{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XI75II53MQJDBHWOAGXQAP5CL4","short_pith_number":"pith:XI75II53","schema_version":"1.0","canonical_sha256":"ba3fd423bb6412309ece01af003fa25f3e688d1357d0aa6a1a08b400aa71d9a3","source":{"kind":"arxiv","id":"2506.00178","version":2},"attestation_state":"computed","paper":{"title":"Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.AI","authors_text":"Adi Banerjee, Anirudh Nair, Laurent Mombaerts, Matthew Hagen, Tarik Borogovac","submitted_at":"2025-05-30T19:33:41Z","abstract_excerpt":"Prompt engineering represents a critical bottleneck to harness the full potential of Large Language Models (LLMs) for solving complex tasks, as it requires specialized expertise, significant trial-and-error, and manual intervention. This challenge is particularly pronounced for tasks involving subjective quality assessment, where defining explicit optimization objectives becomes fundamentally problematic. Existing automated prompt optimization methods falter in these scenarios, as they typically require well-defined task-specific numerical fitness functions or rely on generic templates that ca"},"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":"2506.00178","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-30T19:33:41Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"c8087db25913fa9ccb1cce85e76dc87790679473c9b1aab79044ca2502731902","abstract_canon_sha256":"61d0fbf333f688de844458ce01129d85ec72f50a7b74b83b6bade2e5047c9ce7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:42.475354Z","signature_b64":"HZ+vkAFiajF5ETuWL0qTGXHwCox82lvNEfi9EyuN0Bt8qLij1lczmDH2cz+H7NWOPF0gb4Pv997698kAlh6NCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba3fd423bb6412309ece01af003fa25f3e688d1357d0aa6a1a08b400aa71d9a3","last_reissued_at":"2026-07-05T11:41:42.474589Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:42.474589Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"cs.AI","authors_text":"Adi Banerjee, Anirudh Nair, Laurent Mombaerts, Matthew Hagen, Tarik Borogovac","submitted_at":"2025-05-30T19:33:41Z","abstract_excerpt":"Prompt engineering represents a critical bottleneck to harness the full potential of Large Language Models (LLMs) for solving complex tasks, as it requires specialized expertise, significant trial-and-error, and manual intervention. This challenge is particularly pronounced for tasks involving subjective quality assessment, where defining explicit optimization objectives becomes fundamentally problematic. Existing automated prompt optimization methods falter in these scenarios, as they typically require well-defined task-specific numerical fitness functions or rely on generic templates that ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00178","kind":"arxiv","version":2},"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/2506.00178/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":"2506.00178","created_at":"2026-07-05T11:41:42.474676+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00178v2","created_at":"2026-07-05T11:41:42.474676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00178","created_at":"2026-07-05T11:41:42.474676+00:00"},{"alias_kind":"pith_short_12","alias_value":"XI75II53MQJD","created_at":"2026-07-05T11:41:42.474676+00:00"},{"alias_kind":"pith_short_16","alias_value":"XI75II53MQJDBHWO","created_at":"2026-07-05T11:41:42.474676+00:00"},{"alias_kind":"pith_short_8","alias_value":"XI75II53","created_at":"2026-07-05T11:41:42.474676+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/XI75II53MQJDBHWOAGXQAP5CL4","json":"https://pith.science/pith/XI75II53MQJDBHWOAGXQAP5CL4.json","graph_json":"https://pith.science/api/pith-number/XI75II53MQJDBHWOAGXQAP5CL4/graph.json","events_json":"https://pith.science/api/pith-number/XI75II53MQJDBHWOAGXQAP5CL4/events.json","paper":"https://pith.science/paper/XI75II53"},"agent_actions":{"view_html":"https://pith.science/pith/XI75II53MQJDBHWOAGXQAP5CL4","download_json":"https://pith.science/pith/XI75II53MQJDBHWOAGXQAP5CL4.json","view_paper":"https://pith.science/paper/XI75II53","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00178&json=true","fetch_graph":"https://pith.science/api/pith-number/XI75II53MQJDBHWOAGXQAP5CL4/graph.json","fetch_events":"https://pith.science/api/pith-number/XI75II53MQJDBHWOAGXQAP5CL4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XI75II53MQJDBHWOAGXQAP5CL4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XI75II53MQJDBHWOAGXQAP5CL4/action/storage_attestation","attest_author":"https://pith.science/pith/XI75II53MQJDBHWOAGXQAP5CL4/action/author_attestation","sign_citation":"https://pith.science/pith/XI75II53MQJDBHWOAGXQAP5CL4/action/citation_signature","submit_replication":"https://pith.science/pith/XI75II53MQJDBHWOAGXQAP5CL4/action/replication_record"}},"created_at":"2026-07-05T11:41:42.474676+00:00","updated_at":"2026-07-05T11:41:42.474676+00:00"}