{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:72WCD6QS7AKHSBTM6HQWUOAHRR","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":"9c8995a3ed7f4323a673243f42a120a5416c2a2b777ca51c0c735e2b4ae8bfe8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-17T09:27:26Z","title_canon_sha256":"822130a11d20cc5be549bc095121893b0cf68f16bd3063ab6fdb0470f20278b7"},"schema_version":"1.0","source":{"id":"2605.17342","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17342","created_at":"2026-05-20T00:03:53Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17342v1","created_at":"2026-05-20T00:03:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17342","created_at":"2026-05-20T00:03:53Z"},{"alias_kind":"pith_short_12","alias_value":"72WCD6QS7AKH","created_at":"2026-05-20T00:03:53Z"},{"alias_kind":"pith_short_16","alias_value":"72WCD6QS7AKHSBTM","created_at":"2026-05-20T00:03:53Z"},{"alias_kind":"pith_short_8","alias_value":"72WCD6QS","created_at":"2026-05-20T00:03:53Z"}],"graph_snapshots":[{"event_id":"sha256:cdfb5fa31f9ac1e2cfe7170bee0d5db29b47775b0ac2299e4768064a8c8ed448","target":"graph","created_at":"2026-05-20T00:03:53Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T21:41:57.800951Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.736671Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.17342/integrity.json","findings":[],"snapshot_sha256":"a6865b272f050d74a9c20d1b87dd04628af0f4dbd9c143f1fd9a094f4843d4f6","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Standard RLHF relies on transitive scalar rewards, failing to capture the cyclic nature of human preferences. While some approaches like the General Preference Model (GPM) address this, we identify a theoretical limitation: their implicit formulation entangles hierarchy with cyclicity, failing to guarantee dominant solutions. To address this, we propose the Hybrid Reward-Cyclic (HRC) model, which utilizes game-theoretic decomposition to explicitly disentangle preferences into orthogonal transitive (scalar) and cyclic (vector) components. Complementing this, we introduce Dynamic Self-Play Prefe","authors_text":"Jing Li, Kaiqi Zhao, Xiucheng Li, Yucong Huang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-17T09:27:26Z","title":"Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17342","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:f97e11d602cd776878286694c6a216680e538a1a2ed53300781d01c658965034","target":"record","created_at":"2026-05-20T00:03:53Z","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":"9c8995a3ed7f4323a673243f42a120a5416c2a2b777ca51c0c735e2b4ae8bfe8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-17T09:27:26Z","title_canon_sha256":"822130a11d20cc5be549bc095121893b0cf68f16bd3063ab6fdb0470f20278b7"},"schema_version":"1.0","source":{"id":"2605.17342","kind":"arxiv","version":1}},"canonical_sha256":"feac21fa12f81479066cf1e16a38078c5bd99b8bb6c057bc8dddea530ffe4be9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"feac21fa12f81479066cf1e16a38078c5bd99b8bb6c057bc8dddea530ffe4be9","first_computed_at":"2026-05-20T00:03:53.185289Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:53.185289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OTyw52x7kVD7xbtG4FgVKF3LnXZ+iJFiz3lXusEu/3vIYvcSypscLdD/NYxJ28NJmTMsmO2V2pmSCIHPwV53Ag==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:53.185998Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17342","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f97e11d602cd776878286694c6a216680e538a1a2ed53300781d01c658965034","sha256:cdfb5fa31f9ac1e2cfe7170bee0d5db29b47775b0ac2299e4768064a8c8ed448"],"state_sha256":"a9e14de1661cf257f358df8842e4cd6abeb694d498c8e2f1ab5fb95c4c49d1ea"}