{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KC7S72DAQ224ONJWQHGEJOEBL4","short_pith_number":"pith:KC7S72DA","canonical_record":{"source":{"id":"2311.14766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-24T07:50:52Z","cross_cats_sorted":["math.ST","stat.ME","stat.TH"],"title_canon_sha256":"d73d99ff89f1e898c20e5433f2315e5e6ac0a22af07abf7dde83fab82d870546","abstract_canon_sha256":"734753553cf5cdfbb6d475927832c24467ba2a43393e66a852dba8f09b6330f2"},"schema_version":"1.0"},"canonical_sha256":"50bf2fe86086b5c7353681cc44b8815f0281a0cf77b581689329c04e58c3f60d","source":{"kind":"arxiv","id":"2311.14766","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.14766","created_at":"2026-07-05T07:16:52Z"},{"alias_kind":"arxiv_version","alias_value":"2311.14766v1","created_at":"2026-07-05T07:16:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14766","created_at":"2026-07-05T07:16:52Z"},{"alias_kind":"pith_short_12","alias_value":"KC7S72DAQ224","created_at":"2026-07-05T07:16:52Z"},{"alias_kind":"pith_short_16","alias_value":"KC7S72DAQ224ONJW","created_at":"2026-07-05T07:16:52Z"},{"alias_kind":"pith_short_8","alias_value":"KC7S72DA","created_at":"2026-07-05T07:16:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KC7S72DAQ224ONJWQHGEJOEBL4","target":"record","payload":{"canonical_record":{"source":{"id":"2311.14766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-24T07:50:52Z","cross_cats_sorted":["math.ST","stat.ME","stat.TH"],"title_canon_sha256":"d73d99ff89f1e898c20e5433f2315e5e6ac0a22af07abf7dde83fab82d870546","abstract_canon_sha256":"734753553cf5cdfbb6d475927832c24467ba2a43393e66a852dba8f09b6330f2"},"schema_version":"1.0"},"canonical_sha256":"50bf2fe86086b5c7353681cc44b8815f0281a0cf77b581689329c04e58c3f60d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:16:52.322698Z","signature_b64":"kgdIX3tMzMLSRbvWIzycIw2EdWxW9KJIKdixnAKA4JEX1xJIxstxgqhXeLOCK/NJWuwwRe5UEdeE2ebHTALVDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50bf2fe86086b5c7353681cc44b8815f0281a0cf77b581689329c04e58c3f60d","last_reissued_at":"2026-07-05T07:16:52.322258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:16:52.322258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.14766","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:16:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"njan2YqPZfUQU9RNvXJSvOKkvaAVmbO0lXB80GtlvWVhPi45U8lHr1FskeDftvJsrUEIua1WdFeMnrG8p5dBAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:13:41.635984Z"},"content_sha256":"f32ee60314c733992925054aa73b393e903809eab4018006c684eb9637fdceb4","schema_version":"1.0","event_id":"sha256:f32ee60314c733992925054aa73b393e903809eab4018006c684eb9637fdceb4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KC7S72DAQ224ONJWQHGEJOEBL4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning from Statistical Feedback: the Journey from AB Testing to ANT Testing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.ST","stat.ME","stat.TH"],"primary_cat":"cs.LG","authors_text":"Feiyang Han, Yanxing Qi, Yimin Wei, Zhaofeng Liu","submitted_at":"2023-11-24T07:50:52Z","abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has played a crucial role in the success of large models such as ChatGPT. RLHF is a reinforcement learning framework which combines human feedback to improve learning effectiveness and performance. However, obtaining preferences feedback manually is quite expensive in commercial applications. Some statistical commercial indicators are usually more valuable and always ignored in RLHF. There exists a gap between commercial target and model training. In our research, we will attempt to fill this gap with statistical business feedback instead of hu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14766","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/2311.14766/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:16:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ux0dXfJ1zh5tSogcEXt/SICScSxPvFnFA/6iYQrymRWKMTuJOR9vCcIT5psN3o7S0PEEhQ6G6pcQtBWdrQT4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:13:41.636516Z"},"content_sha256":"5bccb626204853d9d9bbf8546c200e15762a54fffe972ecb112482e79ead9346","schema_version":"1.0","event_id":"sha256:5bccb626204853d9d9bbf8546c200e15762a54fffe972ecb112482e79ead9346"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KC7S72DAQ224ONJWQHGEJOEBL4/bundle.json","state_url":"https