{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:S4KIC3SAQUMIEPM7IKVDV5W7WK","merge_version":"pith-open-graph-merge-v1","event_count":6,"valid_event_count":6,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2e4e2a0d767f1ced054029b33077b3acc55c7cc71ba264bf1b9d92cac90a11b6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-06T01:33:12Z","title_canon_sha256":"7fb9fbab7e65e0e2cb47a9ab233b47a7828ff25d130708f8add853f83339dcfc"},"schema_version":"1.0","source":{"id":"2607.04590","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04590","created_at":"2026-07-07T02:19:26Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04590v1","created_at":"2026-07-07T02:19:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04590","created_at":"2026-07-07T02:19:26Z"},{"alias_kind":"pith_short_12","alias_value":"S4KIC3SAQUMI","created_at":"2026-07-07T02:19:26Z"},{"alias_kind":"pith_short_16","alias_value":"S4KIC3SAQUMIEPM7","created_at":"2026-07-07T02:19:26Z"},{"alias_kind":"pith_short_8","alias_value":"S4KIC3SA","created_at":"2026-07-07T02:19:26Z"}],"graph_snapshots":[{"event_id":"sha256:7c5b1e57e79e185b317135362b65505a39aee66a6517349525248bbdf08eaf02","target":"graph","created_at":"2026-07-07T02:19:26Z","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/2607.04590/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pairwise human comparisons are a primary interface through which modern AI systems learn human preferences. RLHF and related alignment pipelines typically model such comparisons with Bradley--Terry log-odds, where choice probabilities are governed by latent reward differences. This paper examines what this assumption misses through a reduced-form model motivated by rational inattention, in which each label is generated by a low-capacity evaluation channel. The model separates two forms of ambiguity that standard reward modeling tends to conflate: a comparison may be difficult because the two c","authors_text":"Wenqian Xing","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-06T01:33:12Z","title":"Attention Limited Reward Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04590","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":"sha256:5570f2291fe15f430cd1007d54a027c8c24559069d5219fb86afe088d4a3cb2b","target":"record","created_at":"2026-07-07T02:19:26Z","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":"2e4e2a0d767f1ced054029b33077b3acc55c7cc71ba264bf1b9d92cac90a11b6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-06T01:33:12Z","title_canon_sha256":"7fb9fbab7e65e0e2cb47a9ab233b47a7828ff25d130708f8add853f83339dcfc"},"schema_version":"1.0","source":{"id":"2607.04590","kind":"arxiv","version":1}},"canonical_sha256":"9714816e408518823d9f42aa3af6dfb283493faccce1439f100738503887d862","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9714816e408518823d9f42aa3af6dfb283493faccce1439f100738503887d862","first_computed_at":"2026-07-07T02:19:26.094896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:26.094896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fiWPE4jLfhYxrA8l2/bZVv8M2fdGUnZv5Xc7sxnFIH3FRGmgcw091RqUVlMgHJI/izFioFMy/1QsBnFiKCvFDQ==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:26.095732Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04590","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:655a3b1d7b61abf60952cb0b9802233cc21019ea962b3833789d17631c70792d","sha256:8bdb76c19ecf846e4516437f6871390d18e442e2c9f5b807aec89393f690cce1","sha256:b6694713bdb8bbc21b3cfd4ef51ca391f885be4fad533b94671e872976532bd3","sha256:dc6b5f05724581891ca40117866bdb9f50248e2a20205c450543dd2cfc8c2646"]}],"invalid_events":[],"applied_event_ids":["sha256:5570f2291fe15f430cd1007d54a027c8c24559069d5219fb86afe088d4a3cb2b","sha256:7c5b1e57e79e185b317135362b65505a39aee66a6517349525248bbdf08eaf02"],"state_sha256":"fd9f366a3f76253f563a60d13bedd14fb96dba4a80f92f5ef7c57125fe06fb71"}