{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DOXTM6MSDVNVAGY4637GHR3JFW","short_pith_number":"pith:DOXTM6MS","schema_version":"1.0","canonical_sha256":"1baf3679921d5b501b1cf6fe63c7692db9ca4d9a125faa1903a589f1876184f6","source":{"kind":"arxiv","id":"2504.02052","version":2},"attestation_state":"computed","paper":{"title":"From Prompts to Templates: A Systematic Prompt Template Analysis for Real-world LLMapps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chunyang Chen, Junjie He, Yuetian Mao","submitted_at":"2025-04-02T18:20:06Z","abstract_excerpt":"Large Language Models (LLMs) have revolutionized human-AI interaction by enabling intuitive task execution through natural language prompts. Despite their potential, designing effective prompts remains a significant challenge, as small variations in structure or wording can result in substantial differences in output. To address these challenges, LLM-powered applications (LLMapps) rely on prompt templates to simplify interactions, enhance usability, and support specialized tasks such as document analysis, creative content generation, and code synthesis. However, current practices heavily depen"},"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":"2504.02052","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-04-02T18:20:06Z","cross_cats_sorted":[],"title_canon_sha256":"fb53497e50e5d2b34a489af03c2c5c10b60a3ffdd880522de882f6deac507052","abstract_canon_sha256":"5cecda27671a11f28ae6bd081beb64db4f2048f4da2e2ca885e6e7999ec97d39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:20.690299Z","signature_b64":"I727MrkgHE5y/nhymmVQgVDiQvefiNmFR14oiFY16VkgaWxYHzxy5GGX9/8B4Eraa2SCQiB3sCUERkaUZGKSCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1baf3679921d5b501b1cf6fe63c7692db9ca4d9a125faa1903a589f1876184f6","last_reissued_at":"2026-07-05T10:45:20.689757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:20.689757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Prompts to Templates: A Systematic Prompt Template Analysis for Real-world LLMapps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Chunyang Chen, Junjie He, Yuetian Mao","submitted_at":"2025-04-02T18:20:06Z","abstract_excerpt":"Large Language Models (LLMs) have revolutionized human-AI interaction by enabling intuitive task execution through natural language prompts. Despite their potential, designing effective prompts remains a significant challenge, as small variations in structure or wording can result in substantial differences in output. To address these challenges, LLM-powered applications (LLMapps) rely on prompt templates to simplify interactions, enhance usability, and support specialized tasks such as document analysis, creative content generation, and code synthesis. However, current practices heavily depen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.02052","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/2504.02052/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":"2504.02052","created_at":"2026-07-05T10:45:20.689834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.02052v2","created_at":"2026-07-05T10:45:20.689834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.02052","created_at":"2026-07-05T10:45:20.689834+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOXTM6MSDVNV","created_at":"2026-07-05T10:45:20.689834+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOXTM6MSDVNVAGY4","created_at":"2026-07-05T10:45:20.689834+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOXTM6MS","created_at":"2026-07-05T10:45:20.689834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19114","citing_title":"OOPrompt: Reifying Intents into Structured Artifacts for Modular and Iterative Prompting","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DOXTM6MSDVNVAGY4637GHR3JFW","json":"https://pith.science/pith/DOXTM6MSDVNVAGY4637GHR3JFW.json","graph_json":"https://pith.science/api/pith-number/DOXTM6MSDVNVAGY4637GHR3JFW/graph.json","events_json":"https://pith.science/api/pith-number/DOXTM6MSDVNVAGY4637GHR3JFW/events.json","paper":"https://pith.science/paper/DOXTM6MS"},"agent_actions":{"view_html":"https://pith.science/pith/DOXTM6MSDVNVAGY4637GHR3JFW","download_json":"https://pith.science/pith/DOXTM6MSDVNVAGY4637GHR3JFW.json","view_paper":"https://pith.science/paper/DOXTM6MS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.02052&json=true","fetch_graph":"https://pith.science/api/pith-number/DOXTM6MSDVNVAGY4637GHR3JFW/graph.json","fetch_events":"https://pith.science/api/pith-number/DOXTM6MSDVNVAGY4637GHR3JFW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOXTM6MSDVNVAGY4637GHR3JFW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOXTM6MSDVNVAGY4637GHR3JFW/action/storage_attestation","attest_author":"https://pith.science/pith/DOXTM6MSDVNVAGY4637GHR3JFW/action/author_attestation","sign_citation":"https://pith.science/pith/DOXTM6MSDVNVAGY4637GHR3JFW/action/citation_signature","submit_replication":"https://pith.science/pith/DOXTM6MSDVNVAGY4637GHR3JFW/action/replication_record"}},"created_at":"2026-07-05T10:45:20.689834+00:00","updated_at":"2026-07-05T10:45:20.689834+00:00"}