{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YT3F6NDZ2WMTWJMQOL7N6YZ372","short_pith_number":"pith:YT3F6NDZ","schema_version":"1.0","canonical_sha256":"c4f65f3479d5993b259072fedf633bfebf24d77525a23ab1a6f7c652fc674e3b","source":{"kind":"arxiv","id":"2401.10899","version":1},"attestation_state":"computed","paper":{"title":"Concrete Problems in AI Safety, Revisited","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Inioluwa Deborah Raji, Roel Dobbe","submitted_at":"2023-12-18T23:38:05Z","abstract_excerpt":"As AI systems proliferate in society, the AI community is increasingly preoccupied with the concept of AI Safety, namely the prevention of failures due to accidents that arise from an unanticipated departure of a system's behavior from designer intent in AI deployment. We demonstrate through an analysis of real world cases of such incidents that although current vocabulary captures a range of the encountered issues of AI deployment, an expanded socio-technical framing will be required for a more complete understanding of how AI systems and implemented safety mechanisms fail and succeed in real"},"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":"2401.10899","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2023-12-18T23:38:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c01018264562f7fbeb99ac8053810a4050ffaa367e0d2dc423718686fc6d27c0","abstract_canon_sha256":"ba924bb22c9af3f9e746d28cb4a8b12131f590a413c409f2094ca59ba1cde24e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:42.740660Z","signature_b64":"TLpSpYIuAaepZjNIf6X7jvlRzIQMJo2fDwR5/tTxNhjTozYZqhO6qKb9WXMhYZUaYZQbuT/tinH2gamstPC0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4f65f3479d5993b259072fedf633bfebf24d77525a23ab1a6f7c652fc674e3b","last_reissued_at":"2026-07-05T07:35:42.740209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:42.740209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Concrete Problems in AI Safety, Revisited","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Inioluwa Deborah Raji, Roel Dobbe","submitted_at":"2023-12-18T23:38:05Z","abstract_excerpt":"As AI systems proliferate in society, the AI community is increasingly preoccupied with the concept of AI Safety, namely the prevention of failures due to accidents that arise from an unanticipated departure of a system's behavior from designer intent in AI deployment. We demonstrate through an analysis of real world cases of such incidents that although current vocabulary captures a range of the encountered issues of AI deployment, an expanded socio-technical framing will be required for a more complete understanding of how AI systems and implemented safety mechanisms fail and succeed in real"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.10899","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/2401.10899/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":"2401.10899","created_at":"2026-07-05T07:35:42.740265+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.10899v1","created_at":"2026-07-05T07:35:42.740265+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.10899","created_at":"2026-07-05T07:35:42.740265+00:00"},{"alias_kind":"pith_short_12","alias_value":"YT3F6NDZ2WMT","created_at":"2026-07-05T07:35:42.740265+00:00"},{"alias_kind":"pith_short_16","alias_value":"YT3F6NDZ2WMTWJMQ","created_at":"2026-07-05T07:35:42.740265+00:00"},{"alias_kind":"pith_short_8","alias_value":"YT3F6NDZ","created_at":"2026-07-05T07:35:42.740265+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09711","citing_title":"Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization","ref_index":120,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17871","citing_title":"StepGuard: Guarding Web Navigation via Single-Step Calibration","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2601.06033","citing_title":"How Generative AI Empowers Attackers and Defenders Across the Trust & Safety Landscape","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12693","citing_title":"Risk-Calibrated Learning: Minimizing Fatal Errors in Medical AI","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20805","citing_title":"Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02544","citing_title":"Improving Model Safety by Targeted Error Correction","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YT3F6NDZ2WMTWJMQOL7N6YZ372","json":"https://pith.science/pith/YT3F6NDZ2WMTWJMQOL7N6YZ372.json","graph_json":"https://pith.science/api/pith-number/YT3F6NDZ2WMTWJMQOL7N6YZ372/graph.json","events_json":"https://pith.science/api/pith-number/YT3F6NDZ2WMTWJMQOL7N6YZ372/events.json","paper":"https://pith.science/paper/YT3F6NDZ"},"agent_actions":{"view_html":"https://pith.science/pith/YT3F6NDZ2WMTWJMQOL7N6YZ372","download_json":"https://pith.science/pith/YT3F6NDZ2WMTWJMQOL7N6YZ372.json","view_paper":"https://pith.science/paper/YT3F6NDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.10899&json=true","fetch_graph":"https://pith.science/api/pith-number/YT3F6NDZ2WMTWJMQOL7N6YZ372/graph.json","fetch_events":"https://pith.science/api/pith-number/YT3F6NDZ2WMTWJMQOL7N6YZ372/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YT3F6NDZ2WMTWJMQOL7N6YZ372/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YT3F6NDZ2WMTWJMQOL7N6YZ372/action/storage_attestation","attest_author":"https://pith.science/pith/YT3F6NDZ2WMTWJMQOL7N6YZ372/action/author_attestation","sign_citation":"https://pith.science/pith/YT3F6NDZ2WMTWJMQOL7N6YZ372/action/citation_signature","submit_replication":"https://pith.science/pith/YT3F6NDZ2WMTWJMQOL7N6YZ372/action/replication_record"}},"created_at":"2026-07-05T07:35:42.740265+00:00","updated_at":"2026-07-05T07:35:42.740265+00:00"}