{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YF3WE2F6MYLAB3BE2Z4HEDAT6L","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":"a770920161e117d9739be56afbd63d8361854995175d7d14f436409034c638a8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T19:56:56Z","title_canon_sha256":"e469532c0745df46482ffa8467216d611d5479887559a4c92e75d9e82939b513"},"schema_version":"1.0","source":{"id":"2606.22652","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22652","created_at":"2026-06-23T02:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22652v1","created_at":"2026-06-23T02:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22652","created_at":"2026-06-23T02:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"YF3WE2F6MYLA","created_at":"2026-06-23T02:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"YF3WE2F6MYLAB3BE","created_at":"2026-06-23T02:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"YF3WE2F6","created_at":"2026-06-23T02:13:44Z"}],"graph_snapshots":[{"event_id":"sha256:58cd98942fc4bbb4dcdc985d686d0cf53e48c9522ef53025751200d626364791","target":"graph","created_at":"2026-06-23T02:13:44Z","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/2606.22652/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Markov Chain from Human Feedback (MCHF), an elementary approach for aligning generative models from pairwise human preferences. Unlike Reinforcement Learning from Human Feedback (RLHF), which reduces comparisons to a scalar reward, and Nash Learning from Human Feedback (NLHF), which preserves pairwise utilities through a KL-regularized minimax optimization, MCHF uses pairwise preferences directly to define a transition mechanism over model outputs. Given a pairwise utility $U(x,y)$, which quantifies human preference for $y$ over $x$, and a reference probability distribution $\\mu_{\\m","authors_text":"Takuya Koriyama, Tengyuan Liang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T19:56:56Z","title":"A Markov Chain Approach to Preference Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22652","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":"sha256:540f54af2d4ca4f4b388362420b292d61fb907eab1fe27159b5abf47b1123a6a","target":"record","created_at":"2026-06-23T02:13:44Z","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":"a770920161e117d9739be56afbd63d8361854995175d7d14f436409034c638a8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T19:56:56Z","title_canon_sha256":"e469532c0745df46482ffa8467216d611d5479887559a4c92e75d9e82939b513"},"schema_version":"1.0","source":{"id":"2606.22652","kind":"arxiv","version":1}},"canonical_sha256":"c1776268be661600ec24d678720c13f2e46d10721d01e35272665a4901f8625f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1776268be661600ec24d678720c13f2e46d10721d01e35272665a4901f8625f","first_computed_at":"2026-06-23T02:13:44.009494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:44.009494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HLvxPhVOvm/fw/1Hg8fIB5F1ne9wzEMYal5KBev6DHvzNOB21Mn/7el54D80IJKEyo6zX1jDwn87erTiEPR2Bg==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:44.009875Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22652","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:540f54af2d4ca4f4b388362420b292d61fb907eab1fe27159b5abf47b1123a6a","sha256:58cd98942fc4bbb4dcdc985d686d0cf53e48c9522ef53025751200d626364791"],"state_sha256":"0f20614b40f446513ee6bd4a362a574636d042d93e2843a0129a1fdd9b3a7b2d"}