{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OANF2QKPBY5X5GKFYQBTDXTPYU","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":"eb949104562565356bed4eef4344db0b93380a632014664c81c9df73765331bd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-21T10:21:17Z","title_canon_sha256":"dd4d4e1e9b5c828fb242bc22041753ca1e0708fdabc167d457101c2c09db8e51"},"schema_version":"1.0","source":{"id":"2310.13961","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.13961","created_at":"2026-07-05T07:03:37Z"},{"alias_kind":"arxiv_version","alias_value":"2310.13961v1","created_at":"2026-07-05T07:03:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13961","created_at":"2026-07-05T07:03:37Z"},{"alias_kind":"pith_short_12","alias_value":"OANF2QKPBY5X","created_at":"2026-07-05T07:03:37Z"},{"alias_kind":"pith_short_16","alias_value":"OANF2QKPBY5X5GKF","created_at":"2026-07-05T07:03:37Z"},{"alias_kind":"pith_short_8","alias_value":"OANF2QKP","created_at":"2026-07-05T07:03:37Z"}],"graph_snapshots":[{"event_id":"sha256:55a8bf4c1004d580aec092f4723beb64eb74dc0952da56fe59ca23e85640e22a","target":"graph","created_at":"2026-07-05T07:03:37Z","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/2310.13961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Md Arafat Sultan, Radu Florian, Ram\\'on Fernandez Astudillo, Salim Roukos, Tahira Naseem Asim Munawar, Young-Suk Lee, Yousef El-Kurdi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-21T10:21:17Z","title":"Ensemble-Instruct: Generating Instruction-Tuning Data with a Heterogeneous Mixture of LMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13961","kind":"arxiv","version":1},"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:bba7f096573caa748dd0a71bef982ba061d435ee728d09a7b8c13f951fd28ffd","target":"record","created_at":"2026-07-05T07:03:37Z","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":"eb949104562565356bed4eef4344db0b93380a632014664c81c9df73765331bd","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-21T10:21:17Z","title_canon_sha256":"dd4d4e1e9b5c828fb242bc22041753ca1e0708fdabc167d457101c2c09db8e51"},"schema_version":"1.0","source":{"id":"2310.13961","kind":"arxiv","version":1}},"canonical_sha256":"701a5d414f0e3b7e9945c40331de6fc52a078d1dd3ea44664ef50f11f13b673a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"701a5d414f0e3b7e9945c40331de6fc52a078d1dd3ea44664ef50f11f13b673a","first_computed_at":"2026-07-05T07:03:37.483757Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:37.483757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xVzNUb5uxRhER9PijlJiScybvRA66W78yePfiZD2e53H3TUnfrzueln4rc6WUF6N6hE7QbT2JJL/BiQmg0heDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:37.484148Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.13961","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bba7f096573caa748dd0a71bef982ba061d435ee728d09a7b8c13f951fd28ffd","sha256:55a8bf4c1004d580aec092f4723beb64eb74dc0952da56fe59ca23e85640e22a"],"state_sha256":"c4c14b57a42ea02dccd10d4e2d111dcb81651dd9d19a663972937dc64591e777"}