{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JWNWGB7N25ZL6PV7GXBLPMT55T","short_pith_number":"pith:JWNWGB7N","schema_version":"1.0","canonical_sha256":"4d9b6307edd772bf3ebf35c2b7b27decd2385ced961c8524142b102dfe1a0bcf","source":{"kind":"arxiv","id":"2606.04057","version":1},"attestation_state":"computed","paper":{"title":"The Invisible Lottery: How Subtle Cues Steer Algorithm Choice in LLM Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Akanksha Narula, Laurent Bindschaedler, Mofasshara Binte Rafique","submitted_at":"2026-06-02T11:17:28Z","abstract_excerpt":"Large language models (LLMs) now generate substantial production code, often for tasks with multiple valid algorithmic solutions. Incidental prompt cues, meaning contextual words or metadata outside the task specification, can steer which algorithm the model selects, even when all outputs pass the same tests. Prompt sensitivity is well studied as a tool to improve output quality. Here, output policy means algorithm choice under fixed correctness. We define algorithm steering as cue-induced shifts in algorithm-family distributions and run 46,535 controlled experiments across 11 tasks, 19 cue ty"},"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":"2606.04057","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-02T11:17:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f5eac70d1ef5eba2422efded5b9e01835b2e079baf68bd840ab50ac5989b4e86","abstract_canon_sha256":"43da6e1595b4698d13eb32b2093b6c5f00525c3ebcc759f36eb6d0d2d013d68a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T00:06:45.407464Z","signature_b64":"4BL8kjuIOiKIGL5mpgDlBsRB6jGq0MQLZZ1iyFYG5WsrEdHo/5adec8/fhbPK5o/9YJxa4n966QnBlmMN8muAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d9b6307edd772bf3ebf35c2b7b27decd2385ced961c8524142b102dfe1a0bcf","last_reissued_at":"2026-06-04T00:06:45.407051Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T00:06:45.407051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Invisible Lottery: How Subtle Cues Steer Algorithm Choice in LLM Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Akanksha Narula, Laurent Bindschaedler, Mofasshara Binte Rafique","submitted_at":"2026-06-02T11:17:28Z","abstract_excerpt":"Large language models (LLMs) now generate substantial production code, often for tasks with multiple valid algorithmic solutions. Incidental prompt cues, meaning contextual words or metadata outside the task specification, can steer which algorithm the model selects, even when all outputs pass the same tests. Prompt sensitivity is well studied as a tool to improve output quality. Here, output policy means algorithm choice under fixed correctness. We define algorithm steering as cue-induced shifts in algorithm-family distributions and run 46,535 controlled experiments across 11 tasks, 19 cue ty"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04057","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/2606.04057/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":"2606.04057","created_at":"2026-06-04T00:06:45.407108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04057v1","created_at":"2026-06-04T00:06:45.407108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04057","created_at":"2026-06-04T00:06:45.407108+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWNWGB7N25ZL","created_at":"2026-06-04T00:06:45.407108+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWNWGB7N25ZL6PV7","created_at":"2026-06-04T00:06:45.407108+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWNWGB7N","created_at":"2026-06-04T00:06:45.407108+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/JWNWGB7N25ZL6PV7GXBLPMT55T","json":"https://pith.science/pith/JWNWGB7N25ZL6PV7GXBLPMT55T.json","graph_json":"https://pith.science/api/pith-number/JWNWGB7N25ZL6PV7GXBLPMT55T/graph.json","events_json":"https://pith.science/api/pith-number/JWNWGB7N25ZL6PV7GXBLPMT55T/events.json","paper":"https://pith.science/paper/JWNWGB7N"},"agent_actions":{"view_html":"https://pith.science/pith/JWNWGB7N25ZL6PV7GXBLPMT55T","download_json":"https://pith.science/pith/JWNWGB7N25ZL6PV7GXBLPMT55T.json","view_paper":"https://pith.science/paper/JWNWGB7N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04057&json=true","fetch_graph":"https://pith.science/api/pith-number/JWNWGB7N25ZL6PV7GXBLPMT55T/graph.json","fetch_events":"https://pith.science/api/pith-number/JWNWGB7N25ZL6PV7GXBLPMT55T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWNWGB7N25ZL6PV7GXBLPMT55T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWNWGB7N25ZL6PV7GXBLPMT55T/action/storage_attestation","attest_author":"https://pith.science/pith/JWNWGB7N25ZL6PV7GXBLPMT55T/action/author_attestation","sign_citation":"https://pith.science/pith/JWNWGB7N25ZL6PV7GXBLPMT55T/action/citation_signature","submit_replication":"https://pith.science/pith/JWNWGB7N25ZL6PV7GXBLPMT55T/action/replication_record"}},"created_at":"2026-06-04T00:06:45.407108+00:00","updated_at":"2026-06-04T00:06:45.407108+00:00"}