{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DWAY4NKUKV7S7NMP2RFKP6S5F3","short_pith_number":"pith:DWAY4NKU","schema_version":"1.0","canonical_sha256":"1d818e3554557f2fb58fd44aa7fa5d2ec3759e905e67a39920948e51bba3224b","source":{"kind":"arxiv","id":"2304.14402","version":3},"attestation_state":"computed","paper":{"title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdul Waheed, Alham Fikri Aji, Chiyu Zhang, Minghao Wu, Muhammad Abdul-Mageed","submitted_at":"2023-04-27T17:58:49Z","abstract_excerpt":"Large language models (LLMs) with instruction fine-tuning demonstrate superior generative capabilities. However, these models are resource-intensive. To alleviate this issue, we explore distilling knowledge from instruction-tuned LLMs into much smaller ones. To this end, we carefully develop a large set of 2.58M instructions based on both existing and newly-generated instructions. In addition to being sizable, we design our instructions to cover a broad set of topics to ensure diversity. Extensive analysis of our instruction dataset confirms its diversity, and we generate responses for these i"},"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":"2304.14402","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-27T17:58:49Z","cross_cats_sorted":[],"title_canon_sha256":"7b3df3d7c3b8f24859c0ab7a844b3e2e27d4e58c4443ab33e02389dd20025224","abstract_canon_sha256":"18661a9b5dd476bd613b984d4e5fac182c5f4c9080e87cbc744512c253d39955"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:38:27.156735Z","signature_b64":"7aIbwgNmQuyEYOlAhecSOP5On4XARHkmDu4caMbF3Sy3PdNXMsfMWvR3UTZYJ7sreSVzCWefTIcDDJZgtpDSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d818e3554557f2fb58fd44aa7fa5d2ec3759e905e67a39920948e51bba3224b","last_reissued_at":"2026-07-05T07:38:27.156273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:38:27.156273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdul Waheed, Alham Fikri Aji, Chiyu Zhang, Minghao Wu, Muhammad Abdul-Mageed","submitted_at":"2023-04-27T17:58:49Z","abstract_excerpt":"Large language models (LLMs) with instruction fine-tuning demonstrate superior generative capabilities. However, these models are resource-intensive. To alleviate this issue, we explore distilling knowledge from instruction-tuned LLMs into much smaller ones. To this end, we carefully develop a large set of 2.58M instructions based on both existing and newly-generated instructions. In addition to being sizable, we design our instructions to cover a broad set of topics to ensure diversity. Extensive analysis of our instruction dataset confirms its diversity, and we generate responses for these i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14402","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/2304.14402/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":"2304.14402","created_at":"2026-07-05T07:38:27.156326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14402v3","created_at":"2026-07-05T07:38:27.156326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14402","created_at":"2026-07-05T07:38:27.156326+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWAY4NKUKV7S","created_at":"2026-07-05T07:38:27.156326+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWAY4NKUKV7S7NMP","created_at":"2026-07-05T07:38:27.156326+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWAY4NKU","created_at":"2026-07-05T07:38:27.156326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19993","citing_title":"Activation- and Influence-Aware Ranks (AIR): Function-Preserving SVD Compression for LLMs","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2411.16821","citing_title":"Logit-KL Flow Matching: Non-Autoregressive Text Generation via Sampling-Hybrid Inference","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2503.08223","citing_title":"Will LLMs Scaling Hit the Wall? Breaking Barriers via Distributed Resources on Massive Edge Devices","ref_index":166,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15416","citing_title":"Margin-Adaptive Confidence Ranking for Reliable LLM Judgement","ref_index":299,"is_internal_anchor":false},{"citing_arxiv_id":"2404.14294","citing_title":"A Survey on Efficient Inference for Large Language Models","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2306.08543","citing_title":"MiniLLM: On-Policy Distillation of Large Language Models","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DWAY4NKUKV7S7NMP2RFKP6S5F3","json":"https://pith.science/pith/DWAY4NKUKV7S7NMP2RFKP6S5F3.json","graph_json":"https://pith.science/api/pith-number/DWAY4NKUKV7S7NMP2RFKP6S5F3/graph.json","events_json":"https://pith.science/api/pith-number/DWAY4NKUKV7S7NMP2RFKP6S5F3/events.json","paper":"https://pith.science/paper/DWAY4NKU"},"agent_actions":{"view_html":"https://pith.science/pith/DWAY4NKUKV7S7NMP2RFKP6S5F3","download_json":"https://pith.science/pith/DWAY4NKUKV7S7NMP2RFKP6S5F3.json","view_paper":"https://pith.science/paper/DWAY4NKU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14402&json=true","fetch_graph":"https://pith.science/api/pith-number/DWAY4NKUKV7S7NMP2RFKP6S5F3/graph.json","fetch_events":"https://pith.science/api/pith-number/DWAY4NKUKV7S7NMP2RFKP6S5F3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWAY4NKUKV7S7NMP2RFKP6S5F3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWAY4NKUKV7S7NMP2RFKP6S5F3/action/storage_attestation","attest_author":"https://pith.science/pith/DWAY4NKUKV7S7NMP2RFKP6S5F3/action/author_attestation","sign_citation":"https://pith.science/pith/DWAY4NKUKV7S7NMP2RFKP6S5F3/action/citation_signature","submit_replication":"https://pith.science/pith/DWAY4NKUKV7S7NMP2RFKP6S5F3/action/replication_record"}},"created_at":"2026-07-05T07:38:27.156326+00:00","updated_at":"2026-07-05T07:38:27.156326+00:00"}