{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:B2LHYFXEKVRIPCJDP2O6GD7TXC","short_pith_number":"pith:B2LHYFXE","schema_version":"1.0","canonical_sha256":"0e967c16e455628789237e9de30ff3b88cf1c311c81cb284a20ea5d79b6e8a91","source":{"kind":"arxiv","id":"2306.04751","version":2},"attestation_state":"computed","paper":{"title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Wadden, Hamish Ivison, Hannaneh Hajishirzi, Iz Beltagy, Jack Hessel, Kelsey MacMillan, Khyathi Raghavi Chandu, Noah A. Smith, Pradeep Dasigi, Tushar Khot, Yizhong Wang","submitted_at":"2023-06-07T19:59:23Z","abstract_excerpt":"In this work we explore recent advances in instruction-tuning language models on a range of open instruction-following datasets. Despite recent claims that open models can be on par with state-of-the-art proprietary models, these claims are often accompanied by limited evaluation, making it difficult to compare models across the board and determine the utility of various resources. We provide a large set of instruction-tuned models from 6.7B to 65B parameters in size, trained on 12 instruction datasets ranging from manually curated (e.g., OpenAssistant) to synthetic and distilled (e.g., Alpaca"},"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":"2306.04751","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-07T19:59:23Z","cross_cats_sorted":[],"title_canon_sha256":"9b7a85d5d4311550f713e385cee6a7195753f691800086f850de44d2f745b722","abstract_canon_sha256":"4ea901f0278fb4b70802a4b3e14ad9f7fec498bbf4124be255b95611eb3fb324"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:11.740877Z","signature_b64":"CMtcfRcsfbhiemuza+UVQyfxiPUPIzFHi5qHAfBfhd1qK2T2d4jH4rjDSX3S1rOUC94RmltgAQgwkCcIQC34Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e967c16e455628789237e9de30ff3b88cf1c311c81cb284a20ea5d79b6e8a91","last_reissued_at":"2026-07-05T07:07:11.740381Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:11.740381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Wadden, Hamish Ivison, Hannaneh Hajishirzi, Iz Beltagy, Jack Hessel, Kelsey MacMillan, Khyathi Raghavi Chandu, Noah A. Smith, Pradeep Dasigi, Tushar Khot, Yizhong Wang","submitted_at":"2023-06-07T19:59:23Z","abstract_excerpt":"In this work we explore recent advances in instruction-tuning language models on a range of open instruction-following datasets. Despite recent claims that open models can be on par with state-of-the-art proprietary models, these claims are often accompanied by limited evaluation, making it difficult to compare models across the board and determine the utility of various resources. We provide a large set of instruction-tuned models from 6.7B to 65B parameters in size, trained on 12 instruction datasets ranging from manually curated (e.g., OpenAssistant) to synthetic and distilled (e.g., Alpaca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04751","kind":"arxiv","version":2},"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/2306.04751/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":"2306.04751","created_at":"2026-07-05T07:07:11.740448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04751v2","created_at":"2026-07-05T07:07:11.740448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04751","created_at":"2026-07-05T07:07:11.740448+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2LHYFXEKVRI","created_at":"2026-07-05T07:07:11.740448+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2LHYFXEKVRIPCJD","created_at":"2026-07-05T07:07:11.740448+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2LHYFXE","created_at":"2026-07-05T07:07:11.740448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.00724","citing_title":"Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models","ref_index":291,"is_internal_anchor":false},{"citing_arxiv_id":"2305.16264","citing_title":"Scaling Data-Constrained Language Models","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2309.05653","citing_title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2305.17926","citing_title":"Large Language Models are not Fair Evaluators","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2512.02764","citing_title":"PEFT-Factory: Unified Parameter-Efficient Fine-Tuning of Autoregressive Large Language Models","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2402.05070","citing_title":"A Roadmap to Pluralistic Alignment","ref_index":170,"is_internal_anchor":false},{"citing_arxiv_id":"2403.07691","citing_title":"ORPO: Monolithic Preference Optimization without Reference Model","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2401.10020","citing_title":"Self-Rewarding Language Models","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2310.11511","citing_title":"Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09404","citing_title":"Let the Target Select for Itself: Data Selection via Target-Aligned Paths","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2402.06196","citing_title":"Large Language Models: A Survey","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2306.05685","citing_title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B2LHYFXEKVRIPCJDP2O6GD7TXC","json":"https://pith.science/pith/B2LHYFXEKVRIPCJDP2O6GD7TXC.json","graph_json":"https://pith.science/api/pith-number/B2LHYFXEKVRIPCJDP2O6GD7TXC/graph.json","events_json":"https://pith.science/api/pith-number/B2LHYFXEKVRIPCJDP2O6GD7TXC/events.json","paper":"https://pith.science/paper/B2LHYFXE"},"agent_actions":{"view_html":"https://pith.science/pith/B2LHYFXEKVRIPCJDP2O6GD7TXC","download_json":"https://pith.science/pith/B2LHYFXEKVRIPCJDP2O6GD7TXC.json","view_paper":"https://pith.science/paper/B2LHYFXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04751&json=true","fetch_graph":"https://pith.science/api/pith-number/B2LHYFXEKVRIPCJDP2O6GD7TXC/graph.json","fetch_events":"https://pith.science/api/pith-number/B2LHYFXEKVRIPCJDP2O6GD7TXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2LHYFXEKVRIPCJDP2O6GD7TXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2LHYFXEKVRIPCJDP2O6GD7TXC/action/storage_attestation","attest_author":"https://pith.science/pith/B2LHYFXEKVRIPCJDP2O6GD7TXC/action/author_attestation","sign_citation":"https://pith.science/pith/B2LHYFXEKVRIPCJDP2O6GD7TXC/action/citation_signature","submit_replication":"https://pith.science/pith/B2LHYFXEKVRIPCJDP2O6GD7TXC/action/replication_record"}},"created_at":"2026-07-05T07:07:11.740448+00:00","updated_at":"2026-07-05T07:07:11.740448+00:00"}