{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TPP6OY7QXS3XXPVQC2RFAA5JTL","short_pith_number":"pith:TPP6OY7Q","schema_version":"1.0","canonical_sha256":"9bdfe763f0bcb77bbeb016a25003a99ae197f5c7b56639d644c9abf7542f9db9","source":{"kind":"arxiv","id":"2606.30256","version":1},"attestation_state":"computed","paper":{"title":"EMPATH: A Multilingual Auditor-Judge Benchmark for Safety Evaluation of Emotional-Support Chatbots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.AI","authors_text":"Camilo Chac\\'on Sartori","submitted_at":"2026-06-29T13:05:43Z","abstract_excerpt":"Safety benchmarks often buy scalability by fixing the prompt, the language, and the turn structure. For emotional-support chatbots, that bargain hides precisely where safety failures emerge: across a multilingual, multi-turn crisis conversation. We present EMPATH, a benchmark for safety evaluation of emotional-support chatbots. An auditor model role-plays help-seeking users, generating multi-turn conversations from 140 seed instructions and 34 personas. A judge model scores each full transcript against 19 metrics across five dimensions: crisis handling, therapeutic quality, conversational inte"},"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":"2606.30256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T13:05:43Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"5fcef853a621d1cf607cfda9828a77ece70e81c36d5ee0fec44eb20fca8766d6","abstract_canon_sha256":"8c47ae233276612bfd8e3b03522c58f59c95dc9f71b615bebe6a27cc58969a0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:56.418767Z","signature_b64":"q3HO43id7u9yoUrKDhlAMWG+f/PCgTpYRfz+7X9xhxshZAp9/5UiQvREixPkBofNj34YJrJr7mnXaoAmF9LDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bdfe763f0bcb77bbeb016a25003a99ae197f5c7b56639d644c9abf7542f9db9","last_reissued_at":"2026-06-30T02:17:56.418242Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:56.418242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EMPATH: A Multilingual Auditor-Judge Benchmark for Safety Evaluation of Emotional-Support Chatbots","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.AI","authors_text":"Camilo Chac\\'on Sartori","submitted_at":"2026-06-29T13:05:43Z","abstract_excerpt":"Safety benchmarks often buy scalability by fixing the prompt, the language, and the turn structure. For emotional-support chatbots, that bargain hides precisely where safety failures emerge: across a multilingual, multi-turn crisis conversation. We present EMPATH, a benchmark for safety evaluation of emotional-support chatbots. An auditor model role-plays help-seeking users, generating multi-turn conversations from 140 seed instructions and 34 personas. A judge model scores each full transcript against 19 metrics across five dimensions: crisis handling, therapeutic quality, conversational inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30256","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/2606.30256/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":"2606.30256","created_at":"2026-06-30T02:17:56.418330+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30256v1","created_at":"2026-06-30T02:17:56.418330+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30256","created_at":"2026-06-30T02:17:56.418330+00:00"},{"alias_kind":"pith_short_12","alias_value":"TPP6OY7QXS3X","created_at":"2026-06-30T02:17:56.418330+00:00"},{"alias_kind":"pith_short_16","alias_value":"TPP6OY7QXS3XXPVQ","created_at":"2026-06-30T02:17:56.418330+00:00"},{"alias_kind":"pith_short_8","alias_value":"TPP6OY7Q","created_at":"2026-06-30T02:17:56.418330+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/TPP6OY7QXS3XXPVQC2RFAA5JTL","json":"https://pith.science/pith/TPP6OY7QXS3XXPVQC2RFAA5JTL.json","graph_json":"https://pith.science/api/pith-number/TPP6OY7QXS3XXPVQC2RFAA5JTL/graph.json","events_json":"https://pith.science/api/pith-number/TPP6OY7QXS3XXPVQC2RFAA5JTL/events.json","paper":"https://pith.science/paper/TPP6OY7Q"},"agent_actions":{"view_html":"https://pith.science/pith/TPP6OY7QXS3XXPVQC2RFAA5JTL","download_json":"https://pith.science/pith/TPP6OY7QXS3XXPVQC2RFAA5JTL.json","view_paper":"https://pith.science/paper/TPP6OY7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30256&json=true","fetch_graph":"https://pith.science/api/pith-number/TPP6OY7QXS3XXPVQC2RFAA5JTL/graph.json","fetch_events":"https://pith.science/api/pith-number/TPP6OY7QXS3XXPVQC2RFAA5JTL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TPP6OY7QXS3XXPVQC2RFAA5JTL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TPP6OY7QXS3XXPVQC2RFAA5JTL/action/storage_attestation","attest_author":"https://pith.science/pith/TPP6OY7QXS3XXPVQC2RFAA5JTL/action/author_attestation","sign_citation":"https://pith.science/pith/TPP6OY7QXS3XXPVQC2RFAA5JTL/action/citation_signature","submit_replication":"https://pith.science/pith/TPP6OY7QXS3XXPVQC2RFAA5JTL/action/replication_record"}},"created_at":"2026-06-30T02:17:56.418330+00:00","updated_at":"2026-06-30T02:17:56.418330+00:00"}