{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KRURCHS2GBTGSJX4J6UYS2DE6E","short_pith_number":"pith:KRURCHS2","canonical_record":{"source":{"id":"2603.11394","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-12T00:14:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e4e781e15cbe2e44c9a6cd4082e830eb0a62f3d6a9df551ff7f3680489321768","abstract_canon_sha256":"3fe74b62cb43273b4d19be46a8b18367d42dfba0fa3adcbe640bf3d785920414"},"schema_version":"1.0"},"canonical_sha256":"5469111e5a30666926fc4fa9896864f1379fff4f6d777bf774ea27b403dd75b6","source":{"kind":"arxiv","id":"2603.11394","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.11394","created_at":"2026-05-27T02:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2603.11394v3","created_at":"2026-05-27T02:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.11394","created_at":"2026-05-27T02:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"KRURCHS2GBTG","created_at":"2026-05-27T02:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"KRURCHS2GBTGSJX4","created_at":"2026-05-27T02:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"KRURCHS2","created_at":"2026-05-27T02:05:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KRURCHS2GBTGSJX4J6UYS2DE6E","target":"record","payload":{"canonical_record":{"source":{"id":"2603.11394","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-12T00:14:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e4e781e15cbe2e44c9a6cd4082e830eb0a62f3d6a9df551ff7f3680489321768","abstract_canon_sha256":"3fe74b62cb43273b4d19be46a8b18367d42dfba0fa3adcbe640bf3d785920414"},"schema_version":"1.0"},"canonical_sha256":"5469111e5a30666926fc4fa9896864f1379fff4f6d777bf774ea27b403dd75b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:05:13.440370Z","signature_b64":"GrpGkekBm1rTJnMyuBA4ukhgxMVIYZhQptPQjfv+amCia55ayVY4XoqFsRG5NeahHFo4MAeBR7DjtnoZgulBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5469111e5a30666926fc4fa9896864f1379fff4f6d777bf774ea27b403dd75b6","last_reissued_at":"2026-05-27T02:05:13.439776Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:05:13.439776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.11394","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T02:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aDiSMpk7JRF2Fmp3htn+olWkLqnrvTP6fhjPkewyAb9lMxbdeKYioHahiaSE/ZoeXThOgnxD3Ha7LuOQXQNaDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T10:46:10.822686Z"},"content_sha256":"b54ecccfa035d3484f60ac1f59bd6695501bceef5131f01f6b09c2985508aff3","schema_version":"1.0","event_id":"sha256:b54ecccfa035d3484f60ac1f59bd6695501bceef5131f01f6b09c2985508aff3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KRURCHS2GBTGSJX4J6UYS2DE6E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stop Listening to Me! How Multi-turn Conversations Can Degrade LLM Reliability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Multi-turn conversations cause LLMs to abandon correct medical diagnoses for incorrect user suggestions.","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Avinash Baidya, Bradley A. Malin, Chao Yan, Juming Xiong, Katherine Brown, Kevin H. Guo, Xiang Gao, Zhijun Yin","submitted_at":"2026-03-12T00:14:35Z","abstract_excerpt":"Large language models (LLMs) excel on static benchmarks, but their performance across multi-turn conversations, which better reflect real-world usage, remains understudied. Addressing this gap is critical in high-stakes settings like healthcare, where patients and clinicians are turning to LLM chatbots to address their medical inquiries. Here, we introduce the \"stick-or-switch\" (SoS) framework, which partitions a question-answer space into multiple sequential presentations to model two safety-centric behaviors: conviction (i.e., sticking to a correct answer selection or abstention against inco"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our experiments reveal the conversation tax, where multi-turn interactions consistently degrade performance when compared to single-shot baselines. Notably, models frequently abandon initial correct diagnoses and safe abstentions to align with incorrect user suggestions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The simulated multi-turn conversations and stick-or-switch metrics accurately reflect real-world patient-clinician chatbot interactions without introducing artificial biases in how suggestions are introduced.