{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DB76LDOTJ4V6V3UEKHMFOTQAXH","short_pith_number":"pith:DB76LDOT","schema_version":"1.0","canonical_sha256":"187fe58dd34f2beaee8451d8574e00b9c584442ee76c75d1fd86300a6a53b79a","source":{"kind":"arxiv","id":"2402.04616","version":3},"attestation_state":"computed","paper":{"title":"Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Nitesh V. Chawla, Wei Wang, Xiusi Chen, Yijun Tian, Yikun Han","submitted_at":"2024-02-07T06:48:24Z","abstract_excerpt":"Transferring the reasoning capability from stronger large language models (LLMs) to smaller ones has been quite appealing, as smaller LLMs are more flexible to deploy with less expense. Among the existing solutions, knowledge distillation stands out due to its outstanding efficiency and generalization. However, existing methods suffer from several drawbacks, including limited knowledge diversity and the lack of rich contextual information. To solve the problems and facilitate the learning of compact language models, we propose TinyLLM, a new knowledge distillation paradigm to learn a small stu"},"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":"2402.04616","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-07T06:48:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"da863daf51005876fd57f0aa4a8c264b2e896a8a5dbb1da8ad28d282629f9cbc","abstract_canon_sha256":"f6f9ce987c3f213149edfa3bd204ff81201e158233ec03c72c3f5b055a29be08"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:21.090202Z","signature_b64":"bV1vcmvcNLDkRXerSaOkWi+L0MViddtUNCb2BpZBFayTQVIbt4Wb/qtEaN2hsVWG2FTNsJEihmrsIPDeBRoDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"187fe58dd34f2beaee8451d8574e00b9c584442ee76c75d1fd86300a6a53b79a","last_reissued_at":"2026-07-05T09:39:21.089766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:21.089766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Answers: Transferring Reasoning Capabilities to Smaller LLMs Using Multi-Teacher Knowledge Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Nitesh V. Chawla, Wei Wang, Xiusi Chen, Yijun Tian, Yikun Han","submitted_at":"2024-02-07T06:48:24Z","abstract_excerpt":"Transferring the reasoning capability from stronger large language models (LLMs) to smaller ones has been quite appealing, as smaller LLMs are more flexible to deploy with less expense. Among the existing solutions, knowledge distillation stands out due to its outstanding efficiency and generalization. However, existing methods suffer from several drawbacks, including limited knowledge diversity and the lack of rich contextual information. To solve the problems and facilitate the learning of compact language models, we propose TinyLLM, a new knowledge distillation paradigm to learn a small stu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04616","kind":"arxiv","version":3},"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/2402.04616/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":"2402.04616","created_at":"2026-07-05T09:39:21.089822+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04616v3","created_at":"2026-07-05T09:39:21.089822+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04616","created_at":"2026-07-05T09:39:21.089822+00:00"},{"alias_kind":"pith_short_12","alias_value":"DB76LDOTJ4V6","created_at":"2026-07-05T09:39:21.089822+00:00"},{"alias_kind":"pith_short_16","alias_value":"DB76LDOTJ4V6V3UE","created_at":"2026-07-05T09:39:21.089822+00:00"},{"alias_kind":"pith_short_8","alias_value":"DB76LDOT","created_at":"2026-07-05T09:39:21.089822+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06840","citing_title":"Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11157","citing_title":"Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08094","citing_title":"MedThink: Enhancing Diagnostic Accuracy in Small Models via Teacher-Guided Reasoning Correction","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DB76LDOTJ4V6V3UEKHMFOTQAXH","json":"https://pith.science/pith/DB76LDOTJ4V6V3UEKHMFOTQAXH.json","graph_json":"https://pith.science/api/pith-number/DB76LDOTJ4V6V3UEKHMFOTQAXH/graph.json","events_json":"https://pith.science/api/pith-number/DB76LDOTJ4V6V3UEKHMFOTQAXH/events.json","paper":"https://pith.science/paper/DB76LDOT"},"agent_actions":{"view_html":"https://pith.science/pith/DB76LDOTJ4V6V3UEKHMFOTQAXH","download_json":"https://pith.science/pith/DB76LDOTJ4V6V3UEKHMFOTQAXH.json","view_paper":"https://pith.science/paper/DB76LDOT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04616&json=true","fetch_graph":"https://pith.science/api/pith-number/DB76LDOTJ4V6V3UEKHMFOTQAXH/graph.json","fetch_events":"https://pith.science/api/pith-number/DB76LDOTJ4V6V3UEKHMFOTQAXH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DB76LDOTJ4V6V3UEKHMFOTQAXH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DB76LDOTJ4V6V3UEKHMFOTQAXH/action/storage_attestation","attest_author":"https://pith.science/pith/DB76LDOTJ4V6V3UEKHMFOTQAXH/action/author_attestation","sign_citation":"https://pith.science/pith/DB76LDOTJ4V6V3UEKHMFOTQAXH/action/citation_signature","submit_replication":"https://pith.science/pith/DB76LDOTJ4V6V3UEKHMFOTQAXH/action/replication_record"}},"created_at":"2026-07-05T09:39:21.089822+00:00","updated_at":"2026-07-05T09:39:21.089822+00:00"}