{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FEE47COFL4HDH7SZWIXZHZHVPN","short_pith_number":"pith:FEE47COF","schema_version":"1.0","canonical_sha256":"2909cf89c55f0e33fe59b22f93e4f57b58f0b009ce959f4541aca571ca34d673","source":{"kind":"arxiv","id":"2605.28228","version":1},"attestation_state":"computed","paper":{"title":"When Seekers Are Hard to Help: Evaluating Emotional Support Dialogue Systems in Worst-Case Interactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guanyi Chen, Jiajie Yang, Rui Fan, Tingting He, Xin Bai, Yangchun Li","submitted_at":"2026-05-27T09:41:32Z","abstract_excerpt":"Emotional Support Dialogue Systems (ESDSes) are increasingly evaluated and trained with LLM-simulated seekers. However, such simulated seekers often behave as cooperative, average-case users who disclose clearly, respond constructively, and accept support within a few turns. This can lead to overly optimistic evaluation and obscure whether ESDSes can handle difficult help-seeking interactions. In this work, we study ESDS evaluation under worst-case interactions, where seekers are hard to help due to low engagement, resistance, limited self-disclosure, emotional volatility, or rigid negative in"},"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":"2605.28228","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-27T09:41:32Z","cross_cats_sorted":[],"title_canon_sha256":"8c70a75fc91661f89399f4fe5c403e334bfb6dd112c22f08c4d870a32eef9cae","abstract_canon_sha256":"e605418bf55817865e34b6519a2638a8cfd5c3aa2f3ef56be6966afc6ced268a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:03.261304Z","signature_b64":"jkA3GqrLFEH3Weq0/1glyE8JLSCIplcVUzq5Ch0vLcDYpPTJxHC5npNRa3z8r2E0EyIqeS+xhPKpXfbZrLJ5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2909cf89c55f0e33fe59b22f93e4f57b58f0b009ce959f4541aca571ca34d673","last_reissued_at":"2026-05-28T01:05:03.260794Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:03.260794Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Seekers Are Hard to Help: Evaluating Emotional Support Dialogue Systems in Worst-Case Interactions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guanyi Chen, Jiajie Yang, Rui Fan, Tingting He, Xin Bai, Yangchun Li","submitted_at":"2026-05-27T09:41:32Z","abstract_excerpt":"Emotional Support Dialogue Systems (ESDSes) are increasingly evaluated and trained with LLM-simulated seekers. However, such simulated seekers often behave as cooperative, average-case users who disclose clearly, respond constructively, and accept support within a few turns. This can lead to overly optimistic evaluation and obscure whether ESDSes can handle difficult help-seeking interactions. In this work, we study ESDS evaluation under worst-case interactions, where seekers are hard to help due to low engagement, resistance, limited self-disclosure, emotional volatility, or rigid negative in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28228","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/2605.28228/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":"2605.28228","created_at":"2026-05-28T01:05:03.260867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28228v1","created_at":"2026-05-28T01:05:03.260867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28228","created_at":"2026-05-28T01:05:03.260867+00:00"},{"alias_kind":"pith_short_12","alias_value":"FEE47COFL4HD","created_at":"2026-05-28T01:05:03.260867+00:00"},{"alias_kind":"pith_short_16","alias_value":"FEE47COFL4HDH7SZ","created_at":"2026-05-28T01:05:03.260867+00:00"},{"alias_kind":"pith_short_8","alias_value":"FEE47COF","created_at":"2026-05-28T01:05:03.260867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FEE47COFL4HDH7SZWIXZHZHVPN","json":"https://pith.science/pith/FEE47COFL4HDH7SZWIXZHZHVPN.json","graph_json":"https://pith.science/api/pith-number/FEE47COFL4HDH7SZWIXZHZHVPN/graph.json","events_json":"https://pith.science/api/pith-number/FEE47COFL4HDH7SZWIXZHZHVPN/events.json","paper":"https://pith.science/paper/FEE47COF"},"agent_actions":{"view_html":"https://pith.science/pith/FEE47COFL4HDH7SZWIXZHZHVPN","download_json":"https://pith.science/pith/FEE47COFL4HDH7SZWIXZHZHVPN.json","view_paper":"https://pith.science/paper/FEE47COF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28228&json=true","fetch_graph":"https://pith.science/api/pith-number/FEE47COFL4HDH7SZWIXZHZHVPN/graph.json","fetch_events":"https://pith.science/api/pith-number/FEE47COFL4HDH7SZWIXZHZHVPN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FEE47COFL4HDH7SZWIXZHZHVPN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FEE47COFL4HDH7SZWIXZHZHVPN/action/storage_attestation","attest_author":"https://pith.science/pith/FEE47COFL4HDH7SZWIXZHZHVPN/action/author_attestation","sign_citation":"https://pith.science/pith/FEE47COFL4HDH7SZWIXZHZHVPN/action/citation_signature","submit_replication":"https://pith.science/pith/FEE47COFL4HDH7SZWIXZHZHVPN/action/replication_record"}},"created_at":"2026-05-28T01:05:03.260867+00:00","updated_at":"2026-05-28T01:05:03.260867+00:00"}