{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4KPFEXWV7HE4XP2SP24WHHDMEE","short_pith_number":"pith:4KPFEXWV","schema_version":"1.0","canonical_sha256":"e29e525ed5f9c9cbbf527eb9639c6c21155461a95ca9647831b77330f6285072","source":{"kind":"arxiv","id":"2207.14157","version":1},"attestation_state":"computed","paper":{"title":"A Hazard Analysis Framework for Code Synthesis Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Gretchen Krueger, Heidy Khlaaf, Joshua Achiam, Miles Brundage, Pamela Mishkin","submitted_at":"2022-07-25T20:44:40Z","abstract_excerpt":"Codex, a large language model (LLM) trained on a variety of codebases, exceeds the previous state of the art in its capacity to synthesize and generate code. Although Codex provides a plethora of benefits, models that may generate code on such scale have significant limitations, alignment problems, the potential to be misused, and the possibility to increase the rate of progress in technical fields that may themselves have destabilizing impacts or have misuse potential. Yet such safety impacts are not yet known or remain to be explored. In this paper, we outline a hazard analysis framework con"},"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":"2207.14157","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SE","submitted_at":"2022-07-25T20:44:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e2548f4c6b043c9f63494312dcba68d16e014a69377bde095281e6eea5806030","abstract_canon_sha256":"e3c74475e0b6dfc95b181f7ab3748657e04625b1cf378fbeefe476668c46b7a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:24.890350Z","signature_b64":"ZIzV6uNT0SNHPMdiHpcnUH0IdF/95sFT16B2blDar6f+hwEEW9Tj7+ei0e2TOfepwGYONLJyU/pMsrfs7lHsDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e29e525ed5f9c9cbbf527eb9639c6c21155461a95ca9647831b77330f6285072","last_reissued_at":"2026-07-05T04:44:24.889915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:24.889915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hazard Analysis Framework for Code Synthesis Large Language Models","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Gretchen Krueger, Heidy Khlaaf, Joshua Achiam, Miles Brundage, Pamela Mishkin","submitted_at":"2022-07-25T20:44:40Z","abstract_excerpt":"Codex, a large language model (LLM) trained on a variety of codebases, exceeds the previous state of the art in its capacity to synthesize and generate code. Although Codex provides a plethora of benefits, models that may generate code on such scale have significant limitations, alignment problems, the potential to be misused, and the possibility to increase the rate of progress in technical fields that may themselves have destabilizing impacts or have misuse potential. Yet such safety impacts are not yet known or remain to be explored. In this paper, we outline a hazard analysis framework con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.14157","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/2207.14157/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":"2207.14157","created_at":"2026-07-05T04:44:24.889971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.14157v1","created_at":"2026-07-05T04:44:24.889971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.14157","created_at":"2026-07-05T04:44:24.889971+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KPFEXWV7HE4","created_at":"2026-07-05T04:44:24.889971+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KPFEXWV7HE4XP2S","created_at":"2026-07-05T04:44:24.889971+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KPFEXWV","created_at":"2026-07-05T04:44:24.889971+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.19173","citing_title":"StarCoder 2 and The Stack v2: The Next Generation","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2305.06161","citing_title":"StarCoder: may the source be with you!","ref_index":154,"is_internal_anchor":false},{"citing_arxiv_id":"2305.06161","citing_title":"StarCoder: may the source be with you!","ref_index":169,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4KPFEXWV7HE4XP2SP24WHHDMEE","json":"https://pith.science/pith/4KPFEXWV7HE4XP2SP24WHHDMEE.json","graph_json":"https://pith.science/api/pith-number/4KPFEXWV7HE4XP2SP24WHHDMEE/graph.json","events_json":"https://pith.science/api/pith-number/4KPFEXWV7HE4XP2SP24WHHDMEE/events.json","paper":"https://pith.science/paper/4KPFEXWV"},"agent_actions":{"view_html":"https://pith.science/pith/4KPFEXWV7HE4XP2SP24WHHDMEE","download_json":"https://pith.science/pith/4KPFEXWV7HE4XP2SP24WHHDMEE.json","view_paper":"https://pith.science/paper/4KPFEXWV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.14157&json=true","fetch_graph":"https://pith.science/api/pith-number/4KPFEXWV7HE4XP2SP24WHHDMEE/graph.json","fetch_events":"https://pith.science/api/pith-number/4KPFEXWV7HE4XP2SP24WHHDMEE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KPFEXWV7HE4XP2SP24WHHDMEE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KPFEXWV7HE4XP2SP24WHHDMEE/action/storage_attestation","attest_author":"https://pith.science/pith/4KPFEXWV7HE4XP2SP24WHHDMEE/action/author_attestation","sign_citation":"https://pith.science/pith/4KPFEXWV7HE4XP2SP24WHHDMEE/action/citation_signature","submit_replication":"https://pith.science/pith/4KPFEXWV7HE4XP2SP24WHHDMEE/action/replication_record"}},"created_at":"2026-07-05T04:44:24.889971+00:00","updated_at":"2026-07-05T04:44:24.889971+00:00"}