{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:X4DHFUJZMTBL5NC22XDCITTBGK","short_pith_number":"pith:X4DHFUJZ","schema_version":"1.0","canonical_sha256":"bf0672d13964c2beb45ad5c6244e6132b3dbc4408400af75be8bc73bf8ab392d","source":{"kind":"arxiv","id":"2603.06910","version":2},"attestation_state":"computed","paper":{"title":"Language Shapes Mental Health Evaluations in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiayi Xu, Xiyang Hu","submitted_at":"2026-03-06T22:15:09Z","abstract_excerpt":"Multilingual large language models (LLMs) are increasingly used in socially sensitive mental health contexts, including support chatbots, screening, and content moderation. This raises a reliability question: do semantically equivalent mental health inputs elicit comparable evaluations across languages, or systematic shifts consistent with language-associated social and cultural contexts? We examine this question in an English-Chinese setting with GPT-4o and Qwen3-32B using a two-level framework: construct-level evaluative orientation, measured by psychometric stigma instruments, and decision-"},"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":"2603.06910","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-03-06T22:15:09Z","cross_cats_sorted":[],"title_canon_sha256":"b918c3956a174e191d531701a46ead0f0a92a866b635eeb3efb21680c1480449","abstract_canon_sha256":"907fdee133bf743c027440e5f76db11ace77c3fbe27999b7f562bcb4bc42e38c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:32.380489Z","signature_b64":"l+A45zf/0Qa4IDGPvTQt3LsompLu5WePNhjfx9z2N3Vvw02QACIJXsUwXagqSyyevzXB+s/nwn36c25U4P1uAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf0672d13964c2beb45ad5c6244e6132b3dbc4408400af75be8bc73bf8ab392d","last_reissued_at":"2026-06-11T01:09:32.379496Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:32.379496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Shapes Mental Health Evaluations in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiayi Xu, Xiyang Hu","submitted_at":"2026-03-06T22:15:09Z","abstract_excerpt":"Multilingual large language models (LLMs) are increasingly used in socially sensitive mental health contexts, including support chatbots, screening, and content moderation. This raises a reliability question: do semantically equivalent mental health inputs elicit comparable evaluations across languages, or systematic shifts consistent with language-associated social and cultural contexts? We examine this question in an English-Chinese setting with GPT-4o and Qwen3-32B using a two-level framework: construct-level evaluative orientation, measured by psychometric stigma instruments, and decision-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.06910","kind":"arxiv","version":2},"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/2603.06910/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":"2603.06910","created_at":"2026-06-11T01:09:32.379660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.06910v2","created_at":"2026-06-11T01:09:32.379660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.06910","created_at":"2026-06-11T01:09:32.379660+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4DHFUJZMTBL","created_at":"2026-06-11T01:09:32.379660+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4DHFUJZMTBL5NC2","created_at":"2026-06-11T01:09:32.379660+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4DHFUJZ","created_at":"2026-06-11T01:09:32.379660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.30256","citing_title":"EMPATH: A Multilingual Auditor-Judge Benchmark for Safety Evaluation of Emotional-Support Chatbots","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4DHFUJZMTBL5NC22XDCITTBGK","json":"https://pith.science/pith/X4DHFUJZMTBL5NC22XDCITTBGK.json","graph_json":"https://pith.science/api/pith-number/X4DHFUJZMTBL5NC22XDCITTBGK/graph.json","events_json":"https://pith.science/api/pith-number/X4DHFUJZMTBL5NC22XDCITTBGK/events.json","paper":"https://pith.science/paper/X4DHFUJZ"},"agent_actions":{"view_html":"https://pith.science/pith/X4DHFUJZMTBL5NC22XDCITTBGK","download_json":"https://pith.science/pith/X4DHFUJZMTBL5NC22XDCITTBGK.json","view_paper":"https://pith.science/paper/X4DHFUJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.06910&json=true","fetch_graph":"https://pith.science/api/pith-number/X4DHFUJZMTBL5NC22XDCITTBGK/graph.json","fetch_events":"https://pith.science/api/pith-number/X4DHFUJZMTBL5NC22XDCITTBGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4DHFUJZMTBL5NC22XDCITTBGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4DHFUJZMTBL5NC22XDCITTBGK/action/storage_attestation","attest_author":"https://pith.science/pith/X4DHFUJZMTBL5NC22XDCITTBGK/action/author_attestation","sign_citation":"https://pith.science/pith/X4DHFUJZMTBL5NC22XDCITTBGK/action/citation_signature","submit_replication":"https://pith.science/pith/X4DHFUJZMTBL5NC22XDCITTBGK/action/replication_record"}},"created_at":"2026-06-11T01:09:32.379660+00:00","updated_at":"2026-06-11T01:09:32.379660+00:00"}