{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ROFBHCCJINRDGDFVYVVV4SO57K","short_pith_number":"pith:ROFBHCCJ","schema_version":"1.0","canonical_sha256":"8b8a1388494362330cb5c56b5e49ddfaac797b168b4a7561d71e165054e241b4","source":{"kind":"arxiv","id":"2507.04221","version":3},"attestation_state":"computed","paper":{"title":"Context Tuning for In-Context Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jack Lu, Mengye Ren, Ryan Teehan, Zhenbang Yang","submitted_at":"2025-07-06T03:23:53Z","abstract_excerpt":"We introduce Context Tuning, a simple and effective method to significantly enhance few-shot adaptation of large language models (LLMs) without weight updates. In-Context Learning (ICL) forms a memory representation of the demonstrations in a single forward pass but cannot refine it when insufficient. Prompt-based methods offer lightweight adaptation by optimizing a trainable prompt or prefix but initialize it independently of the demonstrations. In contrast, Context Tuning leverages the model's inherent ICL ability to initialize a trainable memory representation from demonstrations, then refi"},"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":"2507.04221","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-06T03:23:53Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"93f6bd6b155fd24e300439faea12eb9067f53b7d39d03623dc644e4a7dc3e0ad","abstract_canon_sha256":"43e11c97bb13e03d2f15ada32bb78f27fc867842d05bf86c5d2245fb0af2cabc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:15:55.933950Z","signature_b64":"AomA7lFsQ+cluau1Ssur34aj5ca6Ia66yP6B9kmFuxzcsNCOswo5euC+FDplYeiqknWnLoiiMV8ZADRbfH59Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b8a1388494362330cb5c56b5e49ddfaac797b168b4a7561d71e165054e241b4","last_reissued_at":"2026-07-07T01:15:55.933093Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:15:55.933093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context Tuning for In-Context Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jack Lu, Mengye Ren, Ryan Teehan, Zhenbang Yang","submitted_at":"2025-07-06T03:23:53Z","abstract_excerpt":"We introduce Context Tuning, a simple and effective method to significantly enhance few-shot adaptation of large language models (LLMs) without weight updates. In-Context Learning (ICL) forms a memory representation of the demonstrations in a single forward pass but cannot refine it when insufficient. Prompt-based methods offer lightweight adaptation by optimizing a trainable prompt or prefix but initialize it independently of the demonstrations. In contrast, Context Tuning leverages the model's inherent ICL ability to initialize a trainable memory representation from demonstrations, then refi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04221","kind":"arxiv","version":3},"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/2507.04221/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":"2507.04221","created_at":"2026-07-07T01:15:55.933199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04221v3","created_at":"2026-07-07T01:15:55.933199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04221","created_at":"2026-07-07T01:15:55.933199+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROFBHCCJINRD","created_at":"2026-07-07T01:15:55.933199+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROFBHCCJINRDGDFV","created_at":"2026-07-07T01:15:55.933199+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROFBHCCJ","created_at":"2026-07-07T01:15:55.933199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROFBHCCJINRDGDFVYVVV4SO57K","json":"https://pith.science/pith/ROFBHCCJINRDGDFVYVVV4SO57K.json","graph_json":"https://pith.science/api/pith-number/ROFBHCCJINRDGDFVYVVV4SO57K/graph.json","events_json":"https://pith.science/api/pith-number/ROFBHCCJINRDGDFVYVVV4SO57K/events.json","paper":"https://pith.science/paper/ROFBHCCJ"},"agent_actions":{"view_html":"https://pith.science/pith/ROFBHCCJINRDGDFVYVVV4SO57K","download_json":"https://pith.science/pith/ROFBHCCJINRDGDFVYVVV4SO57K.json","view_paper":"https://pith.science/paper/ROFBHCCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04221&json=true","fetch_graph":"https://pith.science/api/pith-number/ROFBHCCJINRDGDFVYVVV4SO57K/graph.json","fetch_events":"https://pith.science/api/pith-number/ROFBHCCJINRDGDFVYVVV4SO57K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROFBHCCJINRDGDFVYVVV4SO57K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROFBHCCJINRDGDFVYVVV4SO57K/action/storage_attestation","attest_author":"https://pith.science/pith/ROFBHCCJINRDGDFVYVVV4SO57K/action/author_attestation","sign_citation":"https://pith.science/pith/ROFBHCCJINRDGDFVYVVV4SO57K/action/citation_signature","submit_replication":"https://pith.science/pith/ROFBHCCJINRDGDFVYVVV4SO57K/action/replication_record"}},"created_at":"2026-07-07T01:15:55.933199+00:00","updated_at":"2026-07-07T01:15:55.933199+00:00"}