{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BHWRX4UHIEKPQBGSPQZHPUTZWS","short_pith_number":"pith:BHWRX4UH","schema_version":"1.0","canonical_sha256":"09ed1bf2874114f804d27c3277d279b4ab0b3358009c49d77b7186479cb0f06c","source":{"kind":"arxiv","id":"2505.09576","version":1},"attestation_state":"computed","paper":{"title":"Ethics and Persuasion in Reinforcement Learning from Human Feedback: A Procedural Rhetorical Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Alexi Orchard, Shannon Lodoen","submitted_at":"2025-05-14T17:29:19Z","abstract_excerpt":"Since 2022, versions of generative AI chatbots such as ChatGPT and Claude have been trained using a specialized technique called Reinforcement Learning from Human Feedback (RLHF) to fine-tune language model output using feedback from human annotators. As a result, the integration of RLHF has greatly enhanced the outputs of these large language models (LLMs) and made the interactions and responses appear more \"human-like\" than those of previous versions using only supervised learning. The increasing convergence of human and machine-written text has potentially severe ethical, sociotechnical, an"},"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":"2505.09576","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2025-05-14T17:29:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0bbe0a8f9b4d30f07228815342c2221135f9d2fffc6d8c52c4a4ba475fc87da9","abstract_canon_sha256":"84d5ecabe461b7546f7c74714d89e8ec690f5985b151042de5e5674a7e23e04d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:10.734473Z","signature_b64":"4MFvOKhR9Iwrgl7xHDefOJGcR8pBPGQA+90cahdJLCcoRhIMCQYoEuY0Jhlr3GYM1kFcK0bAq5W0ZrXGckE1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09ed1bf2874114f804d27c3277d279b4ab0b3358009c49d77b7186479cb0f06c","last_reissued_at":"2026-07-05T11:03:10.734036Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:10.734036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ethics and Persuasion in Reinforcement Learning from Human Feedback: A Procedural Rhetorical Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CY","authors_text":"Alexi Orchard, Shannon Lodoen","submitted_at":"2025-05-14T17:29:19Z","abstract_excerpt":"Since 2022, versions of generative AI chatbots such as ChatGPT and Claude have been trained using a specialized technique called Reinforcement Learning from Human Feedback (RLHF) to fine-tune language model output using feedback from human annotators. As a result, the integration of RLHF has greatly enhanced the outputs of these large language models (LLMs) and made the interactions and responses appear more \"human-like\" than those of previous versions using only supervised learning. The increasing convergence of human and machine-written text has potentially severe ethical, sociotechnical, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09576","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/2505.09576/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":"2505.09576","created_at":"2026-07-05T11:03:10.734098+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09576v1","created_at":"2026-07-05T11:03:10.734098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09576","created_at":"2026-07-05T11:03:10.734098+00:00"},{"alias_kind":"pith_short_12","alias_value":"BHWRX4UHIEKP","created_at":"2026-07-05T11:03:10.734098+00:00"},{"alias_kind":"pith_short_16","alias_value":"BHWRX4UHIEKPQBGS","created_at":"2026-07-05T11:03:10.734098+00:00"},{"alias_kind":"pith_short_8","alias_value":"BHWRX4UH","created_at":"2026-07-05T11:03:10.734098+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/BHWRX4UHIEKPQBGSPQZHPUTZWS","json":"https://pith.science/pith/BHWRX4UHIEKPQBGSPQZHPUTZWS.json","graph_json":"https://pith.science/api/pith-number/BHWRX4UHIEKPQBGSPQZHPUTZWS/graph.json","events_json":"https://pith.science/api/pith-number/BHWRX4UHIEKPQBGSPQZHPUTZWS/events.json","paper":"https://pith.science/paper/BHWRX4UH"},"agent_actions":{"view_html":"https://pith.science/pith/BHWRX4UHIEKPQBGSPQZHPUTZWS","download_json":"https://pith.science/pith/BHWRX4UHIEKPQBGSPQZHPUTZWS.json","view_paper":"https://pith.science/paper/BHWRX4UH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09576&json=true","fetch_graph":"https://pith.science/api/pith-number/BHWRX4UHIEKPQBGSPQZHPUTZWS/graph.json","fetch_events":"https://pith.science/api/pith-number/BHWRX4UHIEKPQBGSPQZHPUTZWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BHWRX4UHIEKPQBGSPQZHPUTZWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BHWRX4UHIEKPQBGSPQZHPUTZWS/action/storage_attestation","attest_author":"https://pith.science/pith/BHWRX4UHIEKPQBGSPQZHPUTZWS/action/author_attestation","sign_citation":"https://pith.science/pith/BHWRX4UHIEKPQBGSPQZHPUTZWS/action/citation_signature","submit_replication":"https://pith.science/pith/BHWRX4UHIEKPQBGSPQZHPUTZWS/action/replication_record"}},"created_at":"2026-07-05T11:03:10.734098+00:00","updated_at":"2026-07-05T11:03:10.734098+00:00"}