{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Z455GIPQASOY2NT23CKDPL5DW3","short_pith_number":"pith:Z455GIPQ","schema_version":"1.0","canonical_sha256":"cf3bd321f0049d8d367ad89437afa3b6c2397b6f767b46387204d392263a3098","source":{"kind":"arxiv","id":"2605.15665","version":1},"attestation_state":"computed","paper":{"title":"PRISM: Prompt Reliability via Iterative Simulation and Monitoring for Enterprise Conversational AI","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jahnavi Gundakaram, Keshava Chaitanya","submitted_at":"2026-05-15T06:43:07Z","abstract_excerpt":"Deploying large language model (LLM)-driven conversational agents in enterprise settings requires prompts that are simultaneously correct at launch and resilient to the non-deterministic behavioral drift that characterizes production LLM deployments. Existing prompt optimization frameworks address prompt quality as a one-time compile-time problem, leaving open the equally critical question of how to detect and repair prompt regressions caused by silent LLM behavior changes over time. We present PRISM (Prompt Reliability via Iterative Simulation and Monitoring), a closed-loop framework that tre"},"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":"2605.15665","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T06:43:07Z","cross_cats_sorted":[],"title_canon_sha256":"b692280c77b4a42a4f49ab4203bd65e593bf57ea9125797cc149a10514f4d892","abstract_canon_sha256":"7f96e816f54263eee48044f72fb7626d71cb5f2d187887df347b23014dda1f65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:11.104790Z","signature_b64":"EcHEouCoLj0GzrL1gJaN6WW5YoGXzzolYgw2Mm8gu7q8YuamA77gd2KAZywZYOjG9KtTHgXTDl2fAIkE1sgHBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf3bd321f0049d8d367ad89437afa3b6c2397b6f767b46387204d392263a3098","last_reissued_at":"2026-05-20T00:01:11.103904Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:11.103904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PRISM: Prompt Reliability via Iterative Simulation and Monitoring for Enterprise Conversational AI","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jahnavi Gundakaram, Keshava Chaitanya","submitted_at":"2026-05-15T06:43:07Z","abstract_excerpt":"Deploying large language model (LLM)-driven conversational agents in enterprise settings requires prompts that are simultaneously correct at launch and resilient to the non-deterministic behavioral drift that characterizes production LLM deployments. Existing prompt optimization frameworks address prompt quality as a one-time compile-time problem, leaving open the equally critical question of how to detect and repair prompt regressions caused by silent LLM behavior changes over time. We present PRISM (Prompt Reliability via Iterative Simulation and Monitoring), a closed-loop framework that tre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15665","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/2605.15665/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:34.506539Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:56.069984Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ef1d91cc507a0ce5a9e856d4d3e89c7644e44d20111b1181e53a3e94963ea3e0"},"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":"2605.15665","created_at":"2026-05-20T00:01:11.104054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15665v1","created_at":"2026-05-20T00:01:11.104054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15665","created_at":"2026-05-20T00:01:11.104054+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z455GIPQASOY","created_at":"2026-05-20T00:01:11.104054+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z455GIPQASOY2NT2","created_at":"2026-05-20T00:01:11.104054+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z455GIPQ","created_at":"2026-05-20T00:01:11.104054+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/Z455GIPQASOY2NT23CKDPL5DW3","json":"https://pith.science/pith/Z455GIPQASOY2NT23CKDPL5DW3.json","graph_json":"https://pith.science/api/pith-number/Z455GIPQASOY2NT23CKDPL5DW3/graph.json","events_json":"https://pith.science/api/pith-number/Z455GIPQASOY2NT23CKDPL5DW3/events.json","paper":"https://pith.science/paper/Z455GIPQ"},"agent_actions":{"view_html":"https://pith.science/pith/Z455GIPQASOY2NT23CKDPL5DW3","download_json":"https://pith.science/pith/Z455GIPQASOY2NT23CKDPL5DW3.json","view_paper":"https://pith.science/paper/Z455GIPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15665&json=true","fetch_graph":"https://pith.science/api/pith-number/Z455GIPQASOY2NT23CKDPL5DW3/graph.json","fetch_events":"https://pith.science/api/pith-number/Z455GIPQASOY2NT23CKDPL5DW3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z455GIPQASOY2NT23CKDPL5DW3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z455GIPQASOY2NT23CKDPL5DW3/action/storage_attestation","attest_author":"https://pith.science/pith/Z455GIPQASOY2NT23CKDPL5DW3/action/author_attestation","sign_citation":"https://pith.science/pith/Z455GIPQASOY2NT23CKDPL5DW3/action/citation_signature","submit_replication":"https://pith.science/pith/Z455GIPQASOY2NT23CKDPL5DW3/action/replication_record"}},"created_at":"2026-05-20T00:01:11.104054+00:00","updated_at":"2026-05-20T00:01:11.104054+00:00"}