{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:54726C2YGUFEP6YRJR5JPFY3S6","short_pith_number":"pith:54726C2Y","canonical_record":{"source":{"id":"2312.07910","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-13T05:58:34Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"e783552ab201504d9745a73dedc5553b2ae90f464283137648e6ed560f5def13","abstract_canon_sha256":"7870982ca6c95a5a6835d373784ae5028077729331f098ebf7268780d82a7b9b"},"schema_version":"1.0"},"canonical_sha256":"ef3faf0b58350a47fb114c7a97971b97acd4205a63b82ce0fb2225c722bce901","source":{"kind":"arxiv","id":"2312.07910","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.07910","created_at":"2026-07-05T08:56:58Z"},{"alias_kind":"arxiv_version","alias_value":"2312.07910v3","created_at":"2026-07-05T08:56:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07910","created_at":"2026-07-05T08:56:58Z"},{"alias_kind":"pith_short_12","alias_value":"54726C2YGUFE","created_at":"2026-07-05T08:56:58Z"},{"alias_kind":"pith_short_16","alias_value":"54726C2YGUFEP6YR","created_at":"2026-07-05T08:56:58Z"},{"alias_kind":"pith_short_8","alias_value":"54726C2Y","created_at":"2026-07-05T08:56:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:54726C2YGUFEP6YRJR5JPFY3S6","target":"record","payload":{"canonical_record":{"source":{"id":"2312.07910","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-13T05:58:34Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"e783552ab201504d9745a73dedc5553b2ae90f464283137648e6ed560f5def13","abstract_canon_sha256":"7870982ca6c95a5a6835d373784ae5028077729331f098ebf7268780d82a7b9b"},"schema_version":"1.0"},"canonical_sha256":"ef3faf0b58350a47fb114c7a97971b97acd4205a63b82ce0fb2225c722bce901","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:58.417783Z","signature_b64":"wVmN1eI5i1Mcq3oPKpanVpeUzM3O54tG1YQDMk//iVeeViUXTIgE6AFnPqxkAJG8sM3pbqHCEUFn1qB3ICjiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef3faf0b58350a47fb114c7a97971b97acd4205a63b82ce0fb2225c722bce901","last_reissued_at":"2026-07-05T08:56:58.417340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:58.417340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.07910","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:56:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MXmn2Am5yXJOd7CVWaz3D7RdKlq+WFxn//vWB8BY2NCnPEXk3lj3UDwRUeR/zeW/JPT6FeAtRv1OWDJYQtCHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:40:44.502172Z"},"content_sha256":"e4cb671e78061d978bdce53f91ac92a87cffc417ee93fec794d24eb4803d44f8","schema_version":"1.0","event_id":"sha256:e4cb671e78061d978bdce53f91ac92a87cffc417ee93fec794d24eb4803d44f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:54726C2YGUFEP6YRJR5JPFY3S6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PromptBench: A Unified Library for Evaluation of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Hao Chen, Jindong Wang, Kaijie Zhu, Qinlin Zhao, Xing Xie","submitted_at":"2023-12-13T05:58:34Z","abstract_excerpt":"The evaluation of large language models (LLMs) is crucial to assess their performance and mitigate potential security risks. In this paper, we introduce PromptBench, a unified library to evaluate LLMs. It consists of several key components that are easily used and extended by researchers: prompt construction, prompt engineering, dataset and model loading, adversarial prompt attack, dynamic evaluation protocols, and analysis tools. PromptBench is designed to be an open, general, and flexible codebase for research purposes that can facilitate original study in creating new benchmarks, deploying "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07910","kind":"arxiv","version":3},"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/2312.07910/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:56:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fpCCYWQQExE1nICjIKfiE0sE4fCA9v4PNVqdcTy2zCbG735nNMz5fH2JxCvxKJX1OhmSv0dacR7qnGcw2+ScCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T03:40:44.502675Z"},"content_sha256":"96a92d9e8e4da6a8c539e84f1611779a05159a9c7026e342151ea16a59403f31","schema_version":"1.0","event_id":"sha256:96a92d9e8e4da6a8c539e84f1611779a05159a9c7026e342151ea16a59403f31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/54726C2YGUFEP6YRJR5JPFY3S6/bundle.json","state