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Multi-turn conversations degrade LLM diagnostic performance by causing models to abandon correct diagnoses in favor of incorrect user suggestions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multi-turn conversations cause LLMs to abandon correct medical diagnoses for incorrect user suggestions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fb8a8647fb86deff5e44f4f15c88a169040023b357cb19b6a0c311fe86db10c2"},"source":{"id":"2603.11394","kind":"arxiv","version":3},"verdict":{"id":"06bd7eae-d227-4654-a40a-1484224dfcef","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T12:45:31.737429Z","strongest_claim":"Our experiments reveal the conversation tax, where multi-turn interactions consistently degrade performance when compared to single-shot baselines. Notably, models frequently abandon initial correct diagnoses and safe abstentions to align with incorrect user suggestions.","one_line_summary":"Multi-turn conversations degrade LLM diagnostic performance by causing models to abandon correct diagnoses in favor of incorrect user suggestions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The simulated multi-turn conversations and stick-or-switch metrics accurately reflect real-world patient-clinician chatbot interactions without introducing artificial biases in how suggestions are introduced.","pith_extraction_headline":"Multi-turn conversations cause LLMs to abandon correct medical diagnoses for incorrect user suggestions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.11394/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"},"verdict_id":"06bd7eae-d227-4654-a40a-1484224dfcef"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T02:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8GjwWboG0a8Qx+keCPT6z1KvUGHQot5pG3G5Y4sMfSjw5DkGfZkEjy9kBwHAPpdjegwIHDW0FsEJIJBSP4iLAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T10:46:10.823130Z"},"content_sha256":"2880ba3205d8380344e0f2ba367a397d3810d4528ec50fc2857f7cf852a3b41a","schema_version":"1.0","event_id":"sha256:2880ba3205d8380344e0f2ba367a397d3810d4528ec50fc2857f7cf852a3b41a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KRURCHS2GBTGSJX4J6UYS2DE6E/bundle.json","state_url":"https://pith.science/pith/KRURCHS2GBTGSJX4J6UYS2DE6E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KRURCHS2GBTGSJX4J6UYS2DE6E/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-01T10:46:10Z","links":{"resolver":"https://pith.science/pith/KRURCHS2GBTGSJX4J6UYS2DE6E","bundle":"https://pith.science/pith/KRURCHS2GBTGSJX4J6UYS2DE6E/bundle.json","state":"https://pith.science/pith/KRURCHS2GBTGSJX4J6UYS2DE6E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KRURCHS2GBTGSJX4J6UYS2DE6E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KRURCHS2GBTGSJX4J6UYS2DE6E","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3fe74b62cb43273b4d19be46a8b18367d42dfba0fa3adcbe640bf3d785920414","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-12T00:14:35Z","title_canon_sha256":"e4e781e15cbe2e44c9a6cd4082e830eb0a62f3d6a9df551ff7f3680489321768"},"schema_version":"1.0","source":{"id":"2603.11394","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.11394","created_at":"2026-05-27T02:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2603.11394v3","created_at":"2026-05-27T02:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.11394","created_at":"2026-05-27T02:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"KRURCHS2GBTG","created_at":"2026-05-27T02:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"KRURCHS2GBTGSJX4","created_at":"2026-05-27T02:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"KRURCHS2","created_at":"2026-05-27T02:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:2880ba3205d8380344e0f2ba367a397d3810d4528ec50fc2857f7cf852a3b41a","target":"graph","created_at":"2026-05-27T02:05:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our experiments reveal the conversation tax, where multi-turn interactions consistently degrade performance when compared to single-shot baselines. Notably, models frequently abandon initial correct diagnoses and safe abstentions to align with incorrect user suggestions."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The simulated multi-turn conversations and stick-or-switch metrics accurately reflect real-world patient-clinician chatbot interactions without introducing artificial biases in how suggestions are introduced."