{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FS2IFN7TUHALLZAPWTIQQP7BSI","short_pith_number":"pith:FS2IFN7T","schema_version":"1.0","canonical_sha256":"2cb482b7f3a1c0b5e40fb4d1083fe19235430df24ded7733aa56a024414ef57f","source":{"kind":"arxiv","id":"2305.08714","version":2},"attestation_state":"computed","paper":{"title":"Sensitivity and Robustness of Large Language Models to Prompt Template in Japanese Text Classification Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengguang Gan, Tatsunori Mori","submitted_at":"2023-05-15T15:19:08Z","abstract_excerpt":"Prompt engineering relevance research has seen a notable surge in recent years, primarily driven by advancements in pre-trained language models and large language models. However, a critical issue has been identified within this domain: the inadequate of sensitivity and robustness of these models towards Prompt Templates, particularly in lesser-studied languages such as Japanese. This paper explores this issue through a comprehensive evaluation of several representative Large Language Models (LLMs) and a widely-utilized pre-trained model(PLM). These models are scrutinized using a benchmark dat"},"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":"2305.08714","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-15T15:19:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c6de13a1db530a3402d1580aa00f302345502d85f61ba8da779a193e006f5d0d","abstract_canon_sha256":"d30db055832a48986909700c8dd1d21693fb597da788ba95795327c5a8255491"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:38.999110Z","signature_b64":"DEKQH7Y2KQ0fUnRR0Uwxw4jK3j9D9k2N3yTWudlURZJA18fUMPEVUAewKSWAlyvj47OKiJtVlF5miEO3+a8kCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cb482b7f3a1c0b5e40fb4d1083fe19235430df24ded7733aa56a024414ef57f","last_reissued_at":"2026-07-05T06:18:38.998625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:38.998625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sensitivity and Robustness of Large Language Models to Prompt Template in Japanese Text Classification Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengguang Gan, Tatsunori Mori","submitted_at":"2023-05-15T15:19:08Z","abstract_excerpt":"Prompt engineering relevance research has seen a notable surge in recent years, primarily driven by advancements in pre-trained language models and large language models. However, a critical issue has been identified within this domain: the inadequate of sensitivity and robustness of these models towards Prompt Templates, particularly in lesser-studied languages such as Japanese. This paper explores this issue through a comprehensive evaluation of several representative Large Language Models (LLMs) and a widely-utilized pre-trained model(PLM). These models are scrutinized using a benchmark dat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08714","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/2305.08714/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":"2305.08714","created_at":"2026-07-05T06:18:38.998691+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.08714v2","created_at":"2026-07-05T06:18:38.998691+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08714","created_at":"2026-07-05T06:18:38.998691+00:00"},{"alias_kind":"pith_short_12","alias_value":"FS2IFN7TUHAL","created_at":"2026-07-05T06:18:38.998691+00:00"},{"alias_kind":"pith_short_16","alias_value":"FS2IFN7TUHALLZAP","created_at":"2026-07-05T06:18:38.998691+00:00"},{"alias_kind":"pith_short_8","alias_value":"FS2IFN7T","created_at":"2026-07-05T06:18:38.998691+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.08068","citing_title":"DICE: Entropy-Regularized Equilibrium Selection for Stable Multi-Agent LLM Coordination","ref_index":120,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08522","citing_title":"Coordinates of Capability: A Unified MTMM-Geometric Framework for LLM Evaluation","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FS2IFN7TUHALLZAPWTIQQP7BSI","json":"https://pith.science/pith/FS2IFN7TUHALLZAPWTIQQP7BSI.json","graph_json":"https://pith.science/api/pith-number/FS2IFN7TUHALLZAPWTIQQP7BSI/graph.json","events_json":"https://pith.science/api/pith-number/FS2IFN7TUHALLZAPWTIQQP7BSI/events.json","paper":"https://pith.science/paper/FS2IFN7T"},"agent_actions":{"view_html":"https://pith.science/pith/FS2IFN7TUHALLZAPWTIQQP7BSI","download_json":"https://pith.science/pith/FS2IFN7TUHALLZAPWTIQQP7BSI.json","view_paper":"https://pith.science/paper/FS2IFN7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.08714&json=true","fetch_graph":"https://pith.science/api/pith-number/FS2IFN7TUHALLZAPWTIQQP7BSI/graph.json","fetch_events":"https://pith.science/api/pith-number/FS2IFN7TUHALLZAPWTIQQP7BSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FS2IFN7TUHALLZAPWTIQQP7BSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FS2IFN7TUHALLZAPWTIQQP7BSI/action/storage_attestation","attest_author":"https://pith.science/pith/FS2IFN7TUHALLZAPWTIQQP7BSI/action/author_attestation","sign_citation":"https://pith.science/pith/FS2IFN7TUHALLZAPWTIQQP7BSI/action/citation_signature","submit_replication":"https://pith.science/pith/FS2IFN7TUHALLZAPWTIQQP7BSI/action/replication_record"}},"created_at":"2026-07-05T06:18:38.998691+00:00","updated_at":"2026-07-05T06:18:38.998691+00:00"}