{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QAZPHQC5ZUIBPAEJMQA5BAPKMX","short_pith_number":"pith:QAZPHQC5","schema_version":"1.0","canonical_sha256":"8032f3c05dcd101780896401d081ea65c29a9d6d8bbeac553b562da0de886bc3","source":{"kind":"arxiv","id":"2405.10632","version":7},"attestation_state":"computed","paper":{"title":"Towards interactive evaluations for interaction harms in human-AI systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CY","authors_text":"Lama Ahmad, Lujain Ibrahim, Markus Anderljung, Saffron Huang, Umang Bhatt","submitted_at":"2024-05-17T08:49:34Z","abstract_excerpt":"Current AI evaluation methods, which rely on static, model-only tests, fail to account for harms that emerge through sustained human-AI interaction. As AI systems proliferate and are increasingly integrated into real-world applications, this disconnect between evaluation approaches and actual usage becomes more significant. In this paper, we propose a shift towards evaluation based on \\textit{interactional ethics}, which focuses on \\textit{interaction harms} - issues like inappropriate parasocial relationships, social manipulation, and cognitive overreliance that develop over time through repe"},"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":"2405.10632","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-05-17T08:49:34Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"e30347494a36212fcef8f929cf5b89ca43080f03844ad0f67d3b8d175ca26031","abstract_canon_sha256":"f797f7f93fa798e2ef606219538e1f8a8f4713480739f9623ac556eab3ba2c96"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:28.007743Z","signature_b64":"pF4sLu2yZG6zS5041ZGW3H8fsMLnZe07a+xmHiL3+XIX9kfi0DipHodKY1YGvl9U+1vlF0PNz6D2NlxAxnNLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8032f3c05dcd101780896401d081ea65c29a9d6d8bbeac553b562da0de886bc3","last_reissued_at":"2026-07-05T11:45:28.007254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:28.007254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards interactive evaluations for interaction harms in human-AI systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CY","authors_text":"Lama Ahmad, Lujain Ibrahim, Markus Anderljung, Saffron Huang, Umang Bhatt","submitted_at":"2024-05-17T08:49:34Z","abstract_excerpt":"Current AI evaluation methods, which rely on static, model-only tests, fail to account for harms that emerge through sustained human-AI interaction. As AI systems proliferate and are increasingly integrated into real-world applications, this disconnect between evaluation approaches and actual usage becomes more significant. In this paper, we propose a shift towards evaluation based on \\textit{interactional ethics}, which focuses on \\textit{interaction harms} - issues like inappropriate parasocial relationships, social manipulation, and cognitive overreliance that develop over time through repe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10632","kind":"arxiv","version":7},"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/2405.10632/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":"2405.10632","created_at":"2026-07-05T11:45:28.007321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10632v7","created_at":"2026-07-05T11:45:28.007321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10632","created_at":"2026-07-05T11:45:28.007321+00:00"},{"alias_kind":"pith_short_12","alias_value":"QAZPHQC5ZUIB","created_at":"2026-07-05T11:45:28.007321+00:00"},{"alias_kind":"pith_short_16","alias_value":"QAZPHQC5ZUIBPAEJ","created_at":"2026-07-05T11:45:28.007321+00:00"},{"alias_kind":"pith_short_8","alias_value":"QAZPHQC5","created_at":"2026-07-05T11:45:28.007321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29473","citing_title":"Inform, Coach, Relate, Listen: Auditing LLM Caregiving Support Roles","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2509.08010","citing_title":"Measuring and mitigating overreliance to build human-compatible AI","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2506.06414","citing_title":"Benchmarking Misuse Mitigation Against Covert Adversaries","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16304","citing_title":"Results-Actionability Gap: Understanding How Practitioners Evaluate LLM Products in the Wild","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QAZPHQC5ZUIBPAEJMQA5BAPKMX","json":"https://pith.science/pith/QAZPHQC5ZUIBPAEJMQA5BAPKMX.json","graph_json":"https://pith.science/api/pith-number/QAZPHQC5ZUIBPAEJMQA5BAPKMX/graph.json","events_json":"https://pith.science/api/pith-number/QAZPHQC5ZUIBPAEJMQA5BAPKMX/events.json","paper":"https://pith.science/paper/QAZPHQC5"},"agent_actions":{"view_html":"https://pith.science/pith/QAZPHQC5ZUIBPAEJMQA5BAPKMX","download_json":"https://pith.science/pith/QAZPHQC5ZUIBPAEJMQA5BAPKMX.json","view_paper":"https://pith.science/paper/QAZPHQC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10632&json=true","fetch_graph":"https://pith.science/api/pith-number/QAZPHQC5ZUIBPAEJMQA5BAPKMX/graph.json","fetch_events":"https://pith.science/api/pith-number/QAZPHQC5ZUIBPAEJMQA5BAPKMX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QAZPHQC5ZUIBPAEJMQA5BAPKMX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QAZPHQC5ZUIBPAEJMQA5BAPKMX/action/storage_attestation","attest_author":"https://pith.science/pith/QAZPHQC5ZUIBPAEJMQA5BAPKMX/action/author_attestation","sign_citation":"https://pith.science/pith/QAZPHQC5ZUIBPAEJMQA5BAPKMX/action/citation_signature","submit_replication":"https://pith.science/pith/QAZPHQC5ZUIBPAEJMQA5BAPKMX/action/replication_record"}},"created_at":"2026-07-05T11:45:28.007321+00:00","updated_at":"2026-07-05T11:45:28.007321+00:00"}