{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TO5UXKDGBWQFAREJ5RDBOUKK5O","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":"df6c957c914e28f9ff83b8e08d45cb4573ee6a39eff0137153ce177c9754c981","cross_cats_sorted":["cs.AI","cs.CY","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-22T01:21:40Z","title_canon_sha256":"f518d71aa23614ea898987f042dab1f50773f63e8c3b9fc20580729dbbcd4181"},"schema_version":"1.0","source":{"id":"2504.07114","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07114","created_at":"2026-07-05T11:52:19Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07114v2","created_at":"2026-07-05T11:52:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07114","created_at":"2026-07-05T11:52:19Z"},{"alias_kind":"pith_short_12","alias_value":"TO5UXKDGBWQF","created_at":"2026-07-05T11:52:19Z"},{"alias_kind":"pith_short_16","alias_value":"TO5UXKDGBWQFAREJ","created_at":"2026-07-05T11:52:19Z"},{"alias_kind":"pith_short_8","alias_value":"TO5UXKDG","created_at":"2026-07-05T11:52:19Z"}],"graph_snapshots":[{"event_id":"sha256:6f1557ffc11afbfab44fa13de6c8a3b6220951c8823074145499a107d02fb7eb","target":"graph","created_at":"2026-07-05T11:52:19Z","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/2504.07114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rapid adoption of LLM-based chatbots, there is a pressing need to evaluate what humans and LLMs can achieve together. However, standard benchmarks, such as MMLU, measure LLM capabilities in isolation (i.e., \"AI-alone\"). Here, we design and conduct a user study to convert MMLU questions into user-AI conversations, by seeding the user with the question and having them carry out a conversation with the LLM to answer their question. We release ChatBench, a new dataset with AI-alone, user-alone, and user-AI data for 396 questions and two LLMs, including 144K answers and 7,336 user-AI conve","authors_text":"Ashton Anderson, Jake M. Hofman, Serina Chang","cross_cats":["cs.AI","cs.CY","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-22T01:21:40Z","title":"ChatBench: From Static Benchmarks to Human-AI Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07114","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:d28f1a46467ffc401b0513c058c8c2f2803165c3f65a1841511db67006fc1477","target":"record","created_at":"2026-07-05T11:52:19Z","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":"df6c957c914e28f9ff83b8e08d45cb4573ee6a39eff0137153ce177c9754c981","cross_cats_sorted":["cs.AI","cs.CY","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-22T01:21:40Z","title_canon_sha256":"f518d71aa23614ea898987f042dab1f50773f63e8c3b9fc20580729dbbcd4181"},"schema_version":"1.0","source":{"id":"2504.07114","kind":"arxiv","version":2}},"canonical_sha256":"9bbb4ba8660da0504489ec4617514aebb6ad1244fb49d6c6dc4d98b552ec60c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bbb4ba8660da0504489ec4617514aebb6ad1244fb49d6c6dc4d98b552ec60c9","first_computed_at":"2026-07-05T11:52:19.795445Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:19.795445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZCqhchKRP2tSpocHz2MbgP0rb49W7XdEeGbhHBapSzTd357kEvsLoXMzf/kYPiecf2rqu/yxhFxyJRQDcLupCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:19.795968Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07114","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d28f1a46467ffc401b0513c058c8c2f2803165c3f65a1841511db67006fc1477","sha256:6f1557ffc11afbfab44fa13de6c8a3b6220951c8823074145499a107d02fb7eb"],"state_sha256":"68edadf6152741b9818be3b2d5d24c09a41b9e427f76362c48c8c8fd8f10fba7"}