{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4TV434K2HHCVPYLVHAAKAOJEIN","short_pith_number":"pith:4TV434K2","schema_version":"1.0","canonical_sha256":"e4ebcdf15a39c557e1753800a03924436a116e1fb021ddb3e7c6269eacf92045","source":{"kind":"arxiv","id":"2511.10871","version":2},"attestation_state":"computed","paper":{"title":"From Fact to Judgment: Investigating the Impact of Task Framing on LLM Conviction in Dialogue Systems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dilek Hakkani-T\\\"ur, Nimet Beyza Bozdag, Parisa Rabbani","submitted_at":"2025-11-14T00:55:28Z","abstract_excerpt":"LLMs are increasingly employed as judges across a variety of tasks, including those involving everyday social interactions. Yet, it remains unclear whether such LLM-judges can reliably assess tasks that require social or conversational judgment. We investigate how an LLM's conviction is changed when a task is reframed from a direct factual query to a Conversational Judgment Task. Our evaluation framework contrasts the model's performance on direct factual queries with its assessment of a speaker's correctness when the same information is presented within a minimal dialogue, effectively shiftin"},"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":"2511.10871","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-14T00:55:28Z","cross_cats_sorted":[],"title_canon_sha256":"685a07304951d0dc2faec1896cbc3c21c92324e3cb8a6cec192c61ae354d70eb","abstract_canon_sha256":"3dec1d89d528eeb4884e71e35770e0c2d74d954c8a3f1fb5fb9d82484ac760ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:39:45.501674Z","signature_b64":"PaTNxqh1jS21bstVuVgekS9Ni7/OlVPTcQ8YM4HFBND6ModmXX/ifD8BANxxtJIsJGrz6CL7xLiJvb5C6zdECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4ebcdf15a39c557e1753800a03924436a116e1fb021ddb3e7c6269eacf92045","last_reissued_at":"2026-08-04T02:39:45.498968Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:39:45.498968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Fact to Judgment: Investigating the Impact of Task Framing on LLM Conviction in Dialogue Systems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dilek Hakkani-T\\\"ur, Nimet Beyza Bozdag, Parisa Rabbani","submitted_at":"2025-11-14T00:55:28Z","abstract_excerpt":"LLMs are increasingly employed as judges across a variety of tasks, including those involving everyday social interactions. Yet, it remains unclear whether such LLM-judges can reliably assess tasks that require social or conversational judgment. We investigate how an LLM's conviction is changed when a task is reframed from a direct factual query to a Conversational Judgment Task. Our evaluation framework contrasts the model's performance on direct factual queries with its assessment of a speaker's correctness when the same information is presented within a minimal dialogue, effectively shiftin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.10871","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/2511.10871/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":"2511.10871","created_at":"2026-08-04T02:39:45.501292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.10871v2","created_at":"2026-08-04T02:39:45.501292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.10871","created_at":"2026-08-04T02:39:45.501292+00:00"},{"alias_kind":"pith_short_12","alias_value":"4TV434K2HHCV","created_at":"2026-08-04T02:39:45.501292+00:00"},{"alias_kind":"pith_short_16","alias_value":"4TV434K2HHCVPYLV","created_at":"2026-08-04T02:39:45.501292+00:00"},{"alias_kind":"pith_short_8","alias_value":"4TV434K2","created_at":"2026-08-04T02:39:45.501292+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/4TV434K2HHCVPYLVHAAKAOJEIN","json":"https://pith.science/pith/4TV434K2HHCVPYLVHAAKAOJEIN.json","graph_json":"https://pith.science/api/pith-number/4TV434K2HHCVPYLVHAAKAOJEIN/graph.json","events_json":"https://pith.science/api/pith-number/4TV434K2HHCVPYLVHAAKAOJEIN/events.json","paper":"https://pith.science/paper/4TV434K2"},"agent_actions":{"view_html":"https://pith.science/pith/4TV434K2HHCVPYLVHAAKAOJEIN","download_json":"https://pith.science/pith/4TV434K2HHCVPYLVHAAKAOJEIN.json","view_paper":"https://pith.science/paper/4TV434K2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.10871&json=true","fetch_graph":"https://pith.science/api/pith-number/4TV434K2HHCVPYLVHAAKAOJEIN/graph.json","fetch_events":"https://pith.science/api/pith-number/4TV434K2HHCVPYLVHAAKAOJEIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4TV434K2HHCVPYLVHAAKAOJEIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4TV434K2HHCVPYLVHAAKAOJEIN/action/storage_attestation","attest_author":"https://pith.science/pith/4TV434K2HHCVPYLVHAAKAOJEIN/action/author_attestation","sign_citation":"https://pith.science/pith/4TV434K2HHCVPYLVHAAKAOJEIN/action/citation_signature","submit_replication":"https://pith.science/pith/4TV434K2HHCVPYLVHAAKAOJEIN/action/replication_record"}},"created_at":"2026-08-04T02:39:45.501292+00:00","updated_at":"2026-08-04T02:39:45.501292+00:00"}