{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IZTLQT75QNFB3KASPEC4Y553UZ","short_pith_number":"pith:IZTLQT75","schema_version":"1.0","canonical_sha256":"4666b84ffd834a1da8127905cc77bba67817c18f6d01ca429dca0b1bcf71a0ab","source":{"kind":"arxiv","id":"2605.01017","version":2},"attestation_state":"computed","paper":{"title":"Psychologically Potent, Computationally Invisible: LLMs Generate Social-Comparison-Eliciting Posts They Fail to Detect","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"LLMs generate social-comparison triggers but fail to detect them with prompts","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hua Zhao, Jiapei Gu, Michelle Mingyue Gu","submitted_at":"2026-05-01T18:28:10Z","abstract_excerpt":"We introduce Xiaohongshu Social Comparison Reader Elicitation (XHS-SCoRE), a reader-grounded benchmark for detecting whether text-only Xiaohongshu (RedNote) posts elicit Upward, Downward, or Neutral/no clear social comparison from a first-person reader perspective. The task targets a socially meaningful relational, behaviorally real signal not reducible to sentiment. Across prompted LLM classifiers and supervised Chinese encoders, we find a consistent generation--detection mismatch: the signal is textually learnable in-domain, but not robustly accessible to prompt-based classification. Prompte"},"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":"2605.01017","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-01T18:28:10Z","cross_cats_sorted":[],"title_canon_sha256":"622639ffa36106924bfe93c7ce8cb7d020acc10fae5e5025a4918d9d30cf0b62","abstract_canon_sha256":"ddc9af28890cea725f17c17959fe89f31c75a23ac17c2049796303af67d7c27b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:05:09.744387Z","signature_b64":"L6M04jjGvI8iSgG7nny9D6M/8o4xmaALuWzRA4Rm1T+UPcOsxv8XZlD6YL/RgaKN/jBaNkwOr4QCkuSXy1VRCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4666b84ffd834a1da8127905cc77bba67817c18f6d01ca429dca0b1bcf71a0ab","last_reissued_at":"2026-05-26T02:05:09.743395Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:05:09.743395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Psychologically Potent, Computationally Invisible: LLMs Generate Social-Comparison-Eliciting Posts They Fail to Detect","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"LLMs generate social-comparison triggers but fail to detect them with prompts","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hua Zhao, Jiapei Gu, Michelle Mingyue Gu","submitted_at":"2026-05-01T18:28:10Z","abstract_excerpt":"We introduce Xiaohongshu Social Comparison Reader Elicitation (XHS-SCoRE), a reader-grounded benchmark for detecting whether text-only Xiaohongshu (RedNote) posts elicit Upward, Downward, or Neutral/no clear social comparison from a first-person reader perspective. The task targets a socially meaningful relational, behaviorally real signal not reducible to sentiment. Across prompted LLM classifiers and supervised Chinese encoders, we find a consistent generation--detection mismatch: the signal is textually learnable in-domain, but not robustly accessible to prompt-based classification. Prompte"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Across prompted LLM classifiers and supervised Chinese encoder baselines, we find a consistent mismatch between generation fluency and reliable detection ability: the signal is textually learnable in-domain, but not robustly accessible to prompt-based classification.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the XHS-SCoRE benchmark, built from first-person reader labels on Xiaohongshu posts, accurately and stably captures the psychologically real construct of social comparison rather than artifacts of the platform or labeling process.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLMs generate social media posts that shift readers' perceived standing and comparison-related feelings but fail to reliably detect the same social-comparison triggers via prompt-based classification.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LLMs generate social-comparison triggers but fail to detect them with prompts","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1dec7981c689fbd8e240192513233b5a6b2e3b0f366167baa5f246cda2ef1cd2"},"source":{"id":"2605.01017","kind":"arxiv","version":2},"verdict":{"id":"faa2a280-3e0a-436f-8cff-3fe4f47fee45","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T19:07:55.214667Z","strongest_claim":"Across prompted LLM classifiers and supervised Chinese encoder baselines, we find a consistent mismatch between generation fluency and reliable detection ability: the signal is textually learnable in-domain, but not robustly accessible to prompt-based classification.","one_line_summary":"LLMs generate social media posts that shift readers' perceived standing and comparison-related feelings but fail to reliably detect the same social-comparison triggers via prompt-based classification.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the XHS-SCoRE benchmark, built from first-person reader labels on Xiaohongshu posts, accurately and stably captures the psychologically real construct of social comparison rather than artifacts of the platform or labeling process.","pith_extraction_headline":"LLMs generate social-comparison triggers but fail to detect them with prompts"},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.01017/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T18:39:46.997562Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T17:42:29.121409Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"27aacbd322e55789702054b54b9bb14a31f7184e2b51f1b711b84c221a108cc2"},"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":"2605.01017","created_at":"2026-05-26T02:05:09.743536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.01017v2","created_at":"2026-05-26T02:05:09.743536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01017","created_at":"2026-05-26T02:05:09.743536+00:00"},{"alias_kind":"pith_short_12","alias_value":"IZTLQT75QNFB","created_at":"2026-05-26T02:05:09.743536+00:00"},{"alias_kind":"pith_short_16","alias_value":"IZTLQT75QNFB3KAS","created_at":"2026-05-26T02:05:09.743536+00:00"},{"alias_kind":"pith_short_8","alias_value":"IZTLQT75","created_at":"2026-05-26T02:05:09.743536+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/IZTLQT75QNFB3KASPEC4Y553UZ","json":"https://pith.science/pith/IZTLQT75QNFB3KASPEC4Y553UZ.json","graph_json":"https://pith.science/api/pith-number/IZTLQT75QNFB3KASPEC4Y553UZ/graph.json","events_json":"https://pith.science/api/pith-number/IZTLQT75QNFB3KASPEC4Y553UZ/events.json","paper":"https://pith.science/paper/IZTLQT75"},"agent_actions":{"view_html":"https://pith.science/pith/IZTLQT75QNFB3KASPEC4Y553UZ","download_json":"https://pith.science/pith/IZTLQT75QNFB3KASPEC4Y553UZ.json","view_paper":"https://pith.science/paper/IZTLQT75","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.01017&json=true","fetch_graph":"https://pith.science/api/pith-number/IZTLQT75QNFB3KASPEC4Y553UZ/graph.json","fetch_events":"https://pith.science/api/pith-number/IZTLQT75QNFB3KASPEC4Y553UZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IZTLQT75QNFB3KASPEC4Y553UZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IZTLQT75QNFB3KASPEC4Y553UZ/action/storage_attestation","attest_author":"https://pith.science/pith/IZTLQT75QNFB3KASPEC4Y553UZ/action/author_attestation","sign_citation":"https://pith.science/pith/IZTLQT75QNFB3KASPEC4Y553UZ/action/citation_signature","submit_replication":"https://pith.science/pith/IZTLQT75QNFB3KASPEC4Y553UZ/action/replication_record"}},"created_at":"2026-05-26T02:05:09.743536+00:00","updated_at":"2026-05-26T02:05:09.743536+00:00"}