{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Q4W5BFER2XN2PILTEZ3VFKZVDP","short_pith_number":"pith:Q4W5BFER","schema_version":"1.0","canonical_sha256":"872dd09491d5dba7a173267752ab351bd5a19767be211ab922461b9f8485a65d","source":{"kind":"arxiv","id":"2306.05539","version":1},"attestation_state":"computed","paper":{"title":"Instruction Tuned Models are Quick Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arindam Mitra, Chitta Baral, Himanshu Gupta, Mutsumi Nakamura, Santosh Mashetty, Saurabh Arjun Sawant, Swaroop Mishra","submitted_at":"2023-05-17T22:30:01Z","abstract_excerpt":"Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream training data for finetuning. Often in real-world situations, there is a scarcity of data available for finetuning, falling somewhere between few shot inference and fully supervised finetuning. In this work, we demonstrate the sample efficiency of instruction tuned models over various tasks by estimating the minimal downstream training data required by them to"},"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":"2306.05539","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-17T22:30:01Z","cross_cats_sorted":[],"title_canon_sha256":"1c3d617bdc4dc1cb307d48d878b6e7181cb7d0b8df9cd022161802f807d01176","abstract_canon_sha256":"af73eab9c2c36582ea3b0b1116a557de56f7f0e71b5ebdacaed1e3f4599020f2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:19:07.183707Z","signature_b64":"9jdFS/YFvX7/ntdi3jJgroV1TO5rrO5VeIhMr4tJGYvQVPi/Y5Tm2OtUXTyfdHmTNL1eb4HiKU/GfMjg9c+3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"872dd09491d5dba7a173267752ab351bd5a19767be211ab922461b9f8485a65d","last_reissued_at":"2026-07-05T06:19:07.183266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:19:07.183266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instruction Tuned Models are Quick Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arindam Mitra, Chitta Baral, Himanshu Gupta, Mutsumi Nakamura, Santosh Mashetty, Saurabh Arjun Sawant, Swaroop Mishra","submitted_at":"2023-05-17T22:30:01Z","abstract_excerpt":"Instruction tuning of language models has demonstrated the ability to enhance model generalization to unseen tasks via in-context learning using a few examples. However, typical supervised learning still requires a plethora of downstream training data for finetuning. Often in real-world situations, there is a scarcity of data available for finetuning, falling somewhere between few shot inference and fully supervised finetuning. In this work, we demonstrate the sample efficiency of instruction tuned models over various tasks by estimating the minimal downstream training data required by them to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05539","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/2306.05539/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":"2306.05539","created_at":"2026-07-05T06:19:07.183323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05539v1","created_at":"2026-07-05T06:19:07.183323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05539","created_at":"2026-07-05T06:19:07.183323+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q4W5BFER2XN2","created_at":"2026-07-05T06:19:07.183323+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q4W5BFER2XN2PILT","created_at":"2026-07-05T06:19:07.183323+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q4W5BFER","created_at":"2026-07-05T06:19:07.183323+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23267","citing_title":"Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":183,"is_internal_anchor":false},{"citing_arxiv_id":"2305.16264","citing_title":"Scaling Data-Constrained Language Models","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23267","citing_title":"Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q4W5BFER2XN2PILTEZ3VFKZVDP","json":"https://pith.science/pith/Q4W5BFER2XN2PILTEZ3VFKZVDP.json","graph_json":"https://pith.science/api/pith-number/Q4W5BFER2XN2PILTEZ3VFKZVDP/graph.json","events_json":"https://pith.science/api/pith-number/Q4W5BFER2XN2PILTEZ3VFKZVDP/events.json","paper":"https://pith.science/paper/Q4W5BFER"},"agent_actions":{"view_html":"https://pith.science/pith/Q4W5BFER2XN2PILTEZ3VFKZVDP","download_json":"https://pith.science/pith/Q4W5BFER2XN2PILTEZ3VFKZVDP.json","view_paper":"https://pith.science/paper/Q4W5BFER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05539&json=true","fetch_graph":"https://pith.science/api/pith-number/Q4W5BFER2XN2PILTEZ3VFKZVDP/graph.json","fetch_events":"https://pith.science/api/pith-number/Q4W5BFER2XN2PILTEZ3VFKZVDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q4W5BFER2XN2PILTEZ3VFKZVDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q4W5BFER2XN2PILTEZ3VFKZVDP/action/storage_attestation","attest_author":"https://pith.science/pith/Q4W5BFER2XN2PILTEZ3VFKZVDP/action/author_attestation","sign_citation":"https://pith.science/pith/Q4W5BFER2XN2PILTEZ3VFKZVDP/action/citation_signature","submit_replication":"https://pith.science/pith/Q4W5BFER2XN2PILTEZ3VFKZVDP/action/replication_record"}},"created_at":"2026-07-05T06:19:07.183323+00:00","updated_at":"2026-07-05T06:19:07.183323+00:00"}