{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WD3VKSROPOZACPQMMQSI2WBOPK","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":"5cf04606b0ee0ffa6eed69fbec5c12a155e15c797e549216bc4337d6dad751df","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T07:57:50Z","title_canon_sha256":"92bd987f5b27dc98227028800b67d20a1016b0392c4124651979ac85a2f2f837"},"schema_version":"1.0","source":{"id":"2606.10528","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10528","created_at":"2026-06-10T01:10:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10528v1","created_at":"2026-06-10T01:10:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10528","created_at":"2026-06-10T01:10:24Z"},{"alias_kind":"pith_short_12","alias_value":"WD3VKSROPOZA","created_at":"2026-06-10T01:10:24Z"},{"alias_kind":"pith_short_16","alias_value":"WD3VKSROPOZACPQM","created_at":"2026-06-10T01:10:24Z"},{"alias_kind":"pith_short_8","alias_value":"WD3VKSRO","created_at":"2026-06-10T01:10:24Z"}],"graph_snapshots":[{"event_id":"sha256:a0ab475e53ce18110f231751ea14ee967bddf9b4c11f0c468e0100d7fde5cd7b","target":"graph","created_at":"2026-06-10T01:10:24Z","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/2606.10528/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current reinforcement learning from human feedback (RLHF) methods primarily rely on scalar rewards from a trained reward model (RM). While effective, scalar rewards are often noisy and fail to capture fine-grained preference differences, whereas RM hidden states encode richer semantic and preference information. We introduce the representation-aware advantage estimation, which leverages RM hidden states and models them as auxiliary signals for better advantage estimation. Specifically, we propose the Graph-based Advantage Estimation (GraphAE), treat each sampled group as a graph, where nodes c","authors_text":"Guozheng Li, Xiyan Fu, Yiwen Guo","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T07:57:50Z","title":"Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar Output"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10528","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:c54a81b57e94865b0ed8878c10e99814e45c12f5817ac703456be042d4acc9e9","target":"record","created_at":"2026-06-10T01:10:24Z","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":"5cf04606b0ee0ffa6eed69fbec5c12a155e15c797e549216bc4337d6dad751df","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T07:57:50Z","title_canon_sha256":"92bd987f5b27dc98227028800b67d20a1016b0392c4124651979ac85a2f2f837"},"schema_version":"1.0","source":{"id":"2606.10528","kind":"arxiv","version":1}},"canonical_sha256":"b0f7554a2e7bb2013e0c64248d582e7a90c61ec7568a628da3efb057537c434f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0f7554a2e7bb2013e0c64248d582e7a90c61ec7568a628da3efb057537c434f","first_computed_at":"2026-06-10T01:10:24.422230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:24.422230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XiAwGitcpW9C5rzKOEY31T8d2tbkks0xxLqWOg40Af/gP7Fs10tEPGdl1wwtsdlxtMD3Wubq02DeNeFgaro/AA==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:24.423099Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10528","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c54a81b57e94865b0ed8878c10e99814e45c12f5817ac703456be042d4acc9e9","sha256:a0ab475e53ce18110f231751ea14ee967bddf9b4c11f0c468e0100d7fde5cd7b"],"state_sha256":"ce70f9b3800f3a74d3f3b28bc9d32683ce4bce8de3f114553b34e3ba92c3188c"}