{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TFQ7EIFLQ6XGY3AYT52XDR4COI","short_pith_number":"pith:TFQ7EIFL","schema_version":"1.0","canonical_sha256":"9961f220ab87ae6c6c189f7571c7827215d442585abaeeb7967df037f054e48d","source":{"kind":"arxiv","id":"2305.11430","version":2},"attestation_state":"computed","paper":{"title":"TELeR: A General Taxonomy of LLM Prompts for Benchmarking Complex Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.AI","authors_text":"Dongji Feng, Shubhra Kanti Karmaker Santu","submitted_at":"2023-05-19T04:59:34Z","abstract_excerpt":"While LLMs have shown great success in understanding and generating text in traditional conversational settings, their potential for performing ill-defined complex tasks is largely under-studied. Indeed, we are yet to conduct comprehensive benchmarking studies with multiple LLMs that are exclusively focused on a complex task. However, conducting such benchmarking studies is challenging because of the large variations in LLMs' performance when different prompt types/styles are used and different degrees of detail are provided in the prompts. To address this issue, the paper proposes a general t"},"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":"2305.11430","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-05-19T04:59:34Z","cross_cats_sorted":["cs.CL","cs.IR","cs.LG"],"title_canon_sha256":"e9e6c7ebbf051f157e9fbe0bba21100cef5b7bca66d02596d73bb912742e3324","abstract_canon_sha256":"65b2b92e738f7e6fb9dfd300074db5ca27d658f4bec83b916706a1539e9418a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:47.100999Z","signature_b64":"H0BeOKthe38bK3dlNhFok+7c9bg1quF7zpErKM8zo8X/89G6fEkErPVCPNwqSsvYXOpnWioXxw/NsCGoNxajAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9961f220ab87ae6c6c189f7571c7827215d442585abaeeb7967df037f054e48d","last_reissued_at":"2026-07-05T07:04:47.100333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:47.100333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TELeR: A General Taxonomy of LLM Prompts for Benchmarking Complex Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.LG"],"primary_cat":"cs.AI","authors_text":"Dongji Feng, Shubhra Kanti Karmaker Santu","submitted_at":"2023-05-19T04:59:34Z","abstract_excerpt":"While LLMs have shown great success in understanding and generating text in traditional conversational settings, their potential for performing ill-defined complex tasks is largely under-studied. Indeed, we are yet to conduct comprehensive benchmarking studies with multiple LLMs that are exclusively focused on a complex task. However, conducting such benchmarking studies is challenging because of the large variations in LLMs' performance when different prompt types/styles are used and different degrees of detail are provided in the prompts. To address this issue, the paper proposes a general t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11430","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/2305.11430/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":"2305.11430","created_at":"2026-07-05T07:04:47.100429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11430v2","created_at":"2026-07-05T07:04:47.100429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11430","created_at":"2026-07-05T07:04:47.100429+00:00"},{"alias_kind":"pith_short_12","alias_value":"TFQ7EIFLQ6XG","created_at":"2026-07-05T07:04:47.100429+00:00"},{"alias_kind":"pith_short_16","alias_value":"TFQ7EIFLQ6XGY3AY","created_at":"2026-07-05T07:04:47.100429+00:00"},{"alias_kind":"pith_short_8","alias_value":"TFQ7EIFL","created_at":"2026-07-05T07:04:47.100429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05522","citing_title":"Exploring LLMs for South Asian Music Understanding and Generation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04534","citing_title":"Characterizing Students' LLM Usage Behaviors and Their Association with Learning in Critical Thinking Tasks","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04534","citing_title":"Characterizing Students' LLM Usage Behaviors and Their Association with Learning in Critical Thinking Tasks","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TFQ7EIFLQ6XGY3AYT52XDR4COI","json":"https://pith.science/pith/TFQ7EIFLQ6XGY3AYT52XDR4COI.json","graph_json":"https://pith.science/api/pith-number/TFQ7EIFLQ6XGY3AYT52XDR4COI/graph.json","events_json":"https://pith.science/api/pith-number/TFQ7EIFLQ6XGY3AYT52XDR4COI/events.json","paper":"https://pith.science/paper/TFQ7EIFL"},"agent_actions":{"view_html":"https://pith.science/pith/TFQ7EIFLQ6XGY3AYT52XDR4COI","download_json":"https://pith.science/pith/TFQ7EIFLQ6XGY3AYT52XDR4COI.json","view_paper":"https://pith.science/paper/TFQ7EIFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11430&json=true","fetch_graph":"https://pith.science/api/pith-number/TFQ7EIFLQ6XGY3AYT52XDR4COI/graph.json","fetch_events":"https://pith.science/api/pith-number/TFQ7EIFLQ6XGY3AYT52XDR4COI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TFQ7EIFLQ6XGY3AYT52XDR4COI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TFQ7EIFLQ6XGY3AYT52XDR4COI/action/storage_attestation","attest_author":"https://pith.science/pith/TFQ7EIFLQ6XGY3AYT52XDR4COI/action/author_attestation","sign_citation":"https://pith.science/pith/TFQ7EIFLQ6XGY3AYT52XDR4COI/action/citation_signature","submit_replication":"https://pith.science/pith/TFQ7EIFLQ6XGY3AYT52XDR4COI/action/replication_record"}},"created_at":"2026-07-05T07:04:47.100429+00:00","updated_at":"2026-07-05T07:04:47.100429+00:00"}