{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:L35O5XZNRQX27XPGYRG3XFSU25","short_pith_number":"pith:L35O5XZN","canonical_record":{"source":{"id":"2410.02504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-03T14:09:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"596627a9f5029e1a483ff50cbfaa8023bd02a50a694a05bf09636f77ff18738d","abstract_canon_sha256":"e36326ce0e10a31931f2290983b980c5511bff49166f63ae6cd3aacbe554fe95"},"schema_version":"1.0"},"canonical_sha256":"5efaeedf2d8c2fafdde6c44dbb9654d77006511faa231d4ee83ab156fcb93909","source":{"kind":"arxiv","id":"2410.02504","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02504","created_at":"2026-07-05T09:55:34Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02504v2","created_at":"2026-07-05T09:55:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02504","created_at":"2026-07-05T09:55:34Z"},{"alias_kind":"pith_short_12","alias_value":"L35O5XZNRQX2","created_at":"2026-07-05T09:55:34Z"},{"alias_kind":"pith_short_16","alias_value":"L35O5XZNRQX27XPG","created_at":"2026-07-05T09:55:34Z"},{"alias_kind":"pith_short_8","alias_value":"L35O5XZN","created_at":"2026-07-05T09:55:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:L35O5XZNRQX27XPGYRG3XFSU25","target":"record","payload":{"canonical_record":{"source":{"id":"2410.02504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-03T14:09:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"596627a9f5029e1a483ff50cbfaa8023bd02a50a694a05bf09636f77ff18738d","abstract_canon_sha256":"e36326ce0e10a31931f2290983b980c5511bff49166f63ae6cd3aacbe554fe95"},"schema_version":"1.0"},"canonical_sha256":"5efaeedf2d8c2fafdde6c44dbb9654d77006511faa231d4ee83ab156fcb93909","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:55:34.988602Z","signature_b64":"XYBjel0MoqMLKJhkRDhVi0NQ+xvRmoeIKqhNbmHA+f7UUmdsPNYqGASWSYdvZtoPIPeaop+jlCqT1qfXiC9gDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5efaeedf2d8c2fafdde6c44dbb9654d77006511faa231d4ee83ab156fcb93909","last_reissued_at":"2026-07-05T09:55:34.988059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:55:34.988059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.02504","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:55:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Dd+7wnbMVDBCE3ev6XOWROljfPwy2+SpHntTbfAEkmBioqMSZbzz+if7ZJh5pfAw5Bz1UWkuAT84JB/KhOOTDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:08:18.647873Z"},"content_sha256":"210b865e0039a4230e8ee6da15d514ec7447feae2b4851316c81826955e1600b","schema_version":"1.0","event_id":"sha256:210b865e0039a4230e8ee6da15d514ec7447feae2b4851316c81826955e1600b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:L35O5XZNRQX27XPGYRG3XFSU25","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dual Active Learning for Reinforcement Learning from Human Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chengchun Shi, Pangpang Liu, Will Wei Sun","submitted_at":"2024-10-03T14:09:58Z","abstract_excerpt":"Aligning large language models (LLMs) with human preferences is critical to recent advances in generative artificial intelligence. Reinforcement learning from human feedback (RLHF) is widely applied to achieve this objective. A key step in RLHF is to learn the reward function from human feedback. However, human feedback is costly and time-consuming, making it essential to collect high-quality conversation data for human teachers to label. Additionally, different human teachers have different levels of expertise. It is thus critical to query the most appropriate teacher for their opinions. In t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02504","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/2410.02504/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":"2026-07-05T09:55:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J/uGueweZG4bGZuSJuDv4HYDcIh3jKhLA7GV3PYyc5i5AG+I4ndB9pipYyBWrGJaAP+RJXfwZYpd4b9/2TbkDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:08:18.648409Z"},"content_sha256":"490e34fbd9c5ae0ae56e3a8fdb07b8a90a00becedc728e47fc167dfc1e77e905","schema_version":"1.0","event_id":"sha256:490e34fbd9c5ae0ae56e3a8fdb07b8a90a00becedc728e47fc167dfc1e77e905"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L35O5XZNRQX27XPGYRG3XFSU25/bundle.json","state_url":"https://pith.science/pith/L35O5XZNRQX27XPGYRG3XFSU25/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L35O5XZNRQX27XPGYRG3XFSU25/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":"2026-08-10T14:08:18Z","links":{"resolver":"https://pith.science/pith/L35O5XZNRQX27XPGYRG3XFSU25","bundle":"https://pith.science/pith/L35O5XZNRQX27XPGYRG3XFSU25/bundle.json","state":"https://pith.science/pith/L35O5XZNRQX27XPGYRG3XFSU25/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L35O5XZNRQX27XPGYRG3XFSU25/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L35O5XZNRQX27XPGYRG3XFSU25","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":"e36326ce0e10a31931f2290983b980c5511bff49166f63ae6cd3aacbe554fe95","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-03T14:09:58Z","title_canon_sha256":"596627a9f5029e1a483ff50cbfaa8023bd02a50a694a05bf09636f77ff18738d"},"schema_version":"1.0","source":{"id":"2410.02504","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02504","created_at":"2026-07-05T09:55:34Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02504v2","created_at":"2026-07-05T09:55:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02504","created_at":"2026-07-05T09:55:34Z"},{"alias_kind":"pith_short_12","alias_value":"L35O5XZNRQX2","created_at":"2026-07-05T09:55:34Z"},{"alias_kind":"pith_short_16","alias_value":"L35O5XZNRQX27XPG","created_at":"2026-07-05T09:55:34Z"},{"alias_kind":"pith_short_8","alias_value":"L35O5XZN","created_at":"2026-07-05T09:55:34Z"}],"graph_snapshots":[{"event_id":"sha256:490e34fbd9c5ae0ae56e3a8fdb07b8a90a00becedc728e47fc167dfc1e77e905","target":"graph","created_at":"2026-07-05T09:55:34Z","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/2410.02504/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning large language models (LLMs) with human preferences is critical to recent advances in generative artificial intelligence. Reinforcement learning from human feedback (RLHF) is widely applied to achieve this objective. A key step in RLHF is to learn the reward function from human feedback. However, human feedback is costly and time-consuming, making it essential to collect high-quality conversation data for human teachers to label. Additionally, different human teachers have different levels of expertise. It is thus critical to query the most appropriate teacher for their opinions. In t","authors_text":"Chengchun Shi, Pangpang Liu, Will Wei Sun","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-03T14:09:58Z","title":"Dual Active Learning for Reinforcement Learning from Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02504","kind":"arxiv","version":2},"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":"sha256:210b865e0039a4230e8ee6da15d514ec7447feae2b4851316c81826955e1600b","target":"record","created_at":"2026-07-05T09:55:34Z","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":"e36326ce0e10a31931f2290983b980c5511bff49166f63ae6cd3aacbe554fe95","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-03T14:09:58Z","title_canon_sha256":"596627a9f5029e1a483ff50cbfaa8023bd02a50a694a05bf09636f77ff18738d"},"schema_version":"1.0","source":{"id":"2410.02504","kind":"arxiv","version":2}},"canonical_sha256":"5efaeedf2d8c2fafdde6c44dbb9654d77006511faa231d4ee83ab156fcb93909","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5efaeedf2d8c2fafdde6c44dbb9654d77006511faa231d4ee83ab156fcb93909","first_computed_at":"2026-07-05T09:55:34.988059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:55:34.988059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XYBjel0MoqMLKJhkRDhVi0NQ+xvRmoeIKqhNbmHA+f7UUmdsPNYqGASWSYdvZtoPIPeaop+jlCqT1qfXiC9gDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:55:34.988602Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02504","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:210b865e0039a4230e8ee6da15d514ec7447feae2b4851316c81826955e1600b","sha256:490e34fbd9c5ae0ae56e3a8fdb07b8a90a00becedc728e47fc167dfc1e77e905"],"state_sha256":"f6bf63ed419f532c8ccc9d3da364a4c97737141252ba2f84ac46704ad57821bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A/9E7lqS2+0365mj8Z8HzA2Ur14MMRKubXp0rPJf+Io1oD9NyV4/J2iPrwQN16gDHC9qb59HN8rIv3x5/x83Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T14:08:18.653671Z","bundle_sha256":"61f19ebe2bd3890a10a40a60b77ea0ebdbbeab9c1ad8f47f10c4dde372513874"}}