{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DCE5ZVJRDP3KOX64TBYMGUK2XS","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":"5ae57f6d809f9f59b20e37ab4c5a2ddadaa0a06889b7952d0cf62454d4144812","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-13T06:02:37Z","title_canon_sha256":"8458b9a5b661d764044cebd35da0d184dd539065dda8b2936389ef7ca56217bc"},"schema_version":"1.0","source":{"id":"2505.08253","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08253","created_at":"2026-07-05T11:02:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08253v1","created_at":"2026-07-05T11:02:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08253","created_at":"2026-07-05T11:02:27Z"},{"alias_kind":"pith_short_12","alias_value":"DCE5ZVJRDP3K","created_at":"2026-07-05T11:02:27Z"},{"alias_kind":"pith_short_16","alias_value":"DCE5ZVJRDP3KOX64","created_at":"2026-07-05T11:02:27Z"},{"alias_kind":"pith_short_8","alias_value":"DCE5ZVJR","created_at":"2026-07-05T11:02:27Z"}],"graph_snapshots":[{"event_id":"sha256:70f2fdc94e21f62f19d1d8fb47413dac2781e257cf98ebab384b10ed62cddd3d","target":"graph","created_at":"2026-07-05T11:02:27Z","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/2505.08253/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As generative AI becomes increasingly embedded in everyday workflows, it is important to evaluate its performance in ways that reflect real-world usage rather than abstract notions of intelligence. Unlike many existing benchmarks that assess general intelligence, our approach focuses on real-world utility, evaluating how well models support users in everyday tasks. While current benchmarks emphasize code generation or factual recall, users rely on AI for a much broader range of activities-from writing assistance and summarization to citation formatting and stylistic feedback. In this paper, we","authors_text":"Justin K Miller, Wenjia Tang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-13T06:02:37Z","title":"Evaluating LLM Metrics Through Real-World Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08253","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":"sha256:3b888199180a186482c4e78b5eb5bea34c4ead1795cab57a2b5820f82082b7ca","target":"record","created_at":"2026-07-05T11:02:27Z","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":"5ae57f6d809f9f59b20e37ab4c5a2ddadaa0a06889b7952d0cf62454d4144812","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-13T06:02:37Z","title_canon_sha256":"8458b9a5b661d764044cebd35da0d184dd539065dda8b2936389ef7ca56217bc"},"schema_version":"1.0","source":{"id":"2505.08253","kind":"arxiv","version":1}},"canonical_sha256":"1889dcd5311bf6a75fdc9870c3515abca0facd0007b6b33955f98446cf6103ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1889dcd5311bf6a75fdc9870c3515abca0facd0007b6b33955f98446cf6103ca","first_computed_at":"2026-07-05T11:02:27.356097Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:27.356097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5+x0cOAoLf7K47r4u09A3XRiTXpjpUpp8OLTL7V3OruCme+4JAPNLjNvIfsLa1iqOVZjRJYezDpujApinndqAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:27.356525Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.08253","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b888199180a186482c4e78b5eb5bea34c4ead1795cab57a2b5820f82082b7ca","sha256:70f2fdc94e21f62f19d1d8fb47413dac2781e257cf98ebab384b10ed62cddd3d"],"state_sha256":"f12fd0fbcfea9f975958243bdf8905231d16ed2e1d7d8eaf96e81a407e5a1ebc"}