{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4YWAW2EV45KXDMK3CHFVHXIIGN","short_pith_number":"pith:4YWAW2EV","schema_version":"1.0","canonical_sha256":"e62c0b6895e75571b15b11cb53dd083365ae8fc2bd0edbfb1991b6eedbf8e95f","source":{"kind":"arxiv","id":"2311.02801","version":1},"attestation_state":"computed","paper":{"title":"On the Intersection of Self-Correction and Trust in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Satyapriya Krishna","submitted_at":"2023-11-06T00:04:12Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities in performing complex cognitive tasks. However, their complexity and lack of transparency have raised several trustworthiness concerns, including the propagation of misinformation and toxicity. Recent research has explored the self-correction capabilities of LLMs to enhance their performance. In this work, we investigate whether these self-correction capabilities can be harnessed to improve the trustworthiness of LLMs. We conduct experiments focusing on two key aspects of trustworthiness: truthfulness and toxicity. Our find"},"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":"2311.02801","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-06T00:04:12Z","cross_cats_sorted":[],"title_canon_sha256":"8200b6c17b9ad72b348949500da67189ef023ce85f9604cc887dd5326db2bf3d","abstract_canon_sha256":"bd17457192d0fbdac4c24425153bd4e3993bf3d43f8b7e5d81951d971c794e27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:09:18.270898Z","signature_b64":"bKHFdL4D+5zR1Q7qN34jq65mjuOYhDxRg+XxvGDo5ww8q4SrGcIuG9Vo7dU8QALc8Ac8Ww45jnKT06918dX+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e62c0b6895e75571b15b11cb53dd083365ae8fc2bd0edbfb1991b6eedbf8e95f","last_reissued_at":"2026-07-05T07:09:18.270481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:09:18.270481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Intersection of Self-Correction and Trust in Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Satyapriya Krishna","submitted_at":"2023-11-06T00:04:12Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable capabilities in performing complex cognitive tasks. However, their complexity and lack of transparency have raised several trustworthiness concerns, including the propagation of misinformation and toxicity. Recent research has explored the self-correction capabilities of LLMs to enhance their performance. In this work, we investigate whether these self-correction capabilities can be harnessed to improve the trustworthiness of LLMs. We conduct experiments focusing on two key aspects of trustworthiness: truthfulness and toxicity. Our find"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02801","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/2311.02801/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":"2311.02801","created_at":"2026-07-05T07:09:18.270545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.02801v1","created_at":"2026-07-05T07:09:18.270545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02801","created_at":"2026-07-05T07:09:18.270545+00:00"},{"alias_kind":"pith_short_12","alias_value":"4YWAW2EV45KX","created_at":"2026-07-05T07:09:18.270545+00:00"},{"alias_kind":"pith_short_16","alias_value":"4YWAW2EV45KXDMK3","created_at":"2026-07-05T07:09:18.270545+00:00"},{"alias_kind":"pith_short_8","alias_value":"4YWAW2EV","created_at":"2026-07-05T07:09:18.270545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.16120","citing_title":"A Data-Centric Approach for Safe and Secure Large Language Models against Threatening and Toxic Content","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4YWAW2EV45KXDMK3CHFVHXIIGN","json":"https://pith.science/pith/4YWAW2EV45KXDMK3CHFVHXIIGN.json","graph_json":"https://pith.science/api/pith-number/4YWAW2EV45KXDMK3CHFVHXIIGN/graph.json","events_json":"https://pith.science/api/pith-number/4YWAW2EV45KXDMK3CHFVHXIIGN/events.json","paper":"https://pith.science/paper/4YWAW2EV"},"agent_actions":{"view_html":"https://pith.science/pith/4YWAW2EV45KXDMK3CHFVHXIIGN","download_json":"https://pith.science/pith/4YWAW2EV45KXDMK3CHFVHXIIGN.json","view_paper":"https://pith.science/paper/4YWAW2EV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.02801&json=true","fetch_graph":"https://pith.science/api/pith-number/4YWAW2EV45KXDMK3CHFVHXIIGN/graph.json","fetch_events":"https://pith.science/api/pith-number/4YWAW2EV45KXDMK3CHFVHXIIGN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4YWAW2EV45KXDMK3CHFVHXIIGN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4YWAW2EV45KXDMK3CHFVHXIIGN/action/storage_attestation","attest_author":"https://pith.science/pith/4YWAW2EV45KXDMK3CHFVHXIIGN/action/author_attestation","sign_citation":"https://pith.science/pith/4YWAW2EV45KXDMK3CHFVHXIIGN/action/citation_signature","submit_replication":"https://pith.science/pith/4YWAW2EV45KXDMK3CHFVHXIIGN/action/replication_record"}},"created_at":"2026-07-05T07:09:18.270545+00:00","updated_at":"2026-07-05T07:09:18.270545+00:00"}