{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MU5C35BCCF2KLHQWPAN47S4IUD","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":"4044c9aef0f75cceade9864064dc92d70c44f740fe2b2a8b353a09a2eb1ca45d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-10T19:04:28Z","title_canon_sha256":"74ff74138bc63b4449c33fee004cb39cf7a1360bd71027f6df3265491c2b77f5"},"schema_version":"1.0","source":{"id":"2510.09801","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.09801","created_at":"2026-06-10T01:09:45Z"},{"alias_kind":"arxiv_version","alias_value":"2510.09801v3","created_at":"2026-06-10T01:09:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.09801","created_at":"2026-06-10T01:09:45Z"},{"alias_kind":"pith_short_12","alias_value":"MU5C35BCCF2K","created_at":"2026-06-10T01:09:45Z"},{"alias_kind":"pith_short_16","alias_value":"MU5C35BCCF2KLHQW","created_at":"2026-06-10T01:09:45Z"},{"alias_kind":"pith_short_8","alias_value":"MU5C35BC","created_at":"2026-06-10T01:09:45Z"}],"graph_snapshots":[{"event_id":"sha256:b298d28d795360b3c447249b0233e3e78c17e68c44fcc918dbc800d4731ece88","target":"graph","created_at":"2026-06-10T01:09:45Z","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/2510.09801/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While benchmarks measure the accuracy of LLM-powered agents, they mostly assume full automation, failing to represent the collaborative nature of real-world use cases. In this paper, we make two major steps towards the rigorous assessment of human-agent interactions. First, we propose PULSE, a framework for more efficient human-centric evaluation of agent designs, which comprises collecting user feedback, training an ML model to predict user satisfaction, and computing results by combining human satisfaction ratings with model-generated pseudo-labels. Second, we deploy PULSE in software engine","authors_text":"Aditya Bharat Soni, Ameet Talwalkar, Calvin Smith, Graham Neubig, Hoang H. Tran, Juan Michelini, Rohit Malhotra, Valerie Chen, Xingyao Wang, Xuhui Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-10T19:04:28Z","title":"How can we assess human-agent interactions? Case studies in software agent design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.09801","kind":"arxiv","version":3},"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":"sha256:0a2585e17589641fe05f121f3ab85b34ce651ac3cbc639170a875c25be4bda67","target":"record","created_at":"2026-06-10T01:09:45Z","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":"4044c9aef0f75cceade9864064dc92d70c44f740fe2b2a8b353a09a2eb1ca45d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-10-10T19:04:28Z","title_canon_sha256":"74ff74138bc63b4449c33fee004cb39cf7a1360bd71027f6df3265491c2b77f5"},"schema_version":"1.0","source":{"id":"2510.09801","kind":"arxiv","version":3}},"canonical_sha256":"653a2df4221174a59e16781bcfcb88a0cc4ef9f195c0fef652f3b4efad7d4763","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"653a2df4221174a59e16781bcfcb88a0cc4ef9f195c0fef652f3b4efad7d4763","first_computed_at":"2026-06-10T01:09:45.067212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:09:45.067212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"npcrcArh+Bqulaiqvoxb595pV10B4HzdFIKaGFmjVgaXAQUhsaYB+7tOMV0ay+dAi2yb/WCWHrZSzbUrtrtSDg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:09:45.068017Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.09801","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a2585e17589641fe05f121f3ab85b34ce651ac3cbc639170a875c25be4bda67","sha256:b298d28d795360b3c447249b0233e3e78c17e68c44fcc918dbc800d4731ece88"],"state_sha256":"76d2a5e3afae3f0ae2535fc3b7d6a2cd65717a39d609e95882e499ecde0ab924"}