{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:A5CVL77XK6UKZ3XIZHW45AWZQG","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":"d21dc0e1a9c243dc23dde61e93c41d0e688ad620f8693fcd7ef3b5f36b967fc4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T04:52:15Z","title_canon_sha256":"819d516e442049615f00997918840ab6e4a882b123af8f9825dec1f1f5609c4a"},"schema_version":"1.0","source":{"id":"2406.10307","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10307","created_at":"2026-07-05T08:32:14Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10307v1","created_at":"2026-07-05T08:32:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10307","created_at":"2026-07-05T08:32:14Z"},{"alias_kind":"pith_short_12","alias_value":"A5CVL77XK6UK","created_at":"2026-07-05T08:32:14Z"},{"alias_kind":"pith_short_16","alias_value":"A5CVL77XK6UKZ3XI","created_at":"2026-07-05T08:32:14Z"},{"alias_kind":"pith_short_8","alias_value":"A5CVL77X","created_at":"2026-07-05T08:32:14Z"}],"graph_snapshots":[{"event_id":"sha256:27189edfa85b6b78704037f86d07c6d3de98b5b37c636b3e60cd9e83d113f110","target":"graph","created_at":"2026-07-05T08:32:14Z","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/2406.10307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"General large language models enhanced with supervised fine-tuning and reinforcement learning from human feedback are increasingly popular in academia and industry as they generalize foundation models to various practical tasks in a prompt manner. To assist users in selecting the best model in practical application scenarios, i.e., choosing the model that meets the application requirements while minimizing cost, we introduce A-Eval, an application-driven LLMs evaluation benchmark for general large language models. First, we categorize evaluation tasks into five main categories and 27 sub-categ","authors_text":"Bikun Yang, Kaikai Zhao, Kai Wang, Shiguo Lian, Wenjing Zhang, Xinhui Liu, Xuejiao Lei, Zhaoxiang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T04:52:15Z","title":"What is the best model? Application-driven Evaluation for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10307","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":"sha256:0f982e32123579855ee43b2a9bf988c1aa7cd77815215d21e95353ca77a343ed","target":"record","created_at":"2026-07-05T08:32:14Z","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":"d21dc0e1a9c243dc23dde61e93c41d0e688ad620f8693fcd7ef3b5f36b967fc4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T04:52:15Z","title_canon_sha256":"819d516e442049615f00997918840ab6e4a882b123af8f9825dec1f1f5609c4a"},"schema_version":"1.0","source":{"id":"2406.10307","kind":"arxiv","version":1}},"canonical_sha256":"074555fff757a8aceee8c9edce82d9818545b42887386359d08b17806d5fcaad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"074555fff757a8aceee8c9edce82d9818545b42887386359d08b17806d5fcaad","first_computed_at":"2026-07-05T08:32:14.602448Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:14.602448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eYi2PX+NGROySDq3vx88husqcZ7XaeraiqdRzMoFLkBt98HMdz0s+SvfFHhLMnxydgdvv5QkD7ihGsuB7r/xDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:14.602946Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10307","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f982e32123579855ee43b2a9bf988c1aa7cd77815215d21e95353ca77a343ed","sha256:27189edfa85b6b78704037f86d07c6d3de98b5b37c636b3e60cd9e83d113f110"],"state_sha256":"0100a2046592abad6079815339cad681eed7734254d91c50c2f99d6a0324a6a6"}