{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VLFXKXM4GQU4RLZU7EXCSF4IPO","short_pith_number":"pith:VLFXKXM4","canonical_record":{"source":{"id":"2410.00847","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-01T16:29:59Z","cross_cats_sorted":[],"title_canon_sha256":"dfc3b7dc6e673cd82203dee627eee9ebd8c18a183d2f27af5f83397be80154f0","abstract_canon_sha256":"7a9ec2ddd8fd973f5dfb64a560e1092abf126aecc77c6aca100b59145ed826ba"},"schema_version":"1.0"},"canonical_sha256":"aacb755d9c3429c8af34f92e2917887b86f904c62a30b7946fd06f5c2675666f","source":{"kind":"arxiv","id":"2410.00847","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00847","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00847v2","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00847","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_12","alias_value":"VLFXKXM4GQU4","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_16","alias_value":"VLFXKXM4GQU4RLZU","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_8","alias_value":"VLFXKXM4","created_at":"2026-07-05T10:13:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VLFXKXM4GQU4RLZU7EXCSF4IPO","target":"record","payload":{"canonical_record":{"source":{"id":"2410.00847","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-01T16:29:59Z","cross_cats_sorted":[],"title_canon_sha256":"dfc3b7dc6e673cd82203dee627eee9ebd8c18a183d2f27af5f83397be80154f0","abstract_canon_sha256":"7a9ec2ddd8fd973f5dfb64a560e1092abf126aecc77c6aca100b59145ed826ba"},"schema_version":"1.0"},"canonical_sha256":"aacb755d9c3429c8af34f92e2917887b86f904c62a30b7946fd06f5c2675666f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:04.064187Z","signature_b64":"CbMEs7QeiP5amF0ygq/aYAwLzzJ9rXzAwHG7YtpE17PjBxVuBLZR/YBxiWtbeer6El055q8gRYKZI/Js+Cp9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aacb755d9c3429c8af34f92e2917887b86f904c62a30b7946fd06f5c2675666f","last_reissued_at":"2026-07-05T10:13:04.063729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:04.063729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.00847","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":"2026-07-05T10:13:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"38kipjnxRdmVTR8hE2EuS8yVenY6vLsU1QXfDwQrTdUfIFQ86/gNLH7UYEfX/MPl3Uvx7sYiURbLfwqeLZEEDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:52:19.125330Z"},"content_sha256":"ce92a3e9e57b4810fc2dda1f0792183e79d64a30cf1a3e9db26110012d427a09","schema_version":"1.0","event_id":"sha256:ce92a3e9e57b4810fc2dda1f0792183e79d64a30cf1a3e9db26110012d427a09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VLFXKXM4GQU4RLZU7EXCSF4IPO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dong Yan, Jian Xie, Junge Zhang, Wei Shen, Xingzhou Lou, Yuzi Yan","submitted_at":"2024-10-01T16:29:59Z","abstract_excerpt":"Reward models (RMs) are essential for aligning large language models (LLM) with human expectations. However, existing RMs struggle to capture the stochastic and uncertain nature of human preferences and fail to assess the reliability of reward predictions. To address these challenges, we introduce the Uncertainty-aware Reward Model (URM) and its ensemble variant, URME. URM employs a probabilistic value head to capture aleatoric uncertainty by modeling the distribution of disentangled human preference attributes. URME further quantifies epistemic uncertainty by examining discrepancies among ind"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00847","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/2410.00847/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":"2026-07-05T10:13:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pi43bJpsE2aab3TGWoaK1St7wfRhpbqVL1Naq5MOD7oA1kx1DTKOdTZKcpyxk1x1nuJ8lLvABVyVU7SlgjZxCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:52:19.126376Z"},"content_sha256":"afa502d382b7f7fbe45e4b930a236c65b8f322875472e0ea9746686acd9570ec","schema_version":"1.0","event_id":"sha256:afa502d382b7f7fbe45e4b930a236c65b8f322875472e0ea9746686acd9570ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VLFXKXM4GQU4RLZU7EXCSF4IPO/bundle.json","state_url":"https://pith.science/pith/VLFXKXM4GQU4RLZU7EXCSF4IPO