{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EX56JLTDCDPAQREG6S6BTSZVHO","short_pith_number":"pith:EX56JLTD","schema_version":"1.0","canonical_sha256":"25fbe4ae6310de084486f4bc19cb353b872fb79ff2d82c0fac2ee410a83fb013","source":{"kind":"arxiv","id":"2405.13448","version":2},"attestation_state":"computed","paper":{"title":"Distilling Instruction-following Abilities of Large Language Models with Task-aware Curriculum Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengyu Wang, Jun Huang, Peng Wang, Yuanhao Yue","submitted_at":"2024-05-22T08:38:26Z","abstract_excerpt":"Instruction tuning aims to align large language models (LLMs) with open-domain instructions and human-preferred responses. While several studies have explored autonomous approaches to distilling and annotating instructions from powerful proprietary LLMs, such as ChatGPT, they often neglect the impact of the distributions and characteristics of tasks, together with the varying difficulty of instructions in training sets. This oversight can lead to imbalanced knowledge capabilities and poor generalization powers of student LLMs. To address these challenges, we introduce Task-Aware Curriculum Pla"},"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":"2405.13448","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-05-22T08:38:26Z","cross_cats_sorted":[],"title_canon_sha256":"2571306e3a0e1ac49b0448a9c65835a70c52035774b616706fbe36f9d6264882","abstract_canon_sha256":"607e41e9f2728112c864c7b6712563766db5a15105e40f1e803231fc4864a560"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:10.542991Z","signature_b64":"2arQ9iWoawdTzuSL2CaKK8JIiCZ3zcQTjfA72dmVfY7+4bimZ0CFrOQSREsLZdO38akLzHj5rTTucxnhslIBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25fbe4ae6310de084486f4bc19cb353b872fb79ff2d82c0fac2ee410a83fb013","last_reissued_at":"2026-07-05T09:15:10.542569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:10.542569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling Instruction-following Abilities of Large Language Models with Task-aware Curriculum Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengyu Wang, Jun Huang, Peng Wang, Yuanhao Yue","submitted_at":"2024-05-22T08:38:26Z","abstract_excerpt":"Instruction tuning aims to align large language models (LLMs) with open-domain instructions and human-preferred responses. While several studies have explored autonomous approaches to distilling and annotating instructions from powerful proprietary LLMs, such as ChatGPT, they often neglect the impact of the distributions and characteristics of tasks, together with the varying difficulty of instructions in training sets. This oversight can lead to imbalanced knowledge capabilities and poor generalization powers of student LLMs. To address these challenges, we introduce Task-Aware Curriculum Pla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13448","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/2405.13448/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":"2405.13448","created_at":"2026-07-05T09:15:10.542626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13448v2","created_at":"2026-07-05T09:15:10.542626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13448","created_at":"2026-07-05T09:15:10.542626+00:00"},{"alias_kind":"pith_short_12","alias_value":"EX56JLTDCDPA","created_at":"2026-07-05T09:15:10.542626+00:00"},{"alias_kind":"pith_short_16","alias_value":"EX56JLTDCDPAQREG","created_at":"2026-07-05T09:15:10.542626+00:00"},{"alias_kind":"pith_short_8","alias_value":"EX56JLTD","created_at":"2026-07-05T09:15:10.542626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11290","citing_title":"ReAD: Reinforcement-Guided Capability Distillation for Large Language Models","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EX56JLTDCDPAQREG6S6BTSZVHO","json":"https://pith.science/pith/EX56JLTDCDPAQREG6S6BTSZVHO.json","graph_json":"https://pith.science/api/pith-number/EX56JLTDCDPAQREG6S6BTSZVHO/graph.json","events_json":"https://pith.science/api/pith-number/EX56JLTDCDPAQREG6S6BTSZVHO/events.json","paper":"https://pith.science/paper/EX56JLTD"},"agent_actions":{"view_html":"https://pith.science/pith/EX56JLTDCDPAQREG6S6BTSZVHO","download_json":"https://pith.science/pith/EX56JLTDCDPAQREG6S6BTSZVHO.json","view_paper":"https://pith.science/paper/EX56JLTD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13448&json=true","fetch_graph":"https://pith.science/api/pith-number/EX56JLTDCDPAQREG6S6BTSZVHO/graph.json","fetch_events":"https://pith.science/api/pith-number/EX56JLTDCDPAQREG6S6BTSZVHO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EX56JLTDCDPAQREG6S6BTSZVHO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EX56JLTDCDPAQREG6S6BTSZVHO/action/storage_attestation","attest_author":"https://pith.science/pith/EX56JLTDCDPAQREG6S6BTSZVHO/action/author_attestation","sign_citation":"https://pith.science/pith/EX56JLTDCDPAQREG6S6BTSZVHO/action/citation_signature","submit_replication":"https://pith.science/pith/EX56JLTDCDPAQREG6S6BTSZVHO/action/replication_record"}},"created_at":"2026-07-05T09:15:10.542626+00:00","updated_at":"2026-07-05T09:15:10.542626+00:00"}