{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A4G7R6DNPRRL3WMBFPWVOSN44V","short_pith_number":"pith:A4G7R6DN","schema_version":"1.0","canonical_sha256":"070df8f86d7c62bdd9812bed5749bce542d61654e78305095c9115109375b072","source":{"kind":"arxiv","id":"2406.12382","version":5},"attestation_state":"computed","paper":{"title":"From Instance Training to Instruction Learning: Task Adapters Generation from Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huanxuan Liao, Jun Zhao, Kang Liu, Shengping Liu, Shizhu He, YanChao Hao, Yao Xu, Yuanzhe Zhang","submitted_at":"2024-06-18T08:14:28Z","abstract_excerpt":"Large language models (LLMs) have acquired the ability to solve general tasks by utilizing instruction finetuning (IFT). However, IFT still relies heavily on instance training of extensive task data, which greatly limits the adaptability of LLMs to real-world scenarios where labeled task instances are scarce and broader task generalization becomes paramount. Contrary to LLMs, humans acquire skills and complete tasks not merely through repeated practice but also by understanding and following instructional guidelines. This paper is dedicated to simulating human learning to address the shortcomi"},"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":"2406.12382","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T08:14:28Z","cross_cats_sorted":[],"title_canon_sha256":"65912fcac015a02f8ac24e8d56e57d8a1bc2fe6a162b7dacd8b9f274a06c438c","abstract_canon_sha256":"60f2ef6178e22fe4fce4375a01faeafc73bb72ea306eb6eecfaaa27170024f3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:10.848894Z","signature_b64":"GVWvUWtdSC86IxomkZJc+glESGKKoNaKbOFL5IuSfDII0SQE/SjSia0WKX22nj5Jydz5RKyvYsGp4cUvYg24Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"070df8f86d7c62bdd9812bed5749bce542d61654e78305095c9115109375b072","last_reissued_at":"2026-07-05T10:16:10.848349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:10.848349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Instance Training to Instruction Learning: Task Adapters Generation from Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huanxuan Liao, Jun Zhao, Kang Liu, Shengping Liu, Shizhu He, YanChao Hao, Yao Xu, Yuanzhe Zhang","submitted_at":"2024-06-18T08:14:28Z","abstract_excerpt":"Large language models (LLMs) have acquired the ability to solve general tasks by utilizing instruction finetuning (IFT). However, IFT still relies heavily on instance training of extensive task data, which greatly limits the adaptability of LLMs to real-world scenarios where labeled task instances are scarce and broader task generalization becomes paramount. Contrary to LLMs, humans acquire skills and complete tasks not merely through repeated practice but also by understanding and following instructional guidelines. This paper is dedicated to simulating human learning to address the shortcomi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12382","kind":"arxiv","version":5},"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/2406.12382/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":"2406.12382","created_at":"2026-07-05T10:16:10.848405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12382v5","created_at":"2026-07-05T10:16:10.848405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12382","created_at":"2026-07-05T10:16:10.848405+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4G7R6DNPRRL","created_at":"2026-07-05T10:16:10.848405+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4G7R6DNPRRL3WMB","created_at":"2026-07-05T10:16:10.848405+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4G7R6DN","created_at":"2026-07-05T10:16:10.848405+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14436","citing_title":"Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A4G7R6DNPRRL3WMBFPWVOSN44V","json":"https://pith.science/pith/A4G7R6DNPRRL3WMBFPWVOSN44V.json","graph_json":"https://pith.science/api/pith-number/A4G7R6DNPRRL3WMBFPWVOSN44V/graph.json","events_json":"https://pith.science/api/pith-number/A4G7R6DNPRRL3WMBFPWVOSN44V/events.json","paper":"https://pith.science/paper/A4G7R6DN"},"agent_actions":{"view_html":"https://pith.science/pith/A4G7R6DNPRRL3WMBFPWVOSN44V","download_json":"https://pith.science/pith/A4G7R6DNPRRL3WMBFPWVOSN44V.json","view_paper":"https://pith.science/paper/A4G7R6DN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12382&json=true","fetch_graph":"https://pith.science/api/pith-number/A4G7R6DNPRRL3WMBFPWVOSN44V/graph.json","fetch_events":"https://pith.science/api/pith-number/A4G7R6DNPRRL3WMBFPWVOSN44V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4G7R6DNPRRL3WMBFPWVOSN44V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4G7R6DNPRRL3WMBFPWVOSN44V/action/storage_attestation","attest_author":"https://pith.science/pith/A4G7R6DNPRRL3WMBFPWVOSN44V/action/author_attestation","sign_citation":"https://pith.science/pith/A4G7R6DNPRRL3WMBFPWVOSN44V/action/citation_signature","submit_replication":"https://pith.science/pith/A4G7R6DNPRRL3WMBFPWVOSN44V/action/replication_record"}},"created_at":"2026-07-05T10:16:10.848405+00:00","updated_at":"2026-07-05T10:16:10.848405+00:00"}