{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RPBMOL5R7GFLN543REM3VRBJ63","short_pith_number":"pith:RPBMOL5R","schema_version":"1.0","canonical_sha256":"8bc2c72fb1f98ab6f79b8919bac429f6c6d6eb569ee031898654f975160b24ba","source":{"kind":"arxiv","id":"2303.02891","version":1},"attestation_state":"computed","paper":{"title":"Perspectives on the Social Impacts of Reinforcement Learning with Human Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CY","authors_text":"Gabrielle Kaili-May Liu","submitted_at":"2023-03-06T04:49:38Z","abstract_excerpt":"Is it possible for machines to think like humans? And if it is, how should we go about teaching them to do so? As early as 1950, Alan Turing stated that we ought to teach machines in the way of teaching a child. Reinforcement learning with human feedback (RLHF) has emerged as a strong candidate toward allowing agents to learn from human feedback in a naturalistic manner. RLHF is distinct from traditional reinforcement learning as it provides feedback from a human teacher in addition to a reward signal. It has been catapulted into public view by multiple high-profile AI applications, including "},"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":"2303.02891","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2023-03-06T04:49:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"450175c911332fb03ef68f03a7f3df59ce02652a86f11261811b2bb74da429ff","abstract_canon_sha256":"9b34b3f2f58843f22d9833d1578b4051f123f55b4bb65ea943692ae88b549f7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:16.697948Z","signature_b64":"9oS9yJ2Xu+Ly5JI79sBAdZGn7jzbB274xRDmZfrE3FyRfdMm8s44HhV7StBs5tNmRjbLMdiOxVZNZWorjGe2Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bc2c72fb1f98ab6f79b8919bac429f6c6d6eb569ee031898654f975160b24ba","last_reissued_at":"2026-07-05T05:48:16.697552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:16.697552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perspectives on the Social Impacts of Reinforcement Learning with Human Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CY","authors_text":"Gabrielle Kaili-May Liu","submitted_at":"2023-03-06T04:49:38Z","abstract_excerpt":"Is it possible for machines to think like humans? And if it is, how should we go about teaching them to do so? As early as 1950, Alan Turing stated that we ought to teach machines in the way of teaching a child. Reinforcement learning with human feedback (RLHF) has emerged as a strong candidate toward allowing agents to learn from human feedback in a naturalistic manner. RLHF is distinct from traditional reinforcement learning as it provides feedback from a human teacher in addition to a reward signal. It has been catapulted into public view by multiple high-profile AI applications, including "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02891","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/2303.02891/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":"2303.02891","created_at":"2026-07-05T05:48:16.697613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.02891v1","created_at":"2026-07-05T05:48:16.697613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02891","created_at":"2026-07-05T05:48:16.697613+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPBMOL5R7GFL","created_at":"2026-07-05T05:48:16.697613+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPBMOL5R7GFLN543","created_at":"2026-07-05T05:48:16.697613+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPBMOL5R","created_at":"2026-07-05T05:48:16.697613+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20331","citing_title":"Surrogate modeling for interpreting black-box LLMs in medical predictions","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPBMOL5R7GFLN543REM3VRBJ63","json":"https://pith.science/pith/RPBMOL5R7GFLN543REM3VRBJ63.json","graph_json":"https://pith.science/api/pith-number/RPBMOL5R7GFLN543REM3VRBJ63/graph.json","events_json":"https://pith.science/api/pith-number/RPBMOL5R7GFLN543REM3VRBJ63/events.json","paper":"https://pith.science/paper/RPBMOL5R"},"agent_actions":{"view_html":"https://pith.science/pith/RPBMOL5R7GFLN543REM3VRBJ63","download_json":"https://pith.science/pith/RPBMOL5R7GFLN543REM3VRBJ63.json","view_paper":"https://pith.science/paper/RPBMOL5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.02891&json=true","fetch_graph":"https://pith.science/api/pith-number/RPBMOL5R7GFLN543REM3VRBJ63/graph.json","fetch_events":"https://pith.science/api/pith-number/RPBMOL5R7GFLN543REM3VRBJ63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPBMOL5R7GFLN543REM3VRBJ63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPBMOL5R7GFLN543REM3VRBJ63/action/storage_attestation","attest_author":"https://pith.science/pith/RPBMOL5R7GFLN543REM3VRBJ63/action/author_attestation","sign_citation":"https://pith.science/pith/RPBMOL5R7GFLN543REM3VRBJ63/action/citation_signature","submit_replication":"https://pith.science/pith/RPBMOL5R7GFLN543REM3VRBJ63/action/replication_record"}},"created_at":"2026-07-05T05:48:16.697613+00:00","updated_at":"2026-07-05T05:48:16.697613+00:00"}