{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5I2GCXOPJSPILGDY44K6EDSR46","short_pith_number":"pith:5I2GCXOP","schema_version":"1.0","canonical_sha256":"ea34615dcf4c9e859878e715e20e51e7ae348dd2cb64936a85a9e3ea33af7694","source":{"kind":"arxiv","id":"2503.13518","version":1},"attestation_state":"computed","paper":{"title":"Examples as the Prompt: A Scalable Approach for Efficient LLM Adaptation in E-Commerce","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Luo, Hui Liu, Jingying Zeng, Qi He, Samarth Varshney, Xianfeng Tang, Zhen Li, Zhenwei Dai, Zhiji Liu","submitted_at":"2025-03-14T18:22:43Z","abstract_excerpt":"Prompting LLMs offers an efficient way to guide output generation without explicit model training. In the e-commerce domain, prompting-based applications are widely used for tasks such as query understanding, recommender systems, and customer support. However, adapting LLMs to different tasks often requires extensive prompt engineering by domain experts, along with frequent updates to align with evolving business needs. Additionally, crafting fully unbiased natural language prompts remains a challenge for humans. To address these challenges, we propose a novel framework, Examples as the Prompt"},"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":"2503.13518","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-14T18:22:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3a26c07bb57e6b3fa64ab5eed0fc80902b8ea786e33fe478085ac86372562836","abstract_canon_sha256":"69927d1e7cacb083b984054bea9730bf69807dce3e7382c4e6bdd92f0eff29ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:12.026272Z","signature_b64":"KorGyFtLSVnyzWB+kscsUA7fVsFIHMd/pU8SzmXDoa2X/NJjgXgUoWPDHhOwp6qgWFxxvCUHPDTP2uC/cVa8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea34615dcf4c9e859878e715e20e51e7ae348dd2cb64936a85a9e3ea33af7694","last_reissued_at":"2026-07-05T10:33:12.025540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:12.025540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Examples as the Prompt: A Scalable Approach for Efficient LLM Adaptation in E-Commerce","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chen Luo, Hui Liu, Jingying Zeng, Qi He, Samarth Varshney, Xianfeng Tang, Zhen Li, Zhenwei Dai, Zhiji Liu","submitted_at":"2025-03-14T18:22:43Z","abstract_excerpt":"Prompting LLMs offers an efficient way to guide output generation without explicit model training. In the e-commerce domain, prompting-based applications are widely used for tasks such as query understanding, recommender systems, and customer support. However, adapting LLMs to different tasks often requires extensive prompt engineering by domain experts, along with frequent updates to align with evolving business needs. Additionally, crafting fully unbiased natural language prompts remains a challenge for humans. To address these challenges, we propose a novel framework, Examples as the Prompt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13518","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/2503.13518/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":"2503.13518","created_at":"2026-07-05T10:33:12.025637+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.13518v1","created_at":"2026-07-05T10:33:12.025637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13518","created_at":"2026-07-05T10:33:12.025637+00:00"},{"alias_kind":"pith_short_12","alias_value":"5I2GCXOPJSPI","created_at":"2026-07-05T10:33:12.025637+00:00"},{"alias_kind":"pith_short_16","alias_value":"5I2GCXOPJSPILGDY","created_at":"2026-07-05T10:33:12.025637+00:00"},{"alias_kind":"pith_short_8","alias_value":"5I2GCXOP","created_at":"2026-07-05T10:33:12.025637+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/5I2GCXOPJSPILGDY44K6EDSR46","json":"https://pith.science/pith/5I2GCXOPJSPILGDY44K6EDSR46.json","graph_json":"https://pith.science/api/pith-number/5I2GCXOPJSPILGDY44K6EDSR46/graph.json","events_json":"https://pith.science/api/pith-number/5I2GCXOPJSPILGDY44K6EDSR46/events.json","paper":"https://pith.science/paper/5I2GCXOP"},"agent_actions":{"view_html":"https://pith.science/pith/5I2GCXOPJSPILGDY44K6EDSR46","download_json":"https://pith.science/pith/5I2GCXOPJSPILGDY44K6EDSR46.json","view_paper":"https://pith.science/paper/5I2GCXOP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.13518&json=true","fetch_graph":"https://pith.science/api/pith-number/5I2GCXOPJSPILGDY44K6EDSR46/graph.json","fetch_events":"https://pith.science/api/pith-number/5I2GCXOPJSPILGDY44K6EDSR46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5I2GCXOPJSPILGDY44K6EDSR46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5I2GCXOPJSPILGDY44K6EDSR46/action/storage_attestation","attest_author":"https://pith.science/pith/5I2GCXOPJSPILGDY44K6EDSR46/action/author_attestation","sign_citation":"https://pith.science/pith/5I2GCXOPJSPILGDY44K6EDSR46/action/citation_signature","submit_replication":"https://pith.science/pith/5I2GCXOPJSPILGDY44K6EDSR46/action/replication_record"}},"created_at":"2026-07-05T10:33:12.025637+00:00","updated_at":"2026-07-05T10:33:12.025637+00:00"}