{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FFTC4EDOVTDCUQPVICUGAPFC2H","short_pith_number":"pith:FFTC4EDO","schema_version":"1.0","canonical_sha256":"29662e106eacc62a41f540a8603ca2d1c523de7c2851b57aadad062d66c2b9c5","source":{"kind":"arxiv","id":"2305.13729","version":1},"attestation_state":"computed","paper":{"title":"Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Jeongyeon Seo, Jong C. Park, Soyeong Jeong, Sukmin Cho","submitted_at":"2023-05-23T06:35:33Z","abstract_excerpt":"Re-rankers, which order retrieved documents with respect to the relevance score on the given query, have gained attention for the information retrieval (IR) task. Rather than fine-tuning the pre-trained language model (PLM), the large-scale language model (LLM) is utilized as a zero-shot re-ranker with excellent results. While LLM is highly dependent on the prompts, the impact and the optimization of the prompts for the zero-shot re-ranker are not explored yet. Along with highlighting the impact of optimization on the zero-shot re-ranker, we propose a novel discrete prompt optimization method,"},"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":"2305.13729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2023-05-23T06:35:33Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8ee3bd515a80c1aaadd1d2ef55777f28cfd7e163d310d0fb9fb04cb02f91c2ad","abstract_canon_sha256":"5ff27cb9d4e37e0f73ebb2543fbc79b5d74baa82f195fa7c649666d9e4132c4a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:56.759412Z","signature_b64":"+0KEY5w6hvIqnm8Y5JJEUnEm9lE3PFBDKQt31AIXozI9tt1EUF40t3iCu8Jt9SOT7tP1YjQ3JqKXVQ3LZBbWBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29662e106eacc62a41f540a8603ca2d1c523de7c2851b57aadad062d66c2b9c5","last_reissued_at":"2026-07-05T06:12:56.758970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:56.758970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Jeongyeon Seo, Jong C. Park, Soyeong Jeong, Sukmin Cho","submitted_at":"2023-05-23T06:35:33Z","abstract_excerpt":"Re-rankers, which order retrieved documents with respect to the relevance score on the given query, have gained attention for the information retrieval (IR) task. Rather than fine-tuning the pre-trained language model (PLM), the large-scale language model (LLM) is utilized as a zero-shot re-ranker with excellent results. While LLM is highly dependent on the prompts, the impact and the optimization of the prompts for the zero-shot re-ranker are not explored yet. Along with highlighting the impact of optimization on the zero-shot re-ranker, we propose a novel discrete prompt optimization method,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13729","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/2305.13729/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":"2305.13729","created_at":"2026-07-05T06:12:56.759026+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13729v1","created_at":"2026-07-05T06:12:56.759026+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13729","created_at":"2026-07-05T06:12:56.759026+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFTC4EDOVTDC","created_at":"2026-07-05T06:12:56.759026+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFTC4EDOVTDCUQPV","created_at":"2026-07-05T06:12:56.759026+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFTC4EDO","created_at":"2026-07-05T06:12:56.759026+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.10120","citing_title":"PaSa: An LLM Agent for Comprehensive Academic Paper Search","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFTC4EDOVTDCUQPVICUGAPFC2H","json":"https://pith.science/pith/FFTC4EDOVTDCUQPVICUGAPFC2H.json","graph_json":"https://pith.science/api/pith-number/FFTC4EDOVTDCUQPVICUGAPFC2H/graph.json","events_json":"https://pith.science/api/pith-number/FFTC4EDOVTDCUQPVICUGAPFC2H/events.json","paper":"https://pith.science/paper/FFTC4EDO"},"agent_actions":{"view_html":"https://pith.science/pith/FFTC4EDOVTDCUQPVICUGAPFC2H","download_json":"https://pith.science/pith/FFTC4EDOVTDCUQPVICUGAPFC2H.json","view_paper":"https://pith.science/paper/FFTC4EDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13729&json=true","fetch_graph":"https://pith.science/api/pith-number/FFTC4EDOVTDCUQPVICUGAPFC2H/graph.json","fetch_events":"https://pith.science/api/pith-number/FFTC4EDOVTDCUQPVICUGAPFC2H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFTC4EDOVTDCUQPVICUGAPFC2H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFTC4EDOVTDCUQPVICUGAPFC2H/action/storage_attestation","attest_author":"https://pith.science/pith/FFTC4EDOVTDCUQPVICUGAPFC2H/action/author_attestation","sign_citation":"https://pith.science/pith/FFTC4EDOVTDCUQPVICUGAPFC2H/action/citation_signature","submit_replication":"https://pith.science/pith/FFTC4EDOVTDCUQPVICUGAPFC2H/action/replication_record"}},"created_at":"2026-07-05T06:12:56.759026+00:00","updated_at":"2026-07-05T06:12:56.759026+00:00"}