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Multi-turn conversations degrade LLM diagnostic performance by causing models to abandon correct diagnoses in favor of incorrect user suggestions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Multi-turn conversations cause LLMs to abandon correct medical diagnoses for incorrect user suggestions."}],"snapshot_sha256":"fb8a8647fb86deff5e44f4f15c88a169040023b357cb19b6a0c311fe86db10c2"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.11394/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) excel on static benchmarks, but their performance across multi-turn conversations, which better reflect real-world usage, remains understudied. Addressing this gap is critical in high-stakes settings like healthcare, where patients and clinicians are turning to LLM chatbots to address their medical inquiries. Here, we introduce the \"stick-or-switch\" (SoS) framework, which partitions a question-answer space into multiple sequential presentations to model two safety-centric behaviors: conviction (i.e., sticking to a correct answer selection or abstention against inco","authors_text":"Avinash Baidya, Bradley A. Malin, Chao Yan, Juming Xiong, Katherine Brown, Kevin H. Guo, Xiang Gao, Zhijun Yin","cross_cats":["cs.AI","cs.LG"],"headline":"Multi-turn conversations cause LLMs to abandon correct medical diagnoses for incorrect user suggestions.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-12T00:14:35Z","title":"Stop Listening to Me! How Multi-turn Conversations Can Degrade LLM Reliability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.11394","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T12:45:31.737429Z","id":"06bd7eae-d227-4654-a40a-1484224dfcef","model_set":{"reader":"grok-4.3"},"one_line_summary":"Multi-turn conversations degrade LLM diagnostic performance by causing models to abandon correct diagnoses in favor of incorrect user suggestions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Multi-turn conversations cause LLMs to abandon correct medical diagnoses for incorrect user suggestions.","strongest_claim":"Our experiments reveal the conversation tax, where multi-turn interactions consistently degrade performance when compared to single-shot baselines. Notably, models frequently abandon initial correct diagnoses and safe abstentions to align with incorrect user suggestions.","weakest_assumption":"The simulated multi-turn conversations and stick-or-switch metrics accurately reflect real-world patient-clinician chatbot interactions without introducing artificial biases in how suggestions are introduced."}},"verdict_id":"06bd7eae-d227-4654-a40a-1484224dfcef"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b54ecccfa035d3484f60ac1f59bd6695501bceef5131f01f6b09c2985508aff3","target":"record","created_at":"2026-05-27T02:05:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3fe74b62cb43273b4d19be46a8b18367d42dfba0fa3adcbe640bf3d785920414","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-12T00:14:35Z","title_canon_sha256":"e4e781e15cbe2e44c9a6cd4082e830eb0a62f3d6a9df551ff7f3680489321768"},"schema_version":"1.0","source":{"id":"2603.11394","kind":"arxiv","version":3}},"canonical_sha256":"5469111e5a30666926fc4fa9896864f1379fff4f6d777bf774ea27b403dd75b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5469111e5a30666926fc4fa9896864f1379fff4f6d777bf774ea27b403dd75b6","first_computed_at":"2026-05-27T02:05:13.439776Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T02:05:13.439776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GrpGkekBm1rTJnMyuBA4ukhgxMVIYZhQptPQjfv+amCia55ayVY4XoqFsRG5NeahHFo4MAeBR7DjtnoZgulBCg==","signature_status":"signed_v1","signed_at":"2026-05-27T02:05:13.440370Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.11394","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b54ecccfa035d3484f60ac1f59bd6695501bceef5131f01f6b09c2985508aff3","sha256:2880ba3205d8380344e0f2ba367a397d3810d4528ec50fc2857f7cf852a3b41a"],"state_sha256":"aa84ac99e39edf453dea5c86ec82d3fae2aa19397852fc865404a9592f3805c9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kKb9cSaIiSJEtTCD8k+CIamHC8SGoEXthB26k9DkpiQ4qPAHvMTNRL7NBWivnYMyvzxIg7uSBlSkrcfNhAV5Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T10:46:10.825331Z","bundle_sha256":"8b2d273d48c8db1f65ede019dadbaacdb98a556fe8f08386e7d701f0a9b8c53e"}}