{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XORIATRP2IUT23E4IVOYRUMAIR","short_pith_number":"pith:XORIATRP","schema_version":"1.0","canonical_sha256":"bba2804e2fd2293d6c9c455d88d180447335bf7bba6953721bd911b1bdae9665","source":{"kind":"arxiv","id":"2409.15199","version":1},"attestation_state":"computed","paper":{"title":"Learning from Contrastive Prompts: Automated Optimization and Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aitzaz Ahmad, Karan Aggarwal, Mingqi Li, Stephen Lau, Yong Xie","submitted_at":"2024-09-23T16:47:23Z","abstract_excerpt":"As LLMs evolve, significant effort is spent on manually crafting prompts. While existing prompt optimization methods automate this process, they rely solely on learning from incorrect samples, leading to a sub-optimal performance. Additionally, an unexplored challenge in the literature is prompts effective for prior models may not perform well on newer versions or different languages. We propose the Learning from Contrastive Prompts (LCP) framework to address these gaps, enhancing both prompt optimization and adaptation. LCP employs contrastive learning to generate effective prompts by analyzi"},"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":"2409.15199","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-23T16:47:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6020eb42fd7c082bb26e115132fd233f390f3a266bffdf2dac51fc43a8ea7fbc","abstract_canon_sha256":"e96c3cd1276d059031e798ce4e4cac403f830c1531782f94629c8299b218a90f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:37.549928Z","signature_b64":"9YEkar71L8AlAdX+M81cQhFgPf5qfFYAxsMuXDBqbIhLVUhCWTVtc71ev/XId5Dm1yUbSqjCZZ2sekLGOvIMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bba2804e2fd2293d6c9c455d88d180447335bf7bba6953721bd911b1bdae9665","last_reissued_at":"2026-07-05T09:10:37.549483Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:37.549483Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from Contrastive Prompts: Automated Optimization and Adaptation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aitzaz Ahmad, Karan Aggarwal, Mingqi Li, Stephen Lau, Yong Xie","submitted_at":"2024-09-23T16:47:23Z","abstract_excerpt":"As LLMs evolve, significant effort is spent on manually crafting prompts. While existing prompt optimization methods automate this process, they rely solely on learning from incorrect samples, leading to a sub-optimal performance. Additionally, an unexplored challenge in the literature is prompts effective for prior models may not perform well on newer versions or different languages. We propose the Learning from Contrastive Prompts (LCP) framework to address these gaps, enhancing both prompt optimization and adaptation. LCP employs contrastive learning to generate effective prompts by analyzi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.15199","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/2409.15199/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":"2409.15199","created_at":"2026-07-05T09:10:37.549539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.15199v1","created_at":"2026-07-05T09:10:37.549539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.15199","created_at":"2026-07-05T09:10:37.549539+00:00"},{"alias_kind":"pith_short_12","alias_value":"XORIATRP2IUT","created_at":"2026-07-05T09:10:37.549539+00:00"},{"alias_kind":"pith_short_16","alias_value":"XORIATRP2IUT23E4","created_at":"2026-07-05T09:10:37.549539+00:00"},{"alias_kind":"pith_short_8","alias_value":"XORIATRP","created_at":"2026-07-05T09:10:37.549539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17937","citing_title":"ContraPrompt: Contrastive Prompt Optimization via Dyadic Reasoning Trace Analysis","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XORIATRP2IUT23E4IVOYRUMAIR","json":"https://pith.science/pith/XORIATRP2IUT23E4IVOYRUMAIR.json","graph_json":"https://pith.science/api/pith-number/XORIATRP2IUT23E4IVOYRUMAIR/graph.json","events_json":"https://pith.science/api/pith-number/XORIATRP2IUT23E4IVOYRUMAIR/events.json","paper":"https://pith.science/paper/XORIATRP"},"agent_actions":{"view_html":"https://pith.science/pith/XORIATRP2IUT23E4IVOYRUMAIR","download_json":"https://pith.science/pith/XORIATRP2IUT23E4IVOYRUMAIR.json","view_paper":"https://pith.science/paper/XORIATRP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.15199&json=true","fetch_graph":"https://pith.science/api/pith-number/XORIATRP2IUT23E4IVOYRUMAIR/graph.json","fetch_events":"https://pith.science/api/pith-number/XORIATRP2IUT23E4IVOYRUMAIR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XORIATRP2IUT23E4IVOYRUMAIR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XORIATRP2IUT23E4IVOYRUMAIR/action/storage_attestation","attest_author":"https://pith.science/pith/XORIATRP2IUT23E4IVOYRUMAIR/action/author_attestation","sign_citation":"https://pith.science/pith/XORIATRP2IUT23E4IVOYRUMAIR/action/citation_signature","submit_replication":"https://pith.science/pith/XORIATRP2IUT23E4IVOYRUMAIR/action/replication_record"}},"created_at":"2026-07-05T09:10:37.549539+00:00","updated_at":"2026-07-05T09:10:37.549539+00:00"}