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VLFXKXM4GQU4RLZU7EXCSF4IPO/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":"2026-08-08T09:52:19Z","links":{"resolver":"https://pith.science/pith/VLFXKXM4GQU4RLZU7EXCSF4IPO","bundle":"https://pith.science/pith/VLFXKXM4GQU4RLZU7EXCSF4IPO/bundle.json","state":"https://pith.science/pith/VLFXKXM4GQU4RLZU7EXCSF4IPO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VLFXKXM4GQU4RLZU7EXCSF4IPO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VLFXKXM4GQU4RLZU7EXCSF4IPO","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":"7a9ec2ddd8fd973f5dfb64a560e1092abf126aecc77c6aca100b59145ed826ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-01T16:29:59Z","title_canon_sha256":"dfc3b7dc6e673cd82203dee627eee9ebd8c18a183d2f27af5f83397be80154f0"},"schema_version":"1.0","source":{"id":"2410.00847","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.00847","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"arxiv_version","alias_value":"2410.00847v2","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.00847","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_12","alias_value":"VLFXKXM4GQU4","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_16","alias_value":"VLFXKXM4GQU4RLZU","created_at":"2026-07-05T10:13:04Z"},{"alias_kind":"pith_short_8","alias_value":"VLFXKXM4","created_at":"2026-07-05T10:13:04Z"}],"graph_snapshots":[{"event_id":"sha256:afa502d382b7f7fbe45e4b930a236c65b8f322875472e0ea9746686acd9570ec","target":"graph","created_at":"2026-07-05T10:13:04Z","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/2410.00847/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward models (RMs) are essential for aligning large language models (LLM) with human expectations. However, existing RMs struggle to capture the stochastic and uncertain nature of human preferences and fail to assess the reliability of reward predictions. To address these challenges, we introduce the Uncertainty-aware Reward Model (URM) and its ensemble variant, URME. URM employs a probabilistic value head to capture aleatoric uncertainty by modeling the distribution of disentangled human preference attributes. URME further quantifies epistemic uncertainty by examining discrepancies among ind","authors_text":"Dong Yan, Jian Xie, Junge Zhang, Wei Shen, Xingzhou Lou, Yuzi Yan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-01T16:29:59Z","title":"Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.00847","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:ce92a3e9e57b4810fc2dda1f0792183e79d64a30cf1a3e9db26110012d427a09","target":"record","created_at":"2026-07-05T10:13:04Z","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":"7a9ec2ddd8fd973f5dfb64a560e1092abf126aecc77c6aca100b59145ed826ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-01T16:29:59Z","title_canon_sha256":"dfc3b7dc6e673cd82203dee627eee9ebd8c18a183d2f27af5f83397be80154f0"},"schema_version":"1.0","source":{"id":"2410.00847","kind":"arxiv","version":2}},"canonical_sha256":"aacb755d9c3429c8af34f92e2917887b86f904c62a30b7946fd06f5c2675666f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aacb755d9c3429c8af34f92e2917887b86f904c62a30b7946fd06f5c2675666f","first_computed_at":"2026-07-05T10:13:04.063729Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:04.063729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CbMEs7QeiP5amF0ygq/aYAwLzzJ9rXzAwHG7YtpE17PjBxVuBLZR/YBxiWtbeer6El055q8gRYKZI/Js+Cp9Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:04.064187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.00847","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ce92a3e9e57b4810fc2dda1f0792183e79d64a30cf1a3e9db26110012d427a09","sha256:afa502d382b7f7fbe45e4b930a236c65b8f322875472e0ea9746686acd9570ec"],"state_sha256":"2202c523d81c6f64f680f837df84e1fdf86f18ff932b1603b0a6b9ea3e70ff83"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7CO5DPHnWARcwlFrp9kTYvRftJtj3ErkezGjfKg/smohFnMxFHhbxR5vIaQiZ77Bj4undkULu1JUTG8/I0WPDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:52:19.130865Z","bundle_sha256":"c3e3acf5485191ea5df7455d26fd38f67c35aef2c4620998192de14ded6ebc96"}}