{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GGN5JAISBHGMFBIOIFK3R2WFEL","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":"78373312a58171816553fb87f0d5f81fc94d0b2aa4043cca210b9b1718319900","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T20:49:04Z","title_canon_sha256":"a866a9373f9417976fc3c292a913b8721c9f0fb05fcfa219bf7fa9d3052d6c58"},"schema_version":"1.0","source":{"id":"2507.09016","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09016","created_at":"2026-07-05T11:38:09Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09016v2","created_at":"2026-07-05T11:38:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09016","created_at":"2026-07-05T11:38:09Z"},{"alias_kind":"pith_short_12","alias_value":"GGN5JAISBHGM","created_at":"2026-07-05T11:38:09Z"},{"alias_kind":"pith_short_16","alias_value":"GGN5JAISBHGMFBIO","created_at":"2026-07-05T11:38:09Z"},{"alias_kind":"pith_short_8","alias_value":"GGN5JAIS","created_at":"2026-07-05T11:38:09Z"}],"graph_snapshots":[{"event_id":"sha256:16443b63e42ebfca04b35de57bb0c1ac9f1b2f226bacf8b95f259950df671768","target":"graph","created_at":"2026-07-05T11:38:09Z","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/2507.09016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback (RLHF) aligns language models with human preferences but is computationally expensive. We explore two approaches that leverage human gaze modeling to enhance RLHF: (1) gaze-aware reward models and (2) gaze-based distribution of sparse rewards at token level. Our experiments demonstate that gaze-informed RLHF achieves faster convergence while maintaining or slightly improving performance, thus, reducing computational costs during policy optimization. These results show that human gaze provides a valuable and underused signal for policy optimization, po","authors_text":"Ilya Pershin, Ivan Titov, Karim Galliamov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T20:49:04Z","title":"Enhancing RLHF with Human Gaze Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09016","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":"sha256:0c00ee15f2d723ba4c1419132f6355664e40005bf71e1ed69c35f567f6f1d57d","target":"record","created_at":"2026-07-05T11:38:09Z","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":"78373312a58171816553fb87f0d5f81fc94d0b2aa4043cca210b9b1718319900","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T20:49:04Z","title_canon_sha256":"a866a9373f9417976fc3c292a913b8721c9f0fb05fcfa219bf7fa9d3052d6c58"},"schema_version":"1.0","source":{"id":"2507.09016","kind":"arxiv","version":2}},"canonical_sha256":"319bd4811209ccc2850e4155b8eac522d8094d1cba9928f0bddba95f54543b04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"319bd4811209ccc2850e4155b8eac522d8094d1cba9928f0bddba95f54543b04","first_computed_at":"2026-07-05T11:38:09.172888Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:09.172888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AO0RF5iP3TuZSOpnoyw4CXwA6yhNb2gMgKR3VPhFYRfwMGCX2G2xu65sIOOi83U4YyJVxyDBCA7F3WacRP8RBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:09.173408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09016","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c00ee15f2d723ba4c1419132f6355664e40005bf71e1ed69c35f567f6f1d57d","sha256:16443b63e42ebfca04b35de57bb0c1ac9f1b2f226bacf8b95f259950df671768"],"state_sha256":"7b9440ae6181e4e5feb4c0366489f1d563297a3f36ae9b9f2314e0f367de5de4"}