{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OANF2QKPBY5X5GKFYQBTDXTPYU","short_pith_number":"pith:OANF2QKP","schema_version":"1.0","canonical_sha256":"701a5d414f0e3b7e9945c40331de6fc52a078d1dd3ea44664ef50f11f13b673a","source":{"kind":"arxiv","id":"2310.13961","version":1},"attestation_state":"computed","paper":{"title":"Ensemble-Instruct: Generating Instruction-Tuning Data with a Heterogeneous Mixture of LMs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Md Arafat Sultan, Radu Florian, Ram\\'on Fernandez Astudillo, Salim Roukos, Tahira Naseem Asim Munawar, Young-Suk Lee, Yousef El-Kurdi","submitted_at":"2023-10-21T10:21:17Z","abstract_excerpt":"Using in-context learning (ICL) for data generation, techniques such as Self-Instruct (Wang et al., 2023) or the follow-up Alpaca (Taori et al., 2023) can train strong conversational agents with only a small amount of human supervision. One limitation of these approaches is that they resort to very large language models (around 175B parameters) that are also proprietary and non-public. Here we explore the application of such techniques to language models that are much smaller (around 10B--40B parameters) and have permissive licenses. We find the Self-Instruct approach to be less effective at t"},"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":"2310.13961","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-21T10:21:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dd4d4e1e9b5c828fb242bc22041753ca1e0708fdabc167d457101c2c09db8e51","abstract_canon_sha256":"eb949104562565356bed4eef4344db0b93380a632014664c81c9df73765331bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:37.484148Z","signature_b64":"xVzNUb5uxRhER9PijlJiScybvRA66W78yePfiZD2e53H3TUnfrzueln4rc6WUF6N6hE7QbT2JJL/BiQmg0heDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"701a5d414f0e3b7e9945c40331de6fc52a078d1dd3ea44664ef50f11f13b673a","last_reissued_at":"2026-07-05T07:03:37.483757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:37.483757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ensemble-Instruct: Generating Instruction-Tuning Data with a Heterogeneous Mixture of LMs","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Md Arafat Sultan, Radu Florian, Ram\\'on Fernandez Astudillo, Salim Roukos, Tahira Naseem Asim Munawar, Young-Suk Lee, Yousef El-Kurdi","submitted_at":"2023-10-21T10:21:17Z","abstract_excerpt":"Using in-context learning (ICL) for data generation, techniques such as Self-Instruct (Wang et al., 2023) or the follow-up Alpaca (Taori et al., 2023) can train strong conversational agents with only a small amount of human supervision. One limitation of these approaches is that they resort to very large language models (around 175B parameters) that are also proprietary and non-public. Here we explore the application of such techniques to language models that are much smaller (around 10B--40B parameters) and have permissive licenses. We find the Self-Instruct approach to be less effective at t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13961","kind":"arxiv","version":1},"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/2310.13961/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":"2310.13961","created_at":"2026-07-05T07:03:37.483811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.13961v1","created_at":"2026-07-05T07:03:37.483811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13961","created_at":"2026-07-05T07:03:37.483811+00:00"},{"alias_kind":"pith_short_12","alias_value":"OANF2QKPBY5X","created_at":"2026-07-05T07:03:37.483811+00:00"},{"alias_kind":"pith_short_16","alias_value":"OANF2QKPBY5X5GKF","created_at":"2026-07-05T07:03:37.483811+00:00"},{"alias_kind":"pith_short_8","alias_value":"OANF2QKP","created_at":"2026-07-05T07:03:37.483811+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.18036","citing_title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OANF2QKPBY5X5GKFYQBTDXTPYU","json":"https://pith.science/pith/OANF2QKPBY5X5GKFYQBTDXTPYU.json","graph_json":"https://pith.science/api/pith-number/OANF2QKPBY5X5GKFYQBTDXTPYU/graph.json","events_json":"https://pith.science/api/pith-number/OANF2QKPBY5X5GKFYQBTDXTPYU/events.json","paper":"https://pith.science/paper/OANF2QKP"},"agent_actions":{"view_html":"https://pith.science/pith/OANF2QKPBY5X5GKFYQBTDXTPYU","download_json":"https://pith.science/pith/OANF2QKPBY5X5GKFYQBTDXTPYU.json","view_paper":"https://pith.science/paper/OANF2QKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.13961&json=true","fetch_graph":"https://pith.science/api/pith-number/OANF2QKPBY5X5GKFYQBTDXTPYU/graph.json","fetch_events":"https://pith.science/api/pith-number/OANF2QKPBY5X5GKFYQBTDXTPYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OANF2QKPBY5X5GKFYQBTDXTPYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OANF2QKPBY5X5GKFYQBTDXTPYU/action/storage_attestation","attest_author":"https://pith.science/pith/OANF2QKPBY5X5GKFYQBTDXTPYU/action/author_attestation","sign_citation":"https://pith.science/pith/OANF2QKPBY5X5GKFYQBTDXTPYU/action/citation_signature","submit_replication":"https://pith.science/pith/OANF2QKPBY5X5GKFYQBTDXTPYU/action/replication_record"}},"created_at":"2026-07-05T07:03:37.483811+00:00","updated_at":"2026-07-05T07:03:37.483811+00:00"}