{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GDDC2FSO5VQE3XDMIWED5KUORU","short_pith_number":"pith:GDDC2FSO","schema_version":"1.0","canonical_sha256":"30c62d164eed604ddc6c45883eaa8e8d1770fae01084ce8e2c453d9050430d6e","source":{"kind":"arxiv","id":"2504.07971","version":1},"attestation_state":"computed","paper":{"title":"SPHERE: An Evaluation Card for Human-AI Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Chenglei Si, Chenyang Yang, Diyi Yang, Dora Zhao, Ehud Reiter, Qianou Ma, Ryan Louie, Tongshuang Wu, Xinran Zhao","submitted_at":"2025-03-24T20:17:20Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.07971","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-03-24T20:17:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2e244a93cdb8e2e74e07185a24e4e0203f040d9c6cecc720a5e9a1ca33a2a304","abstract_canon_sha256":"58d68c2630f8163c2cf4d75be8d9b0d07c7b5bda9a3efba5e06b59a56608b001"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:22.866852Z","signature_b64":"srvLZhYZNR1e7sDT7FrcsJn3Ghmf+00eJ4lTtMCZ9OlHz16v/gDLkxFG8MHKFxaG2Q+NqFpFePuZiw46tmvACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30c62d164eed604ddc6c45883eaa8e8d1770fae01084ce8e2c453d9050430d6e","last_reissued_at":"2026-06-30T01:17:22.866051Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:22.866051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPHERE: An Evaluation Card for Human-AI Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Chenglei Si, Chenyang Yang, Diyi Yang, Dora Zhao, Ehud Reiter, Qianou Ma, Ryan Louie, Tongshuang Wu, Xinran Zhao","submitted_at":"2025-03-24T20:17:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07971","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.07971/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2504.07971","created_at":"2026-06-30T01:17:22.866145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.07971v1","created_at":"2026-06-30T01:17:22.866145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07971","created_at":"2026-06-30T01:17:22.866145+00:00"},{"alias_kind":"pith_short_12","alias_value":"GDDC2FSO5VQE","created_at":"2026-06-30T01:17:22.866145+00:00"},{"alias_kind":"pith_short_16","alias_value":"GDDC2FSO5VQE3XDM","created_at":"2026-06-30T01:17:22.866145+00:00"},{"alias_kind":"pith_short_8","alias_value":"GDDC2FSO","created_at":"2026-06-30T01:17:22.866145+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.10448","citing_title":"Can Agent Benchmarks Support Their Scores? Evidence-Supported Bounds for Interactive-Agent Evaluation","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GDDC2FSO5VQE3XDMIWED5KUORU","json":"https://pith.science/pith/GDDC2FSO5VQE3XDMIWED5KUORU.json","graph_json":"https://pith.science/api/pith-number/GDDC2FSO5VQE3XDMIWED5KUORU/graph.json","events_json":"https://pith.science/api/pith-number/GDDC2FSO5VQE3XDMIWED5KUORU/events.json","paper":"https://pith.science/paper/GDDC2FSO"},"agent_actions":{"view_html":"https://pith.science/pith/GDDC2FSO5VQE3XDMIWED5KUORU","download_json":"https://pith.science/pith/GDDC2FSO5VQE3XDMIWED5KUORU.json","view_paper":"https://pith.science/paper/GDDC2FSO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.07971&json=true","fetch_graph":"https://pith.science/api/pith-number/GDDC2FSO5VQE3XDMIWED5KUORU/graph.json","fetch_events":"https://pith.science/api/pith-number/GDDC2FSO5VQE3XDMIWED5KUORU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GDDC2FSO5VQE3XDMIWED5KUORU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GDDC2FSO5VQE3XDMIWED5KUORU/action/storage_attestation","attest_author":"https://pith.science/pith/GDDC2FSO5VQE3XDMIWED5KUORU/action/author_attestation","sign_citation":"https://pith.science/pith/GDDC2FSO5VQE3XDMIWED5KUORU/action/citation_signature","submit_replication":"https://pith.science/pith/GDDC2FSO5VQE3XDMIWED5KUORU/action/replication_record"}},"created_at":"2026-06-30T01:17:22.866145+00:00","updated_at":"2026-06-30T01:17:22.866145+00:00"}