{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:UQRSETF3WXZP4Z2PRLL35T4C4F","short_pith_number":"pith:UQRSETF3","canonical_record":{"source":{"id":"2308.07902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-15T17:40:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4a59120b73576f65d8c021a7b0083876b9a7fbcbffc716f144c2671fa45afaad","abstract_canon_sha256":"dcb4c7880343d258838cc392edd5c4eef6e21f910c62a12414589a32273d7740"},"schema_version":"1.0"},"canonical_sha256":"a423224cbbb5f2fe674f8ad7becf82e15d68c34bb65a5ef0522d86d0880dedc2","source":{"kind":"arxiv","id":"2308.07902","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.07902","created_at":"2026-07-05T06:41:33Z"},{"alias_kind":"arxiv_version","alias_value":"2308.07902v1","created_at":"2026-07-05T06:41:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07902","created_at":"2026-07-05T06:41:33Z"},{"alias_kind":"pith_short_12","alias_value":"UQRSETF3WXZP","created_at":"2026-07-05T06:41:33Z"},{"alias_kind":"pith_short_16","alias_value":"UQRSETF3WXZP4Z2P","created_at":"2026-07-05T06:41:33Z"},{"alias_kind":"pith_short_8","alias_value":"UQRSETF3","created_at":"2026-07-05T06:41:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:UQRSETF3WXZP4Z2PRLL35T4C4F","target":"record","payload":{"canonical_record":{"source":{"id":"2308.07902","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-15T17:40:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4a59120b73576f65d8c021a7b0083876b9a7fbcbffc716f144c2671fa45afaad","abstract_canon_sha256":"dcb4c7880343d258838cc392edd5c4eef6e21f910c62a12414589a32273d7740"},"schema_version":"1.0"},"canonical_sha256":"a423224cbbb5f2fe674f8ad7becf82e15d68c34bb65a5ef0522d86d0880dedc2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:33.066193Z","signature_b64":"PUPLBbW5VHZ0w6KnkOSzDMlfA2dXgGHAbL2Fn8810P8t6yDoRx0gnK5C/FOQifBD0U8LJKova3D/DmkPAIpDAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a423224cbbb5f2fe674f8ad7becf82e15d68c34bb65a5ef0522d86d0880dedc2","last_reissued_at":"2026-07-05T06:41:33.065750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:33.065750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.07902","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:41:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RUhi1KDCixQNAgyYy9E3GFI0STs+cy6lI0E7rTnjlzYlzb4cssqpgbFKtff+DZFHo81gHb9zuxmrvEGxyYqfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:19:11.494899Z"},"content_sha256":"f125a733d7838332ac140b7da0ff683ee7a2a8da2121b0e0cd046504c398fd58","schema_version":"1.0","event_id":"sha256:f125a733d7838332ac140b7da0ff683ee7a2a8da2121b0e0cd046504c398fd58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:UQRSETF3WXZP4Z2PRLL35T4C4F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Through the Lens of Core Competency: Survey on Evaluation of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haopeng Bai, Longxuan Ma, Mingda Li, Qiguang Chen, Ting Liu, Weinan Zhang, Yi Han, Yushan Qian, Zixian Feng, Ziyu Zhuang","submitted_at":"2023-08-15T17:40:34Z","abstract_excerpt":"From pre-trained language model (PLM) to large language model (LLM), the field of natural language processing (NLP) has witnessed steep performance gains and wide practical uses. The evaluation of a research field guides its direction of improvement. However, LLMs are extremely hard to thoroughly evaluate for two reasons. First of all, traditional NLP tasks become inadequate due to the excellent performance of LLM. Secondly, existing evaluation tasks are difficult to keep up with the wide range of applications in real-world scenarios. To tackle these problems, existing works proposed various b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07902","kind":"arxiv","version":1},"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/2308.07902/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":"2026-07-05T06:41:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mDqDddKl+JTOWO59DdFUPJ+cyiwcZ7Z6YXKnrvzhYTHPdNWH5w/A8hUwDKLIO97qzWYrqEk0972SbY7PoAgNCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T08:19:11.495279Z"},"content_sha256":"c4686223339add5addcf663691301eee36c570a668f2d54d005bfa3313e238da","schema_version":"1.0","event_id":"sha256:c4686223339add5addcf663691301eee36c570a668f2d54d005bfa3313e238da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UQRSETF3WXZP4Z2PRLL35T4C4F/bundle.json","state_url":"https://pith.science/