{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DR23RK6ZDUW5UE5HJ542BCWNKM","short_pith_number":"pith:DR23RK6Z","schema_version":"1.0","canonical_sha256":"1c75b8abd91d2dda13a74f79a08acd532976469a8da3d2ba3884cc499d0d597d","source":{"kind":"arxiv","id":"2502.10450","version":2},"attestation_state":"computed","paper":{"title":"Trustworthy AI: Safety, Bias, and Privacy -- A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Jianwei Li, Jung-Eun Kim, Varun Mulchandani, Xingli Fang","submitted_at":"2025-02-11T20:08:42Z","abstract_excerpt":"The capabilities of artificial intelligence systems have been advancing to a great extent, but these systems still struggle with failure modes, vulnerabilities, and biases. In this paper, we study the current state of the field, and present promising insights and perspectives regarding concerns that challenge the trustworthiness of AI models. In particular, this paper investigates the issues regarding three thrusts: safety, privacy, and bias, which hurt models' trustworthiness. For safety, we discuss safety alignment in the context of large language models, preventing them from generating toxi"},"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":"2502.10450","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2025-02-11T20:08:42Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"f9414e242fc071294e4956bf9f2c5ffbc9da73e6c2a9f485ffeb7fa7c6f96991","abstract_canon_sha256":"cf2d2663820747c0fb03f5dd3c5949fd5ee3844447d79244d616e7c04474b371"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:51.407575Z","signature_b64":"w0648Cbk8/rI0P1ie45jP4nxsEWjIvhQkLxW3bEt8H7Z2iOuASbm3QFxlZ6UDtqel99Nn500Sav/mcHLDPO3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c75b8abd91d2dda13a74f79a08acd532976469a8da3d2ba3884cc499d0d597d","last_reissued_at":"2026-07-05T11:19:51.406933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:51.406933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trustworthy AI: Safety, Bias, and Privacy -- A Survey","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Jianwei Li, Jung-Eun Kim, Varun Mulchandani, Xingli Fang","submitted_at":"2025-02-11T20:08:42Z","abstract_excerpt":"The capabilities of artificial intelligence systems have been advancing to a great extent, but these systems still struggle with failure modes, vulnerabilities, and biases. In this paper, we study the current state of the field, and present promising insights and perspectives regarding concerns that challenge the trustworthiness of AI models. In particular, this paper investigates the issues regarding three thrusts: safety, privacy, and bias, which hurt models' trustworthiness. For safety, we discuss safety alignment in the context of large language models, preventing them from generating toxi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10450","kind":"arxiv","version":2},"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/2502.10450/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":"2502.10450","created_at":"2026-07-05T11:19:51.407014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10450v2","created_at":"2026-07-05T11:19:51.407014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10450","created_at":"2026-07-05T11:19:51.407014+00:00"},{"alias_kind":"pith_short_12","alias_value":"DR23RK6ZDUW5","created_at":"2026-07-05T11:19:51.407014+00:00"},{"alias_kind":"pith_short_16","alias_value":"DR23RK6ZDUW5UE5H","created_at":"2026-07-05T11:19:51.407014+00:00"},{"alias_kind":"pith_short_8","alias_value":"DR23RK6Z","created_at":"2026-07-05T11:19:51.407014+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/DR23RK6ZDUW5UE5HJ542BCWNKM","json":"https://pith.science/pith/DR23RK6ZDUW5UE5HJ542BCWNKM.json","graph_json":"https://pith.science/api/pith-number/DR23RK6ZDUW5UE5HJ542BCWNKM/graph.json","events_json":"https://pith.science/api/pith-number/DR23RK6ZDUW5UE5HJ542BCWNKM/events.json","paper":"https://pith.science/paper/DR23RK6Z"},"agent_actions":{"view_html":"https://pith.science/pith/DR23RK6ZDUW5UE5HJ542BCWNKM","download_json":"https://pith.science/pith/DR23RK6ZDUW5UE5HJ542BCWNKM.json","view_paper":"https://pith.science/paper/DR23RK6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10450&json=true","fetch_graph":"https://pith.science/api/pith-number/DR23RK6ZDUW5UE5HJ542BCWNKM/graph.json","fetch_events":"https://pith.science/api/pith-number/DR23RK6ZDUW5UE5HJ542BCWNKM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DR23RK6ZDUW5UE5HJ542BCWNKM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DR23RK6ZDUW5UE5HJ542BCWNKM/action/storage_attestation","attest_author":"https://pith.science/pith/DR23RK6ZDUW5UE5HJ542BCWNKM/action/author_attestation","sign_citation":"https://pith.science/pith/DR23RK6ZDUW5UE5HJ542BCWNKM/action/citation_signature","submit_replication":"https://pith.science/pith/DR23RK6ZDUW5UE5HJ542BCWNKM/action/replication_record"}},"created_at":"2026-07-05T11:19:51.407014+00:00","updated_at":"2026-07-05T11:19:51.407014+00:00"}