{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ICDB5MOYUELAQ3VSFY5JWJPR35","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":"cfc137d89f0b889044d76942d69feb4166924c7a204a5e1c21dc06f495d26a86","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T14:45:21Z","title_canon_sha256":"5eee88b2e31295848675593cb45b110328b5e46e34245d05fe6916c5286c8b3b"},"schema_version":"1.0","source":{"id":"2406.01382","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.01382","created_at":"2026-07-05T08:26:39Z"},{"alias_kind":"arxiv_version","alias_value":"2406.01382v1","created_at":"2026-07-05T08:26:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01382","created_at":"2026-07-05T08:26:39Z"},{"alias_kind":"pith_short_12","alias_value":"ICDB5MOYUELA","created_at":"2026-07-05T08:26:39Z"},{"alias_kind":"pith_short_16","alias_value":"ICDB5MOYUELAQ3VS","created_at":"2026-07-05T08:26:39Z"},{"alias_kind":"pith_short_8","alias_value":"ICDB5MOY","created_at":"2026-07-05T08:26:39Z"}],"graph_snapshots":[{"event_id":"sha256:bee69f49c2e82f528a466be813c1f8fd6bd8b4d5ce26095a7b3eff913bc22a39","target":"graph","created_at":"2026-07-05T08:26:39Z","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/2406.01382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"What makes large language models (LLMs) impressive is also what makes them hard to evaluate: their diversity of uses. To evaluate these models, we must understand the purposes they will be used for. We consider a setting where these deployment decisions are made by people, and in particular, people's beliefs about where an LLM will perform well. We model such beliefs as the consequence of a human generalization function: having seen what an LLM gets right or wrong, people generalize to where else it might succeed. We collect a dataset of 19K examples of how humans make generalizations across 7","authors_text":"Ashesh Rambachan, Keyon Vafa, Sendhil Mullainathan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T14:45:21Z","title":"Do Large Language Models Perform the Way People Expect? Measuring the Human Generalization Function"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01382","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:bc980f169df08a9fc4a0a9477f7e415f2d580d84192bf2ce9e85030534cac892","target":"record","created_at":"2026-07-05T08:26:39Z","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":"cfc137d89f0b889044d76942d69feb4166924c7a204a5e1c21dc06f495d26a86","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T14:45:21Z","title_canon_sha256":"5eee88b2e31295848675593cb45b110328b5e46e34245d05fe6916c5286c8b3b"},"schema_version":"1.0","source":{"id":"2406.01382","kind":"arxiv","version":1}},"canonical_sha256":"40861eb1d8a116086eb22e3a9b25f1df49d41300b9948f43fbee7b19bb2f9db5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40861eb1d8a116086eb22e3a9b25f1df49d41300b9948f43fbee7b19bb2f9db5","first_computed_at":"2026-07-05T08:26:39.319346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:39.319346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TlgZhZneRFYkm/wSrDDryMyCxRI709IK/1T1vhnDZYESz0rS+QmZJsLAdzcHyo+8mW0wU9iAuDkyOfEOigDzBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:39.319843Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.01382","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc980f169df08a9fc4a0a9477f7e415f2d580d84192bf2ce9e85030534cac892","sha256:bee69f49c2e82f528a466be813c1f8fd6bd8b4d5ce26095a7b3eff913bc22a39"],"state_sha256":"bd20332f84ee594d452f375c38cbfa8d9cad305028aa962a8833ea8e949d5977"}