{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YS7XIGSZ7A3UHJURD4DLXMTZU3","short_pith_number":"pith:YS7XIGSZ","schema_version":"1.0","canonical_sha256":"c4bf741a59f83743a6911f06bbb279a6ca857c8baea0bb72db5bc2ea802867db","source":{"kind":"arxiv","id":"2402.03049","version":4},"attestation_state":"computed","paper":{"title":"EasyInstruct: An Easy-to-use Instruction Processing Framework for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Guozhou Zheng, Honghao Gui, Huajun Chen, Kangwei Liu, Lei Li, Ningyu Zhang, Runnan Fang, Shuofei Qiao, Yida Xue, Yixin Ou, Zhen Bi, Ziwen Xu","submitted_at":"2024-02-05T14:33:56Z","abstract_excerpt":"In recent years, instruction tuning has gained increasing attention and emerged as a crucial technique to enhance the capabilities of Large Language Models (LLMs). To construct high-quality instruction datasets, many instruction processing approaches have been proposed, aiming to achieve a delicate balance between data quantity and data quality. Nevertheless, due to inconsistencies that persist among various instruction processing methods, there is no standard open-source instruction processing implementation framework available for the community, which hinders practitioners from further devel"},"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":"2402.03049","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-05T14:33:56Z","cross_cats_sorted":["cs.AI","cs.HC","cs.IR","cs.LG"],"title_canon_sha256":"a490629010a0052bf5468e73062feb646f1a37ba5c6e1a97bd458b08d7e54a09","abstract_canon_sha256":"ce2c7a3244c6b3f9249c4121f43b94149fa7b0748cb95b6b6605f285491dd3ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:41.569010Z","signature_b64":"TwW/S0lD+pv0oxCYZNiHFdndxhzsAuZdB20A4uNsZ8DCZvB/LZpyFFITzg5CtNLsxx9IJVubVxOaYu6o4DOgCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4bf741a59f83743a6911f06bbb279a6ca857c8baea0bb72db5bc2ea802867db","last_reissued_at":"2026-07-05T08:35:41.568397Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:41.568397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EasyInstruct: An Easy-to-use Instruction Processing Framework for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Guozhou Zheng, Honghao Gui, Huajun Chen, Kangwei Liu, Lei Li, Ningyu Zhang, Runnan Fang, Shuofei Qiao, Yida Xue, Yixin Ou, Zhen Bi, Ziwen Xu","submitted_at":"2024-02-05T14:33:56Z","abstract_excerpt":"In recent years, instruction tuning has gained increasing attention and emerged as a crucial technique to enhance the capabilities of Large Language Models (LLMs). To construct high-quality instruction datasets, many instruction processing approaches have been proposed, aiming to achieve a delicate balance between data quantity and data quality. Nevertheless, due to inconsistencies that persist among various instruction processing methods, there is no standard open-source instruction processing implementation framework available for the community, which hinders practitioners from further devel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03049","kind":"arxiv","version":4},"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/2402.03049/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":"2402.03049","created_at":"2026-07-05T08:35:41.568465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03049v4","created_at":"2026-07-05T08:35:41.568465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03049","created_at":"2026-07-05T08:35:41.568465+00:00"},{"alias_kind":"pith_short_12","alias_value":"YS7XIGSZ7A3U","created_at":"2026-07-05T08:35:41.568465+00:00"},{"alias_kind":"pith_short_16","alias_value":"YS7XIGSZ7A3UHJUR","created_at":"2026-07-05T08:35:41.568465+00:00"},{"alias_kind":"pith_short_8","alias_value":"YS7XIGSZ","created_at":"2026-07-05T08:35:41.568465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.11344","citing_title":"Can AI Extract Antecedent Factors of Human Trust in AI? An Application of Information Extraction for Scientific Literature in Behavioural and Computer Sciences","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YS7XIGSZ7A3UHJURD4DLXMTZU3","json":"https://pith.science/pith/YS7XIGSZ7A3UHJURD4DLXMTZU3.json","graph_json":"https://pith.science/api/pith-number/YS7XIGSZ7A3UHJURD4DLXMTZU3/graph.json","events_json":"https://pith.science/api/pith-number/YS7XIGSZ7A3UHJURD4DLXMTZU3/events.json","paper":"https://pith.science/paper/YS7XIGSZ"},"agent_actions":{"view_html":"https://pith.science/pith/YS7XIGSZ7A3UHJURD4DLXMTZU3","download_json":"https://pith.science/pith/YS7XIGSZ7A3UHJURD4DLXMTZU3.json","view_paper":"https://pith.science/paper/YS7XIGSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03049&json=true","fetch_graph":"https://pith.science/api/pith-number/YS7XIGSZ7A3UHJURD4DLXMTZU3/graph.json","fetch_events":"https://pith.science/api/pith-number/YS7XIGSZ7A3UHJURD4DLXMTZU3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YS7XIGSZ7A3UHJURD4DLXMTZU3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YS7XIGSZ7A3UHJURD4DLXMTZU3/action/storage_attestation","attest_author":"https://pith.science/pith/YS7XIGSZ7A3UHJURD4DLXMTZU3/action/author_attestation","sign_citation":"https://pith.science/pith/YS7XIGSZ7A3UHJURD4DLXMTZU3/action/citation_signature","submit_replication":"https://pith.science/pith/YS7XIGSZ7A3UHJURD4DLXMTZU3/action/replication_record"}},"created_at":"2026-07-05T08:35:41.568465+00:00","updated_at":"2026-07-05T08:35:41.568465+00:00"}