{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DS7RIPSJ7CURSWS3JYMJKSMPZW","short_pith_number":"pith:DS7RIPSJ","schema_version":"1.0","canonical_sha256":"1cbf143e49f8a9195a5b4e1895498fcd97672aef7f03ca943f7b620a5462a247","source":{"kind":"arxiv","id":"2308.12711","version":1},"attestation_state":"computed","paper":{"title":"Harnessing the Power of David against Goliath: Exploring Instruction Data Generation without Using Closed-Source Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guannan Zhang, Jinxiong Chang, Juntao Li, Min Zhang, Qishen Zhang, Xinrui Wang, Yue Wang, Zhongyi Liu","submitted_at":"2023-08-24T11:07:47Z","abstract_excerpt":"Instruction tuning is instrumental in enabling Large Language Models~(LLMs) to follow user instructions to complete various open-domain tasks. The success of instruction tuning depends on the availability of high-quality instruction data. Owing to the exorbitant cost and substandard quality of human annotation, recent works have been deeply engaged in the exploration of the utilization of powerful closed-source models to generate instruction data automatically. However, these methods carry potential risks arising from the usage requirements of powerful closed-source models, which strictly forb"},"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":"2308.12711","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-24T11:07:47Z","cross_cats_sorted":[],"title_canon_sha256":"88d4cda7d8a03272bf908a26fee48f7e3f24574977f327a3b298a21ed9e0ed68","abstract_canon_sha256":"de8de2640b38c6434659e484117e8e54bd08b4ddeee0a7c7f11285067ecd5e44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:17.138704Z","signature_b64":"00RDwzdUukEnzeSmWAjT6V/50H3K5DWF9L/VAO61+cTc9+2w+77XUZhGG6cePxYjYJe2ggLmOsMgDXmmW3sBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cbf143e49f8a9195a5b4e1895498fcd97672aef7f03ca943f7b620a5462a247","last_reissued_at":"2026-07-05T06:44:17.138182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:17.138182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Harnessing the Power of David against Goliath: Exploring Instruction Data Generation without Using Closed-Source Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guannan Zhang, Jinxiong Chang, Juntao Li, Min Zhang, Qishen Zhang, Xinrui Wang, Yue Wang, Zhongyi Liu","submitted_at":"2023-08-24T11:07:47Z","abstract_excerpt":"Instruction tuning is instrumental in enabling Large Language Models~(LLMs) to follow user instructions to complete various open-domain tasks. The success of instruction tuning depends on the availability of high-quality instruction data. Owing to the exorbitant cost and substandard quality of human annotation, recent works have been deeply engaged in the exploration of the utilization of powerful closed-source models to generate instruction data automatically. However, these methods carry potential risks arising from the usage requirements of powerful closed-source models, which strictly forb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12711","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/2308.12711/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":"2308.12711","created_at":"2026-07-05T06:44:17.138251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.12711v1","created_at":"2026-07-05T06:44:17.138251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12711","created_at":"2026-07-05T06:44:17.138251+00:00"},{"alias_kind":"pith_short_12","alias_value":"DS7RIPSJ7CUR","created_at":"2026-07-05T06:44:17.138251+00:00"},{"alias_kind":"pith_short_16","alias_value":"DS7RIPSJ7CURSWS3","created_at":"2026-07-05T06:44:17.138251+00:00"},{"alias_kind":"pith_short_8","alias_value":"DS7RIPSJ","created_at":"2026-07-05T06:44:17.138251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.29175","citing_title":"Execution-First Synthetic Tool-Use Trace Generation for LLM Agents","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DS7RIPSJ7CURSWS3JYMJKSMPZW","json":"https://pith.science/pith/DS7RIPSJ7CURSWS3JYMJKSMPZW.json","graph_json":"https://pith.science/api/pith-number/DS7RIPSJ7CURSWS3JYMJKSMPZW/graph.json","events_json":"https://pith.science/api/pith-number/DS7RIPSJ7CURSWS3JYMJKSMPZW/events.json","paper":"https://pith.science/paper/DS7RIPSJ"},"agent_actions":{"view_html":"https://pith.science/pith/DS7RIPSJ7CURSWS3JYMJKSMPZW","download_json":"https://pith.science/pith/DS7RIPSJ7CURSWS3JYMJKSMPZW.json","view_paper":"https://pith.science/paper/DS7RIPSJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.12711&json=true","fetch_graph":"https://pith.science/api/pith-number/DS7RIPSJ7CURSWS3JYMJKSMPZW/graph.json","fetch_events":"https://pith.science/api/pith-number/DS7RIPSJ7CURSWS3JYMJKSMPZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DS7RIPSJ7CURSWS3JYMJKSMPZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DS7RIPSJ7CURSWS3JYMJKSMPZW/action/storage_attestation","attest_author":"https://pith.science/pith/DS7RIPSJ7CURSWS3JYMJKSMPZW/action/author_attestation","sign_citation":"https://pith.science/pith/DS7RIPSJ7CURSWS3JYMJKSMPZW/action/citation_signature","submit_replication":"https://pith.science/pith/DS7RIPSJ7CURSWS3JYMJKSMPZW/action/replication_record"}},"created_at":"2026-07-05T06:44:17.138251+00:00","updated_at":"2026-07-05T06:44:17.138251+00:00"}