{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:72WCD6QS7AKHSBTM6HQWUOAHRR","short_pith_number":"pith:72WCD6QS","schema_version":"1.0","canonical_sha256":"feac21fa12f81479066cf1e16a38078c5bd99b8bb6c057bc8dddea530ffe4be9","source":{"kind":"arxiv","id":"2605.17342","version":1},"attestation_state":"computed","paper":{"title":"Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jing Li, Kaiqi Zhao, Xiucheng Li, Yucong Huang","submitted_at":"2026-05-17T09:27:26Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.17342","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-17T09:27:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"822130a11d20cc5be549bc095121893b0cf68f16bd3063ab6fdb0470f20278b7","abstract_canon_sha256":"9c8995a3ed7f4323a673243f42a120a5416c2a2b777ca51c0c735e2b4ae8bfe8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:53.185998Z","signature_b64":"OTyw52x7kVD7xbtG4FgVKF3LnXZ+iJFiz3lXusEu/3vIYvcSypscLdD/NYxJ28NJmTMsmO2V2pmSCIHPwV53Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"feac21fa12f81479066cf1e16a38078c5bd99b8bb6c057bc8dddea530ffe4be9","last_reissued_at":"2026-05-20T00:03:53.185289Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:53.185289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jing Li, Kaiqi Zhao, Xiucheng Li, Yucong Huang","submitted_at":"2026-05-17T09:27:26Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17342","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.17342/integrity.json","findings":[],"available":true,"detectors_run":[{"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","findings_count":0}],"snapshot_sha256":"a6865b272f050d74a9c20d1b87dd04628af0f4dbd9c143f1fd9a094f4843d4f6"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.17342","created_at":"2026-05-20T00:03:53.185443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17342v1","created_at":"2026-05-20T00:03:53.185443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17342","created_at":"2026-05-20T00:03:53.185443+00:00"},{"alias_kind":"pith_short_12","alias_value":"72WCD6QS7AKH","created_at":"2026-05-20T00:03:53.185443+00:00"},{"alias_kind":"pith_short_16","alias_value":"72WCD6QS7AKHSBTM","created_at":"2026-05-20T00:03:53.185443+00:00"},{"alias_kind":"pith_short_8","alias_value":"72WCD6QS","created_at":"2026-05-20T00:03:53.185443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/72WCD6QS7AKHSBTM6HQWUOAHRR","json":"https://pith.science/pith/72WCD6QS7AKHSBTM6HQWUOAHRR.json","graph_json":"https://pith.science/api/pith-number/72WCD6QS7AKHSBTM6HQWUOAHRR/graph.json","events_json":"https://pith.science/api/pith-number/72WCD6QS7AKHSBTM6HQWUOAHRR/events.json","paper":"https://pith.science/paper/72WCD6QS"},"agent_actions":{"view_html":"https://pith.science/pith/72WCD6QS7AKHSBTM6HQWUOAHRR","download_json":"https://pith.science/pith/72WCD6QS7AKHSBTM6HQWUOAHRR.json","view_paper":"https://pith.science/paper/72WCD6QS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17342&json=true","fetch_graph":"https://pith.science/api/pith-number/72WCD6QS7AKHSBTM6HQWUOAHRR/graph.json","fetch_events":"https://pith.science/api/pith-number/72WCD6QS7AKHSBTM6HQWUOAHRR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/72WCD6QS7AKHSBTM6HQWUOAHRR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/72WCD6QS7AKHSBTM6HQWUOAHRR/action/storage_attestation","attest_author":"https://pith.science/pith/72WCD6QS7AKHSBTM6HQWUOAHRR/action/author_attestation","sign_citation":"https://pith.science/pith/72WCD6QS7AKHSBTM6HQWUOAHRR/action/citation_signature","submit_replication":"https://pith.science/pith/72WCD6QS7AKHSBTM6HQWUOAHRR/action/replication_record"}},"created_at":"2026-05-20T00:03:53.185443+00:00","updated_at":"2026-05-20T00:03:53.185443+00:00"}