{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RTXGESE6KNFYDP6XCTMQBJFXQ2","short_pith_number":"pith:RTXGESE6","schema_version":"1.0","canonical_sha256":"8cee62489e534b81bfd714d900a4b786b37b48296071fd07df824340e6c271c0","source":{"kind":"arxiv","id":"2402.10949","version":2},"attestation_state":"computed","paper":{"title":"The Unreasonable Effectiveness of Eccentric Automatic Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Rick Battle, Teja Gollapudi","submitted_at":"2024-02-09T22:48:45Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable problem-solving and basic mathematics abilities. However, their efficacy is highly contingent on the formulation of the prompt. This study endeavors to quantify the influence of incorporating \"positive thinking\" into the system message of the prompt, then compare that to systematic prompt optimization. We assess the performance of 60 combinations of system message snippets, tested with and without Chain of Thought prompting, across three models with parameters ranging from 7 to 70 billion on the GSM8K dataset. Our findings reveal that r"},"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":"2402.10949","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-09T22:48:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bc5359604c91725ad90844b5fa65f5e9c30679ea9d187a374aa4d8b15449bcda","abstract_canon_sha256":"d8388281161ad64510c890e684ba06fd91ec0b2a47e271ada2cbcf9c27416cf0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:09.938545Z","signature_b64":"ZRBb3luKcahvA6tBzxzlul96cxqnejCx43jaXT3GUjsIHeXXw94tZgnVGRjfI38boujKyuJZdlbbhg/79HFYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cee62489e534b81bfd714d900a4b786b37b48296071fd07df824340e6c271c0","last_reissued_at":"2026-07-05T07:47:09.938065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:09.938065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Unreasonable Effectiveness of Eccentric Automatic Prompts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Rick Battle, Teja Gollapudi","submitted_at":"2024-02-09T22:48:45Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable problem-solving and basic mathematics abilities. However, their efficacy is highly contingent on the formulation of the prompt. This study endeavors to quantify the influence of incorporating \"positive thinking\" into the system message of the prompt, then compare that to systematic prompt optimization. We assess the performance of 60 combinations of system message snippets, tested with and without Chain of Thought prompting, across three models with parameters ranging from 7 to 70 billion on the GSM8K dataset. Our findings reveal that r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.10949","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/2402.10949/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":"2402.10949","created_at":"2026-07-05T07:47:09.938132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.10949v2","created_at":"2026-07-05T07:47:09.938132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.10949","created_at":"2026-07-05T07:47:09.938132+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTXGESE6KNFY","created_at":"2026-07-05T07:47:09.938132+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTXGESE6KNFYDP6X","created_at":"2026-07-05T07:47:09.938132+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTXGESE6","created_at":"2026-07-05T07:47:09.938132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07539","citing_title":"Prompt Governance? On Governing Technologies Governed by Natural Language","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05716","citing_title":"More Is Not Always Better: Cross-Component Interference in LLM Agent Scaffolding","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTXGESE6KNFYDP6XCTMQBJFXQ2","json":"https://pith.science/pith/RTXGESE6KNFYDP6XCTMQBJFXQ2.json","graph_json":"https://pith.science/api/pith-number/RTXGESE6KNFYDP6XCTMQBJFXQ2/graph.json","events_json":"https://pith.science/api/pith-number/RTXGESE6KNFYDP6XCTMQBJFXQ2/events.json","paper":"https://pith.science/paper/RTXGESE6"},"agent_actions":{"view_html":"https://pith.science/pith/RTXGESE6KNFYDP6XCTMQBJFXQ2","download_json":"https://pith.science/pith/RTXGESE6KNFYDP6XCTMQBJFXQ2.json","view_paper":"https://pith.science/paper/RTXGESE6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.10949&json=true","fetch_graph":"https://pith.science/api/pith-number/RTXGESE6KNFYDP6XCTMQBJFXQ2/graph.json","fetch_events":"https://pith.science/api/pith-number/RTXGESE6KNFYDP6XCTMQBJFXQ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTXGESE6KNFYDP6XCTMQBJFXQ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTXGESE6KNFYDP6XCTMQBJFXQ2/action/storage_attestation","attest_author":"https://pith.science/pith/RTXGESE6KNFYDP6XCTMQBJFXQ2/action/author_attestation","sign_citation":"https://pith.science/pith/RTXGESE6KNFYDP6XCTMQBJFXQ2/action/citation_signature","submit_replication":"https://pith.science/pith/RTXGESE6KNFYDP6XCTMQBJFXQ2/action/replication_record"}},"created_at":"2026-07-05T07:47:09.938132+00:00","updated_at":"2026-07-05T07:47:09.938132+00:00"}