{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KPC3WA6DXKE2MMDVKRFS4RSGAI","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":"06f6a8ce05e76c4b443cfe9a5a020c6dedb774488ca7067656c0e44de6c3f569","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T14:17:53Z","title_canon_sha256":"6833098c61ffb88bf3a978b2df5ef0fc4d120fb5fd37425139afa8e3695a8b10"},"schema_version":"1.0","source":{"id":"2606.30339","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.30339","created_at":"2026-06-30T02:18:11Z"},{"alias_kind":"arxiv_version","alias_value":"2606.30339v1","created_at":"2026-06-30T02:18:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30339","created_at":"2026-06-30T02:18:11Z"},{"alias_kind":"pith_short_12","alias_value":"KPC3WA6DXKE2","created_at":"2026-06-30T02:18:11Z"},{"alias_kind":"pith_short_16","alias_value":"KPC3WA6DXKE2MMDV","created_at":"2026-06-30T02:18:11Z"},{"alias_kind":"pith_short_8","alias_value":"KPC3WA6D","created_at":"2026-06-30T02:18:11Z"}],"graph_snapshots":[{"event_id":"sha256:30cc95b35f6e98f2549ecd8e0960b1b00a4147663bcfaea87edbcee3874c3626","target":"graph","created_at":"2026-06-30T02:18:11Z","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/2606.30339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Aligning large language models (LLMs) with diverse user preferences is a critical yet challenging task. While post-training methods can adapt models to specific needs, they often require costly data curation and additional training. Test-time scaling (TTS) presents an efficient, training-free alternative, but its application has been largely limited to verifiable domains like mathematics and coding, where response correctness is easily judged. To extend TTS to preference alignment, we introduce a novel framework that models the task as a realignment problem, since the base model often fails to","authors_text":"Bo An, Chenfeng Xu, Chenran Li, Fuxiang Zhang, Lang Feng, Masayoshi Tomizuka, Pengcheng Wang, Yi-Chen Li, Yuxin Chen","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T14:17:53Z","title":"REAR: Test-time Preference Realignment through Reward Decomposition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30339","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":"sha256:5d9d61ba0ccdc8fdd31715233296edc21099c5e69a51b3e376175856cb693e04","target":"record","created_at":"2026-06-30T02:18:11Z","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":"06f6a8ce05e76c4b443cfe9a5a020c6dedb774488ca7067656c0e44de6c3f569","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T14:17:53Z","title_canon_sha256":"6833098c61ffb88bf3a978b2df5ef0fc4d120fb5fd37425139afa8e3695a8b10"},"schema_version":"1.0","source":{"id":"2606.30339","kind":"arxiv","version":1}},"canonical_sha256":"53c5bb03c3ba89a63075544b2e4646022d703a5550d0f919ca9d31bc888a9c13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53c5bb03c3ba89a63075544b2e4646022d703a5550d0f919ca9d31bc888a9c13","first_computed_at":"2026-06-30T02:18:11.009928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:18:11.009928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"waGbgvrML19Z7fUSQsysUfA6Hf/j9SJwbhAoqQc/oowFJ/fTP+vZKN+1/PiD4D4C02Q9TQ7tTWYNSv8+/MHaDw==","signature_status":"signed_v1","signed_at":"2026-06-30T02:18:11.010433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.30339","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d9d61ba0ccdc8fdd31715233296edc21099c5e69a51b3e376175856cb693e04","sha256:30cc95b35f6e98f2549ecd8e0960b1b00a4147663bcfaea87edbcee3874c3626"],"state_sha256":"a088a6b709b443d69211e55aa5acf830cbcd6624843c5aef6f6acae9dd201034"}