{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LVSTAX4SKGUPVI3WNJDJTFBR5A","short_pith_number":"pith:LVSTAX4S","schema_version":"1.0","canonical_sha256":"5d65305f9251a8faa3766a46999431e8272ec90cb9308ce9fdd2c0330c385352","source":{"kind":"arxiv","id":"2606.07834","version":1},"attestation_state":"computed","paper":{"title":"Cherry-pick Override: Unsafe Directional Commitment in LLM Judges under Mixed Evidence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MA"],"primary_cat":"cs.SE","authors_text":"Haoran Xu","submitted_at":"2026-06-05T20:51:51Z","abstract_excerpt":"LLM judges increasingly turn verdicts into system commitments. Under mixed evidence (claims with both supporting and refuting sources) this is unsafe: when the schema exposes CONFLICTING as the authorized non-directional verdict, returning SUPPORTS/REFUTES is an unauthorized directional commitment, a failure we name Cherry-pick Override (CCO). We define CCO under an explicit task contract and report it with a same-denominator diagnostic protocol paired with matched-coverage bootstrap and an apples-to-apples random-veto null. On AVeriTeC's Conflicting subset (N_C = 150), three-option judges ret"},"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":"2606.07834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-06-05T20:51:51Z","cross_cats_sorted":["cs.AI","cs.CL","cs.MA"],"title_canon_sha256":"7c9021b9cfb70a8bd4da1acfa681c94362f4eaffa9ae70d0910f2069f8f8ad85","abstract_canon_sha256":"06c5ca6a2b7c0465c23d521f0deed08187c20d42ef71cc12b8c4786e86bd7742"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:53.349388Z","signature_b64":"X1X4L73uYDaUZTd1zL+1cARZwXqjs6RgYspuro0t8ksFIhKTm761D5XuayNvWpvcjRDL/sdKih/BTL6GNC0LAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d65305f9251a8faa3766a46999431e8272ec90cb9308ce9fdd2c0330c385352","last_reissued_at":"2026-06-09T01:04:53.348992Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:53.348992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cherry-pick Override: Unsafe Directional Commitment in LLM Judges under Mixed Evidence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.MA"],"primary_cat":"cs.SE","authors_text":"Haoran Xu","submitted_at":"2026-06-05T20:51:51Z","abstract_excerpt":"LLM judges increasingly turn verdicts into system commitments. Under mixed evidence (claims with both supporting and refuting sources) this is unsafe: when the schema exposes CONFLICTING as the authorized non-directional verdict, returning SUPPORTS/REFUTES is an unauthorized directional commitment, a failure we name Cherry-pick Override (CCO). We define CCO under an explicit task contract and report it with a same-denominator diagnostic protocol paired with matched-coverage bootstrap and an apples-to-apples random-veto null. On AVeriTeC's Conflicting subset (N_C = 150), three-option judges ret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07834","kind":"arxiv","version":1},"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/2606.07834/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":"2606.07834","created_at":"2026-06-09T01:04:53.349055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07834v1","created_at":"2026-06-09T01:04:53.349055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07834","created_at":"2026-06-09T01:04:53.349055+00:00"},{"alias_kind":"pith_short_12","alias_value":"LVSTAX4SKGUP","created_at":"2026-06-09T01:04:53.349055+00:00"},{"alias_kind":"pith_short_16","alias_value":"LVSTAX4SKGUPVI3W","created_at":"2026-06-09T01:04:53.349055+00:00"},{"alias_kind":"pith_short_8","alias_value":"LVSTAX4S","created_at":"2026-06-09T01:04:53.349055+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/LVSTAX4SKGUPVI3WNJDJTFBR5A","json":"https://pith.science/pith/LVSTAX4SKGUPVI3WNJDJTFBR5A.json","graph_json":"https://pith.science/api/pith-number/LVSTAX4SKGUPVI3WNJDJTFBR5A/graph.json","events_json":"https://pith.science/api/pith-number/LVSTAX4SKGUPVI3WNJDJTFBR5A/events.json","paper":"https://pith.science/paper/LVSTAX4S"},"agent_actions":{"view_html":"https://pith.science/pith/LVSTAX4SKGUPVI3WNJDJTFBR5A","download_json":"https://pith.science/pith/LVSTAX4SKGUPVI3WNJDJTFBR5A.json","view_paper":"https://pith.science/paper/LVSTAX4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07834&json=true","fetch_graph":"https://pith.science/api/pith-number/LVSTAX4SKGUPVI3WNJDJTFBR5A/graph.json","fetch_events":"https://pith.science/api/pith-number/LVSTAX4SKGUPVI3WNJDJTFBR5A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LVSTAX4SKGUPVI3WNJDJTFBR5A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LVSTAX4SKGUPVI3WNJDJTFBR5A/action/storage_attestation","attest_author":"https://pith.science/pith/LVSTAX4SKGUPVI3WNJDJTFBR5A/action/author_attestation","sign_citation":"https://pith.science/pith/LVSTAX4SKGUPVI3WNJDJTFBR5A/action/citation_signature","submit_replication":"https://pith.science/pith/LVSTAX4SKGUPVI3WNJDJTFBR5A/action/replication_record"}},"created_at":"2026-06-09T01:04:53.349055+00:00","updated_at":"2026-06-09T01:04:53.349055+00:00"}