{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EGG4HS5KO3WLYMLQCEYXOKTGIF","short_pith_number":"pith:EGG4HS5K","canonical_record":{"source":{"id":"2403.06754","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T14:28:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fc1dcd1e93d033f67d6a8d5efec8e5f66241428ded935e927ae5ebc1d0895140","abstract_canon_sha256":"5f24e2391fd44a064981a9408451df04c4060be87ff7f4603e6046b82944bc78"},"schema_version":"1.0"},"canonical_sha256":"218dc3cbaa76ecbc31701131772a66417444a196e16cf67b790dec9b17c815ad","source":{"kind":"arxiv","id":"2403.06754","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06754","created_at":"2026-07-05T07:57:01Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06754v2","created_at":"2026-07-05T07:57:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06754","created_at":"2026-07-05T07:57:01Z"},{"alias_kind":"pith_short_12","alias_value":"EGG4HS5KO3WL","created_at":"2026-07-05T07:57:01Z"},{"alias_kind":"pith_short_16","alias_value":"EGG4HS5KO3WLYMLQ","created_at":"2026-07-05T07:57:01Z"},{"alias_kind":"pith_short_8","alias_value":"EGG4HS5K","created_at":"2026-07-05T07:57:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EGG4HS5KO3WLYMLQCEYXOKTGIF","target":"record","payload":{"canonical_record":{"source":{"id":"2403.06754","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T14:28:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fc1dcd1e93d033f67d6a8d5efec8e5f66241428ded935e927ae5ebc1d0895140","abstract_canon_sha256":"5f24e2391fd44a064981a9408451df04c4060be87ff7f4603e6046b82944bc78"},"schema_version":"1.0"},"canonical_sha256":"218dc3cbaa76ecbc31701131772a66417444a196e16cf67b790dec9b17c815ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:01.547292Z","signature_b64":"ulXzoikTt6oOa6e5cMuIkMrd9oqoLFin6eq59x0/eIo9LpfVurVDXhoSim3dPoRnPa/lmhtDUrpXxYd/s1nZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"218dc3cbaa76ecbc31701131772a66417444a196e16cf67b790dec9b17c815ad","last_reissued_at":"2026-07-05T07:57:01.546787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:01.546787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.06754","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":"2026-07-05T07:57:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JHw+T5xrxVP0CI1dxsxjRXg3QC8d5o3GTiJxl5S8DFbErkw8e71mzIRkSge+VoNgFplxzEq0KPutczC4Qy+wCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:44:08.490047Z"},"content_sha256":"0c95b66fc66ece748f72e1c8e543c30f69fbd9e4602267f430c187ab5c021b9c","schema_version":"1.0","event_id":"sha256:0c95b66fc66ece748f72e1c8e543c30f69fbd9e4602267f430c187ab5c021b9c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EGG4HS5KO3WLYMLQCEYXOKTGIF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ALaRM: Align Language Models via Hierarchical Rewards Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Shujun Liu, Siyuan Wang, Xuanjing Huang, Yuhang Lai, Zhongyu Wei","submitted_at":"2024-03-11T14:28:40Z","abstract_excerpt":"We introduce ALaRM, the first framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF), which is designed to enhance the alignment of large language models (LLMs) with human preferences. The framework addresses the limitations of current alignment approaches, which often struggle with the inconsistency and sparsity of human supervision signals, by integrating holistic rewards with aspect-specific rewards. This integration enables more precise and consistent guidance of language models towards desired outcomes, particularly in complex and open text generation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06754","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/2403.06754/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":"2026-07-05T07:57:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ms5JvQ804bJNytLFWikThm9Og153KZ3A+mCE6xMaX2Uqs2REw85MUunLi8drXzjVnx6C9yOka1GDVA2+4gyNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:44:08.490620Z"},"content_sha256":"aa34ccac71ba0fd0fc5a20f8e4d144cbba2120a9f7f57ffe8317b99ddd41a6af","schema_version":"1.0","event_id":"sha256:aa34ccac71ba0fd0fc5a20f8e4d144cbba2120a9f7f57ffe8317b99ddd41a6af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EGG4HS5KO3WLYMLQCEYXOKTGIF/bundle.json","state_url":"https://pith