{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GDDC2FSO5VQE3XDMIWED5KUORU","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":"58d68c2630f8163c2cf4d75be8d9b0d07c7b5bda9a3efba5e06b59a56608b001","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-03-24T20:17:20Z","title_canon_sha256":"2e244a93cdb8e2e74e07185a24e4e0203f040d9c6cecc720a5e9a1ca33a2a304"},"schema_version":"1.0","source":{"id":"2504.07971","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.07971","created_at":"2026-06-30T01:17:22Z"},{"alias_kind":"arxiv_version","alias_value":"2504.07971v1","created_at":"2026-06-30T01:17:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07971","created_at":"2026-06-30T01:17:22Z"},{"alias_kind":"pith_short_12","alias_value":"GDDC2FSO5VQE","created_at":"2026-06-30T01:17:22Z"},{"alias_kind":"pith_short_16","alias_value":"GDDC2FSO5VQE3XDM","created_at":"2026-06-30T01:17:22Z"},{"alias_kind":"pith_short_8","alias_value":"GDDC2FSO","created_at":"2026-06-30T01:17:22Z"}],"graph_snapshots":[{"event_id":"sha256:08b4bf3644009d6709d9ac9782e852ddecb87e0b5953671ffa6b0dc55526f0f5","target":"graph","created_at":"2026-06-30T01:17:22Z","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/2504.07971/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the era of Large Language Models (LLMs), establishing effective evaluation methods and standards for diverse human-AI interaction systems is increasingly challenging. To encourage more transparent documentation and facilitate discussion on human-AI system evaluation design options, we present an evaluation card SPHERE, which encompasses five key dimensions: 1) What is being evaluated?; 2) How is the evaluation conducted?; 3) Who is participating in the evaluation?; 4) When is evaluation conducted?; 5) How is evaluation validated? We conduct a review of 39 human-AI systems using SPHERE, outl","authors_text":"Chenglei Si, Chenyang Yang, Diyi Yang, Dora Zhao, Ehud Reiter, Qianou Ma, Ryan Louie, Tongshuang Wu, Xinran Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-03-24T20:17:20Z","title":"SPHERE: An Evaluation Card for Human-AI Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07971","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:d2e944eee982e4154c16f0f97402ccfa7bf11270cf97717302142cddfc5323dd","target":"record","created_at":"2026-06-30T01:17:22Z","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":"58d68c2630f8163c2cf4d75be8d9b0d07c7b5bda9a3efba5e06b59a56608b001","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-03-24T20:17:20Z","title_canon_sha256":"2e244a93cdb8e2e74e07185a24e4e0203f040d9c6cecc720a5e9a1ca33a2a304"},"schema_version":"1.0","source":{"id":"2504.07971","kind":"arxiv","version":1}},"canonical_sha256":"30c62d164eed604ddc6c45883eaa8e8d1770fae01084ce8e2c453d9050430d6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30c62d164eed604ddc6c45883eaa8e8d1770fae01084ce8e2c453d9050430d6e","first_computed_at":"2026-06-30T01:17:22.866051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T01:17:22.866051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"srvLZhYZNR1e7sDT7FrcsJn3Ghmf+00eJ4lTtMCZ9OlHz16v/gDLkxFG8MHKFxaG2Q+NqFpFePuZiw46tmvACw==","signature_status":"signed_v1","signed_at":"2026-06-30T01:17:22.866852Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.07971","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2e944eee982e4154c16f0f97402ccfa7bf11270cf97717302142cddfc5323dd","sha256:08b4bf3644009d6709d9ac9782e852ddecb87e0b5953671ffa6b0dc55526f0f5"],"state_sha256":"3e36cc8561b0cb9c87e7e5b7935cca5976cb2b3d3c78b688f41fa4e3c43ec1ba"}