_url":"https://pith.science/pith/54726C2YGUFEP6YRJR5JPFY3S6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/54726C2YGUFEP6YRJR5JPFY3S6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T03:40:44Z","links":{"resolver":"https://pith.science/pith/54726C2YGUFEP6YRJR5JPFY3S6","bundle":"https://pith.science/pith/54726C2YGUFEP6YRJR5JPFY3S6/bundle.json","state":"https://pith.science/pith/54726C2YGUFEP6YRJR5JPFY3S6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/54726C2YGUFEP6YRJR5JPFY3S6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:54726C2YGUFEP6YRJR5JPFY3S6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7870982ca6c95a5a6835d373784ae5028077729331f098ebf7268780d82a7b9b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-13T05:58:34Z","title_canon_sha256":"e783552ab201504d9745a73dedc5553b2ae90f464283137648e6ed560f5def13"},"schema_version":"1.0","source":{"id":"2312.07910","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.07910","created_at":"2026-07-05T08:56:58Z"},{"alias_kind":"arxiv_version","alias_value":"2312.07910v3","created_at":"2026-07-05T08:56:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07910","created_at":"2026-07-05T08:56:58Z"},{"alias_kind":"pith_short_12","alias_value":"54726C2YGUFE","created_at":"2026-07-05T08:56:58Z"},{"alias_kind":"pith_short_16","alias_value":"54726C2YGUFEP6YR","created_at":"2026-07-05T08:56:58Z"},{"alias_kind":"pith_short_8","alias_value":"54726C2Y","created_at":"2026-07-05T08:56:58Z"}],"graph_snapshots":[{"event_id":"sha256:96a92d9e8e4da6a8c539e84f1611779a05159a9c7026e342151ea16a59403f31","target":"graph","created_at":"2026-07-05T08:56:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2312.07910/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The evaluation of large language models (LLMs) is crucial to assess their performance and mitigate potential security risks. In this paper, we introduce PromptBench, a unified library to evaluate LLMs. It consists of several key components that are easily used and extended by researchers: prompt construction, prompt engineering, dataset and model loading, adversarial prompt attack, dynamic evaluation protocols, and analysis tools. PromptBench is designed to be an open, general, and flexible codebase for research purposes that can facilitate original study in creating new benchmarks, deploying ","authors_text":"Hao Chen, Jindong Wang, Kaijie Zhu, Qinlin Zhao, Xing Xie","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-13T05:58:34Z","title":"PromptBench: A Unified Library for Evaluation of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07910","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e4cb671e78061d978bdce53f91ac92a87cffc417ee93fec794d24eb4803d44f8","target":"record","created_at":"2026-07-05T08:56:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7870982ca6c95a5a6835d373784ae5028077729331f098ebf7268780d82a7b9b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-12-13T05:58:34Z","title_canon_sha256":"e783552ab201504d9745a73dedc5553b2ae90f464283137648e6ed560f5def13"},"schema_version":"1.0","source":{"id":"2312.07910","kind":"arxiv","version":3}},"canonical_sha256":"ef3faf0b58350a47fb114c7a97971b97acd4205a63b82ce0fb2225c722bce901","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef3faf0b58350a47fb114c7a97971b97acd4205a63b82ce0fb2225c722bce901","first_computed_at":"2026-07-05T08:56:58.417340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:58.417340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wVmN1eI5i1Mcq3oPKpanVpeUzM3O54tG1YQDMk//iVeeViUXTIgE6AFnPqxkAJG8sM3pbqHCEUFn1qB3ICjiBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:58.417783Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.07910","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4cb671e78061d978bdce53f91ac92a87cffc417ee93fec794d24eb4803d44f8","sha256:96a92d9e8e4da6a8c539e84f1611779a05159a9c7026e342151ea16a59403f31"],"state_sha256":"d66641385d39c8fbddd9995a13e745fb25bdeddea669f03f3b83eccfe9f7fdc9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XQEt6Xpdxvq0hzjPY1CFdORC8njwVD3GPdrAK4E8N3rvbEN/SgnNMJ8tLxa3UAQOF1vIQKMPP9TxCHQGoMFJAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T03:40:44.506470Z","bundle_sha256":"42e6400c0d6990f73944fb45040e84ca81fce036e1dc1416d1bc42d5d804d69b"}}