.science/pith/EGG4HS5KO3WLYMLQCEYXOKTGIF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EGG4HS5KO3WLYMLQCEYXOKTGIF/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":"2026-08-06T08:44:08Z","links":{"resolver":"https://pith.science/pith/EGG4HS5KO3WLYMLQCEYXOKTGIF","bundle":"https://pith.science/pith/EGG4HS5KO3WLYMLQCEYXOKTGIF/bundle.json","state":"https://pith.science/pith/EGG4HS5KO3WLYMLQCEYXOKTGIF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EGG4HS5KO3WLYMLQCEYXOKTGIF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EGG4HS5KO3WLYMLQCEYXOKTGIF","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":"5f24e2391fd44a064981a9408451df04c4060be87ff7f4603e6046b82944bc78","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T14:28:40Z","title_canon_sha256":"fc1dcd1e93d033f67d6a8d5efec8e5f66241428ded935e927ae5ebc1d0895140"},"schema_version":"1.0","source":{"id":"2403.06754","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06754","created_at":"2026-07-05T07:57:01Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06754v2","created_at":"2026-07-05T07:57:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06754","created_at":"2026-07-05T07:57:01Z"},{"alias_kind":"pith_short_12","alias_value":"EGG4HS5KO3WL","created_at":"2026-07-05T07:57:01Z"},{"alias_kind":"pith_short_16","alias_value":"EGG4HS5KO3WLYMLQ","created_at":"2026-07-05T07:57:01Z"},{"alias_kind":"pith_short_8","alias_value":"EGG4HS5K","created_at":"2026-07-05T07:57:01Z"}],"graph_snapshots":[{"event_id":"sha256:aa34ccac71ba0fd0fc5a20f8e4d144cbba2120a9f7f57ffe8317b99ddd41a6af","target":"graph","created_at":"2026-07-05T07:57:01Z","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/2403.06754/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce ALaRM, the first framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF), which is designed to enhance the alignment of large language models (LLMs) with human preferences. The framework addresses the limitations of current alignment approaches, which often struggle with the inconsistency and sparsity of human supervision signals, by integrating holistic rewards with aspect-specific rewards. This integration enables more precise and consistent guidance of language models towards desired outcomes, particularly in complex and open text generation","authors_text":"Shujun Liu, Siyuan Wang, Xuanjing Huang, Yuhang Lai, Zhongyu Wei","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T14:28:40Z","title":"ALaRM: Align Language Models via Hierarchical Rewards Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06754","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":"sha256:0c95b66fc66ece748f72e1c8e543c30f69fbd9e4602267f430c187ab5c021b9c","target":"record","created_at":"2026-07-05T07:57:01Z","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":"5f24e2391fd44a064981a9408451df04c4060be87ff7f4603e6046b82944bc78","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-11T14:28:40Z","title_canon_sha256":"fc1dcd1e93d033f67d6a8d5efec8e5f66241428ded935e927ae5ebc1d0895140"},"schema_version":"1.0","source":{"id":"2403.06754","kind":"arxiv","version":2}},"canonical_sha256":"218dc3cbaa76ecbc31701131772a66417444a196e16cf67b790dec9b17c815ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"218dc3cbaa76ecbc31701131772a66417444a196e16cf67b790dec9b17c815ad","first_computed_at":"2026-07-05T07:57:01.546787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:01.546787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ulXzoikTt6oOa6e5cMuIkMrd9oqoLFin6eq59x0/eIo9LpfVurVDXhoSim3dPoRnPa/lmhtDUrpXxYd/s1nZBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:01.547292Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06754","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c95b66fc66ece748f72e1c8e543c30f69fbd9e4602267f430c187ab5c021b9c","sha256:aa34ccac71ba0fd0fc5a20f8e4d144cbba2120a9f7f57ffe8317b99ddd41a6af"],"state_sha256":"1fcb1cb5597add3415d144fc2eb98989dcc4ddf6db24d94204486354d4f4d576"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1GyF/h9jTP11EIYW1cyBbrgFff0R4v85s+ZoqINuQEkpjtxempBxofV2iXvK01Yu5IzeUlQjnfdMg+LYo74HDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:44:08.494204Z","bundle_sha256":"0255678a21e11753e4c39ce105a7a5b5b0b0b06d0710a4ff2fb375cc37bb9125"}}