{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SYV4NUYLCVHITW2ZG3ZQNI7NFI","short_pith_number":"pith:SYV4NUYL","schema_version":"1.0","canonical_sha256":"962bc6d30b154e89db5936f306a3ed2a19feba010264c9aeae44e4d06c242bb3","source":{"kind":"arxiv","id":"2408.01452","version":1},"attestation_state":"computed","paper":{"title":"Building a Domain-specific Guardrail Model in Production","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CY","authors_text":"Aditya Vempaty, Ashish Jagmohan, Ayan Kumar Bhowmick, Hema Maheshwari, Latha Ramanan, Mohammad Niknazar, Nick Haber, Paul V Haley, Prasenjit Dey, Robert Smith, Sang T. Truong, Sanmi Koyejo, Sharad Sundararajan, Shom Ponoth, Yedendra Shrinivasan","submitted_at":"2024-07-24T15:53:29Z","abstract_excerpt":"Generative AI holds the promise of enabling a range of sought-after capabilities and revolutionizing workflows in various consumer and enterprise verticals. However, putting a model in production involves much more than just generating an output. It involves ensuring the model is reliable, safe, performant and also adheres to the policy of operation in a particular domain. Guardrails as a necessity for models has evolved around the need to enforce appropriate behavior of models, especially when they are in production. In this paper, we use education as a use case, given its stringent requireme"},"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":"2408.01452","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2024-07-24T15:53:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3d029729f0df84869c33afea426a48ade9c3a0cff7c2967dbc09a021e41ac793","abstract_canon_sha256":"f1431f53c274b3c3059b358c87487dead7ff36a6eeb9c8adf4b70d3cb2669431"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:58.024174Z","signature_b64":"0rq3J0plQAOSj6IfXiMRUNSpWRrUH6EeHtS31OqmuV/iFEHmw3T37O9BvaqsqYW6MfRVRZh7slXaLB84hBEvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"962bc6d30b154e89db5936f306a3ed2a19feba010264c9aeae44e4d06c242bb3","last_reissued_at":"2026-07-05T08:51:58.023776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:58.023776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Building a Domain-specific Guardrail Model in Production","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CY","authors_text":"Aditya Vempaty, Ashish Jagmohan, Ayan Kumar Bhowmick, Hema Maheshwari, Latha Ramanan, Mohammad Niknazar, Nick Haber, Paul V Haley, Prasenjit Dey, Robert Smith, Sang T. Truong, Sanmi Koyejo, Sharad Sundararajan, Shom Ponoth, Yedendra Shrinivasan","submitted_at":"2024-07-24T15:53:29Z","abstract_excerpt":"Generative AI holds the promise of enabling a range of sought-after capabilities and revolutionizing workflows in various consumer and enterprise verticals. However, putting a model in production involves much more than just generating an output. It involves ensuring the model is reliable, safe, performant and also adheres to the policy of operation in a particular domain. Guardrails as a necessity for models has evolved around the need to enforce appropriate behavior of models, especially when they are in production. In this paper, we use education as a use case, given its stringent requireme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.01452","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/2408.01452/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":"2408.01452","created_at":"2026-07-05T08:51:58.023834+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.01452v1","created_at":"2026-07-05T08:51:58.023834+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.01452","created_at":"2026-07-05T08:51:58.023834+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYV4NUYLCVHI","created_at":"2026-07-05T08:51:58.023834+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYV4NUYLCVHITW2Z","created_at":"2026-07-05T08:51:58.023834+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYV4NUYL","created_at":"2026-07-05T08:51:58.023834+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19940","citing_title":"Robotics-Inspired Guardrails for Foundation Models in Socially Sensitive Domains","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17329","citing_title":"LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SYV4NUYLCVHITW2ZG3ZQNI7NFI","json":"https://pith.science/pith/SYV4NUYLCVHITW2ZG3ZQNI7NFI.json","graph_json":"https://pith.science/api/pith-number/SYV4NUYLCVHITW2ZG3ZQNI7NFI/graph.json","events_json":"https://pith.science/api/pith-number/SYV4NUYLCVHITW2ZG3ZQNI7NFI/events.json","paper":"https://pith.science/paper/SYV4NUYL"},"agent_actions":{"view_html":"https://pith.science/pith/SYV4NUYLCVHITW2ZG3ZQNI7NFI","download_json":"https://pith.science/pith/SYV4NUYLCVHITW2ZG3ZQNI7NFI.json","view_paper":"https://pith.science/paper/SYV4NUYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.01452&json=true","fetch_graph":"https://pith.science/api/pith-number/SYV4NUYLCVHITW2ZG3ZQNI7NFI/graph.json","fetch_events":"https://pith.science/api/pith-number/SYV4NUYLCVHITW2ZG3ZQNI7NFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYV4NUYLCVHITW2ZG3ZQNI7NFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYV4NUYLCVHITW2ZG3ZQNI7NFI/action/storage_attestation","attest_author":"https://pith.science/pith/SYV4NUYLCVHITW2ZG3ZQNI7NFI/action/author_attestation","sign_citation":"https://pith.science/pith/SYV4NUYLCVHITW2ZG3ZQNI7NFI/action/citation_signature","submit_replication":"https://pith.science/pith/SYV4NUYLCVHITW2ZG3ZQNI7NFI/action/replication_record"}},"created_at":"2026-07-05T08:51:58.023834+00:00","updated_at":"2026-07-05T08:51:58.023834+00:00"}