{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:23SUBWWJ4MWF3WKIMBB2GSWGMX","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":"83046a7dfef6e7c7c710ea4a7150f4402a2fdd5138ac5de5f441c5d80c3e12aa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T21:34:33Z","title_canon_sha256":"b9ebbde5bf72c09bc45011ce8260a649e39c7485bbfc32e10f54093d8c948e49"},"schema_version":"1.0","source":{"id":"2605.12772","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.12772","created_at":"2026-05-18T03:09:20Z"},{"alias_kind":"arxiv_version","alias_value":"2605.12772v1","created_at":"2026-05-18T03:09:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.12772","created_at":"2026-05-18T03:09:20Z"},{"alias_kind":"pith_short_12","alias_value":"23SUBWWJ4MWF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"23SUBWWJ4MWF3WKI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"23SUBWWJ","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:312b0828106703e5f8df461bc77bcbf2d1ec17044d375c6aff4355af240ace72","target":"graph","created_at":"2026-05-18T03:09:20Z","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":"a thirty-token user prompt that asks the assistant for a neutral comparison table first cuts sponsored recommendation from 46.9% to 1.0% averaged across our ten open-source models, and from 53.0% to 0% averaged across the two OpenAI models."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the automated judge (gpt-4o) reliably and without bias labels whether a recommendation is sponsored or neutral."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A 30-token prompt requesting a neutral comparison table cuts sponsored recommendations in LLMs from roughly 50% to near zero."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A thirty-token prompt asking LLMs for a neutral comparison table reduces sponsored recommendations from about 50 percent to near zero across twelve models."}],"snapshot_sha256":"7b02f378149c537cd169061b2430a62909be51c0630ac15410005f4e8f3c2f5c"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Wu et al. (2026) showed that most frontier large language models (LLMs) recommend a sponsored, roughly twice-as-expensive flight when their system prompt contains a soft sponsorship cue. We reproduce their evaluation on ten open-weight chat models plus the two of their twenty-three models that are still reachable today (gpt-3.5-turbo, gpt-4o). All reported rates in this paper are produced under the same judge the original paper used (gpt-4o); we additionally store every label under an open-weight (gpt-oss-120b) and a smaller proprietary (gpt-4o-mini) judge for an ablation. Three findings emerg","authors_text":"Andreas Maier, Gozde Gul Sahin, Jeta Sopa, Paula Perez-Toro, Siming Bayer","cross_cats":[],"headline":"A thirty-token prompt asking LLMs for a neutral comparison table reduces sponsored recommendations from about 50 percent to near zero across twelve models.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T21:34:33Z","title":"Just Ask for a Table: A Thirty-Token User Prompt Defeats Sponsored Recommendations in Twelve LLMs"},"references":{"count":14,"internal_anchors":6,"resolved_work":14,"sample":[{"cited_arxiv_id":"2212.08073","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Constitutional AI: Harmlessness from AI Feedback","work_id":"faaaa4e0-2676-4fac-a0b4-99aef10d2095","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"AI Magazine45(3), 354–368 (2024).https://doi.org/10.1002/ aaai.12188","work_id":"a414183b-92fc-4db0-b6ab-5113004a37b6","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"ACM SIGecom Exchanges22(2), 66–81 (2025), https://www.sigecom.org/exchanges/volume_22/2/FEIZI.pdf","work_id":"b4f9ba61-0012-48fa-900b-02b4e5a3a1f9","year":2025},{"cited_arxiv_id":"2411.15594","doi":"","is_internal_anchor":true,"ref_index":4,"title":"A Survey on LLM-as-a-Judge","work_id":"2676656a-67bd-4ad5-bad6-cb6f5fcdbfbe","year":2024},{"cited_arxiv_id":"2103.03874","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Measuring Mathematical Problem Solving With the MATH Dataset","work_id":"50652ac6-fb7c-4675-a2c2-159c241feb17","year":2021}],"snapshot_sha256":"9475e2cb6e315178624ffa5dd531f90fe5f85c039b8cdc0eb70f180513cd2b2b"},"source":{"id":"2605.12772","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T20:39:31.237172Z","id":"ddfce423-5d9e-4534-90de-c0be07b468ef","model_set":{"reader":"grok-4.3"},"one_line_summary":"A 30-token prompt requesting a neutral comparison table cuts sponsored recommendations in LLMs from roughly 50% to near zero.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A thirty-token prompt asking LLMs for a neutral comparison table reduces sponsored recommendations from about 50 percent to near zero across twelve models.","strongest_claim":"a thirty-token user prompt that asks the assistant for a neutral comparison table first cuts sponsored recommendation from 46.9% to 1.0% averaged across our ten open-source models, and from 53.0% to 0% averaged across the two OpenAI models.","weakest_assumption":"That the automated judge (gpt-4o) reliably and without bias labels whether a recommendation is sponsored or neutral."}},"verdict_id":"ddfce423-5d9e-4534-90de-c0be07b468ef"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5805c71ad9dc8628bb7bc8c1f9bd388b081cbd1c461add03e7f93f77f6ca775c","target":"record","created_at":"2026-05-18T03:09:20Z","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":"83046a7dfef6e7c7c710ea4a7150f4402a2fdd5138ac5de5f441c5d80c3e12aa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T21:34:33Z","title_canon_sha256":"b9ebbde5bf72c09bc45011ce8260a649e39c7485bbfc32e10f54093d8c948e49"},"schema_version":"1.0","source":{"id":"2605.12772","kind":"arxiv","version":1}},"canonical_sha256":"d6e540dac9e32c5dd9486043a34ac665d5ab0642e6500e1e7ab1b858dca34426","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6e540dac9e32c5dd9486043a34ac665d5ab0642e6500e1e7ab1b858dca34426","first_computed_at":"2026-05-18T03:09:20.082830Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:09:20.082830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r0LGlDNXL7zHpmHGrnsxGOKQh3l/Uvopm7tz8t4qK9UlmsGs+AetJZ0qqFx7aleT8uoKjrPv53fRTVz6KrvXAg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:09:20.083623Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.12772","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5805c71ad9dc8628bb7bc8c1f9bd388b081cbd1c461add03e7f93f77f6ca775c","sha256:312b0828106703e5f8df461bc77bcbf2d1ec17044d375c6aff4355af240ace72"],"state_sha256":"1cbadf48567fdd38f3d1ef563c4fc24135406e461488beac514110995158a1e2"}