{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:MIGDVJSSEGD6Z53PPDQSUTTYWK","short_pith_number":"pith:MIGDVJSS","canonical_record":{"source":{"id":"2407.04069","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-04T17:15:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6b229d27aae9990328f6d2e09d06fcc74d05e1e463670616ebb3c9fd94220013","abstract_canon_sha256":"050b638d51e75e19b97f5a40c4fc7db01c2f4d595f4dd2d1ec87fc8f5e3ed228"},"schema_version":"1.0"},"canonical_sha256":"620c3aa6522187ecf76f78e12a4e78b28237c28e39c88c97e70ba2b76b83507f","source":{"kind":"arxiv","id":"2407.04069","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04069","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04069v2","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04069","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"pith_short_12","alias_value":"MIGDVJSSEGD6","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"pith_short_16","alias_value":"MIGDVJSSEGD6Z53P","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"pith_short_8","alias_value":"MIGDVJSS","created_at":"2026-07-05T09:15:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:MIGDVJSSEGD6Z53PPDQSUTTYWK","target":"record","payload":{"canonical_record":{"source":{"id":"2407.04069","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-04T17:15:37Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6b229d27aae9990328f6d2e09d06fcc74d05e1e463670616ebb3c9fd94220013","abstract_canon_sha256":"050b638d51e75e19b97f5a40c4fc7db01c2f4d595f4dd2d1ec87fc8f5e3ed228"},"schema_version":"1.0"},"canonical_sha256":"620c3aa6522187ecf76f78e12a4e78b28237c28e39c88c97e70ba2b76b83507f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:12.798827Z","signature_b64":"64YMuqJi5m5URk9FxWtofwwXtBO+/8bxOhhfy6QQLZ7YbULKY8+8Mq6FZIZxzPaaktLDbRgLbLPHMCmz84x/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"620c3aa6522187ecf76f78e12a4e78b28237c28e39c88c97e70ba2b76b83507f","last_reissued_at":"2026-07-05T09:15:12.798351Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:12.798351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.04069","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SzRwQsbfGcBU9kPvsVXx7pGpdjYDYyA+L2sZePEeR4AU8OUIo2L/E9PS5yZQ3GL2FfO+FIjpszp3dIFsISHUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:15:42.485944Z"},"content_sha256":"73775dde4dee57877bbc0b30cb8f2d966ec37a5769d33b2b835061e217574ee1","schema_version":"1.0","event_id":"sha256:73775dde4dee57877bbc0b30cb8f2d966ec37a5769d33b2b835061e217574ee1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:MIGDVJSSEGD6Z53PPDQSUTTYWK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Amran Bhuiyan, Chee Wei Tan, Enamul Hoque, Haidar Khan, Israt Jahan, Jimmy Huang, Md Rizwan Parvez, Md Tahmid Rahman Laskar, Mizanur Rahman, Mohammad Abdullah Matin Khan, M Saiful Bari, Sawsan Alqahtani, Shafiq Joty","submitted_at":"2024-07-04T17:15:37Z","abstract_excerpt":"Large Language Models (LLMs) have recently gained significant attention due to their remarkable capabilities in performing diverse tasks across various domains. However, a thorough evaluation of these models is crucial before deploying them in real-world applications to ensure they produce reliable performance. Despite the well-established importance of evaluating LLMs in the community, the complexity of the evaluation process has led to varied evaluation setups, causing inconsistencies in findings and interpretations. To address this, we systematically review the primary challenges and limita"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04069","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/2407.04069/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":"2026-07-05T09:15:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jAhMDKYPbm3o2yVrHfSrl0Q97ezeSbRBpDpXLeCU03Kk9Thf97ljTi/0itf8eNFvjbeIlLJz86GLUF/HPuzqDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:15:42.486343Z"},"content_sha256":"06dcccc209a6370424ee7bd790a85cb8a477f1b8cc95602b4bc016a0fbd64c4e","schema_version":"1.0","event_id":"sha256:06dcccc209a6370424ee7bd790a85cb8a477f1b8cc95602b4bc016a0fbd64c4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MIGDVJSSEGD6Z53PPDQSUTTYWK/bundle.json","state_url":"https://pith.science/pith/MIGDVJSSEGD6Z53PPDQSUTTYWK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