=","work_id":"c2cc414b-17c6-4006-b389-f3ec0bf8141b","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"arXiv preprint arXiv:2304.14233 , year=","work_id":"6ee50a7d-801e-4444-93a9-5496cce785bd","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"arXiv preprint arXiv:2305.07402 , year=","work_id":"5ead8756-3597-48cb-afe3-a2ec06e20dbf","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"arXiv preprint arXiv:2212.10192 , year=","work_id":"e82d7266-b4ea-4926-b70c-0833cea400f0","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"The Eleventh International Conference on Learning Representations , year=","work_id":"49c26f65-5708-4074-91fa-3703224fe0a9","year":null}],"snapshot_sha256":"e603a99c43e130929671350775832f5916ccf292fb130c9e311d07ebe0688d0f"},"source":{"id":"2402.13116","kind":"arxiv","version":4},"verdict":{"created_at":"2026-05-17T23:27:17.705659Z","id":"c8c748e0-8724-479c-9fec-65c18e1c3267","model_set":{"reader":"grok-4.3"},"one_line_summary":"A comprehensive survey of knowledge distillation for LLMs structured around algorithms, skill enhancement, and vertical applications, highlighting data augmentation as a key enabler.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Knowledge distillation transfers advanced capabilities from proprietary LLMs like GPT-4 to open-source models such as LLaMA and Mistral.","strongest_claim":"KD emerges as a pivotal methodology for transferring advanced capabilities from leading proprietary LLMs, such as GPT-4, to their open-source counterparts like LLaMA and Mistral, while also enabling model compression and self-improvement.","weakest_assumption":"That data augmentation within the KD framework can reliably enable open-source models to approximate the contextual adeptness, ethical alignment, and deep semantic insights of proprietary models."}},"verdict_id":"c8c748e0-8724-479c-9fec-65c18e1c3267"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:45fce9f306d788782325078bac58536d1dc9fe1be1048b7f41a13fa61fedde62","target":"record","created_at":"2026-05-17T23:37:42Z","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":"d3883b76b02e2cc11bb101e4b4b99096c4653e9dddd62c8cc77bd4da17007bbb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T16:17:37Z","title_canon_sha256":"12f954505e87a6800491342b9b9738cfea9318a753e579e6b7d8f80c95b99e9c"},"schema_version":"1.0","source":{"id":"2402.13116","kind":"arxiv","version":4}},"canonical_sha256":"70ef68c30dba9d1de6fe2d7122df2ba0b9441751d771fab7e32eafc994127e60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"70ef68c30dba9d1de6fe2d7122df2ba0b9441751d771fab7e32eafc994127e60","first_computed_at":"2026-05-17T23:37:42.480803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:37:42.480803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wEcu2611nmi9Jfj0Tt7tMsbDgTH8hYmgJh+500Gp/LqzmqRVgrfwOnLL45qpeEHs8KlKFzRLd+v4hmBjChEADA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:37:42.481483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13116","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45fce9f306d788782325078bac58536d1dc9fe1be1048b7f41a13fa61fedde62","sha256:605c635a09d7178390da94bbbd10f557a4c3c350f0219f2bb616964123d4dbd5"],"state_sha256":"fe30589919f19e5c672d855f1d23e1e2baffec7b35cb4a5f6559e90ffd9bda33"}