://pith.science/pith/KC7S72DAQ224ONJWQHGEJOEBL4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KC7S72DAQ224ONJWQHGEJOEBL4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T21:13:41Z","links":{"resolver":"https://pith.science/pith/KC7S72DAQ224ONJWQHGEJOEBL4","bundle":"https://pith.science/pith/KC7S72DAQ224ONJWQHGEJOEBL4/bundle.json","state":"https://pith.science/pith/KC7S72DAQ224ONJWQHGEJOEBL4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KC7S72DAQ224ONJWQHGEJOEBL4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KC7S72DAQ224ONJWQHGEJOEBL4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"734753553cf5cdfbb6d475927832c24467ba2a43393e66a852dba8f09b6330f2","cross_cats_sorted":["math.ST","stat.ME","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-24T07:50:52Z","title_canon_sha256":"d73d99ff89f1e898c20e5433f2315e5e6ac0a22af07abf7dde83fab82d870546"},"schema_version":"1.0","source":{"id":"2311.14766","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.14766","created_at":"2026-07-05T07:16:52Z"},{"alias_kind":"arxiv_version","alias_value":"2311.14766v1","created_at":"2026-07-05T07:16:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.14766","created_at":"2026-07-05T07:16:52Z"},{"alias_kind":"pith_short_12","alias_value":"KC7S72DAQ224","created_at":"2026-07-05T07:16:52Z"},{"alias_kind":"pith_short_16","alias_value":"KC7S72DAQ224ONJW","created_at":"2026-07-05T07:16:52Z"},{"alias_kind":"pith_short_8","alias_value":"KC7S72DA","created_at":"2026-07-05T07:16:52Z"}],"graph_snapshots":[{"event_id":"sha256:5bccb626204853d9d9bbf8546c200e15762a54fffe972ecb112482e79ead9346","target":"graph","created_at":"2026-07-05T07:16:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.14766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) has played a crucial role in the success of large models such as ChatGPT. RLHF is a reinforcement learning framework which combines human feedback to improve learning effectiveness and performance. However, obtaining preferences feedback manually is quite expensive in commercial applications. Some statistical commercial indicators are usually more valuable and always ignored in RLHF. There exists a gap between commercial target and model training. In our research, we will attempt to fill this gap with statistical business feedback instead of hu","authors_text":"Feiyang Han, Yanxing Qi, Yimin Wei, Zhaofeng Liu","cross_cats":["math.ST","stat.ME","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-24T07:50:52Z","title":"Reinforcement Learning from Statistical Feedback: the Journey from AB Testing to ANT Testing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.14766","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f32ee60314c733992925054aa73b393e903809eab4018006c684eb9637fdceb4","target":"record","created_at":"2026-07-05T07:16:52Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"734753553cf5cdfbb6d475927832c24467ba2a43393e66a852dba8f09b6330f2","cross_cats_sorted":["math.ST","stat.ME","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-24T07:50:52Z","title_canon_sha256":"d73d99ff89f1e898c20e5433f2315e5e6ac0a22af07abf7dde83fab82d870546"},"schema_version":"1.0","source":{"id":"2311.14766","kind":"arxiv","version":1}},"canonical_sha256":"50bf2fe86086b5c7353681cc44b8815f0281a0cf77b581689329c04e58c3f60d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50bf2fe86086b5c7353681cc44b8815f0281a0cf77b581689329c04e58c3f60d","first_computed_at":"2026-07-05T07:16:52.322258Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:16:52.322258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kgdIX3tMzMLSRbvWIzycIw2EdWxW9KJIKdixnAKA4JEX1xJIxstxgqhXeLOCK/NJWuwwRe5UEdeE2ebHTALVDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:16:52.322698Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.14766","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f32ee60314c733992925054aa73b393e903809eab4018006c684eb9637fdceb4","sha256:5bccb626204853d9d9bbf8546c200e15762a54fffe972ecb112482e79ead9346"],"state_sha256":"158260d8e000146ce559124ee9dd3526cf0bfe3adcbfb211a1b2d4df17ae7011"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vGwCEelJcfrZNfxpy42JbNKo4WptgEQ9KnNg3pxy+EjnyvnMQtPOWow8iPJWl22kmAY/0yydOvxOTgHUCL+FBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T21:13:41.641667Z","bundle_sha256":"8a98622e8a1e010d819c56da387cd31cfa04f94a07af5eaf3d771d185f295ffd"}}