MIGDVJSSEGD6Z53PPDQSUTTYWK/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":"2026-08-07T21:15:42Z","links":{"resolver":"https://pith.science/pith/MIGDVJSSEGD6Z53PPDQSUTTYWK","bundle":"https://pith.science/pith/MIGDVJSSEGD6Z53PPDQSUTTYWK/bundle.json","state":"https://pith.science/pith/MIGDVJSSEGD6Z53PPDQSUTTYWK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MIGDVJSSEGD6Z53PPDQSUTTYWK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MIGDVJSSEGD6Z53PPDQSUTTYWK","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":"050b638d51e75e19b97f5a40c4fc7db01c2f4d595f4dd2d1ec87fc8f5e3ed228","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-04T17:15:37Z","title_canon_sha256":"6b229d27aae9990328f6d2e09d06fcc74d05e1e463670616ebb3c9fd94220013"},"schema_version":"1.0","source":{"id":"2407.04069","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.04069","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"arxiv_version","alias_value":"2407.04069v2","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04069","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"pith_short_12","alias_value":"MIGDVJSSEGD6","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"pith_short_16","alias_value":"MIGDVJSSEGD6Z53P","created_at":"2026-07-05T09:15:12Z"},{"alias_kind":"pith_short_8","alias_value":"MIGDVJSS","created_at":"2026-07-05T09:15:12Z"}],"graph_snapshots":[{"event_id":"sha256:06dcccc209a6370424ee7bd790a85cb8a477f1b8cc95602b4bc016a0fbd64c4e","target":"graph","created_at":"2026-07-05T09:15:12Z","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/2407.04069/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have recently gained significant attention due to their remarkable capabilities in performing diverse tasks across various domains. However, a thorough evaluation of these models is crucial before deploying them in real-world applications to ensure they produce reliable performance. Despite the well-established importance of evaluating LLMs in the community, the complexity of the evaluation process has led to varied evaluation setups, causing inconsistencies in findings and interpretations. To address this, we systematically review the primary challenges and limita","authors_text":"Amran Bhuiyan, Chee Wei Tan, Enamul Hoque, Haidar Khan, Israt Jahan, Jimmy Huang, Md Rizwan Parvez, Md Tahmid Rahman Laskar, Mizanur Rahman, Mohammad Abdullah Matin Khan, M Saiful Bari, Sawsan Alqahtani, Shafiq Joty","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-04T17:15:37Z","title":"A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04069","kind":"arxiv","version":2},"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":"sha256:73775dde4dee57877bbc0b30cb8f2d966ec37a5769d33b2b835061e217574ee1","target":"record","created_at":"2026-07-05T09:15:12Z","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":"050b638d51e75e19b97f5a40c4fc7db01c2f4d595f4dd2d1ec87fc8f5e3ed228","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-04T17:15:37Z","title_canon_sha256":"6b229d27aae9990328f6d2e09d06fcc74d05e1e463670616ebb3c9fd94220013"},"schema_version":"1.0","source":{"id":"2407.04069","kind":"arxiv","version":2}},"canonical_sha256":"620c3aa6522187ecf76f78e12a4e78b28237c28e39c88c97e70ba2b76b83507f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"620c3aa6522187ecf76f78e12a4e78b28237c28e39c88c97e70ba2b76b83507f","first_computed_at":"2026-07-05T09:15:12.798351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:12.798351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"64YMuqJi5m5URk9FxWtofwwXtBO+/8bxOhhfy6QQLZ7YbULKY8+8Mq6FZIZxzPaaktLDbRgLbLPHMCmz84x/DA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:12.798827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.04069","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73775dde4dee57877bbc0b30cb8f2d966ec37a5769d33b2b835061e217574ee1","sha256:06dcccc209a6370424ee7bd790a85cb8a477f1b8cc95602b4bc016a0fbd64c4e"],"state_sha256":"13a009b89d978d20145fa93a39f6b642478e76ebba955071aaef700a57384454"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I8ToLXlA6A9vfs2seYrfJK6l3lIkpI+zkIw5wO44IPOyimAdn+XmaOHE5KXINMv7i4Fb5lbsjQ+na6IwXPd6Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:15:42.489204Z","bundle_sha256":"90f8ac63b203c30ffff153771dab653b96a2ba81648730e424be13d0d3bbf4a5"}}