pith/UQRSETF3WXZP4Z2PRLL35T4C4F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UQRSETF3WXZP4Z2PRLL35T4C4F/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":"2026-07-07T08:19:11Z","links":{"resolver":"https://pith.science/pith/UQRSETF3WXZP4Z2PRLL35T4C4F","bundle":"https://pith.science/pith/UQRSETF3WXZP4Z2PRLL35T4C4F/bundle.json","state":"https://pith.science/pith/UQRSETF3WXZP4Z2PRLL35T4C4F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UQRSETF3WXZP4Z2PRLL35T4C4F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UQRSETF3WXZP4Z2PRLL35T4C4F","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":"dcb4c7880343d258838cc392edd5c4eef6e21f910c62a12414589a32273d7740","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-15T17:40:34Z","title_canon_sha256":"4a59120b73576f65d8c021a7b0083876b9a7fbcbffc716f144c2671fa45afaad"},"schema_version":"1.0","source":{"id":"2308.07902","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.07902","created_at":"2026-07-05T06:41:33Z"},{"alias_kind":"arxiv_version","alias_value":"2308.07902v1","created_at":"2026-07-05T06:41:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07902","created_at":"2026-07-05T06:41:33Z"},{"alias_kind":"pith_short_12","alias_value":"UQRSETF3WXZP","created_at":"2026-07-05T06:41:33Z"},{"alias_kind":"pith_short_16","alias_value":"UQRSETF3WXZP4Z2P","created_at":"2026-07-05T06:41:33Z"},{"alias_kind":"pith_short_8","alias_value":"UQRSETF3","created_at":"2026-07-05T06:41:33Z"}],"graph_snapshots":[{"event_id":"sha256:c4686223339add5addcf663691301eee36c570a668f2d54d005bfa3313e238da","target":"graph","created_at":"2026-07-05T06:41:33Z","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/2308.07902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"From pre-trained language model (PLM) to large language model (LLM), the field of natural language processing (NLP) has witnessed steep performance gains and wide practical uses. The evaluation of a research field guides its direction of improvement. However, LLMs are extremely hard to thoroughly evaluate for two reasons. First of all, traditional NLP tasks become inadequate due to the excellent performance of LLM. Secondly, existing evaluation tasks are difficult to keep up with the wide range of applications in real-world scenarios. To tackle these problems, existing works proposed various b","authors_text":"Haopeng Bai, Longxuan Ma, Mingda Li, Qiguang Chen, Ting Liu, Weinan Zhang, Yi Han, Yushan Qian, Zixian Feng, Ziyu Zhuang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-15T17:40:34Z","title":"Through the Lens of Core Competency: Survey on Evaluation of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07902","kind":"arxiv","version":1},"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:f125a733d7838332ac140b7da0ff683ee7a2a8da2121b0e0cd046504c398fd58","target":"record","created_at":"2026-07-05T06:41:33Z","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":"dcb4c7880343d258838cc392edd5c4eef6e21f910c62a12414589a32273d7740","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-15T17:40:34Z","title_canon_sha256":"4a59120b73576f65d8c021a7b0083876b9a7fbcbffc716f144c2671fa45afaad"},"schema_version":"1.0","source":{"id":"2308.07902","kind":"arxiv","version":1}},"canonical_sha256":"a423224cbbb5f2fe674f8ad7becf82e15d68c34bb65a5ef0522d86d0880dedc2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a423224cbbb5f2fe674f8ad7becf82e15d68c34bb65a5ef0522d86d0880dedc2","first_computed_at":"2026-07-05T06:41:33.065750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:41:33.065750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PUPLBbW5VHZ0w6KnkOSzDMlfA2dXgGHAbL2Fn8810P8t6yDoRx0gnK5C/FOQifBD0U8LJKova3D/DmkPAIpDAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:41:33.066193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.07902","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f125a733d7838332ac140b7da0ff683ee7a2a8da2121b0e0cd046504c398fd58","sha256:c4686223339add5addcf663691301eee36c570a668f2d54d005bfa3313e238da"],"state_sha256":"58c7071d4ffc529b1427cc40100fc2511255a24a60fc49afd46fd4ea9250e86e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jRoDW/1ktPk7vBbSpeUML7TfhvJuQq9fWQlSIyZV/1TH/09zEsrD3b1JlMdGFHy74Einzb5ib7U3F/5Er9WeDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T08:19:11.497338Z","bundle_sha256":"e048e8339ac9156756b817a5d65e573b39654c791905a7eda76cfee411515272"}}